CN111159356B - Knowledge graph construction method based on teaching content - Google Patents
Knowledge graph construction method based on teaching content Download PDFInfo
- Publication number
- CN111159356B CN111159356B CN201911410556.7A CN201911410556A CN111159356B CN 111159356 B CN111159356 B CN 111159356B CN 201911410556 A CN201911410556 A CN 201911410556A CN 111159356 B CN111159356 B CN 111159356B
- Authority
- CN
- China
- Prior art keywords
- teaching
- content
- quality
- information
- entity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—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
- G06F16/35—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
- G06F16/30—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
- 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—Systems or methods specially adapted for 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention discloses a knowledge graph construction method based on teaching content, which comprises the following steps: s1, classifying teaching contents according to teaching subjects to obtain teaching subject contents; s2, extracting information from the content of the teaching subjects to obtain extracted information; s3, aligning entities in the extracted information by adopting a semantic similarity calculation method to obtain fusion information; s4, judging whether the newly added teaching content in the fusion information meets the quality standard; s5, constructing a knowledge graph based on the fusion information after judgment processing. The knowledge graph construction method based on the teaching content can accurately and efficiently process similarity of entity semantics of the teaching content and improve fusion quality of the teaching content.
Description
Technical Field
The invention relates to the field of knowledge maps, in particular to a knowledge map construction method based on teaching contents.
Background
The knowledge graph is used as a core and a foundation for transition from perception intelligence to cognition intelligence of artificial intelligence, and becomes one of key technologies for transformation and upgrading from networking to intellectualization in various industries; at present, the concept of education knowledge graph is not defined uniformly in academia, students explain the education knowledge graph from different research perspectives, and the existing research can be roughly divided into the following three categories: (1) From the knowledge organization perspective, the educational knowledge graph can be regarded as a knowledge network graph formed by knowledge points and semantic links thereof, and the education domain knowledge represented by the knowledge network graph comprises individual knowledge structures and intelligence of groups. (2) From the cognitive perspective of a learner, the educational knowledge graph aims at expressing different elements involved in the teaching process and various cognitive relations with educational significance, and state information of the learner on knowledge mastering is superimposed on the basis of the knowledge graph, so that a cognitive pattern of the learner can be formed. (3) From the knowledge service perspective, the educational knowledge graph can form a learning path oriented to knowledge learning and capability culture under the technical support of big data, artificial intelligence and the like on the basis of representing subject knowledge and knowledge relation; the education knowledge graph can also carry out semantic connection on discipline knowledge and teaching resource entities in a standardized and formalized mode, so that effective organization of online education resources is realized.
At present, researches on the first major education knowledge graphs are common, however, the researches are only based on analysis and extraction of original data sources, simple data processing is performed, and finally knowledge graphs of corresponding data are formed, so that accurate and efficient similarity processing and effective improvement on fusion quality of the data are not performed.
Therefore, in order to solve the above problems, a knowledge graph construction method based on teaching contents is needed, which can accurately and efficiently process similarity of entity semantics of the teaching contents and improve the fusion quality of the teaching contents.
Disclosure of Invention
Therefore, the invention aims to overcome the defects in the prior art, and provides a knowledge graph construction method based on teaching contents, which can accurately and efficiently process similarity of entity semantics of the teaching contents and can improve the fusion quality of the teaching contents.
The knowledge graph construction method based on the teaching content comprises the following steps:
s1, classifying teaching contents according to teaching subjects to obtain teaching subject contents;
s2, extracting information from the content of the teaching subjects to obtain extracted information; the information extraction includes: entity extraction, relationship extraction and event extraction;
s3, aligning entities in the extracted information by adopting a semantic similarity calculation method to obtain fusion information;
s4, judging whether the newly added teaching content in the fusion information accords with the quality standard, if so, keeping the newly added teaching content in the fusion information; if not, removing the newly added teaching content from the fusion information;
s5, constructing a knowledge graph based on the fusion information after judgment processing.
Further, in step S2, the entity extracts atomic information elements for extracting the content of the teaching subjects; the relation extraction is used for extracting semantic relations among a plurality of different entities in the teaching subject content; the event extraction is used for judging the category of the teaching subject content.
Further, in step S3, the calculation of the semantic similarity between the entities is determined according to the following formula:
wherein pmi (A, B) is the similarity between entity A and entity B; p (A, B) is the probability of correlation between entity A and entity B; p (A) is the probability of occurrence of entity A; p (B) is the probability of occurrence of entity B.
