KR102196457B1 - System for providing random letter shuffle based on english practice service for reading and speaking - Google Patents

Abstract

Provided is a system for providing a random word combination-based English practice service for reading and speaking to enable a learner to intuitively recognize even the form of a sentence. According to the present invention, the system comprises: a learner terminal outputting a Korean sentence format and an English sentence format in which at least one type of word is randomly output at a predetermined position are output and when at least one type of tag is selected, outputting a word corresponding to the tag at a predetermined position in the English sentence format and the Korean sentence format; and an English practice service providing server. The server comprises: a database conversion unit mapping and storing at least one type of tag and at least one type of word to randomly output the at least one type of word at a predetermined position; a setting unit configured to randomly output the at least one type of word previously mapped and stored with the at least one tag when the at least one tag is selected by the learner terminal; and when the at least one type of tag is selected in the learner′s terminal, randomly outputting the at least one type of word mapped and stored with the at least one type of tag, wherein the outputted random words in the English sentence format and the Korean sentence format are matched.

Description

English practice service based on random word combinations for reading and speaking learning {SYSTEM FOR PROVIDING RANDOM LETTER SHUFFLE BASED ON ENGLISH PRACTICE SERVICE FOR READING AND SPEAKING}

The present invention relates to a system for providing an English practice service based on a random word combination for learning reading and speaking, wherein the Korean sentence format and the English sentence format are stored by mapping sentence components and coordinates to be synchronized, and a random word combination corresponding to a selected tag It provides a platform to improve reading and speaking skills by printing them out.

Since English education for elementary school students has been introduced as a formal subject, the goal is to develop basic communication skills to understand and use English necessary for daily life. Accordingly, activities for cultivating communication skills have been mainly introduced and utilized in the field of English education in elementary school, and most elementary school textbooks are also composed and presented as listening activities. However, reading and speaking education has been relatively neglected and its importance has been overlooked, and many educators and scholars have expressed emphasis and concern about the importance of reading and speaking education. For language acquisition, the four functions of listening, speaking, reading, and writing should be complementary, reading a book becomes a very important source for learning a language, and reading a book while understanding the content is reading and writing. This is the only way you can improve your skills.

At this time, an application was developed that can comprehensively learn four areas such as listening, reading, speaking and writing of English. In this regard, Korean Patent Registration No. 10-2062552 (January 6, 2020 In the announcement), users can intensively study the principles and concepts of English online or offline, and comprehensively study four areas such as listening, reading, speaking, and writing of English through various problem solving and repeated speaking practice. In order to be able to do so, it includes phonics chant training to learn the names and sounds of alphabets, decoding board training to intensively learn to speak one word through spelling patterns, sentence conversion training for conversion training through a given sentence, and phonics chant training , Alphabet name training to correctly pronounce alphabetic names, alphabet sound training to accurately pronounce alphabetic sounds, short and long vowels training to accurately pronounce short and long vowels of the alphabet, double consonants and R-controlled vowels of the alphabet A configuration is disclosed that includes training for double consonants and R-control vowels for correct pronunciation.

However, even if the above-described configuration is used, the English sound training learned in the early childhood period only increases confusion while not properly mastering the Korean language unless the Korean and English match correctly. In addition, the only textbooks currently used to improve the English reading ability of elementary school students are the only textbooks provided in the school, and the amount of English reading learning provided in these school textbooks is also very insufficient, and the language is speaking, listening, reading, and writing. It is an integrated function that interacts organically, and it is not effective to teach one or two or three functions separately. Accordingly, there is a need for research and development of a platform that enables reading and speaking practice by matching the Korean sentence format and the English sentence format, but enabling various learning with a combination of randomly progressed words.

In one embodiment of the present invention, the Korean sentence format and the English sentence format are configured to be synchronized with each other, and each time at least one type of tag is selected, at least one Korean word previously mapped to at least one type of tag and stored As English words are placed in preset positions in the Korean sentence format and the English sentence format, sentences for reading and speaking practice can be diversified, and at the same time, Korean and English can be matched to intuitively identify which letters correspond to which words. Whenever each tag is selected, words are randomly selected and combined into sentences, so that the acquisition of various words and the form of sentences can be intuitively recognized.By grasping reading and speaking by voice recognition and analyzing pronunciation It is possible to provide a method of providing English practice services based on random word combinations for reading and speaking learning that can simultaneously analyze pronunciation accuracy and speech training. However, the technical problem to be achieved by the present embodiment is not limited to the technical problem as described above, and other technical problems may exist.

As a technical means for achieving the above-described technical problem, an embodiment of the present invention outputs a Korean sentence format and an English sentence format in which at least one type of word is randomly output to a predetermined position, and at least one type When a tag of is selected, at least one type of tag to randomly output at least one type of word to a predetermined position and a learner terminal in which the word corresponding to the tag is output to a predetermined position in the English sentence format and the Korean sentence format. And a database conversion unit that maps and stores at least one type of word, and a setting unit configured to randomly output at least one type of word previously mapped to at least one tag and stored when at least one tag is selected in the learner's terminal , When at least one type of tag is selected in the learner's terminal, at least one type of word previously mapped to at least one type of tag and stored is randomly output, but the output random word in the English sentence format and the Korean sentence format It includes an English practice service providing server including an output unit to match and output.

