CN116595188A - Educational knowledge graph system based on artificial intelligence and big data - Google Patents
Educational knowledge graph system based on artificial intelligence and big data Download PDFInfo
- Publication number
- CN116595188A CN116595188A CN202310522285.4A CN202310522285A CN116595188A CN 116595188 A CN116595188 A CN 116595188A CN 202310522285 A CN202310522285 A CN 202310522285A CN 116595188 A CN116595188 A CN 116595188A
- Authority
- CN
- China
- Prior art keywords
- data
- knowledge
- teaching
- module
- knowledge graph
- 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
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 28
- 238000004458 analytical method Methods 0.000 claims abstract description 31
- 238000003058 natural language processing Methods 0.000 claims abstract description 24
- 238000007418 data mining Methods 0.000 claims abstract description 11
- 238000004140 cleaning Methods 0.000 claims description 26
- 238000000034 method Methods 0.000 claims description 25
- 238000012986 modification Methods 0.000 claims description 19
- 230000004048 modification Effects 0.000 claims description 19
- 238000010276 construction Methods 0.000 claims description 18
- 238000000605 extraction Methods 0.000 claims description 18
- 230000004927 fusion Effects 0.000 claims description 17
- 238000004422 calculation algorithm Methods 0.000 claims description 15
- 238000012360 testing method Methods 0.000 claims description 14
- 230000002159 abnormal effect Effects 0.000 claims description 10
- 230000003993 interaction Effects 0.000 claims description 9
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 4
- 230000009193 crawling Effects 0.000 claims description 3
- 230000006399 behavior Effects 0.000 abstract description 7
- 230000008569 process Effects 0.000 description 11
- 238000005516 engineering process Methods 0.000 description 10
- 230000008859 change Effects 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 4
- 230000002452 interceptive effect Effects 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 239000013598 vector Substances 0.000 description 4
- 238000012098 association analyses Methods 0.000 description 3
- 230000010354 integration Effects 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000007500 overflow downdraw method Methods 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000007596 consolidation process Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- 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
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- 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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9024—Graphs; Linked lists
-
- 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
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Educational Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (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)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses an educational knowledge graph system based on artificial intelligence and big data, which constructs a knowledge graph through multi-source heterogeneous data, ensures the diversity and coverage of the data, analyzes and updates the educational knowledge graph through natural language processing, can effectively ensure the freshness of the educational knowledge graph and improves the recommending accuracy. According to the invention, through data mining and artificial intelligence analysis, the learning behavior of student users can be effectively analyzed, a learning plan is formulated for the student users, and high-precision knowledge point recommendation is realized.
Description
Technical Field
The invention belongs to the technical field of computers and education, and particularly relates to an educational knowledge graph system based on artificial intelligence and big data.
Background
In the existing teaching system, students can acquire related information by inputting keywords or browsing knowledge points, and perform self-evaluation and consolidation by utilizing functions such as exercise questions and tests provided by the system. Meanwhile, the system can provide feedback according to the learning behaviors of the students so that the students can master core concepts and skills.
However, the prior art has the following problems:
(1) The prior art has insufficient data or low quality, and the practicability of the knowledge graph is limited.
(2) In the prior art, since knowledge maps are constructed in specific disciplines and fields, there may be cases where some important knowledge points are not covered.
(3) The personalized recommendation in the prior art mainly depends on data tag recommendation, and errors may exist in the result, so that the accuracy and precision of recommendation need to be further improved.
Disclosure of Invention
The invention provides an educational knowledge graph system based on artificial intelligence and big data, which is used for solving the technical problems in the prior art.
An educational knowledge graph system based on artificial intelligence and big data comprises a multi-source heterogeneous data fusion module, a natural language processing module, a data mining module and an artificial intelligence analysis module;
the multi-source heterogeneous data fusion module is used for collecting teaching original data from different data sources, constructing a teaching knowledge graph according to the teaching original data, collecting modification operation of the teaching knowledge graph, and modifying the teaching knowledge graph according to the modification operation;
the natural language processing module is used for updating the teaching knowledge graph by adopting a natural language processing method, acquiring an updated teaching knowledge graph and acquiring different application scene data based on the updated teaching knowledge graph;
The data mining module is used for matching knowledge points corresponding to the retrieval operation for student users and performing intelligent tutoring learning according to the updated teaching knowledge graph and application scene data;
the artificial intelligent analysis module is used for intelligently analyzing the student user score to obtain an intelligent analysis result and recommending the intelligent analysis result to teacher users and parent users corresponding to the student users.
In one possible implementation manner, the multi-source heterogeneous data fusion module comprises a data acquisition sub-module, a data cleaning sub-module, a knowledge map construction sub-module and a correlation revision sub-module;
the data acquisition sub-module is used for acquiring data in the public webpage, the public database and the public document through the web crawler to obtain teaching original data, wherein the teaching original data comprises structured data and unstructured data;
the data cleaning sub-module is used for preprocessing the teaching original data to obtain preprocessed teaching original data;
the knowledge graph construction submodule is used for constructing a teaching knowledge graph according to the preprocessed teaching original data;
The association revision submodule is used for receiving modification operation comprising new knowledge points and association matching characters and matching at least one target knowledge point in the teaching knowledge map according to the association matching characters; after at least one target knowledge point is matched, receiving association operation corresponding to the target knowledge point generated by man-machine interaction, associating the target knowledge point corresponding to the association operation with the new knowledge point, and finishing modification of the teaching knowledge map.