Further, in step S4, determining whether the newly added teaching content in the fusion information meets the quality standard includes:
s41, establishing a quality evaluation model; the quality evaluation model is as follows:
wherein L is a quality grade; k (k) i To get knowledge; k is a supervision corpus; m is the knowledge number of the newly added teaching content in the fusion information; i is a mark symbol, and the value is a positive integer;
s42, calculating according to a quality evaluation model to obtain a quality grade, and carrying out normalization processing on the quality grade to obtain a quality grade sequence L n The method comprises the steps of carrying out a first treatment on the surface of the Wherein n is the number of grades and the value is a positive integer;
s43, setting a quality grade threshold value eta, and judging a quality grade sequence L n Quality corresponding to the newly added teaching contentGrade L j Whether the quality level is larger than a quality level threshold eta, if yes, the newly added teaching content does not accord with the quality standard; if not, the newly added teaching content accords with the quality standard; wherein j is a sign symbol, and the value is a positive integer from 0 to n.
The beneficial effects of the invention are as follows: according to the knowledge graph construction method based on the teaching content, through extracting information of the teaching content and carrying out similarity processing on the extracted information entity semantics, fusion information of the teaching content is obtained, quality grade processing is carried out on the fusion information quality, and finally, a knowledge graph of the teaching content is constructed based on the processed fusion information, so that the teaching knowledge graph with clear structural lines and accurate data classification is obtained.
Drawings
The invention is further described below with reference to the accompanying drawings and examples:
FIG. 1 is a schematic flow chart of the method of the present invention.
Detailed Description
The invention is further described with reference to the accompanying drawings, in which:
the knowledge graph construction method based on the teaching content comprises the following steps:
s1, classifying teaching contents according to teaching subjects to obtain teaching subject contents; in this embodiment, according to different purposes of the teaching subjects, the teaching contents are classified, for example, the teaching subjects include Chinese, mathematics, english, history, geography and the like, and the teaching contents of different purposes are classified into one category, so that a plurality of teaching subject contents of different purposes are obtained.
S2, extracting information from the content of the teaching subjects to obtain extracted information; the information extraction includes: entity extraction, relationship extraction and event extraction;
s3, aligning entities in the extracted information by adopting a semantic similarity calculation method to obtain fusion information;
s4, judging whether the newly added teaching content in the fusion information accords with the quality standard, if so, keeping the newly added teaching content in the fusion information; if not, removing the newly added teaching content from the fusion information;
s5, constructing a knowledge graph based on the fusion information after judgment processing.
In this embodiment, in step S2, information extraction is performed on the content of the teaching subject, that is, knowledge extraction is performed from data sources of different grades and different chapters. Knowledge extraction includes entity extraction, relationship extraction, and event extraction;
the entity extraction is used for extracting atomic information elements in the content of the teaching subjects, and generally comprises labels such as terms, definitions/concepts, time/date, belonging relations and the like, and the specific label definition can be adjusted according to different tasks; wherein entity extraction also involves entity identification and linking; entity recognition, namely, recognizing an entity in a sentence or text, and linking the entity with a corresponding entity in a knowledge base. Wherein, the entity recognition and disambiguation technology is involved.
The relation extraction is used for extracting semantic relations among a plurality of different entities in the teaching subject content; the relation extraction is carried out based on a machine learning method, specifically, the category of the relation is predefined, some data are manually marked, the data are represented by design features, a classification method is selected for classifying the data (such as SVM, NN, naive Bayes and the like) to obtain a classification result, and the classification result is evaluated.
The event extraction is used for judging the category of the teaching subject content, extracting the event information interested by the user from natural language, and presenting the event information in a structured form, such as the time, place, reason, participants and the like of the event. Specifically, event extraction is performed on teaching subject content by using an event extraction method based on a dynamic multi-pooling convolutional neural network.
In this embodiment, in step S3, after the information extraction is completed, the information is aligned according to the semantic similarity between the entities by using a natural language processing technology, so as to eliminate contradiction and ambiguity of the entities and redundancy, and reduce the storage space and composition complexity. The method for calculating the similarity of the common semantics comprises the following steps:
wherein pmi (A, B) is the similarity between entity A and entity B; p (A, B) is the probability of correlation between entity A and entity B; p (A) is the probability of occurrence of entity A; p (B) is the probability of occurrence of entity B.