According to any one of the above-described problem solving means of the present invention, the Korean sentence format and the English sentence format are configured to be synchronized with each other, and each time at least one type of tag is selected, it is pre-mapped to and stored in at least one type of tag. By arranging at least one Korean word and English word in a preset position in the Korean sentence format and the English sentence format, it diversifies the sentences for reading and speaking practice, and at the same time, it matches Korean and English so that which letter is a certain word. It is possible to check whether it corresponds to the response, and when each tag is selected, words are randomly selected and combined into sentences, so that the acquisition of various words and the form of sentences can be intuitively recognized, and reading and speaking can be recognized by voice recognition. By grasping and analyzing pronunciation, you can simultaneously analyze pronunciation accuracy and speech training.

1 is a diagram illustrating a system for providing an English practice service based on a random word combination for learning reading and speaking according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating an English practice service providing server included in the system of FIG. 1.
3 is a view for explaining an embodiment in which an English practice service based on a random word combination for learning reading and speaking according to an embodiment of the present invention is implemented.
FIG. 4 is a diagram illustrating a process of transmitting and receiving data between components included in the system for providing an English practice service based on a random word combination for learning reading and speaking of FIG. 1 according to an embodiment of the present invention.
5 is a flowchart illustrating a method of providing a random word combination-based English practice service for reading and speaking learning according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art can easily implement the present invention. However, the present invention may be implemented in various different forms and is not limited to the embodiments described herein. In the drawings, parts irrelevant to the description are omitted in order to clearly describe the present invention, and similar reference numerals are assigned to similar parts throughout the specification.

Throughout the specification, when a part is said to be "connected" to another part, this includes not only "directly connected" but also "electrically connected" with another element interposed therebetween. . In addition, when a part "includes" a certain component, it means that other components may be further included, and one or more other features, not excluding other components, unless specifically stated to the contrary. It is to be understood that it does not preclude the presence or addition of any number, step, action, component, part, or combination thereof.

The terms "about", "substantially" and the like, as used throughout the specification, are used in or close to the numerical value when manufacturing and material tolerances specific to the stated meaning are presented, and are used in the sense of the present invention. To assist, accurate or absolute figures are used to prevent unfair use of the stated disclosure by unscrupulous infringers. As used throughout the specification of the present invention, the term "step (to)" or "step of" does not mean "step for".

In the present specification, the term "unit" includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Further, one unit may be realized by using two or more hardware, or two or more units may be realized by one hardware. Meanwhile,'~ unit' is not meant to be limited to software or hardware, and'~ unit' may be configured to be in an addressable storage medium or configured to reproduce one or more processors. Thus, as an example,'~ unit' refers to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, and procedures. , Subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays and variables. Components and functions provided in the'~ units' may be combined into a smaller number of elements and'~ units', or may be further separated into additional elements and'~ units'. In addition, components and'~ units' may be implemented to play one or more CPUs in a device or a security multimedia card.

In this specification, some of the operations or functions described as being performed by the terminal, device, or device may be performed instead in a server connected to the terminal, device, or device. Likewise, some of the operations or functions described as being performed by the server may also be performed by a terminal, device, or device connected to the server.

In this specification, some of the operations or functions described as mapping or matching with the terminal means mapping or matching the unique number of the terminal or the identification information of the individual, which is the identification information of the terminal. Can be interpreted as.

Hereinafter, the present invention will be described in detail with reference to the accompanying drawings.

1 is a diagram illustrating a system for providing an English practice service based on a random word combination for learning reading and speaking according to an embodiment of the present invention. Referring to FIG. 1, a system 1 for providing an English practice service based on a random word combination for learning reading and speaking includes at least one learner terminal 100, an English practice service providing server 300, and at least one instructor terminal ( 400) may be included. However, since the English practice service providing system 1 based on a random word combination for learning reading and speaking of FIG. 1 is only an embodiment of the present invention, the present invention is not limitedly interpreted through FIG. 1.

In this case, each component of FIG. 1 is generally connected through a network 200. For example, as shown in FIG. 1, at least one learner terminal 100 may be connected to an English practice service providing server 300 through a network 200. In addition, the English practice service providing server 300 may be connected to at least one learner terminal 100 and at least one instructor terminal 400 through the network 200. In addition, at least one instructor terminal 400 may be connected to the English practice service providing server 300 through the network 200.

Here, the network refers to a connection structure in which information exchange is possible between respective nodes such as a plurality of terminals and servers, and examples of such networks include a local area network (LAN) and a wide area communication network (WAN: Wide Area Network), Internet (WWW: World Wide Web), wired/wireless data communication network, telephone network, wired/wireless television communication network, etc. Examples of wireless data networks include 3G, 4G, 5G, 3GPP (3rd Generation Partnership Project), 5GPP (5th Generation Partnership Project), LTE (Long Term Evolution), WIMAX (World Interoperability for Microwave Access), and Wi-Fi. , Internet, LAN(Local Area Network), Wireless LAN(Wireless Local Area Network), WAN(Wide Area Network), PAN(Personal Area Network), RF(Radio Frequency), Bluetooth(Bluetooth) network, NFC( Near-Field Communication) network, satellite broadcasting network, analog broadcasting network, DMB (Digital Multimedia Broadcasting) network, etc. are included, but are not limited thereto.

