CN111597356A - Intelligent education knowledge map construction system and method - Google Patents
Intelligent education knowledge map construction system and method Download PDFInfo
- Publication number
- CN111597356A CN111597356A CN202010458553.7A CN202010458553A CN111597356A CN 111597356 A CN111597356 A CN 111597356A CN 202010458553 A CN202010458553 A CN 202010458553A CN 111597356 A CN111597356 A CN 111597356A
- Authority
- CN
- China
- Prior art keywords
- text
- knowledge
- education
- knowledge point
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; 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
- G06F16/31—Indexing; Data structures therefor; Storage structures
- G06F16/316—Indexing structures
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06F16/353—Clustering; Classification into predefined classes
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/12—Use of codes for handling textual entities
- G06F40/151—Transformation
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- Educational Technology (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Marketing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an intelligent education knowledge map construction system and method, which can not only carry out targeted text conversion and error correction standardization on education knowledge point data so as to improve the accuracy and reliability of the education knowledge point data, but also effectively mine the entity relevance between different education knowledge point data in the form of text elements, so that the constructed education knowledge map can truly and comprehensively reflect the relation of the different education knowledge point data on the knowledge level, and the data traceability and the data reliability of the education knowledge map are improved.
Description
Technical Field
The invention relates to the technical field of intelligent teaching, in particular to a system and a method for constructing an intelligent education knowledge map.
Background
The intelligent education technology is widely applied to knowledge teaching and course learning in different modes, and intelligent education can help teachers or students to achieve targeted and accurate education knowledge data processing and efficient knowledge teaching and learning. However, in the knowledge education field, the data amount of the related knowledge education data is huge and the data structure is complicated, and in order to improve the comprehensiveness of the education knowledge learning, the education knowledge data needs to be accurately mined and associated to construct the corresponding education knowledge map. However, the prior art is limited to the text attributes of the educational knowledge data, and does not construct the association between different educational knowledge data, which is not favorable for improving the data traceability and data reliability of the educational knowledge map.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides an intelligent education knowledge graph construction system and method, wherein the intelligent education knowledge graph construction system and method classifies the education knowledge point data about a certain subject, performs recognizable text conversion treatment and normalization treatment to generate a knowledge text set, determines the entity relevance among different text elements in the knowledge text set, and finally performs recombination arrangement and index labeling on all the text elements in the knowledge text set according to the entity relevance to construct an education knowledge graph about the certain subject; therefore, the system and the method for constructing the intelligent education knowledge map can not only carry out targeted text conversion and error correction standardization on the education knowledge point data so as to improve the accuracy and the reliability of the education knowledge point data, but also effectively mine the entity relevance among different education knowledge point data in the form of text elements so that the constructed education knowledge map can reflect the relation of the different education knowledge point data on the knowledge level more truly and comprehensively, thereby improving the data traceability and the data reliability of the education knowledge map.
The invention provides an intelligent education knowledge map construction system, which is characterized in that:
the intelligent education knowledge map construction system comprises an education knowledge point data classification module, a knowledge text set generation module, a text meta-entity association determination module and an education knowledge map construction module; wherein,
the education knowledge point data classification module is used for classifying the education knowledge point data of a certain subject from a preset education resource library about the content of the knowledge points;
the knowledge text set generating module is used for performing recognizable text conversion processing and normalized processing on the classified different education knowledge point data so as to generate a knowledge text set;
the text element entity association determining module is used for determining entity association among different text elements in the knowledge point text set;
the education knowledge map construction module is used for recombining, arranging and indexing all text elements in the knowledge point text set according to the entity relevance so as to construct and form an education knowledge map about a certain subject;
furthermore, the education knowledge point data classification module comprises an education knowledge point data acquisition sub-module, a knowledge difficulty value calculation sub-module and a classification determination sub-module; wherein,
the education knowledge point data acquisition submodule is used for acquiring the education knowledge point data about the certain subject from the preset education resource library according to a teaching course frame about the certain subject;
the knowledge difficulty value calculation submodule is used for calculating a knowledge content difficulty value corresponding to each piece of education knowledge point data through a preset subject knowledge neural network model;
the classification determination submodule is used for classifying all the education knowledge point data into education knowledge point data with different difficulty levels according to the knowledge content difficulty values;
further, the knowledge text set generation module comprises an identifiable text conversion processing sub-module, a normalization processing sub-module and a knowledge text set composition sub-module; wherein,
the recognizable text conversion processing submodule is used for performing recognizable text conversion processing on participles and/or short sentences on the classified education knowledge point data so as to obtain an initialized knowledge text;
the normalization processing sub-module is used for performing at least one of syntax normalization, logic normalization and wrongly written word normalization on the initialization knowledge text so as to convert the initialization knowledge text into a normalized knowledge text;
the knowledge text set composing submodule is used for composing all the normalized texts into a knowledge text set in a multi-dimensional matrix form according to the respective difficulty levels of the classified different education knowledge point data;
further, the text element entity association determining module comprises a text element generating sub-module and an entity association evaluation value calculating sub-module; wherein,
the text element generation submodule is used for converting each knowledge point text into a corresponding text element according to the text corpus and the text structure of each knowledge point text in the knowledge point text set;
the entity relevance evaluation value calculation submodule is used for analyzing and processing all text elements through a knowledge point text entity relevance evaluation neural network model so as to calculate entity relevance evaluation values of different text elements on text entity linguistic data and/or text entity structures;
further, the education knowledge map construction module comprises a recombination arrangement sub-module, an index labeling sub-module and a map conversion processing sub-module; wherein,
the restructuring and arranging sub-module is used for carrying out restructuring and arranging on all text elements in the knowledge point text set according to the entity relevance evaluation value corresponding to the entity relevance so as to generate a text element structure tree with different high and low entity relevance representation states;
the index labeling submodule is used for performing index labeling on text semantics and/or a text query path on each text element on the text element structure tree so as to obtain an index-labeled text element structure tree;
the map conversion processing submodule is used for performing two-dimensional map conversion processing on the indexing and labeling text element structure tree so as to construct and form an educational knowledge map related to a certain subject;