In probability theory, if a is uncorrelated with B, p (a, B) =p (a) p (B); if the correlation is greater, p (A, B) is greater than p (A) p (B). The log here comes from the theory of information theory, and it can be simply understood that when the function p (x) is log, a probability is converted into the information quantity (to be multiplied by-1 to change it into a positive number), and when the base is 2, it can be simply understood how many bits can be used to represent the variable.
In this embodiment, in step S4, for the newly added teaching content after fusion, the qualified part can be added into the knowledge base to ensure the quality of the knowledge base through quality evaluation and semantic similarity detection. Wherein, judging whether the newly added teaching content in the fusion information accords with the quality standard comprises the following steps:
s41, establishing a quality evaluation model; the quality evaluation model is as follows:
wherein L is a quality grade; k (k) i To get knowledge; k is a supervision corpus, and the supervision corpus is expected to be set manually; m the knowledge number of the teaching content is newly added to the fusion information; i is a mark symbol, and the value is a positive integer;
s42, calculating according to a quality evaluation model to obtain a quality grade, and carrying out normalization processing on the quality grade to obtain a quality grade sequence L n The quality level sequence L n Is composed of a plurality of quality grade values; wherein n is the number of grades and the value is a positive integer;
s43, setting a quality grade threshold value eta (generally setting eta to 0.8), and judging the quality gradeSequence L n Quality level L corresponding to newly added teaching content j Whether the quality level is larger than a quality level threshold eta, if yes, the newly added teaching content does not accord with the quality standard; if not, the newly added teaching content accords with the quality standard; wherein j is a sign symbol, and the value is a positive integer from 0 to n.
Through the judgment processing, the newly added teaching content meeting the quality standard is reserved, and the newly added teaching content not meeting the quality standard is removed from the fusion information set. Thereby making the entire knowledge base more hierarchical.
In this embodiment, in step S5, after the teaching information is fused, the iterative process is performed according to steps S2-S4, so that more teaching fusion information can be obtained, the teaching fusion information is displayed to obtain a teaching knowledge graph, and definition of each knowledge point in the knowledge graph, and division of hierarchical structure and knowledge chain are correspondingly implemented. The multi-source heterogeneous data are integrated through the knowledge graph, so that a simple and easy-to-use discipline knowledge graph is constructed, a teacher is helped to master dynamic and related discipline information, the teaching of the person is helped, and the teaching and research efficiency is improved. Provides structured and integrated learning resources for students, and enhances the learning interests of the students.
Finally, it is noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made thereto without departing from the spirit and scope of the technical solution of the present invention, which is intended to be covered by the scope of the claims of the present invention.
Claims (3)
1. A knowledge graph construction method based on teaching content is characterized in that: the method comprises the following steps:
s1, classifying teaching contents according to teaching subjects to obtain teaching subject contents;
s2, extracting information from the content of the teaching subjects to obtain extracted information; the information extraction includes: entity extraction, relationship extraction and event extraction;
s3, aligning entities in the extracted information by adopting a semantic similarity calculation method to obtain fusion information;
s4, judging whether the newly added teaching content in the fusion information accords with the quality standard, if so, keeping the newly added teaching content in the fusion information; if not, removing the newly added teaching content from the fusion information;
the step of judging whether the newly added teaching content in the fusion information accords with the quality standard comprises the following steps:
s41, establishing a quality evaluation model; the quality evaluation model is as follows:
wherein L is a quality grade; k (k) i To get knowledge; k is a supervision corpus; m is the knowledge number of the newly added teaching content in the fusion information; i is a mark symbol, and the value is a positive integer;
s42, calculating according to a quality evaluation model to obtain a quality grade, and carrying out normalization processing on the quality grade to obtain a quality grade sequence L n The method comprises the steps of carrying out a first treatment on the surface of the Wherein n is the number of grades and the value is a positive integer;
s43, setting a quality grade threshold value eta, and judging a quality grade sequence L n Quality level L corresponding to newly added teaching content j Whether the quality level is larger than a quality level threshold eta, if yes, the newly added teaching content does not accord with the quality standard; if not, the newly added teaching content accords with the quality standard; wherein j is a mark symbol, and the value of j is a positive integer from 0 to n;
s5, constructing a knowledge graph based on the fusion information after judgment processing.
2. The teaching content-based knowledge graph construction method according to claim 1, wherein: in step S2, the entity extracts atomic information elements for extracting the content of the teaching subjects; the relation extraction is used for extracting semantic relations among a plurality of different entities in the teaching subject content; the event extraction is used for judging the category of the teaching subject content.