In the following, the term “at least one” is defined as a term including the singular number and the plural number, and even if the term “at least one” does not exist, each component may exist in the singular or plural, and may mean the singular or plural. It will be self-evident. In addition, it will be possible to change according to the embodiment that each component is provided in a singular or plural.

At least one learner terminal 100 is a terminal of a learner who reads, speaks, writes and listens using a web page, app page, program or application related to a random word combination-based English practice service for reading and speaking learning. I can. At this time, the at least one learner terminal 100 may receive feedback directly from at least one instructor terminal 400 or through the English practice service providing server 300, and from the English practice service providing server 300 You can also receive the results of your own analysis. In addition, at least one learner terminal 100 may be a terminal that arranges and outputs words to correspond to the level of the learner terminal 100 when outputting randomly output English sentences and Korean sentences, and the learner terminal 100 It may be a terminal that transmits the learning result of) to the English practice service providing server 300 as a log.

Here, the at least one learner terminal 100 may be implemented as a computer that can access a remote server or terminal through a network. Here, the computer may include, for example, a navigation system, a notebook equipped with a web browser, a desktop, a laptop, and the like. In this case, the at least one learner terminal 100 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one learner terminal 100, for example, as a wireless communication device that is guaranteed portability and mobility, navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS(Personal Handyphone System), PDA(Personal Digital Assistant), IMT(International Mobile Telecommunication)-2000, CDMA(Code Division Multiple Access)-2000, W-CDMA(W-Code Division Multiple Access), Wibro(Wireless Broadband Internet) ) It may include all kinds of handheld-based wireless communication devices such as terminals, smart phones, smart pads, and tablet PCs.

The English practice service providing server 300 may be a server that provides a web page, an app page, a program, or an application based on a random word combination for learning reading and speaking. In addition, the English practice service providing server 300 may be a server that stores an English sentence format and a Korean sentence format, sets the position of each word in advance, designates and maps coordinates, and stores it. Here, the English sentence format refers to a format in which a preset word arrangement position is designated according to each sentence format, such as S(Subject)+V(Verb)+O(Object). Likewise, the Korean sentence format refers to a format in which the arrangement position of each sentence is designated, such as S+O+V. In addition, the English practice service providing server 300 may be a server that separates and stores words according to each level, but divides words into categories using at least one type of tag and converts a set of words into a database. have. In this case, the tag may be, for example, a tag that identifies whether a word corresponding to a pronoun is an indication pronoun or a personal pronoun. In addition, if it is a word corresponding to a general verb, it may be a tag that identifies whether it is a general verb for a questionable sentence or a general verb for a negative sentence. In addition, the English practice service providing server 300 analyzes the text input by speech and writing learning recognized by the learner terminal 100 as speaking learning using speech recognition, text recognition, and natural language processing, and It may be a server that transmits the result to the learner terminal 100 and maps and stores the analysis result with the learner terminal 100.

Here, the English practice service providing server 300 may be implemented as a computer that can access a server or terminal in a remote location through a network. Here, the computer may include, for example, a navigation system, a notebook equipped with a web browser, a desktop, a laptop, and the like.

The at least one instructor terminal 400 may be a terminal of an instructor using a web page, an app page, a program, or an application related to an English practice service based on a random word combination for learning reading and speaking. In addition, the at least one instructor terminal 400 may be a terminal interlocked with at least one learner terminal 100 after registering an instructor in the English practice service providing server 300. At this time, the at least one instructor terminal 400, the learning result of the learner terminal 100 received through the English practice service providing server 300, or the voice or received text of the learner terminal 100 connected and streamed in real time. It may be a terminal that gives real-time feedback on.

Here, the at least one instructor terminal 400 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, a navigation system, a notebook equipped with a web browser, a desktop, a laptop, and the like. At this time, the at least one instructor terminal 400 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one instructor terminal 400, for example, as a wireless communication device that is guaranteed portability and mobility, navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS(Personal Handyphone System), PDA(Personal Digital Assistant), IMT(International Mobile Telecommunication)-2000, CDMA(Code Division Multiple Access)-2000, W-CDMA(W-Code Division Multiple Access), Wibro(Wireless Broadband Internet) ) It may include all kinds of handheld-based wireless communication devices such as terminals, smart phones, smart pads, and tablet PCs.

FIG. 2 is a block diagram illustrating an English practice service providing server included in the system of FIG. 1, and FIG. 3 is a random word combination-based English practice service for reading and speaking learning according to an embodiment of the present invention. It is a diagram for explaining an embodiment that has been made.