In one possible implementation, the data acquisition submodule includes a text data acquisition unit, a picture data acquisition unit, an audio data acquisition unit and a video data acquisition unit;
the text data acquisition unit is used for acquiring the published web pages, the published databases and the documents in the published documents through the web crawlers to obtain original document data;
the picture data acquisition unit is used for acquiring pictures in the public webpage, the public database and the public document through the web crawler to obtain original picture data;
the audio data acquisition unit is used for acquiring the audio in the public webpage, the public database and the public document through the web crawler to obtain original audio data;
The video data acquisition unit is used for acquiring videos in the public webpage, the public database and the public document through the web crawler to obtain original video data;
wherein, the original document data, the original picture data, the original audio data and the original video data are used as teaching original data together.
In one possible implementation, the data cleaning submodule includes a repeated value cleaning unit and an outlier cleaning unit;
the repeated value cleaning unit is used for cleaning repeated data in the teaching original data;
the abnormal value cleaning unit is used for cleaning abnormal data in teaching original data, and the abnormal data are used for representing data of meaning sensitive words or unidentifiable data.
In one possible implementation manner, the knowledge graph construction submodule comprises a knowledge point extraction unit, a relationship extraction unit and a knowledge graph construction unit;
the knowledge point extraction unit is used for extracting knowledge points in the preprocessed teaching original data;
the relation extracting unit is used for extracting the relation among all knowledge points from the original teaching data;
The knowledge graph construction unit is used for constructing a knowledge graph according to the knowledge points obtained by the knowledge point extraction unit and the relations obtained by the relation extraction unit.
In one possible implementation manner, the association revision submodule includes a new knowledge point acquisition unit, a stored knowledge point retrieval unit and an association storage unit;
the new knowledge point acquisition unit is used for receiving modification operation comprising new knowledge points and associated matching characters;
the stored knowledge point retrieval unit is used for matching at least one target knowledge point in the teaching knowledge map according to the associated matching character and by adopting a neural network algorithm;
and the association storage unit is used for receiving association operation corresponding to the target knowledge points generated by man-machine interaction after being matched with at least one target knowledge point, associating the target knowledge points corresponding to the association operation with the new knowledge points, and finishing modification of the teaching knowledge map.
In one possible implementation manner, the natural language processing module comprises a multi-mode semantic understanding sub-module, a knowledge graph expansion module and a depth fusion scene module;
the multi-mode semantic understanding sub-module is used for carrying out multi-mode semantic understanding on the existing knowledge points by adopting a timing task and a natural language processing algorithm, expanding keywords of the existing knowledge points in the teaching knowledge graph to obtain an expanded teaching knowledge graph, pushing the knowledge points in the expanded teaching knowledge graph to teachers in the same field, wherein the same field is used for representing the same teaching field of teacher users as the field in which the knowledge points are located;
The knowledge graph expansion module is used for crawling new knowledge points related to the existing knowledge point keywords from a designated data source based on the keywords of the existing knowledge points in the teaching knowledge graph, and updating the expanded teaching knowledge graph according to the related new knowledge points to obtain an updated teaching knowledge graph;
the depth fusion scene module is used for acquiring domain knowledge bases of different application scenes based on existing knowledge points in the teaching knowledge graph to obtain different application scene data, and the domain knowledge bases comprise at least one existing knowledge point identical to the application scene domain.
In one possible implementation manner, the data mining module comprises an intelligent auxiliary sub-module and a knowledge point accurate matching sub-module;
the intelligent auxiliary sub-module is used for providing exercise questions of relevant knowledge points in the preset field for student users, recording question making data of the students for answering and writing exercise questions, and the question making data at least comprises correct rate and error exercise questions;
the intelligent auxiliary sub-module is also used for monitoring the accuracy in real time, and pushing analytic answers, learning ideas and associated knowledge points corresponding to the wrong exercise questions to the student users after the accuracy is reduced to a set threshold value; the method comprises the steps of setting a threshold value for representing the lowest accuracy rate set by a teacher user for a student user, wherein analytical answers, learning ideas and associated knowledge points corresponding to exercise questions are all prestored data;
The knowledge point accurate matching sub-module is used for receiving the problem character string input by the student user, matching the knowledge point corresponding to the problem character string in the teaching knowledge graph, and feeding back the knowledge point corresponding to the problem character string to the student user.
In one possible implementation, the artificial intelligence analysis module includes a paper testing sub-module and a performance analysis sub-module;
the test paper testing sub-module is used for providing test paper for student users and recording answering situations of the student users;
the achievement analysis sub-module is used for analyzing the mastering conditions of the student users on different knowledge points based on the answering conditions of the student users, generating learning plan suggestions based on the mastering conditions, and feeding back the mastering conditions and the learning plan suggestions to parent users and teacher users corresponding to the student users.
In one possible implementation manner, the intelligent matching module is further included, and the intelligent matching module is used for accepting target conditions input by the student user or the parent user, matching and recommending target teacher users corresponding to the target conditions for the student user or the parent user.
The beneficial effects of the invention are as follows:
(1) According to the educational knowledge graph system based on artificial intelligence and big data, the knowledge graph is built through the multi-source heterogeneous data, so that the diversity and coverage of the data are guaranteed, the teaching knowledge graph is analyzed and updated through natural language processing, the freshness of the teaching knowledge graph can be effectively guaranteed, and the recommending accuracy is improved.