3. The teaching content-based knowledge graph construction method according to claim 1, wherein: in step S3, the computation of the semantic similarity between entities is determined according to the following formula:
wherein pmi (A, B) is the similarity between entity A and entity B; p (A, B) is the probability of correlation between entity A and entity B; p (A) is the probability of occurrence of entity A; p (B) is the probability of occurrence of entity B.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911410556.7A CN111159356B (en) | 2019-12-31 | 2019-12-31 | Knowledge graph construction method based on teaching content |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911410556.7A CN111159356B (en) | 2019-12-31 | 2019-12-31 | Knowledge graph construction method based on teaching content |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111159356A CN111159356A (en) | 2020-05-15 |
| CN111159356B true CN111159356B (en) | 2023-06-09 |
Family
ID=70559939
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911410556.7A Active CN111159356B (en) | 2019-12-31 | 2019-12-31 | Knowledge graph construction method based on teaching content |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111159356B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111737498A (en) * | 2020-07-06 | 2020-10-02 | 成都信息工程大学 | Domain knowledge base establishing method applied to discrete manufacturing production process |
| CN112035680B (en) * | 2020-09-15 | 2023-07-04 | 重庆广播电视大学重庆工商职业学院 | Knowledge graph construction method of intelligent auxiliary learning machine |
| CN112579796A (en) * | 2020-12-30 | 2021-03-30 | 南京云起网络科技有限公司 | Knowledge graph construction method for teaching resources of online education classroom |
| CN113327473B (en) * | 2021-05-26 | 2023-02-28 | 武汉理工大学 | Virtual simulation teaching training system, control method, device and storage medium |
| CN113535982B (en) * | 2021-07-27 | 2022-05-24 | 南京邮电大学盐城大数据研究院有限公司 | Big data-based teaching system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101727903A (en) * | 2008-10-29 | 2010-06-09 | 中国科学院自动化研究所 | Pronunciation quality assessment and error detection method based on fusion of multiple characteristics and multiple systems |
| CN102945232A (en) * | 2012-11-16 | 2013-02-27 | 沈阳雅译网络技术有限公司 | Training-corpus quality evaluation and selection method orienting to statistical-machine translation |
| CN104794154A (en) * | 2015-03-11 | 2015-07-22 | 南通天呈医流互联网技术有限公司 | O2O service quality evaluation model for medical apparatus based on text mining |
| CN105630901A (en) * | 2015-12-21 | 2016-06-01 | 清华大学 | Knowledge graph representation learning method |
| CN109522545A (en) * | 2018-10-11 | 2019-03-26 | 华东师范大学 | A kind of appraisal procedure that more wheels are talked with coherent property amount |
| CN109857835A (en) * | 2018-12-28 | 2019-06-07 | 北京红山瑞达科技有限公司 | A kind of adaptive network security knowledge assessment method based on cognitive diagnosis theory |
| CN110263349A (en) * | 2019-03-08 | 2019-09-20 | 腾讯科技（深圳）有限公司 | Corpus assessment models training method, device, storage medium and computer equipment |
| CN110457442A (en) * | 2019-08-09 | 2019-11-15 | 国家电网有限公司 | The knowledge mapping construction method of smart grid-oriented customer service question and answer |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7743045B2 (en) * | 2005-08-10 | 2010-06-22 | Google Inc. | Detecting spam related and biased contexts for programmable search engines |
| US9349103B2 (en) * | 2012-01-09 | 2016-05-24 | DecisionQ Corporation | Application of machine learned Bayesian networks to detection of anomalies in complex systems |
| US9880999B2 (en) * | 2015-07-03 | 2018-01-30 | The University Of North Carolina At Charlotte | Natural language relatedness tool using mined semantic analysis |
| CN106909643B (en) * | 2017-02-20 | 2020-08-14 | 同济大学 | Knowledge graph-based social media big data topic discovery method |
| CN108664615A (en) * | 2017-05-12 | 2018-10-16 | 华中师范大学 | A kind of knowledge mapping construction method of discipline-oriented educational resource |
| US10606958B2 (en) * | 2018-01-10 | 2020-03-31 | International Business Machines Corporation | Machine learning modification and natural language processing |
| CN108509420A (en) * | 2018-03-29 | 2018-09-07 | 赵维平 | Gu spectrum and ancient culture knowledge mapping natural language processing method |
| CN109255031B (en) * | 2018-09-20 | 2022-02-11 | 苏州友教习亦教育科技有限公司 | Data processing method based on knowledge graph |