Referring to Figure 2, the English practice service providing server 300, database conversion unit 310, setting unit 320, output unit 330, analysis unit 340, phonics learning unit 350, writing learning unit It may include (360).

An English practice service providing server 300 according to an embodiment of the present invention or another server (not shown) operated in conjunction with at least one learner terminal 100 and at least one instructor terminal 400 to learn reading and speaking When transmitting an English practice service application, program, app page, web page, etc. based on a random word combination, at least one learner terminal 100 and at least one instructor terminal 400 are random for reading and speaking learning You can install or open a word combination-based English practice service application, program, app page, web page, etc. In addition, a service program may be driven in at least one learner terminal 100 and at least one instructor terminal 400 by using a script executed in a web browser. Here, the web browser is a program that allows you to use the Web (WWW: World Wide Web) service, which means a program that receives and displays hypertext described in HTML (Hyper Text Mark-up Language). For example, Netscape , Explorer, Chrome, etc. In addition, the application refers to an application program on the terminal, and includes, for example, an app running on a mobile terminal (smartphone).

Referring to FIG. 2, the database converter 310 may map and store at least one type of tag and at least one type of word so that at least one type of word is randomly output to a predetermined position. At this time, at least one type of tag is matched with at least one Korean word and English word, and at least one English word is matched with Korean word corresponding to the English word and stored, and at least one type of tag is When selected, at least one Korean word may be randomly selected, and an English word corresponding to the randomly selected Korean word may be located in the English sentence format.

The English sentence format includes a first format in which only a subject exists, a second format including a subject and a general verb, a third format including a subject and the verb be, and a fourth format including the subject, be verb, and adjective. , The subject includes Korean words and English words corresponding to the indicating pronoun tags, personal pronoun tags, and other pronoun tags, and the general verb includes Korean words and English words corresponding to plain preface tags, negative sentences and interrogative tags, The verb be may include Korean words and English words corresponding to plain preface tags, negative text tags, and interrogative text tags. However, it is not limited to the listed sentence formats and is not excluded for reasons not listed.

The tag connects Korean and English, and can play a role of mapping English and Korean in the form of a Korean personal pronoun-personal pronoun (tag)-English personal pronoun. In addition, tags may be mapped from a Hangul-Tag-English form to a one-to-many (一對多) form. For example, a plurality of Korean words may be mapped to one tag while forming a set, and the same is true for English words. In addition, the English sentence format and the Korean sentence format may be mapped and stored so as to be synchronized, respectively. For example, in Table 1 below, if the first column (1,1) is S, the second column (1,2) is O, and the third column (1,3) is V in the Korean sentence format, this coordinate is mapped. Then, S, 0, and V are stored. If the first column (2,1) is S, the second column (2,2) is V, and the third column (2,3) is O in the English sentence format, ( 1,1)-(2,1), (1,2)-(2,3), (1,3)-(2,2). After setting in the database converter 310 in this way, if S in Korean is randomly selected, S in English is automatically changed and synchronized to a word corresponding to the random word. For example, if S is a personal pronoun tag selected, and "He" is changed to "I" in Korean, it is changed from "He" to "I" in English and synchronization occurs.

Language classification Sentence component Korean sentence format S O V English sentence format S V O

In addition, since at least one type of word is divided into a personal pronoun and an indication pronoun even if it is a pronoun, a type of word corresponding to each tag is classified. For example, if the tag is "personal pronoun", the word to be in it could be "He, She, I, You, They, We", and at least one kind of word belongs to "personal pronoun". It becomes a kind of word. In addition, the database conversion unit 310 may further map and store an image in which a word is formed. That is, it is possible to provide content including related images including pictures or photos having the meaning of words. For example, when storing and databaseizing words having a shape similar to the shape of the alphabet as a related image to teach the alphabet, people It would be possible to do this one by one, but the system automatically extracts an object from an image, searches for an English word that describes the extracted object, and if there is a spelling corresponding to the outer periphery of the object among the spellings in the English word, object- When the database is stored in a way that word-spelling is interlocked, a more diverse and many types of image databases can be built than a person finds and places them individually. To this end, the database converter 310 converts a plurality of images into gray-level images, and extracts an edge using a Canny edge detector.

In addition, the database conversion unit 310 may generate an edge map from the extracted edge and combine the generated edge map to suit the character structure characteristics to generate an English word-spelling-edge map. In addition, the database conversion unit 310 extracts the text candidate region (spelling candidate region) as an English word-edge map, analyzes the pattern histogram distribution of the English word-edge map, and performs a final verification on the text region. You can also build a database by extracting text (spelling) areas. Here, the Canny edge detection can generate an edge map by extracting an accurate edge from an image with low contrast and combining the directional edge and corner edge with the extracted edge. It will be obvious that a detector can be used.