(2) According to the invention, through data mining and artificial intelligence analysis, the learning behavior of student users can be effectively analyzed, a learning plan is formulated for the student users, and high-precision knowledge point recommendation is realized.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
Fig. 1 is a schematic structural diagram of an educational knowledge graph system based on artificial intelligence and big data according to an embodiment of the present invention.
Specific embodiments of the present invention have been shown by way of the above drawings and will be described in more detail below. The drawings and the written description are not intended to limit the scope of the inventive concepts in any way, but rather to illustrate the inventive concepts to those skilled in the art by reference to the specific embodiments.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the invention. Rather, they are merely examples of apparatus and methods consistent with aspects of the invention as detailed in the accompanying claims.
Embodiments of the present invention are described in detail below with reference to the accompanying drawings.
Example 1
As shown in FIG. 1, the educational knowledge graph system based on artificial intelligence and big data comprises a multi-source heterogeneous data fusion module, a natural language processing module, a data mining module and an artificial intelligence analysis module.
The multi-source heterogeneous data fusion module is used for collecting teaching original data from different data sources, constructing a teaching knowledge graph according to the teaching original data, collecting modification operation of the teaching knowledge graph, and modifying the teaching knowledge graph according to the modification operation.
The natural language processing module is used for updating the teaching knowledge graph by adopting a natural language processing method, acquiring the updated teaching knowledge graph, and acquiring different application scene data based on the updated teaching knowledge graph.
The data mining module is used for matching knowledge points corresponding to the retrieval operation for student users and performing intelligent tutoring learning according to the updated teaching knowledge graph and the application scene data.
The artificial intelligent analysis module is used for intelligently analyzing the student user score to obtain an intelligent analysis result and recommending the intelligent analysis result to teacher users and parent users corresponding to the student users.
In one possible implementation manner, the multi-source heterogeneous data fusion module comprises a data acquisition sub-module, a data cleaning sub-module, a knowledge map construction sub-module and a correlation revision sub-module;
the data acquisition sub-module is used for acquiring data in the public webpage, the public database and the public document through the web crawler to obtain teaching original data, and the teaching original data comprises structured data and unstructured data.
The data cleaning sub-module is used for preprocessing the teaching original data to obtain the preprocessed teaching original data.
The knowledge graph construction submodule is used for constructing a teaching knowledge graph according to the preprocessed teaching original data.
The association revision submodule is used for receiving modification operation comprising new knowledge points and association matching characters and matching at least one target knowledge point in the teaching knowledge map according to the association matching characters; after at least one target knowledge point is matched, receiving association operation corresponding to the target knowledge point generated by man-machine interaction, associating the target knowledge point corresponding to the association operation with the new knowledge point, and finishing modification of the teaching knowledge map.
The invention can acquire data from a plurality of different data sources, and effectively integrate and fuse the data to form a more complete and accurate knowledge graph; first, for structured and semi-structured data (such as text, pictures, and video), the data is split into different standards according to the data type, for example: the text information is cut into a plurality of text knowledge points according to the keywords and the context linkage; the picture information can automatically identify the text in the picture information and convert the text information into text knowledge points; the video information can identify voice information in the video, the video is cut into a plurality of knowledge point videos according to the relation of the front sentence and the rear sentence, keywords in the video are extracted, and the keywords are stored as labels of the video.
The traditional knowledge graph is often only built on the knowledge base of a specific field, and knowledge resources in different fields are difficult to be effectively fused. In the knowledge graph, a cross-domain knowledge fusion method is adopted, so that knowledge resources in different domains can be integrated and analyzed to form a comprehensive knowledge graph covering a plurality of domains. Thus, the user can acquire knowledge of each field on one platform, and the lateral and longitudinal expansion of the knowledge is realized.
The data processed by the unified standard can be classified into a resource library, and various indexes such as data types, discipline types, content keywords and the like are established. In the process of creating the knowledge graph, the subsequent teacher can perform association operation with the newly built knowledge points through the forms of knowledge point type matching, keyword matching and the like. For example: when a physical teacher creates knowledge points, the knowledge points need to be referred to a certain formula in mathematics, the formula can be input in association, and the system searches the formula in a resource library and automatically associates the conforming knowledge points. So that the user can conveniently acquire and use the data, provide richer and more accurate knowledge service for the user, and effectively improve the problems of low integrity, low accuracy and poor reliability of the current knowledge graph. It should be noted that the method may also be used in the subsequent knowledge point retrieval process.
In this embodiment, a recurrent neural network (Recurrent Neural Network, RNN) is added, which is used to implement semantic similarity calculations based on knowledge point data in order to find relevant concepts and knowledge points in the knowledge graph.
Specifically, the RNN is used to encode knowledge point text, representing each word or phrase as a vector. These vectors may convey information through the hidden state of the RNN, capturing context semantic information. These vectors are then used to calculate the similarity between the texts.
In knowledge-graph, this technique can be applied to different scenarios, for example: recommendation of related concepts: according to the query input by the user, the RNN is used for calculating the query and comparing the query with knowledge points in the knowledge graph, finding out the content most relevant to the query, and recommending the content to the user. Classification of knowledge points: the RNN is used to compute an associated quantitative representation of each knowledge point and a clustering algorithm is used to group similar knowledge points into a category to help the learner understand and organize the knowledge better. Recommendation of knowledge points: based on knowledge points that the learner has learned, their associated quantity representation is calculated using the RNN and compared with the unlearned knowledge point vector to find the unlearned knowledge point most relevant to the learner's known knowledge and recommend to the learner.