further, the text element entity association determining module is configured to determine entity associations between different text elements in the knowledge point text set, and the specific implementation process is as follows:
step A1, obtaining the education knowledge point data of a certain subject according to the education knowledge point data obtaining submodule, and obtaining knowledge content difficulty value corresponding to each education knowledge point data through a preset subject knowledge neural network model and the following formula (1)
In the above formula (1), P is the number of data of education knowledge points included in each subject, and P is 1,2,3, P; k is the difficulty level of the data of the knowledge points, and the value range of k is [0,22 ]]，dkThe difficulty level of the knowledge point data is the number of complex grammar structures, o, of the knowledge point data corresponding to kkFor the number of complex text structures of the knowledge point data with the difficulty level k corresponding to the knowledge point data,
the number of sentences with complex grammar structures and complex text structures in each item of education knowledge point data, j is the fraction of the knowledge point data in assessment, wjOrdering important knowledge points corresponding to the score ratio j of the knowledge point data in the assessment, f (o)kD) judging the difficulty of the knowledge points according to the complex grammar structure and the text structure quantity of each knowledge point data, wherein the judgment threshold value is 0.6, namely when the complex grammar structure and the text structure quantity of the knowledge point data exceed 0.6 of the total knowledge, the knowledge points are judged to be difficult knowledge points, otherwise, the knowledge points are easy knowledge points, and f (w)jK) judging whether the data is an important knowledge point according to the fraction ratio of the data of the knowledge points in the examination, wherein the judgment threshold value is 0.3, namely the data of the knowledge points in the examination exceeds 0.3 of the total fraction, the data is judged to be the important knowledge point, P (w)j,dk,ok) Acquiring a knowledge content difficulty value corresponding to each piece of education knowledge point data;
step A2, performing data association combination according to the knowledge content difficulty value corresponding to each item of the education knowledge point data obtained in the step A1 and the following formula (2), and obtaining a knowledge text set in the form of a multi-dimensional matrix
In the above formula (2), Π is a running multiplication, M is the number of subsets of the knowledge text to be composed in the form of a multidimensional matrix, i is the number of words contained in the data of each item of education knowledge point, and aiThe number of words contained in the data of each item of education knowledge point is the total number of phrases/short sentences corresponding to i, l is the number of subsets combined according to the initial, blThe index marking information of each subset corresponding to the subset number l combined according to the initial,
the times of the recombination and arrangement of the knowledge texts are determined, gamma is the multidimensional matrix ordering of each text phrase according to the sequence of the first letter and the second letter, F (a)i,bl) Acquiring a knowledge text set in a multi-dimensional matrix form;
step A3, analyzing and processing all text elements and the following formula (3) by the knowledge text set in the form of the multidimensional matrix acquired in the step A2 through the knowledge point text entity relevance evaluation neural network model, and executing the operation of obtaining entity relevance evaluation values of different text elements on text entity linguistic data or text entity structures according to the evaluation result
In the formula (3), N is the total number of the text elements, the value is greater than 2, h is the same text entity character ratio between two random text elements, x is the same text entity corpus ratio between two random text elements,
retrieving word senses between different text elements for random matching based on a linguistic databaseSimilarity, g is the number of the same text entity structure between two random text elements, y is the text proportion between the two random text elements belonging to the inclusion relation in the sense of word,
in order to retrieve the relevance between different text elements according to the language database random matching, f (a) is the text entity corpus information of each text element, f (b) is the text entity structure information of each text element, when the calculated value of P (h, l) is more than 1, the different text elements are represented to have certain relevance on the text entity corpus or the text entity structure, and the operation of obtaining the entity relevance evaluation value of the different text elements on the text entity corpus or the text entity structure is executed.
The invention also provides an intelligent education knowledge graph construction method, which is characterized by comprising the following steps:
step S1, obtaining education knowledge point data about a certain subject from a preset education resource library, and classifying the education knowledge point data about the content of the knowledge points;
step S2, recognizable text conversion processing and normalization processing are carried out on the classified different education knowledge point data, so that a knowledge text set is generated;
step S3, determining entity relevance among different text elements in the knowledge point text set;
step S4, according to the entity relevance, all the text elements in the knowledge point text set are recombined, arranged and indexed, so as to construct and form an educational knowledge graph related to a certain subject;
further, in the step S1, obtaining the data of education knowledge points about a subject from a preset education resource library, and performing a specific classification of the contents of the knowledge points on the data of education knowledge points,
step S101, acquiring the educational knowledge point data of the certain subject from the preset educational resource library according to a teaching course frame of the certain subject;
step S102, calculating knowledge content difficulty values corresponding to the data of each education knowledge point through a preset discipline knowledge neural network model;
step S103, classifying all education knowledge point data into education knowledge point data with different difficulty levels according to the difficulty values of the knowledge content calculated in the step S102;
or,
in step S2, the classifying the different education knowledge point data is performed with recognizable text conversion processing and normalization processing, so as to generate a knowledge text set specifically including,
step S201, performing recognizable text conversion processing on the classified education knowledge point data about participles and/or short sentences to obtain an initialized knowledge text;
step S202, at least one of grammar normalization, logic normalization and wrongly written word normalization is carried out on the initialization knowledge text, so that the initialization knowledge text is converted into a normalized knowledge text;
step S203, according to the respective difficulty levels of the classified different education knowledge point data, all the normalized texts are combined into a knowledge text set in a multi-dimensional matrix form;
further, in the step S3, the determining entity relevance between different text elements in the knowledge point text set specifically includes,
step S301, converting each knowledge point text into a corresponding text element according to the text corpus and the text structure of each knowledge point text in the knowledge point text set;
step S302, a knowledge point text entity relevance evaluation neural network model is constructed and optimized, and all text elements are analyzed and processed through the knowledge point text entity relevance evaluation neural network model, so that entity relevance evaluation values of different text elements on text entity linguistic data and/or text entity structures are obtained;
further, in the step S4, the step of constructing and forming an educational knowledge graph relating to the certain subject by performing reorganization arrangement and indexing on all text elements in the knowledge point text set according to the entity relevance includes,
step S401, according to the entity relevance evaluation value corresponding to the entity relevance, all text elements in the knowledge point text set are subjected to recombination arrangement related to the evaluation value height, so that a text element structure tree with different height entity relevance representation states is generated;
step S402, performing index labeling on each text element on the text element structure tree about text semantics and/or a text query path so as to obtain an index-labeled text element structure tree;
and S403, performing two-dimensional map conversion processing on the indexing labeled text meta-structure tree to construct and form an educational knowledge map about a certain subject.