When at least one tag is selected by the learner terminal 100, the setting unit 320 may set at least one type of word previously mapped to at least one tag and stored to be randomly output. Here, the at least one type of word may be a corpus, which is a set of words corresponding to each tag. The corpus can be constructed in various ways depending on the purpose of use. The simplest corpus is composed of plain texts to extract various statistics found in language, such as word frequency and word air information. At this time, the text may undergo a refinement process such as spacing or correcting spelling, and texts from various fields may be extracted and structured in a balanced manner. Representative primitive corpuses are owned by each institution at home and abroad. Additional markings may be attached to these corpuses for a specific purpose, and this is called annotated corpus. Marking refers to a piece of analysis information added to the corpus for machine learning, and various markers are attached depending on the problem to be solved. For example, a part of speech tag can be attached to resolve the part-of-speech ambiguity, a vocabulary semantic tag to resolve the vocabulary semantic ambiguity, and a syntax analysis result tag to resolve the structural ambiguity.

For example, if the alphabet is A, B, C, D,....Z in order, a cluster of words starting with A is built into a corpus, but even if a word starts with the same A, by level, You can construct a corpus by dividing it by meaning and by grammar. In addition, if classified into primitive corpus, shape analysis corpus, shape semantic analysis corpus, and syntax analysis corpus, the process of separately tagging meanings or morphemes when automatically placing or writing words or contents in Korean sentence format and English sentence format. You don't have to go through and it's convenient to search for related words or words of interest. In addition, even if it is not in the form of a corpus, any form is possible as long as it is clustered around the query or the analyzed metadata is tagged.

For example, weather news is reported several times a day to convey constantly changing weather conditions, and these weather conditions affect our daily lives. If you map and save Korean weather news corpus and English weather news corpus, Korean weather news Various linguistic units used in English can be converted into English. Since these corpuses are built through online news collection on a website and contain vivid expressions actually used in the weather news area, conversion products without Korean translation can be obtained through corpus-based translation methods. The process of converting Korean words contained in Korean sentences into English words is performed automatically or manually. In the former case, it serves as a basic database in the process of substituting English words suitable for the context through the above-described corpus construction. At this time, since natural language processing (NLP) that occurs after building the corpus is the same or similar to the known technology, it is not described in detail in the specification of the present invention.

When randomly extracting words, the setting unit 320 may extract words based on bag-of-words (BoW). In this case, BoW is a method of modeling the quantification of text data by focusing only on the frequency of occurrence of words without considering the order of words. BoW literally means a bag of words. For example, after shaking a bag containing words to mix the words, if a specific word appears N times in the document, it can be inferred that there are N specific words in the bag. It becomes. Also, the order doesn't matter because the bags are shaken. To this end, the BoW estimates the frequency by assigning a unique index to each word, and creating a vector in which the number of occurrences of the word token is recorded at the position of each index. At this time, the result of assigning an index is called a word set (Vocabulary), and the word set is responsible for assigning an index to a word. In addition, it is possible to make BoW by performing pretreatment to remove "a", "the", etc., which are stop words in English, and purifying them. In this way, frequently appearing English words can be extracted, and a pattern (Cluster) can be generated using high frequency words.

When at least one type of tag is selected in the learner terminal 100, the output unit 330 randomly outputs at least one type of word previously mapped to at least one type of tag and stored, but the English sentence format and It is possible to match and output random words output in the Korean sentence format. For example, as shown in (c) of FIG. 3, if the student selects the "indicative" (indicative pronoun) tag, the word corresponding to the indicative pronoun is output in Korean, and the English word may be changed and output accordingly. . Accordingly, the learner terminal 100 outputs a Korean sentence format and an English sentence format in which at least one type of word is randomly output to a predetermined position, and when at least one type of tag is selected, Words can be output in the designated location in English sentence format and Korean sentence format.

The analysis unit 340, when receiving an English sentence in the English sentence format output from the learner terminal 100 through voice recognition from the learner terminal 100, processes NLP (Natural Language Processing) to read and speak the English sentence It can be analyzed and transmitted to the learner terminal 100. For example, the problem of reading and speaking proceeds in a way that when an arbitrary English sentence is presented, it is read with the eyes and then spoken. Here, stress, intonation, and fluency may be included in the analysis items. However, it is not limited to those listed. Accordingly, in order to automatically analyze in an embodiment of the present invention, first, a sentence uttered in speech is converted into text, the sentence is evaluated according to each evaluation item in the converted text, and stress and intonation are performed using the voice signal. And when analyzing fluency (the degree of speaking without interruption), etc., it becomes possible to score automatically.

On the other hand, in the case of writing, factors such as whether appropriate vocabulary and grammar are used, and accuracy of content can be evaluated and scored automatically. In other words, the overall development and composition of the text, the selection of appropriate vocabulary and the use of clear grammar, effectively describe the topic and problem, use clearly appropriate explanations, examples, and details to be structured and developed systematically and naturally, and consistency, Items such as continuity and unity can be divided and scored. At this time, as a method for automatic scoring for the subjective problem, an automatic scoring algorithm or program can be used, and the automatic scoring algorithm or program is a program based on regression analysis according to a statistical approach, a program based on natural language processing, A program based on latent semantic analysis and a program based on the Bayesian method can be used. Concept-based scoring programs and programs using machine learning methods for essay-type answers describing multiple sentences may be used.