In one possible implementation, the data acquisition submodule includes a text data acquisition unit, a picture data acquisition unit, an audio data acquisition unit and a video data acquisition unit;
the text data acquisition unit is used for acquiring the published web pages, the published databases and the documents in the published documents through the web crawlers to obtain original document data.
The picture data acquisition unit is used for acquiring pictures in the public webpage, the public database and the public document through the web crawler to obtain original picture data.
The audio data acquisition unit is used for acquiring the audio in the public webpage, the public database and the public document through the web crawler to obtain the original audio data.
The video data acquisition unit is used for acquiring videos in the public webpage, the public database and the public document through the web crawler to obtain original video data.
Wherein, the original document data, the original picture data, the original audio data and the original video data are used as teaching original data together.
The traditional knowledge graph can only process text information, but cannot effectively process multimedia type data such as pictures, audio and video. The invention adopts a multi-mode data fusion method based on the deep learning technology, which can integrate and analyze the data of different modes and improves the coverage range and depth of the knowledge graph. For example, in the field of discipline knowledge, the knowledge graph in the invention comprises text data, discipline papers and other traditional discipline knowledge, and can also comprise various discipline resources such as course video, teaching material pictures, experimental data and the like, so that a user can more comprehensively know the discipline knowledge.
In one possible embodiment, the data cleansing submodule includes a repeat value cleansing unit and an outlier cleansing unit.
The repeated value cleaning unit is used for cleaning repeated data in the teaching original data.
The abnormal value cleaning unit is used for cleaning abnormal data in teaching original data, and the abnormal data are used for representing data of meaning sensitive words or unidentifiable data.
The traditional knowledge graph construction process needs to be manually manufactured and marked, so that the efficiency is low and the cost is high. The invention adopts a knowledge graph construction method based on an automation technology, and related knowledge and information can be obtained by grabbing, analyzing and analyzing a large amount of structured and unstructured information of various sources such as public web pages, databases, documents and the like. When the knowledge graph is constructed, a targeted strategy can be adopted, such as guiding and auditing by introducing field experts, and data cleaning and duplication removing by utilizing a machine learning algorithm, so that the accuracy and usability of the knowledge graph are improved.
Optionally, the data cleaning process may include:
a1, data collection: data is collected from different data sources, including various forms of data such as text, images, audio, and the like.
A2, data preprocessing: the original data is preprocessed, including outlier removal, repeated values, etc. (repeated values, means repeated knowledge points, outliers means videos with sensitive content or unrecognizable, etc.)
A3, feature selection and extraction: useful features are selected from the raw data and converted into an algorithmically acceptable format, such as extracting text from the video, and converting to knowledge points.
A4, constructing a model: according to the requirements of the problems, a proper machine learning algorithm is selected and model construction is carried out, such as a classification algorithm based on deep learning, a clustering algorithm and the like, knowledge points of the same type are combined and stored.
A5, training a model: the training is performed by using part of the data, and model parameters are adjusted, so that the model can learn and identify the data better.
A6, an application model: and applying the trained model to the knowledge graph to perform data cleaning and deduplication tasks. For example, natural language processing techniques and deep learning algorithms may be used to identify and correct grammar errors, spelling errors, and remove similar or duplicate text content when cleaning text data. Therefore, the quality and accuracy of the knowledge graph data can be improved, and learning and education tasks are better supported.
In a possible implementation manner, the knowledge graph construction submodule includes a knowledge point extraction unit, a relationship extraction unit and a knowledge graph construction unit.
The knowledge point extraction unit is used for extracting knowledge points in the preprocessed teaching original data.
The relation extracting unit is used for extracting the relation among all knowledge points from the original teaching data.
The knowledge graph construction unit is used for constructing a knowledge graph according to the knowledge points obtained by the knowledge point extraction unit and the relations obtained by the relation extraction unit.
In a possible implementation manner, the association revision submodule includes a new knowledge point acquisition unit, a stored knowledge point retrieval unit and an association storage unit.
The new knowledge point acquisition unit is used for receiving modification operation comprising new knowledge points and associated matching characters.
The stored knowledge point retrieval unit is used for matching characters according to the association and matching at least one target knowledge point in the teaching knowledge map by adopting a neural network algorithm.
And the association storage unit is used for receiving association operation corresponding to the target knowledge points generated by man-machine interaction after being matched with at least one target knowledge point, associating the target knowledge points corresponding to the association operation with the new knowledge points, and finishing modification of the teaching knowledge map.
The invention adopts the technology of a graph database to convert various educational data into the form of nodes and edges, and establishes a relation model among knowledge points on the basis. The model can express semantic relations among knowledge points, such as words, anti-meaning words, inclusion relations and the like, so that association analysis among the knowledge points is realized. Semantic association between knowledge points is achieved. The association analysis not only can help students better understand the association between knowledge points, but also can provide more accurate and targeted teaching guidance and assessment for teachers.