Compared with the prior art, the intelligent education knowledge graph construction system and the intelligent education knowledge graph construction method have the advantages that the education knowledge graph data about a certain subject are classified, recognizable text conversion processing and normalization processing are carried out, so that a knowledge text set is generated, entity relevance among different text elements in the knowledge text set is determined, and finally, recombination arrangement and index labeling are carried out on all the text elements in the knowledge text set according to the entity relevance, so that the education knowledge graph about the certain subject is constructed; therefore, the system and the method for constructing the intelligent education knowledge map can not only carry out targeted text conversion and error correction standardization on the education knowledge point data so as to improve the accuracy and the reliability of the education knowledge point data, but also effectively mine the entity relevance among different education knowledge point data in the form of text elements so that the constructed education knowledge map can reflect the relation of the different education knowledge point data on the knowledge level more truly and comprehensively, thereby improving the data traceability and the data reliability of the education knowledge map.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic structural diagram of an intelligent education knowledge graph construction system provided by the invention.
FIG. 2 is a flow chart of the intelligent education knowledge graph construction method provided by the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a schematic structural diagram of an intelligent education knowledge graph construction system according to an embodiment of the present invention is shown. The intelligent education knowledge map construction system comprises an education knowledge point data classification module, a knowledge text set generation module, a text meta-entity association determination module and an education knowledge map construction module; the education knowledge point data classification module is used for classifying the education knowledge point data of a certain subject from a preset education resource library about the content of the knowledge points;
the knowledge text set generating module is used for performing recognizable text conversion processing and normalized processing on the classified different education knowledge point data so as to generate a knowledge text set;
the text element entity association determining module is used for determining entity association among different text elements in the knowledge point text set;
the education knowledge map construction module is used for recombining, arranging and indexing all text elements in the knowledge point text set according to the entity relevance so as to construct and form an education knowledge map about a certain subject.
The intelligent education knowledge map construction system is different from other knowledge map construction modes in the prior art, and not only can perform preprocessing such as difficulty level classification, recognizable text conversion and error correction specification on education knowledge map data to improve the correctness and reliability of the education knowledge map data so as to ensure the effectiveness of subsequent knowledge map construction, but also can evaluate the entity relevance among different education knowledge map data in a text element form so as to improve the construction efficiency and the knowledge relevance authenticity of the education knowledge map.
Preferably, the education knowledge point data classification module comprises an education knowledge point data acquisition submodule, a knowledge difficulty value calculation submodule and a classification determination submodule; wherein,
the education knowledge point data acquisition submodule is used for acquiring the education knowledge point data about the certain subject from the preset education resource library according to a teaching course frame about the certain subject;
the knowledge difficulty value calculation submodule is used for calculating a knowledge content difficulty value corresponding to each piece of education knowledge point data through a preset subject knowledge neural network model;
the classification determination submodule is used for classifying all the education knowledge point data into the education knowledge point data with different difficulty levels according to the knowledge content difficulty value.
The education knowledge point data classification module classifies all education knowledge point data by taking knowledge content difficulty values of the education knowledge point data as a reference, so that the different processing of the education knowledge point data with different difficulties can be realized, the deviation of subsequent analysis and processing caused by the difference of the difficulties of the different education knowledge point data is avoided, the processing pertinence and effectiveness of the different education knowledge point data are improved, and the repeatability of the processing steps such as subsequent text conversion and error correction specifications is reduced.
Preferably, the knowledge text set generating module comprises an identifiable text conversion processing sub-module, a normalization processing sub-module and a knowledge text set composing sub-module; wherein,
the recognizable text conversion processing submodule is used for performing recognizable text conversion processing on the classified education knowledge point data about participles and/or short sentences so as to obtain an initialized knowledge text;
the normalization processing sub-module is used for performing at least one of syntax normalization, logic normalization and wrongly written word normalization on the initialization knowledge text so as to convert the initialization knowledge text into a normalized knowledge text;
the knowledge text set forming submodule is used for forming all the normalized texts into a knowledge text set in a multi-dimensional matrix form according to the respective difficulty levels of the classified different education knowledge point data.
The knowledge text set generation module can improve the standardization degree of the education knowledge point data and reduce the error rate by performing recognizable text conversion processing and standardized processing on the education knowledge point data, so that the condition that the education knowledge point data cannot be recognized or edited cannot occur during the subsequent analysis processing of the education knowledge point data, and the error rate of processing the education knowledge point data is greatly reduced.
Preferably, the text element entity association determining module comprises a text element generating sub-module and an entity association evaluation value calculating sub-module; wherein,
the text element generation submodule is used for converting each knowledge point text into a corresponding text element according to the text corpus and the text structure of each knowledge point text in the knowledge point text set;
the entity relevance evaluation value calculation submodule is used for analyzing and processing all text elements through a knowledge point text entity relevance evaluation neural network model so as to calculate entity relevance evaluation values of different text elements on text entity linguistic data and/or text entity structures.
The text element entity association determination module converts the text of the knowledge point into the text elements associated with the literary sketch and the text structure, so that the data volume of the education knowledge point data can be effectively compressed, and meanwhile, the effective data part of the education knowledge point data can be reserved to the maximum extent, and the efficiency and the accuracy of calculating the entity association evaluation value are improved.
Preferably, the educational knowledge graph construction module comprises a recombination arrangement submodule, an index labeling submodule and a graph transformation processing submodule; wherein,
the restructuring and arranging sub-module is used for carrying out restructuring and arranging on all text elements in the knowledge point text set according to the entity relevance evaluation value corresponding to the entity relevance so as to generate a text element structure tree with different high and low entity relevance representation states;
the index labeling submodule is used for performing index labeling on each text element on the text element structure tree about text semantics and/or a text query path so as to obtain an index-labeled text element structure tree;
the map conversion processing submodule is used for carrying out two-dimensional map conversion processing on the indexing labeled text meta-structure tree so as to construct and form an educational knowledge map related to a certain subject.
The education knowledge map building module carries out recombination arrangement and index labeling on all text elements by taking the entity association evaluation value as a reference, and can more comprehensively reflect the entity association degree between different education knowledge point data, so that the data traceability and the data reliability of the education knowledge map are improved.
Preferably, the text element entity association determining module is configured to determine entity associations between different text elements in the knowledge point text collection, and a specific implementation process of the text element entity association determining module is as follows:
step A1, obtaining the data of the education knowledge point of a certain subject according to the data obtaining submodule of the education knowledge point, obtaining the knowledge content difficulty value corresponding to each item of the data of the education knowledge point through the preset subject knowledge neural network model and the following formula (1)
In the above formula (1), P is the number of data of education knowledge points included in each subject, and P is 1,2,3, P; k is the difficulty level of the data of the knowledge point, and the value range is [0,22 ]]，dkFor the complex grammar structure quantity, o, of the knowledge point data corresponding to the difficulty level k of the knowledge point datakFor the number of complex text structures of the knowledge point data with the difficulty level k corresponding to the knowledge point data,
the number of sentences with complex grammar structures and complex text structures in each item of education knowledge point data, j is the fraction of the knowledge point data in assessment, wjOrdering important knowledge points corresponding to the score ratio j of the knowledge point data in the assessment, f (o)kD) judging the difficulty of the knowledge points according to the complex grammar structure and the text structure quantity of each knowledge point data, wherein the judgment threshold value is 0.6, namely when the complex grammar structure and the text structure quantity of the knowledge point data exceed 0.6 of the total knowledge, the knowledge points are judged to be difficult knowledge points, otherwise, the knowledge points are easy knowledge points, and f (w)jK) judging whether the data is an important knowledge point according to the fraction ratio of the data of the knowledge points in the examination, wherein the judgment threshold value is 0.3, namely the data of the knowledge points in the examination exceeds 0.3 of the total fraction, the data is judged to be the important knowledge point, P (w)j,dk,ok) Acquiring a knowledge content difficulty value corresponding to each piece of education knowledge point data;
step A2, according to the knowledge content difficulty value corresponding to each item of the education knowledge point data obtained in step A1 and the following formula (2), performing data association combination to obtain a knowledge text set in the form of a multidimensional matrix
In the above formula (2), Π is a running multiplication, M is the number of subsets of the knowledge text to be composed in the form of a multidimensional matrix, i is the number of words contained in the data of each item of education knowledge data, and aiThe number of words contained in the data of each item of education knowledge point is the total number of phrases/short sentences corresponding to i, l is the number of subsets combined according to the initial, blThe index marking information of each subset corresponding to the subset number l combined according to the initial,
gamma is the multidimensional matrix ordering of the text phrases according to the order of the first letter and the second letter, F (a)i,bl) Acquiring a knowledge text set in a multi-dimensional matrix form;
step A3, analyzing all text elements and the following formula (3) by the knowledge text set in the form of the multidimensional matrix acquired in the step A2 through the knowledge point text entity relevance evaluation neural network model, and executing the operation of obtaining the entity relevance evaluation value of different text elements on the text entity corpus or the text entity structure according to the evaluation result
In the formula (3), N is the total number of the text elements, the value is greater than 2, h is the same text entity character ratio between two random text elements, x is the same text entity corpus ratio between two random text elements,
is root ofRandomly matching and searching word sense similarity between different text elements according to a language database, wherein g is the number of the same text entity structures between two random text elements, y is the text proportion between the two random text elements belonging to the inclusion relation on the word sense,
in order to retrieve the relevance between different text elements according to the language database random matching, f (a) is the text entity corpus information of each text element, f (b) is the text entity structure information of each text element, when the calculated value of P (h, l) is more than 1, the different text elements are represented to have certain relevance on the text entity corpus or the text entity structure, and the operation of obtaining the entity relevance evaluation value of the different text elements on the text entity corpus or the text entity structure is executed.
The calculation process of the text element entity association determination module effectively excavates the entity association between different education knowledge point data in a text element form to provide technical support, the content of the education knowledge map is expanded through intelligent education autonomous learning, the relation of the different education knowledge point data on the knowledge level is truly and comprehensively reflected through the constructed education knowledge map, and the data comprehensiveness, traceability and data reliability of the education knowledge map are further improved.
Referring to fig. 2, a flow chart of the intelligent education knowledge graph construction method provided by the embodiment of the invention is schematically shown. The intelligent education knowledge graph construction method comprises the following steps:
step S1, obtaining education knowledge point data about a certain subject from a preset education resource library, and classifying the education knowledge point data about the content of the knowledge points;
step S2, recognizable text conversion processing and normalization processing are carried out on the classified different education knowledge point data, so as to generate a knowledge text set;
step S3, determining entity relevance among different text elements in the knowledge point text set;
and step S4, according to the entity relevance, performing recombination arrangement and index labeling on all text elements in the knowledge point text set so as to construct and form an educational knowledge graph related to a certain subject.