At this time, in the case of the former, as a representative writing (English composition) automatic scoring program based on natural language processing, it is possible to perform automatic scoring that gives a score by evaluating how similar a student answer is to the correct answer in terms of meaning. In the latter case, it can be designed to determine the similarity between the meaning of the correct answer and the meaning of the answer, and can be implemented to evaluate the degree of understanding of a specific subject. In order to perform automatic scoring using such a program, first, the correct answer model should be constructed by extracting only the normalized concept from the correct answer sentence provided by the questioner. At this time, the constructed correct answer concept can appear in various forms in an actual sentence, and one concept that appears as a sentence in various forms is referred to as speaking, extracting the core concepts inherent in various transformed forms expressed through alternating speaking. Thus, you can compare it with the correct answer model and perform scoring.

In addition, the automatic scoring program can perform computer-based scoring by describing the scoring criterion used by the scorer as a correct answer template file in XML format, or writing a scoring criterion and learning big data, and then student answers. It can be scored, or it can be configured by accumulating the scoring results and performing real-time scoring with artificial intelligence using machine learning and feeding back the results. In addition, the analysis unit 340, after recognizing the spoken utterance of the answer provided in speech to the subjective question, converts it into text using STT (Speaking To Text), and a pre-stored correct answer template based on the converted text. You can also perform scoring using ).

Phonics (Phonics) learning unit 350, at least one including a Consonant Vowel Consonant (CVC), Consonant Vowel Consonant Vowel (CVCV), Consonant Consonant Vowel Consonant Vowel (CCVCV) and Consonant Consonant Vowel Consonant Vowel (CCVVCVC) English words, Korean words, and phonetic symbols within the phonics syllable structure of can be mapped and saved. Phonics is a teaching method for learning the sounds and pronunciations of words.

Most Koreans take the form of CVC, that is, consonants, vowels, and consonants, but English does not. In Korean, for example, even if you look at "한" in Korean, "ㅎ" is a consonant, "ㅏ" is a vowel, and "ㄴ" is a consonant. However, in English, consonants and vowels do not appear alternately even if you only see "vacation". The difference between Korean and English syllable structure is that if Korean is a Syllable-timed language, then English is a stress-timed language, so there is a contrast in terms of syllable structure.

First, as described above, the syllable structure of Korean has four syllable types: CVC, V, CV, VC, and CVC, and does not allow consonant clusters at the beginning of syllables. Only 19 consonants can be placed on the Korean Onset, 10 short vowels and 12 double vowels can be placed on the syllable core (Peak), and 7 consonants are neutralized on the Coda. On the contrary, the syllable structure of English is CCCVCCCC, and 20 syllable types are theoretically possible. Up to 3 consonants can be placed on the initial sound (e.g. straw, scream), and 4 consonants can be placed in the end of the syllable.

Second, since many consonants occur inside the syllable, there is a strict arrangement constraint. When there are three initials, the first sound must be /s/, the second sound is one of /p,t,k/, the third sound is /l, Must be one of r,j,w/. Conversely, in Korean, consonant groups are not allowed in the first and last words. In terms of notation, there seems to be a consonant group at the end of the syllable, such as "chicken, no, bright", but one of the consonant groups is eliminated, such as /dak, upta, and balm. Because the arrangement of Korean and English is different, what can be learned at the most basic level is the same CVC arrangement as Korean even if you see the above description, so the phonics learning unit 350 starts learning from the most basic CVC type. Is done. In this case, since short vowels or long vowels are the same as well-known concepts, detailed descriptions are omitted.

In addition, the phonics learning unit 350 may provide a pattern of words in which terminal sounds are combined based on five short vowels. For example, since the CVC type is the default, a word that satisfies the CVC type is extracted at random by extracting a plurality of words including any one of 5 short vowels in V, or the corresponding short vowel is included by extracting from a previously constructed database. It is to cultivate the ability to read the words that have been made without knowing the meaning. For example, cab, dab, gab, jab, lab, nab, and tab belong to the same single sound, and if you know this single sound, the pronunciation of cab is possible regardless of whether the meaning of cab is taxi or not. Also, it is to be able to read words like bam, cam, dam, ham, jam, ram, yam, pam, sam, etc., even though the names are almost always and the meaning is not important.

The phonics learning unit 350 transmits sound-modified content in which CVCV (Consonant Vowel Consonant Vowel) words including long vowels and the pronunciation of words before the long vowels are included and the pronunciation of words after the long vowels are transformed It can be provided as (100). For example, consonant + vowel + consonant + vowel words such as baby, lego, pony, pogo, typo, polo, lady, pity, tuba, and taco are CVCV words. CVCV words including long vowels are, for example, Cake, gate, vase, game, cane, face, race, cage, lake, and rake. At this time, an example in which the pronunciation of the word before the long vowel is included and the pronunciation of the word after the long vowel is included is that an e is attached to can, and a is returned from /e/ to the original pronunciation of /a/. Of course, it is written in Korean and does not coincide with English pronunciation, but this is only an example for convenience of explanation, so it may not coincide with the correct phonetic symbol.

The phonics learning unit 350 is a pattern of words including Consonant Consonant Vowel Consonant (CCVC) or Consonant Consonant Vowel Consonant Vowel (CCVCV) words and R including Consonant Phoneme and Double Consonant. It can be provided to the learner terminal 100. Consecutive consonants are two consonants that make each sound and sound in rapid succession. There are br, cr, dr, fr, pr, bl, cl, fl, sk, sm, sp, st, sw, etc. For example, it may be brick, cream, drink, friend, prince, black, cloud, etc. A double consonant is when two consonants meet and the original sound disappears and a new sound is created.For example, there are ch, sh, th, wh, ng, and if you look at words that contain these consonant doubles, chair , fish, this, long, etc. exist. At this time, looking at the words CCVC and CCVCV, it can be seen that CC is a double consonant or continuous consonant word. In addition, in both CCVC and CCVCV, humans can search for words one by one and provide words, but each consonant and vowel are separated and tagged using a tag of natural language processing (NLP), and whether it is a long vowel, a double vowel, or a continuous vowel. By separating and tagging recognition using tags, it is also possible to automatically extract words containing continuous consonants or words containing double consonants in the CCVC and CCVCV types.

Alternatively, an entity name recognition model may be used. Alphabets such as a, e, i, o, and u are recognized as object names as vowels, and the rest are recognized as object names as consonants. After learning double vowels, continuous consonants, long vowels, short vowels, and single vowels, etc. It is to create a pattern of words needed at each step by making it recognize. The entity name recognition model has been dealt with as one of the sequential labeling problems, and various methods based on CRFs or Structural SVM can be used, and bidirectional Bi is used to reduce the burden of feature engineering (effective feature extraction and selection). -A method in which CRFs are combined with a deep neural network such as Bidirectional Long Short Term Memory (LSTM) or Bidirectional Gated Recurrent Units (Bi-GRU) may be used. For example, if you use Bi-LSTM-CRF,'B-PER','E-PER','O', and'S-LOC' are the beginning of a person's name, the end of a person's name, not an individual name, and an independent word. It is a mark indicating the place name consisting of, and in this way, the mark indicating the name of the object is generally a mark indicating the boundary of the object name (e.g. B (start of boundary), I (inside boundary), E (end of boundary), O (outside boundary), S (Boundary start and end), etc.) and category indicators (e.g., PER (personal name), LOC (place name), ORG (organization name), etc.) can be classified, so the aforementioned short vowels and long vowels When inputting rules or types of monophonic, double vowel, and continuous consonants, it is easy to derive a word containing them. Of course, in addition to the above-described methods, various methods of constructing a database may be used, and a method of constructing a database by selecting one by one by a person is not excluded.

In addition, the phonics learning unit 350 provides a pattern of words in which continuous consonants are combined with short vowels or long vowels, and words in which the frequency of use of words including continuous consonants is more than a preset reference value, R-Family Blends, and Providing a sentence including a word including an R-Blended vowel or a word including an R-Family Blends and R-Blended vowel. At this time, R-Blends or R-Vowel are words that are mixed with r or words that contain r and vowels side by side. For example, Turkey, start, car, north, war, work, standard, dinner, care, ear, etc. R-Family Blends are words in which consonants or vowels are mixed with r, which is a broader concept than R-Vowel or R-Blended vowels. Examples of consonants mixed with r are frog, truck, crop, tree, crab, trunk, drum, brush, fruit, etc. In an embodiment of the present invention, a pattern is to continuously provide at least one word including a continuous consonant + short vowel, and a continuous consonant + long vowel, which may be grouped into one group. For example, if you say that it is a pattern of words that contain A, you are constantly finding and giving words that contain A. So, even if you don't know what car and war mean, you can make this pronunciation and provide a word or a set (pattern) of words with rules applied in each step so that you can easily learn the language of an English-speaking country with a higher literacy rate than Korea. .

The phonics learning unit 350 provides a pattern of words including double vowels and double consonants, and CCVVCVC (Consonant Consonant Vowel Vowel Consonant Vowel Consonant) words including double vowels to the learner terminal 100. May be. Similarly, it can be seen that CCVVCVC contains a double consonant (CC) and a double vowel (VV). For example, words like theaves are words that contain a double consonant (th) and a double vowel (ea) together. In this case, the word structure according to the phonics teaching method is not limited to the above, and may include all known phonics word structures, and the above are not excluded for reasons not listed since they are an embodiment of the present invention.

The writing learning unit 360 receives the English sentence corresponding to the Korean sentence from the learner terminal 100 after randomly providing a Korean sentence in the Korean sentence format as a combination of Korean words, and responds to the English sentence and the Korean sentence. It may be transmitted to the learner terminal 100 by determining the degree of correspondence with the stored English sentence. In this case, the writing learning unit 360 may provide feedback through the feedback of the instructor terminal 400, but may provide feedback as a result of the automatic analysis using the algorithm of the analysis unit 340 described above. The instructor terminal 400 may be interlocked with the learner terminal 100 to share the voice and text input from the learner terminal 100 and transmit the feedback to the learner terminal 100. In this case, since the automatic analysis algorithm is as described above, it will not be described in duplicate.