| CN109902298B (en) * | 2019-02-13 | 2023-04-18 | 东北师范大学 | Domain knowledge modeling and knowledge level estimation method in self-adaptive learning system |
| CN110188147B (en) * | 2019-05-22 | 2022-06-07 | 厦门无常师教育科技有限公司 | Knowledge graph-based document entity relationship discovery method and system |
-
2019
- 2019-12-31 CN CN201911410556.7A patent/CN111159356B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101727903A (en) * | 2008-10-29 | 2010-06-09 | 中国科学院自动化研究所 | Pronunciation quality assessment and error detection method based on fusion of multiple characteristics and multiple systems |
| CN102945232A (en) * | 2012-11-16 | 2013-02-27 | 沈阳雅译网络技术有限公司 | Training-corpus quality evaluation and selection method orienting to statistical-machine translation |
| CN104794154A (en) * | 2015-03-11 | 2015-07-22 | 南通天呈医流互联网技术有限公司 | O2O service quality evaluation model for medical apparatus based on text mining |
| CN105630901A (en) * | 2015-12-21 | 2016-06-01 | 清华大学 | Knowledge graph representation learning method |
| CN109522545A (en) * | 2018-10-11 | 2019-03-26 | 华东师范大学 | A kind of appraisal procedure that more wheels are talked with coherent property amount |
| CN109857835A (en) * | 2018-12-28 | 2019-06-07 | 北京红山瑞达科技有限公司 | A kind of adaptive network security knowledge assessment method based on cognitive diagnosis theory |
| CN110263349A (en) * | 2019-03-08 | 2019-09-20 | 腾讯科技（深圳）有限公司 | Corpus assessment models training method, device, storage medium and computer equipment |
| CN110457442A (en) * | 2019-08-09 | 2019-11-15 | 国家电网有限公司 | The knowledge mapping construction method of smart grid-oriented customer service question and answer |
Non-Patent Citations (2)
| Title |
|---|
| 《Multi-source Knowledge Graph》;Ren Lijuan;《2019 IEEE 3rd International Conference on Circuits，Systems and Devices》;全文 * |
| 《基于数学教学的知识图谱构建》;戈其平;《计算机技术与发展》;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111159356A (en) | 2020-05-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111159356B (en) | Knowledge graph construction method based on teaching content | |
| CN110147436B (en) | Education knowledge map and text-based hybrid automatic question-answering method | |
| CN109598995B (en) | Intelligent teaching system based on Bayesian knowledge tracking model | |
| CN110727779A (en) | Question-answering method and system based on multi-model fusion | |
| CN108182177A (en) | A kind of mathematics knowledge-ID automation mask method and device | |
| CN108228568B (en) | Mathematical problem semantic understanding method | |
| CN116795973B (en) | Text processing method and device based on artificial intelligence, electronic equipment and medium | |
| CN109949637B (en) | Automatic answering method and device for objective questions | |
| CN110990597B (en) | Cross-modal data retrieval system based on text semantic mapping and retrieval method thereof | |
| CN113312461A (en) | Intelligent question-answering method, device, equipment and medium based on natural language processing | |
| CN113886567A (en) | Teaching method and system based on knowledge graph | |
| CN111914550A (en) | Knowledge graph updating method and system for limited field | |
| CN113434688B (en) | Data processing method and device for public opinion classification model training | |
| CN113191148A (en) | Rail transit entity identification method based on semi-supervised learning and clustering | |
| CN110781681A (en) | Translation model-based elementary mathematic application problem automatic solving method and system | |
| CN110968708A (en) | Method and system for labeling education information resource attributes | |
| CN115858758A (en) | Intelligent customer service knowledge graph system with multiple unstructured data identification | |
| CN115600605A (en) | Method, system, equipment and storage medium for jointly extracting Chinese entity relationship | |
| CN106897274B (en) | Cross-language comment replying method | |
| CN110888989A (en) | Intelligent learning platform and construction method thereof | |
| CN116860978B (en) | Primary school Chinese personalized learning system based on knowledge graph and large model | |
| CN113742453A (en) | Artificial intelligence wrong question correlation method and system | |
| CN113901224A (en) | Knowledge distillation-based secret-related text recognition model training method, system and device | |
| Chatsiou | Text classification of manifestos and COVID-19 press briefings using BERT and convolutional neural networks | |
| CN112380868A (en) | Petition-purpose multi-classification device based on event triples and method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |