Abstract

The present disclosure relates to a language learning method by means of an exploratory language learning system based on machine learning, natural language processing, and a pattern-based reference library, by using the exploratory language learning system based on machine learning, natural language processing, and a pattern-based reference library, wherein the language learning method comprises: a first step for determining whether a logged-in user has selected a training sentence; a second step for, after the first step, segmenting the sentence if the user has selected the training sentence; a third step for displaying, on a screen, a lesson matching a pattern in the sentence; a fourth step for displaying a learned lesson result after the user proceeds with the lesson and learns the lesson in the third step; a fifth step for, if the user has requested a quiz after the fourth step, looking a database up for a user sentence learning lesson learning interest and generating, by a quiz generating bot, a quiz; and the user receiving the quiz and performing a quiz learning step, and then, storing a learning history in the database.

IPC Classes  ?

• G06F 16/9535 - Search customisation based on user profiles and personalisation
• G06F 16/901 - IndexingData structures thereforStorage structures
• G06F 40/211 - Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
• G06F 40/58 - Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
• G06F 40/268 - Morphological analysis
• G06N 20/00 - Machine learning
• G09B 19/06 - Foreign languages
• G06F 21/31 - User authentication
• G06Q 50/20 - Education

Abstract

The present invention relates to an ortho-phonic engine construction method using an exploratory language learning system based on machine learning, natural language processing (NLP) and a pattern-based reference library, comprising: a first step in which a user selects, through a user terminal, a pattern on a pattern selection screen and inputs a sentence; a second step, after the first step, in which a language expert receives, through a language expert terminal, the sentence having been input through the user terminal and reviews the input sentence, and requests that same is added to a sentence for NLP; and a step of transmitting a reward message to the user terminal after the second step.

IPC Classes  ?

• G06F 16/36 - Creation of semantic tools, e.g. ontology or thesauri
• G06F 16/9535 - Search customisation based on user profiles and personalisation
• G06F 16/951 - IndexingWeb crawling techniques
• G06F 16/901 - IndexingData structures thereforStorage structures
• G06F 40/211 - Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
• G06F 40/268 - Morphological analysis
• G06F 40/58 - Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
• G06N 20/00 - Machine learning
• G09B 19/06 - Foreign languages
• G06Q 50/20 - Education

Abstract

The present invention relates to an ortho-phonic engine construction method using an exploratory language learning system based on machine learning, natural language processing (NLP) and a pattern-based reference library, comprising: a first step in which a user selects, through a user terminal, a pattern on a pattern selection screen and inputs a sentence; a second step, after the first step, in which a language expert receives, through a language expert terminal, the sentence having been input through the user terminal and reviews the input sentence, and requests that same is added to a sentence for NLP; and a step of transmitting a reward message to the user terminal after the second step.

IPC Classes  ?

• G06F 16/36 - Creation of semantic tools, e.g. ontology or thesauri
• G06F 16/951 - IndexingWeb crawling techniques
• G06F 16/901 - IndexingData structures thereforStorage structures
• G06F 40/268 - Morphological analysis
• G06F 40/211 - Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
• G06F 40/58 - Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
• G06N 20/00 - Machine learning
• G06Q 20/22 - Payment schemes or models
• G06Q 50/20 - Education
• G09B 19/06 - Foreign languages

Abstract

The present invention relates to a field of interest learning method by means of an exploratory language learning system based on machine learning, natural language processing, and a pattern-based reference library, comprising: a first step of, after a user has performed a login process through a user terminal, receiving an interest-based learning target recommendation message through the system and also receiving a learning target; a second step of the user requesting, through the user terminal, sentence selection and sentence segmentation; a third step of the system then segmenting a received sentence and transmitting, to the user terminal, the segmented sentence; a fourth step of the user learning the sentence through the user terminal and, if a practice problem similar to the learned sentence is required, transmitting a request signal; and a fifth step of the system automatically inquiring about a pattern and GLR grammar through a practice problem exploratory bot according to the practice problem request signal from the user terminal, and retrieving real-time news, songs, and dialogues to provide data to the user terminal such that the practice problem can be displayed and learned.

IPC Classes  ?

• G06F 16/9535 - Search customisation based on user profiles and personalisation
• G06F 16/901 - IndexingData structures thereforStorage structures
• G06F 16/9532 - Query formulation
• G06F 16/9538 - Presentation of query results
• G06F 40/205 - Parsing
• G06F 40/268 - Morphological analysis
• G06F 40/58 - Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
• G06N 20/00 - Machine learning
• G06Q 50/20 - Education
• G06F 21/31 - User authentication

Abstract

The present invention relates to a Babel parser based on an exploratory language-learning system based on machine learning, natural language processing, and a pattern-based reference library, the Babel parser comprising: a pre-GLR which comprises an ML engine for building an ML database on the basis of inputted training data and performing machine learning on the basis of the ML database, and an NPL engine for performing natural language processing on the basis of an NPL database for natural language processing while receiving ML training data through the ML engine to analyze sentences that are inputted together; and a language compiler including ENBF tools through a sentence pattern DB, a morpheme DB, a grammar GLR DB, and a reference DB, wherein a generalized LR (GLR) for parsing the results of pre-GLRR processing into a compiled language is included in analyzing inputted sentences.

IPC Classes  ?

• G06F 16/36 - Creation of semantic tools, e.g. ontology or thesauri
• G06F 16/33 - Querying
• G06F 18/22 - Matching criteria, e.g. proximity measures
• G06F 18/28 - Determining representative reference patterns, e.g. by averaging or distortingGenerating dictionaries
• G06F 16/95 - Retrieval from the web
• G06F 16/9535 - Search customisation based on user profiles and personalisation
• G06F 40/58 - Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
• G06F 40/205 - Parsing
• G06F 40/268 - Morphological analysis
• G06F 8/41 - Compilation

Abstract

An exploratory language-learning system based on ML (Machine Learning), NLP (Natural Language Processing) and a pattern-based reference library including: input means for collecting or inputting instances generated in the language; a morphological analyzer for generating linguistic units, words, stems, affixes, and phonetic symbol input characters and part-of-speech in the sentence input through the input means; a reference library indexed by morphological and syntactic patterns; a lexical pattern matcher that processes the contents processed by the word type analyzer with reference to a reference library; a phrase-structure parser for recognizing larger phrases and clause structures by processing the phrase structure processed by the vocabulary pattern matcher; a library pattern-matcher that processes the syntax structure processed through the phrase-structure parser with reference to the reference library, and a reference explorer that allows users to view and explore related reference materials.

IPC Classes  ?

• G09B 19/06 - Foreign languages
• G06F 40/268 - Morphological analysis
• G06F 40/253 - Grammatical analysisStyle critique
• G06F 40/284 - Lexical analysis, e.g. tokenisation or collocates
• G06F 40/211 - Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
• G06F 40/169 - Annotation, e.g. comment data or footnotes
• G06F 16/903 - Querying