The intelligent education knowledge map construction method is different from other knowledge map construction modes in the prior art, and not only can improve the accuracy and reliability of the education knowledge map data by preprocessing the education knowledge map data per se, such as difficulty level classification, recognizable text conversion, error correction specification and the like so as to ensure the effectiveness of subsequent knowledge map construction, but also can evaluate the entity relevance among different education knowledge map data in a text element form so as to improve the construction efficiency and the knowledge relevance authenticity of the education knowledge map.
Preferably, in the step S1, the method includes obtaining educational knowledge point data on a subject from a preset educational resource library, and performing a specific classification on the content of the educational knowledge point data,
step S101, obtaining the data of the education knowledge point of a certain subject from the preset education resource library according to the teaching course frame of the certain subject;
step S102, calculating knowledge content difficulty values corresponding to the data of each item of education knowledge point through a preset disciplinary knowledge neural network model;
and step S103, classifying all the education knowledge point data into education knowledge point data with different difficulty levels according to the difficulty value of the knowledge content calculated in the step S102.
The education knowledge point data with different difficulties can be distinguished and processed by classifying all the education knowledge point data by taking the knowledge content difficulty values of the education knowledge point data as the reference, so that the deviation of subsequent analysis and processing caused by the difference of the difficulties of different education knowledge point data per se is avoided, the processing pertinence and effectiveness of different education knowledge point data are improved, and the complexity of the processing steps such as subsequent text conversion, error correction specification and the like is reduced.
Preferably, in the step S2, the recognizable text conversion processing and the normalization processing are performed on the classified different education knowledge point data, so that the generating of the knowledge text set specifically includes,
step S201, performing recognizable text conversion processing on the classified education knowledge point data about participles and/or short sentences so as to obtain an initialized knowledge text;
step S202, at least one of grammar normalization, logic normalization and wrongly written word normalization is carried out on the initialization knowledge text, so that the initialization knowledge text is converted into a normalized knowledge text;
step S203, according to the respective difficulty level of the classified different education knowledge point data, all the normalized texts are combined into a knowledge text set in a multi-dimensional matrix form.
The education knowledge point data can be subjected to recognizable text conversion processing and normalization processing, so that the standardization degree of the education knowledge point data can be improved, the error rate can be reduced, the subsequent analysis processing of the education knowledge point data can be conveniently carried out, the condition that the education knowledge point data cannot be recognized or edited cannot occur, and the error rate of processing the education knowledge point data is greatly reduced.
Preferably, in this step S3, determining the entity associations between the different text elements in the knowledge point text collection specifically includes,
step S301, converting each knowledge point text into a corresponding text element according to the text corpus and the text structure of each knowledge point text in the knowledge point text set;
step S302, a knowledge point text entity relevance evaluation neural network model is constructed and optimized, and all text elements are analyzed and processed through the knowledge point text entity relevance evaluation neural network model, so that entity relevance evaluation values of different text elements on text entity linguistic data and/or text entity structures are obtained.
By converting the knowledge point text into text elements related to the literary sketch and the text structure, the data volume of the education knowledge point data can be effectively compressed, and meanwhile, the effective data part of the education knowledge point data can be reserved to the maximum extent, so that the efficiency and the accuracy of calculating the entity relevance evaluation value are improved.
Preferably, in step S4, according to the entity relevance, all the text elements in the knowledge point text set are regrouped and indexed, so as to construct an educational knowledge graph relating to the certain subject,
step S401, according to the entity relevance evaluation value corresponding to the entity relevance, all text elements in the knowledge point text set are subjected to recombination arrangement related to the evaluation value height, so that a text element structure tree with different height entity relevance representation states is generated;
step S402, performing index labeling on each text element on the text element structure tree about text semantics and/or a text query path so as to obtain an index-labeled text element structure tree;
step S403, performing two-dimensional map transformation processing on the indexed and labeled text meta-structure tree, so as to construct and form an educational knowledge map related to the certain subject.
By recombining, arranging and indexing all text elements by taking the entity association evaluation value as a reference, the entity association degree between different education knowledge point data can be more comprehensively reflected, so that the data traceability and the data reliability of the education knowledge map are improved.
As can be seen from the content of the above embodiment, the intelligent education knowledge graph construction system and method classify the education knowledge point data about a certain subject, and then perform recognizable text conversion processing and normalization processing to generate a knowledge text set, and further determine the entity association between different text elements in the knowledge text set, and finally perform recombination arrangement and index labeling on all text elements in the knowledge text set according to the entity association to construct an education knowledge graph about the certain subject; therefore, the system and the method for constructing the intelligent education knowledge map can not only carry out targeted text conversion and error correction standardization on the education knowledge point data so as to improve the accuracy and the reliability of the education knowledge point data, but also effectively mine the entity relevance among different education knowledge point data in the form of text elements so that the constructed education knowledge map can reflect the relation of the different education knowledge point data on the knowledge level more truly and comprehensively, thereby improving the data traceability and the data reliability of the education knowledge map.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. Intelligent education knowledge map construction system, its characterized in that:
the intelligent education knowledge map construction system comprises an education knowledge point data classification module, a knowledge text set generation module, a text meta-entity association determination module and an education knowledge map construction module; wherein,
the education knowledge point data classification module is used for classifying the education knowledge point data of a certain subject from a preset education resource library about the content of the knowledge points;
the knowledge text set generating module is used for performing recognizable text conversion processing and normalized processing on the classified different education knowledge point data so as to generate a knowledge text set;
the text element entity association determining module is used for determining entity association among different text elements in the knowledge point text set;
and the education knowledge map construction module is used for recombining, arranging and indexing all text elements in the knowledge point text set according to the entity relevance so as to construct and form an education knowledge map about a certain subject.
2. The intelligent educational knowledge graph building system of claim 1, wherein:
the education knowledge point data classification module comprises an education knowledge point data acquisition submodule, a knowledge difficulty value calculation submodule and a classification determination submodule; wherein,
the education knowledge point data acquisition submodule is used for acquiring the education knowledge point data about the certain subject from the preset education resource library according to a teaching course frame about the certain subject;
the knowledge difficulty value calculation submodule is used for calculating a knowledge content difficulty value corresponding to each piece of education knowledge point data through a preset subject knowledge neural network model;
and the classification determination submodule is used for classifying all the education knowledge point data into the education knowledge point data with different difficulty levels according to the knowledge content difficulty values.
3. The intelligent educational knowledge graph building system of claim 1, wherein:
the knowledge text set generation module comprises an identifiable text conversion processing sub-module, a normalization processing sub-module and a knowledge text set composition sub-module; wherein,
the recognizable text conversion processing submodule is used for performing recognizable text conversion processing on participles and/or short sentences on the classified education knowledge point data so as to obtain an initialized knowledge text;
the normalization processing sub-module is used for performing at least one of syntax normalization, logic normalization and wrongly written word normalization on the initialization knowledge text so as to convert the initialization knowledge text into a normalized knowledge text;
and the knowledge text set forming submodule is used for forming a knowledge text set in a multi-dimensional matrix form from all the normalized texts according to the respective difficulty levels of the classified different education knowledge point data.
4. The intelligent educational knowledge graph building system of claim 1, wherein:
the text element entity association determining module comprises a text element generating sub-module and an entity association evaluation value calculating sub-module; wherein,
the text element generation submodule is used for converting each knowledge point text into a corresponding text element according to the text corpus and the text structure of each knowledge point text in the knowledge point text set;
the entity relevance evaluation value calculation submodule is used for analyzing and processing all text elements through the knowledge point text entity relevance evaluation neural network model so as to calculate entity relevance evaluation values of different text elements on text entity linguistic data and/or text entity structures.
5. The intelligent educational knowledge graph building system of claim 1, wherein:
the education knowledge map construction module comprises a recombination arrangement submodule, an index labeling submodule and a map conversion processing submodule; wherein,
the restructuring and arranging sub-module is used for carrying out restructuring and arranging on all text elements in the knowledge point text set according to the entity relevance evaluation value corresponding to the entity relevance so as to generate a text element structure tree with different high and low entity relevance representation states;
the index labeling submodule is used for performing index labeling on text semantics and/or a text query path on each text element on the text element structure tree so as to obtain an index-labeled text element structure tree;
and the map conversion processing submodule is used for performing two-dimensional map conversion processing on the indexing and labeling text meta-structure tree so as to construct and form an educational knowledge map related to a certain subject.
6. The intelligent educational knowledge graph building system of claim 1, wherein:
the text element entity association determining module is used for determining entity association among different text elements in the knowledge point text set, and the specific implementation process is as follows:
step A1, obtaining the education knowledge point data of a certain subject according to the education knowledge point data obtaining submodule, and obtaining knowledge content difficulty value corresponding to each education knowledge point data through a preset subject knowledge neural network model and the following formula (1)
In the above formula (1), P is the number of data of education knowledge points included in each subject, and P is 1,2,3, P; k is the difficulty level of the data of the knowledge points, and the value range of k is [0,22 ]]，dkThe difficulty level of the knowledge point data is the number of complex grammar structures, o, of the knowledge point data corresponding to kkFor the number of complex text structures of the knowledge point data with the difficulty level k corresponding to the knowledge point data,
the number of sentences with complex grammar structures and complex text structures in each item of education knowledge point data, j is the fraction of the knowledge point data in assessment, wjOrdering important knowledge points corresponding to the score ratio j of the knowledge point data in the assessment, f (o)kD) judging the difficulty of the knowledge points according to the complex grammar structure and the text structure quantity of each knowledge point data, wherein the judgment threshold value is 0.6, namely when the complex grammar structure and the text structure quantity of the knowledge point data exceed 0.6 of the total knowledge, the knowledge points are judged to be difficult knowledge points, otherwise, the knowledge points are easy knowledge points, and f (w)jK) judging whether the data is an important knowledge point according to the fraction ratio of the data of the knowledge points in the examination, wherein the judgment threshold value is 0.3, namely the data of the knowledge points in the examination exceeds 0.3 of the total fraction, the data is judged to be the important knowledge point, P (w)j,dk,ok) Acquiring a knowledge content difficulty value corresponding to each piece of education knowledge point data;
step A2, performing data association combination according to the knowledge content difficulty value corresponding to each item of the education knowledge point data obtained in the step A1 and the following formula (2), and obtaining a knowledge text set in the form of a multi-dimensional matrix
In the above formula (2), Π is a running multiplication, M is the number of subsets of the knowledge text to be composed in the form of a multidimensional matrix, i is the number of words contained in the data of each item of education knowledge point, and aiThe number of words contained in the data of each item of education knowledge point is the total number of phrases/short sentences corresponding to i, l is the number of subsets combined according to the initial, blThe index marking information of each subset corresponding to the subset number l combined according to the initial,
the times of the recombination and arrangement of the knowledge texts are determined, gamma is the multidimensional matrix ordering of each text phrase according to the sequence of the first letter and the second letter, F (a)i,bl) Acquiring a knowledge text set in a multi-dimensional matrix form;
step A3, analyzing and processing all text elements and the following formula (3) by the knowledge text set in the form of the multidimensional matrix acquired in the step A2 through the knowledge point text entity relevance evaluation neural network model, and executing the operation of obtaining entity relevance evaluation values of different text elements on text entity linguistic data or text entity structures according to the evaluation result
In the formula (3), N is the total number of the text elements, the value is greater than 2, h is the same text entity character ratio between two random text elements, x is the same text entity corpus ratio between two random text elements,
in order to search the word sense similarity between different text elements according to the random matching of the language database, g is the number of the same text entity structure between two random text elements, y is the text proportion between the two random text elements belonging to the inclusion relation on the word sense,
in order to retrieve the relevance between different text elements according to the language database random matching, f (a) is the text entity corpus information of each text element, f (b) is the text entity structure information of each text element, when the calculated value of P (h, l) is more than 1, the different text elements are represented to have certain relevance on the text entity corpus or the text entity structure, and the operation of obtaining the entity relevance evaluation value of the different text elements on the text entity corpus or the text entity structure is executed.
7. The intelligent education knowledge graph construction method is characterized by comprising the following steps of:
step S1, obtaining education knowledge point data about a certain subject from a preset education resource library, and classifying the education knowledge point data about the content of the knowledge points;
step S2, recognizable text conversion processing and normalization processing are carried out on the classified different education knowledge point data, so that a knowledge text set is generated;
step S3, determining entity relevance among different text elements in the knowledge point text set;
and step S4, according to the entity relevance, performing recombination arrangement and index labeling on all text elements in the knowledge point text set so as to construct and form an educational knowledge graph related to a certain subject.
8. The intelligent educational knowledge graph construction method of claim 7, wherein:
in the step S1, the step of obtaining the education knowledge point data about a certain subject from the preset education resource library and the step of classifying the education knowledge point data about the content of the knowledge point specifically includes,
step S101, acquiring the educational knowledge point data of the certain subject from the preset educational resource library according to a teaching course frame of the certain subject;
step S102, calculating knowledge content difficulty values corresponding to the data of each education knowledge point through a preset discipline knowledge neural network model;
step S103, classifying all education knowledge point data into education knowledge point data with different difficulty levels according to the difficulty values of the knowledge content calculated in the step S102;
or,
in step S2, the classifying the different education knowledge point data is performed with recognizable text conversion processing and normalization processing, so as to generate a knowledge text set specifically including,
step S201, performing recognizable text conversion processing on the classified education knowledge point data about participles and/or short sentences to obtain an initialized knowledge text;
step S202, at least one of grammar normalization, logic normalization and wrongly written word normalization is carried out on the initialization knowledge text, so that the initialization knowledge text is converted into a normalized knowledge text;
and S203, forming a knowledge text set in a multi-dimensional matrix form by all the normalized texts according to the respective difficulty levels of the classified different education knowledge point data.
9. The intelligent educational knowledge graph construction method of claim 7, wherein:
in step S3, the determining of the entity associations between different text elements in the knowledge point text collection specifically includes,
step S301, converting each knowledge point text into a corresponding text element according to the text corpus and the text structure of each knowledge point text in the knowledge point text set;
step S302, a knowledge point text entity relevance evaluation neural network model is constructed and optimized, and all text elements are analyzed and processed through the knowledge point text entity relevance evaluation neural network model, so that entity relevance evaluation values of different text elements on text entity linguistic data and/or text entity structures are obtained.
10. The intelligent educational knowledge graph construction method of claim 7, wherein:
in step S4, the step of constructing and forming an educational knowledge graph relating to the subject by reorganizing and indexing all the text elements in the knowledge point text set according to the entity relevance includes,
step S401, according to the entity relevance evaluation value corresponding to the entity relevance, all text elements in the knowledge point text set are subjected to recombination arrangement related to the evaluation value height, so that a text element structure tree with different height entity relevance representation states is generated;
step S402, performing index labeling on each text element on the text element structure tree about text semantics and/or a text query path so as to obtain an index-labeled text element structure tree;
and S403, performing two-dimensional map conversion processing on the indexing labeled text meta-structure tree to construct and form an educational knowledge map about a certain subject.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010458553.7A CN111597356B (en) | 2020-05-27 | 2020-05-27 | Intelligent education knowledge map construction system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010458553.7A CN111597356B (en) | 2020-05-27 | 2020-05-27 | Intelligent education knowledge map construction system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111597356A true CN111597356A (en) | 2020-08-28 |
| CN111597356B CN111597356B (en) | 2021-05-11 |
Family
ID=72186305
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010458553.7A Active CN111597356B (en) | 2020-05-27 | 2020-05-27 | Intelligent education knowledge map construction system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111597356B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112183728A (en) * | 2020-09-29 | 2021-01-05 | 上海松鼠课堂人工智能科技有限公司 | Deep learning-based learning strategy generation method and system |
| CN113569054A (en) * | 2021-05-12 | 2021-10-29 | 浙江工业大学 | Knowledge graph construction method and system for multi-source Chinese financial bulletin document |
| CN113935320A (en) * | 2021-10-14 | 2022-01-14 | 重庆翰海睿智大数据科技股份有限公司 | Knowledge graph construction method and system based on big data analysis |
| CN114153360A (en) * | 2021-12-07 | 2022-03-08 | 华南理工大学 | A human-computer interaction system and method based on artificial intelligence |
| CN114637846A (en) * | 2022-03-11 | 2022-06-17 | 游密科技(深圳)有限公司 | Video data processing method, video data processing device, computer equipment and storage medium |
| CN115203441A (en) * | 2022-09-19 | 2022-10-18 | 江西风向标智能科技有限公司 | Method, system, storage medium and equipment for analyzing high school mathematical formula |
| CN115495593A (en) * | 2022-10-13 | 2022-12-20 | 中原工学院 | Mathematical knowledge graph construction method based on big data |
| CN116186020A (en) * | 2023-04-28 | 2023-05-30 | 中信证券股份有限公司 | Feature information processing method, device, electronic equipment and computer readable medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110137919A1 (en) * | 2009-12-09 | 2011-06-09 | Electronics And Telecommunications Research Institute | Apparatus and method for knowledge graph stabilization |
| CN109783693A (en) * | 2019-01-18 | 2019-05-21 | 广东小天才科技有限公司 | Method and system for determining video semantics and knowledge points |
| CN110059130A (en) * | 2019-05-13 | 2019-07-26 | 上海乂学教育科技有限公司 | Artificial intelligence K12 education and study Content Management System |
| CN111046194A (en) * | 2019-12-31 | 2020-04-21 | 重庆和贯科技有限公司 | Method for constructing multi-mode teaching knowledge graph |
-
2020
- 2020-05-27 CN CN202010458553.7A patent/CN111597356B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110137919A1 (en) * | 2009-12-09 | 2011-06-09 | Electronics And Telecommunications Research Institute | Apparatus and method for knowledge graph stabilization |
| CN109783693A (en) * | 2019-01-18 | 2019-05-21 | 广东小天才科技有限公司 | Method and system for determining video semantics and knowledge points |
| CN110059130A (en) * | 2019-05-13 | 2019-07-26 | 上海乂学教育科技有限公司 | Artificial intelligence K12 education and study Content Management System |
| CN111046194A (en) * | 2019-12-31 | 2020-04-21 | 重庆和贯科技有限公司 | Method for constructing multi-mode teaching knowledge graph |
Non-Patent Citations (1)
| Title |
|---|
| 朱福军: "基于学习元的领域知识图谱自动构建研究", 《中国优秀硕士学位论文全文数据库 社会科学Ⅱ辑》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112183728A (en) * | 2020-09-29 | 2021-01-05 | 上海松鼠课堂人工智能科技有限公司 | Deep learning-based learning strategy generation method and system |
| CN113569054A (en) * | 2021-05-12 | 2021-10-29 | 浙江工业大学 | Knowledge graph construction method and system for multi-source Chinese financial bulletin document |
| CN113569054B (en) * | 2021-05-12 | 2024-10-18 | 浙江工业大学 | Knowledge graph construction method and system for multi-source Chinese financial bulletin document |
| CN113935320A (en) * | 2021-10-14 | 2022-01-14 | 重庆翰海睿智大数据科技股份有限公司 | Knowledge graph construction method and system based on big data analysis |
| CN114153360A (en) * | 2021-12-07 | 2022-03-08 | 华南理工大学 | A human-computer interaction system and method based on artificial intelligence |
| CN114637846A (en) * | 2022-03-11 | 2022-06-17 | 游密科技(深圳)有限公司 | Video data processing method, video data processing device, computer equipment and storage medium |
| CN115203441A (en) * | 2022-09-19 | 2022-10-18 | 江西风向标智能科技有限公司 | Method, system, storage medium and equipment for analyzing high school mathematical formula |
| CN115495593A (en) * | 2022-10-13 | 2022-12-20 | 中原工学院 | Mathematical knowledge graph construction method based on big data |
| CN116186020A (en) * | 2023-04-28 | 2023-05-30 | 中信证券股份有限公司 | Feature information processing method, device, electronic equipment and computer readable medium |
| CN116186020B (en) * | 2023-04-28 | 2023-07-04 | 中信证券股份有限公司 | Feature information processing method, device, electronic equipment and computer readable medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111597356B (en) | 2021-05-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111597356B (en) | Intelligent education knowledge map construction system and method | |
| CN110502621B (en) | Question answering method, question answering device, computer equipment and storage medium | |
| CN110147436B (en) | A hybrid automatic question answering method based on educational knowledge graph and text | |
| US9218339B2 (en) | Computer-implemented systems and methods for content scoring of spoken responses | |
| CN100378724C (en) | Method for sentence structure analysis based on mobile configuration concept and method for natural language search using of it | |
| JP3856778B2 (en) | Document classification apparatus and document classification method for multiple languages | |
| CN110727779A (en) | Question-answering method and system based on multi-model fusion | |
| CN112732934A (en) | Power grid equipment word segmentation dictionary and fault case library construction method | |
| CN113191148B (en) | Rail transit entity identification method based on semi-supervised learning and clustering | |
| CN113806563A (en) | Construction method of architect knowledge map for multi-source and heterogeneous architectural humanities historical materials | |
| CN112380848B (en) | Text generation method, device, equipment and storage medium | |
| CN110781681B (en) | Automatic first-class mathematic application problem solving method and system based on translation model | |
| CN112000802A (en) | Software defect positioning method based on similarity integration | |
| CN118981522A (en) | Database AI question answering system and method based on large language model and retrieval enhancement | |
| CN117592470A (en) | Low-cost gazette data extraction method driven by large language model | |
| CN112949410B (en) | Method, device, equipment and storage medium for solving problems of character questions in artificial intelligence science | |
| CN112036169A (en) | Event recognition model optimization method, device and equipment and readable storage medium | |
| CN117573797A (en) | Test question retrieval method based on large language model | |
| CN120104765A (en) | A large language model hallucination detection method and system based on knowledge graph structure | |
| CN112035668A (en) | Event subject recognition model optimization method, device and equipment and readable storage medium | |
| Alrehily et al. | Intelligent electronic assessment for subjective exams | |
| CN119782456A (en) | Data question answering method and system based on graph neural network and large language model | |
| CN114880471B (en) | Electronic medical record quality assessment method and system based on text classification algorithm | |
| Patrick et al. | Developing SNOMED CT subsets from clinical notes for intensive care service | |
| CN110807096A (en) | Information pair matching method and system on small sample set |
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 | ||
| CB02 | Change of applicant information |
Address after: 200237 9 / F and 10 / F, building 2, No. 188, Yizhou Road, Xuhui District, Shanghai Applicant after: Shanghai squirrel classroom Artificial Intelligence Technology Co.,Ltd. Address before: 200237 9 / F and 10 / F, building 2, No. 188, Yizhou Road, Xuhui District, Shanghai Applicant before: SHANGHAI YIXUE EDUCATION TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address |
Address after: 200233 9 / F, 10 / F, building 2, 188 Yizhou Road, Xuhui District, Shanghai Patentee after: SHANGHAI YIXUE EDUCATION TECHNOLOGY Co.,Ltd. Address before: 9 / F and 10 / F, building 2, No. 188, Yizhou Road, Xuhui District, Shanghai, 200237 Patentee before: Shanghai squirrel classroom Artificial Intelligence Technology Co.,Ltd. |
|
| CP03 | Change of name, title or address |