The modeling process is as follows:
b1, knowledge point extraction: knowledge points in different fields of science are extracted from a large amount of educational materials and learning resources by using natural language processing technology and machine learning algorithm. These knowledge points are typically expressed in terms of words or phrases, such as "system of linear equations", "newton's second law", and the like.
B2, defining relation types: relationship types between knowledge points, such as hierarchical structure, relevance, and composition relationships, are defined, as well as the specific meaning of each relationship type. For example, a hierarchical relationship in mathematics may be defined as a knowledge point being a parent or child of another knowledge point.
B3, relation extraction: relationships between knowledge points are extracted from a large number of educational materials using natural language processing techniques and machine learning algorithms. For example, text similarity calculations may be used to identify relevance relationships, and rules or statistical models may be used to identify hierarchical relationships.
B4, relation storage: the extracted knowledge points and relationships are stored in a knowledge graph system, and query and retrieval of the knowledge point relationships are supported by using technologies such as graph databases. For example, a Neo4j graph database may be used to store relationships between knowledge points.
B5, relationship verification and updating: and verifying and updating the knowledge point relationship regularly to ensure the accuracy and the integrity of the knowledge graph. This may be achieved through manual auditing and automation algorithms.
The invention can intelligently plan the optimal learning path according to the learning target and the requirement of the user. The learning path not only can cover all necessary knowledge points, but also can optimize the sequence and combination among the knowledge points through association analysis, thereby improving the learning efficiency and quality of the user. The invention can evaluate the mastering condition of the user on the specific knowledge point according to the learning record and the performance of the user. The assessment not only can help the user to know the learning progress and level of the user, but also can provide targeted teaching guidance and feedback for teachers.
The invention can analyze and evaluate the interaction behavior and the learning path of the user, such as discussion frequency, quality, interaction degree and the like. Through the analysis behavior data, the system can help teachers to better know the learning condition and the performance of students, and further provide accurate teaching guidance and management.
In one possible implementation manner, the natural language processing module comprises a multi-mode semantic understanding sub-module, a knowledge graph extension module and a depth fusion scene module.
The multi-mode semantic understanding sub-module is used for carrying out multi-mode semantic understanding on the existing knowledge points by adopting a timing task and a natural language processing algorithm, expanding keywords of the existing knowledge points in the teaching knowledge graph to obtain an expanded teaching knowledge graph, pushing the knowledge points in the expanded teaching knowledge graph to teachers in the same field, wherein the same field is used for representing the same teaching field of teacher users as the field where the knowledge points are located.
The system provided by the invention not only supports text input, but also supports various forms of input such as pictures, videos and the like, and can perform standard processing on the input contents in different forms through multi-source heterogeneous data fusion. Meanwhile, the system can update and maintain the database data regularly according to the timing task requirement, and re-analyze and cross-compare the database data according to the natural language processing technology, so that the keywords of the prior knowledge points, the video cutting accuracy and the like are continuously improved. For example, the system conducts heat to a keyword of a certain knowledge point of physics, but the system utilizes new data source comparison to expand new keywords such as heat conduction, heat conductivity coefficient and the like, and the keywords are pushed to the instructor for subsequent comparison and update of the instructor.
The knowledge graph expansion module is used for crawling new knowledge points related to the existing knowledge point keywords from the appointed data source based on the keywords of the existing knowledge points in the teaching knowledge graph, and updating the expanded teaching knowledge graph according to the related new knowledge points to obtain an updated teaching knowledge graph.
The system provided by the invention adopts an extensible knowledge graph architecture, and can support massive semantic data storage and retrieval. Meanwhile, the system can actively go to a discipline website or a designated data source to search the content related to the prior knowledge points according to the keywords of the knowledge points and supplement the content to a resource library, so that the knowledge graph is continuously perfected and enriched.
The depth fusion scene module is used for acquiring domain knowledge bases of different application scenes based on existing knowledge points in the teaching knowledge graph to obtain different application scene data, and the domain knowledge bases comprise at least one existing knowledge point identical to the application scene domain.
The system provided by the invention performs deep fusion aiming at different application scenes (such as education, medical treatment or finance, and the like), provides corresponding domain knowledge base and intelligent service, and provides more accurate semantic analysis and intelligent application for users.
In one possible implementation manner, the data mining module comprises an intelligent auxiliary sub-module and a knowledge point accurate matching sub-module;
the intelligent auxiliary sub-module is used for providing exercise questions of relevant knowledge points in the preset field for student users, recording question making data of the student users for answering and writing exercise questions, and the question making data at least comprises accuracy and error exercise questions.
The intelligent auxiliary sub-module is also used for monitoring the accuracy in real time, and pushing analytic answers, learning ideas and associated knowledge points corresponding to the wrong exercise questions to the student users after the accuracy is reduced to a set threshold value; the set threshold is used for representing the lowest accuracy rate set by a teacher user for a student user, and analysis answers, learning ideas and associated knowledge points corresponding to exercise questions are all prestored data.
Aiming at various difficulties and problems encountered by students in learning, the system provided by the invention provides personalized intelligent coaching service for students by deeply analyzing and understanding the learning condition of the students. For example, in daily learning, the system can learn the situation, preference or difficulty level according to the knowledge points of students, and recommend corresponding learning content and methods for the students. For example: the problems in the platform are related to a plurality of knowledge points, and when the accuracy rate of the students to the problems is lower than the value set by a teacher, a learning assistant can actively push the knowledge points to the students to prompt the students to consolidate review. Meanwhile, the system can automatically identify the problems of students in the learning process, and give corresponding solutions and suggestions in a targeted manner for more personalized learning paths. Daily learning data of students are monitored in real time, for example, the current learning time is very short, and learning assistants push course learning reminders to the students according to the current learning plans of the students.
The knowledge point accurate matching sub-module is used for receiving the problem character string input by the student user, matching the knowledge point corresponding to the problem character string in the teaching knowledge graph, and feeding back the knowledge point corresponding to the problem character string to the student user.
Knowledge point grasping is a key to learning for students. The system provided by the invention can quickly locate the knowledge points required by students and provide corresponding explanation and illustration for the knowledge points by accurately modeling and matching the knowledge points. For example, the system can automatically match related knowledge points according to questions input by students and give corresponding answers and explanations to help the students to better understand and master knowledge. The personalized knowledge point matching mode can enable students to learn and grow more efficiently.
In one possible implementation, the artificial intelligence analysis module includes a coupon testing sub-module and a performance analysis sub-module.
The test paper testing sub-module is used for providing test paper for student users and recording answering situations of the student users.
The achievement analysis sub-module is used for analyzing the mastering conditions of the student users on different knowledge points based on the answering conditions of the student users, generating learning plan suggestions based on the mastering conditions, and feeding back the mastering conditions and the learning plan suggestions to parent users and teacher users corresponding to the student users.
The system provided by the invention adopts natural language processing technology to process and analyze language input of students, and enumerates 2 points as follows: 1. syntax error correction: natural language processing techniques can recognize and correct grammar and spelling errors in student language input. 2. Text classification: the student language input can be classified, such as sentence classification, theme classification and the like, so that the student learning requirements and behavior characteristics can be better known. The understanding and response speed of the system to the demands of students are improved through the operation. The system can automatically identify the questions or demands of the students and provide corresponding answers or recommend learning resources, so that the learning efficiency and satisfaction of the students are improved.
In one possible implementation manner, the intelligent matching module is further included, and the intelligent matching module is used for accepting target conditions input by the student user or the parent user, matching and recommending target teacher users corresponding to the target conditions for the student user or the parent user.
The system provided by the invention can analyze and evaluate the learning score of the student, thereby providing more detailed feedback and advice for teachers and parents. The system can analyze the mastering condition and difficulty of students at different knowledge points, identify the weak items and advantages of the students, and provide corresponding improvement suggestions and learning plans.
In the process of using the system, the system can recommend institutions, teachers and courses meeting the requirements for the user according to the historical data and the hobbies of the user. The user can input own requirements and conditions, and the system can give out the result which best meets the requirements of the user in a short time. The invention can realize real-time matching, and along with the continuous change of factors such as market change, demand change and the like, the intelligent matching algorithm can also carry out real-time adjustment according to the change, thereby ensuring the accuracy and timeliness of the matching result.
In summary, in the education field, the system provided by the invention realizes accurate analysis and evaluation of the learning condition of students and personalized intelligent coaching and education services through application innovation of artificial intelligence technology. The education mode based on the knowledge graph can better meet the personalized requirements of students in the learning process, improve the learning efficiency and quality and assist the students in realizing better academic growth. In addition to the several aspects described above, the application of the system provided by the present invention in the educational field encompasses the following aspects:
an interactive learning tool: the system provided by the invention enables students to learn and feel knowledge more vividly by combining the multimedia technology and the interactive learning tool. For example, in classroom teaching, the system may present knowledge points in a multimedia form such as video, audio, etc., so that students can understand and master knowledge more deeply.
Student academic management: the system provided by the invention helps students to formulate effective learning plans and targets through comprehensive monitoring and analysis of the learning conditions of the students, and provides corresponding academic management and guidance services for the students. For example, in learning planning, the system can generate a corresponding learning plan according to the learning objective and time allocation situation of the students, and make intelligent adjustment and recommendation.
Teaching assistance of teachers: the system provided by the invention provides corresponding teaching assistance and guidance services for teachers through monitoring and analyzing teaching behaviors of the teachers. For example, in classroom teaching, the system can automatically record teaching contents of teachers, feedback conditions of students and other information, and perform intelligent analysis and summary, so that the teachers can better adjust and optimize teaching modes and methods.
The invention can integrate and manage a large amount of scattered data, thereby improving the utilization rate in teaching activities; the data in different fields can be fused, cross-field information integration is realized, and support is provided for multidimensional analysis; the data can be subjected to operations such as cleaning, normalization and de-duplication, and the accuracy and the reliability of the data are improved; the data integration and modeling can be rapidly carried out, and the cost of data integration and management is reduced. The visual display interface can be provided for the busy, and a user can quickly acquire the required information through interactive inquiry and analysis, so that the user experience is improved.
The traditional knowledge graph can only provide static knowledge nodes and relations, and cannot realize interactive question-answering and searching functions. In the knowledge graph, the intelligent question-answering and knowledge searching method based on natural language processing and deep learning technology is adopted, so that related knowledge nodes and relations can be quickly found according to natural language input of a user, and the knowledge nodes and relations are visually presented to the user. Meanwhile, the invention also introduces some strategies of man-machine interaction, such as intelligent complement, hot problem recommendation and the like, so that a user can acquire required knowledge more efficiently.
Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.
It is to be understood that the invention is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the invention is limited only by the appended claims.
Claims (10)
1. The educational knowledge graph system based on artificial intelligence and big data is characterized by comprising a multi-source heterogeneous data fusion module, a natural language processing module, a data mining module and an artificial intelligence analysis module;
the multi-source heterogeneous data fusion module is used for collecting teaching original data from different data sources, constructing a teaching knowledge graph according to the teaching original data, collecting modification operation of the teaching knowledge graph, and modifying the teaching knowledge graph according to the modification operation;
the natural language processing module is used for updating the teaching knowledge graph by adopting a natural language processing method, acquiring an updated teaching knowledge graph and acquiring different application scene data based on the updated teaching knowledge graph;
the data mining module is used for matching knowledge points corresponding to the retrieval operation for student users and performing intelligent tutoring learning according to the updated teaching knowledge graph and application scene data;
The artificial intelligent analysis module is used for intelligently analyzing the student user score to obtain an intelligent analysis result and recommending the intelligent analysis result to teacher users and parent users corresponding to the student users.
2. The educational knowledge graph system based on artificial intelligence and big data according to claim 1, wherein the multi-source heterogeneous data fusion module comprises a data acquisition sub-module, a data cleaning sub-module, a knowledge graph construction sub-module and a correlation revision sub-module;
the data acquisition sub-module is used for acquiring data in the public webpage, the public database and the public document through the web crawler to obtain teaching original data, wherein the teaching original data comprises structured data and unstructured data;
the data cleaning sub-module is used for preprocessing the teaching original data to obtain preprocessed teaching original data;
the knowledge graph construction submodule is used for constructing a teaching knowledge graph according to the preprocessed teaching original data;
the association revision submodule is used for receiving modification operation comprising new knowledge points and association matching characters and matching at least one target knowledge point in the teaching knowledge map according to the association matching characters; after at least one target knowledge point is matched, receiving association operation corresponding to the target knowledge point generated by man-machine interaction, associating the target knowledge point corresponding to the association operation with the new knowledge point, and finishing modification of the teaching knowledge map.
3. The educational knowledge graph system based on artificial intelligence and big data according to claim 2, wherein the data acquisition submodule comprises a text data acquisition unit, a picture data acquisition unit, an audio data acquisition unit and a video data acquisition unit;
the text data acquisition unit is used for acquiring the published web pages, the published databases and the documents in the published documents through the web crawlers to obtain original document data;
the picture data acquisition unit is used for acquiring pictures in the public webpage, the public database and the public document through the web crawler to obtain original picture data;
the audio data acquisition unit is used for acquiring the audio in the public webpage, the public database and the public document through the web crawler to obtain original audio data;
the video data acquisition unit is used for acquiring videos in the public webpage, the public database and the public document through the web crawler to obtain original video data;
wherein, the original document data, the original picture data, the original audio data and the original video data are used as teaching original data together.
4. The educational knowledge graph system based on artificial intelligence and big data according to claim 2, wherein the data cleansing submodule includes a repeated value cleansing unit and an abnormal value cleansing unit;
the repeated value cleaning unit is used for cleaning repeated data in the teaching original data;
the abnormal value cleaning unit is used for cleaning abnormal data in teaching original data, and the abnormal data are used for representing data of meaning sensitive words or unidentifiable data.
5. The educational knowledge graph system based on artificial intelligence and big data according to claim 2, wherein the knowledge graph construction submodule comprises a knowledge point extraction unit, a relation extraction unit and a knowledge graph construction unit;
the knowledge point extraction unit is used for extracting knowledge points in the preprocessed teaching original data;
the relation extracting unit is used for extracting the relation among all knowledge points from the original teaching data;
the knowledge graph construction unit is used for constructing a knowledge graph according to the knowledge points obtained by the knowledge point extraction unit and the relations obtained by the relation extraction unit.
6. The educational knowledge graph system based on artificial intelligence and big data according to claim 2, wherein the association revision sub-module comprises a new knowledge point acquisition unit, a stored knowledge point retrieval unit, and an association storage unit;
The new knowledge point acquisition unit is used for receiving modification operation comprising new knowledge points and associated matching characters;
the stored knowledge point retrieval unit is used for matching at least one target knowledge point in the teaching knowledge map according to the associated matching character and by adopting a neural network algorithm;
and the association storage unit is used for receiving association operation corresponding to the target knowledge points generated by man-machine interaction after being matched with at least one target knowledge point, associating the target knowledge points corresponding to the association operation with the new knowledge points, and finishing modification of the teaching knowledge map.
7. The educational knowledge graph system based on artificial intelligence and big data according to claim 1, wherein the natural language processing module comprises a multi-modal semantic understanding sub-module, a knowledge graph expansion module, and a deep fusion scene module;
the multi-mode semantic understanding sub-module is used for carrying out multi-mode semantic understanding on the existing knowledge points by adopting a timing task and a natural language processing algorithm, expanding keywords of the existing knowledge points in the teaching knowledge graph to obtain an expanded teaching knowledge graph, pushing the knowledge points in the expanded teaching knowledge graph to teachers in the same field, wherein the same field is used for representing the same teaching field of teacher users as the field in which the knowledge points are located;
The knowledge graph expansion module is used for crawling new knowledge points related to the existing knowledge point keywords from a designated data source based on the keywords of the existing knowledge points in the teaching knowledge graph, and updating the expanded teaching knowledge graph according to the related new knowledge points to obtain an updated teaching knowledge graph;
the depth fusion scene module is used for acquiring domain knowledge bases of different application scenes based on existing knowledge points in the teaching knowledge graph to obtain different application scene data, and the domain knowledge bases comprise at least one existing knowledge point identical to the application scene domain.
8. The educational knowledge graph system based on artificial intelligence and big data according to claim 7, wherein the data mining module comprises an intelligent assistance sub-module and a knowledge point accurate matching sub-module;
the intelligent auxiliary sub-module is used for providing exercise questions of relevant knowledge points in the preset field for student users, recording question making data of the students for answering and writing exercise questions, and the question making data at least comprises correct rate and error exercise questions;
the intelligent auxiliary sub-module is also used for monitoring the accuracy in real time, and pushing analytic answers, learning ideas and associated knowledge points corresponding to the wrong exercise questions to the student users after the accuracy is reduced to a set threshold value; the method comprises the steps of setting a threshold value for representing the lowest accuracy rate set by a teacher user for a student user, wherein analytical answers, learning ideas and associated knowledge points corresponding to exercise questions are all prestored data;
The knowledge point accurate matching sub-module is used for receiving the problem character string input by the student user, matching the knowledge point corresponding to the problem character string in the teaching knowledge graph, and feeding back the knowledge point corresponding to the problem character string to the student user.
9. The educational knowledge graph system based on artificial intelligence and big data according to claim 8, wherein the artificial intelligence analysis module comprises a test paper testing sub-module and a performance analysis sub-module;
the test paper testing sub-module is used for providing test paper for student users and recording answering situations of the student users;
the achievement analysis sub-module is used for analyzing the mastering conditions of the student users on different knowledge points based on the answering conditions of the student users, generating learning plan suggestions based on the mastering conditions, and feeding back the mastering conditions and the learning plan suggestions to parent users and teacher users corresponding to the student users.
10. The educational knowledge graph system based on artificial intelligence and big data according to claim 1, further comprising an intelligent matching module for accepting a target condition input by a student user or a parent user, matching and recommending a target teacher user corresponding to the target condition for the student user or the parent user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310522285.4A CN116595188A (en) | 2023-05-10 | 2023-05-10 | Educational knowledge graph system based on artificial intelligence and big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310522285.4A CN116595188A (en) | 2023-05-10 | 2023-05-10 | Educational knowledge graph system based on artificial intelligence and big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116595188A true CN116595188A (en) | 2023-08-15 |
Family
ID=87593087
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310522285.4A Pending CN116595188A (en) | 2023-05-10 | 2023-05-10 | Educational knowledge graph system based on artificial intelligence and big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116595188A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117235187A (en) * | 2023-11-14 | 2023-12-15 | 深圳市联特微电脑信息技术开发有限公司 | Data storage method and system based on network teaching resources |
-
2023
- 2023-05-10 CN CN202310522285.4A patent/CN116595188A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117235187A (en) * | 2023-11-14 | 2023-12-15 | 深圳市联特微电脑信息技术开发有限公司 | Data storage method and system based on network teaching resources |
| CN117235187B (en) * | 2023-11-14 | 2024-03-22 | 深圳市联特微电脑信息技术开发有限公司 | Data storage method and system based on network teaching resources |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102262634B (en) | Automatic questioning and answering method and system | |
| CN109947915B (en) | Knowledge management system-based artificial intelligence expert system and construction method thereof | |
| US20080126319A1 (en) | Automated short free-text scoring method and system | |
| CN112395403B (en) | Knowledge graph-based question and answer method, system, electronic equipment and medium | |
| CN108509439B (en) | Algebra teaching system | |
| US20150026184A1 (en) | Methods and systems for content management | |
| CN113886567A (en) | Teaching method and system based on knowledge graph | |
| CN110968708A (en) | Method and system for labeling education information resource attributes | |
| CN116595188A (en) | Educational knowledge graph system based on artificial intelligence and big data | |
| CN116821377A (en) | Primary school Chinese automatic evaluation system based on knowledge graph and large model | |
| Atapattu et al. | Automated extraction of semantic concepts from semi-structured data: Supporting computer-based education through the analysis of lecture notes | |
| CN115238199A (en) | Knowledge graph-based online community learning path recommendation method, system and equipment | |
| CN117150151B (en) | Wrong question analysis and test question recommendation system and method based on large language model | |
| Soares et al. | Education question answering systems: a survey | |
| Tunde et al. | Ontology-based model for E-learning management system (O-Bmems) | |
| Riza et al. | Natural language processing and levenshtein distance for generating error identification typed questions on TOEFL | |
| US20210375148A1 (en) | System and method for autonomous learning of contents using a machine learning algorithm | |
| CN114297404A (en) | Knowledge graph construction method for field evaluation expert behavior track | |
| Reddy et al. | A novel approach for similarity and indexing-based ontology for semantic web educational system | |
| CN116401341A (en) | Interactive answering system oriented to understanding | |
| Fernandez-Manjon et al. | Building educational tools based on formal concept analysis | |
| Stefanov et al. | Computing ontology creation | |
| Jänicke | Teaching on the intersection of visualization and digital humanities | |
| Alemán et al. | A Proposal for Domain Ontological Learning. | |
| Awati et al. | Accurate answers selection and expert recommendation in community question answers system |
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 |