Hereinafter, an operation process according to the configuration of the above-described English practice service providing server of FIG. 2 will be described in detail with reference to FIG. 3 as an example. However, it will be apparent that the embodiment is only any one of various embodiments of the present invention, and is not limited thereto.

Referring to Figure 3a, (a) the English practice service providing server 300 stores each tag is mapped for each component of a sentence, and at least one type of word corresponding thereto is a pair of Korean and English. Can be stored as 2.

circle Plain preface Negative statement question see watch I saw I didn't see Have you seen bet hang Walked I didn't walk Did you walk Knit knit Knit I didn't knit Did you knit Feed feed Feed Did not feed Did you feed it Cook cook Cook Did not cook Do you cook cut cut cut Did not cut Did you cut it dry dry dry Didn't dry Did you dry comb comb comb Did not comb Did you comb it wash wash wash Do not wash Did you wash

(b) At this time, there are cells as shown in the table at each location of the Korean sentence format, and each cell is mapped with coordinates and sentence components to be entered, that is, the location-sentence component is set. And the words in the English sentence format are synchronized and changed. That is, as shown in (c), when the user selects the tag “instruction”, words corresponding to the indicative pronoun are randomly extracted, and both of the extracted words can be automatically changed to Korean-English matching. . And, (d) when a learner performs speaking (speaking) and writing, reading, and listening to read by pronunciation, in an embodiment of the present invention, NLP, STT, TTS, etc. can be used and automatically analyzed. It is also possible to interlock with the instructor terminal 400.

Referring to FIG. 3B, a diagram showing how each tag is classified and categorized. Each word can be divided by part-of-speech, each meaning by phrase, and each sentence by format, which is classified by tagging each tag. A total of 26 tags may be set, and Korean words and English words as a set of a plurality of words may be mapped and stored based on the tags. Table 3 below shows a database in which the present complete plain text, the negative sentence, the question sentence, the past, the present complete, and the person name change are mapped. When each tag is mapped and stored in this way, a random combination screen as shown in Table 4 may be displayed.

Korean English tense Plain preface Negative statement question Random past grammatical person I I have Have I see I don't see Do you see Have seen watched watches you are You have Have you Hang I don't. Are you going Walked hung hangs We are We have Have we To knit Do not knit Do you knit Was knitted knitted knits You are You have Have you Feed Do not feed Do you feed Fed fed feeds they They have Have they Cook Do not cook Do you cook Cooked cooked cooks these are These have Have these Cut Do not cut Do you cut it Cut cut cuts Those are Those have Have those Dry Do not dry Dry Dried up dried dries those are They have Have they Comb Do not comb Miss Combed combed combs he is He has Has he Wash Do not wash Wash Washed washed washes She is She has Has she Brush Do not brush Do you brush Brushed brushed brushes that is It has Has it Listen I don't listen Do you hear Came in listened listens this is This has Has this To clean Do not clean Do you clean Have been cleaned cleaned cleans that That has Has that Wear Do not wear Wear I have been wearing putted on puts on

Korean She is Shake hands Subject (personal)|juer (direction)|juer (random) English She has shook hands

In addition, in the case of tubular nouns and tubular prepositions, a database may be established as shown in Table 5 below, and the screen may be output as shown in FIG. 3C, and words are selected and output at random when clicking or selecting a frame in which Korean words are written At the same time, English words are also changed. In addition, a database may be formed according to various parts of speech, phrases, and formats as illustrated in FIG. 3B, and words may be randomly combined and output in the Korean sentence format and the English sentence format. It will be understood that the above-described phonics can also be output randomly.

Official name Tubular name Tubular name preposition One student a student student a student Books on the desk the book on the desk 2 students students students students Ball going to the girl the ball to the ball 3 The student the student The student the student Students in the classroom the students in the classroom 4 Those students the students Those students the students Girl with a book the girl with a book 5 book a book book a book Arrow focused on apple an arrow at the apple 6 The book the book The book the book Flies on the book a fly on the book 7 Books books Books books Desk in the room the desk in the room 8 Those books the books Those books the books Boy going to girl a boy to the girl 9 girl a girl girl a girl Student next to the teacher the student next to the teacher 10 Girls girls Girls girls Boy with ball the boy with a ball 11 Those girls the girls Those girls the girls Child beside the desk the child next to the desk 12 That girl the girl That girl the girl Arrow focused on Paris an arrow at the fly 13 egg an egg egg an egg Child with arrow a child with an arrow 14 Eggs eggs Eggs eggs Fly towards the ball a fly to the ball 15 That egg the egg That egg the egg Child on the desk the child on the desk 16 Those eggs the eggs Those eggs the eggs Dog in the car the dog in the car

As for the method of providing the random word combination-based English practice service for reading and speaking learning of FIGS. 2 and 3 as described above, the method of providing a random word combination-based English practice service for reading and speaking learning through FIG. Since the contents are the same as those described for or can be easily inferred from the described contents, the following description will be omitted.

4 is a diagram illustrating a process of transmitting and receiving data between components included in the system for providing a random word combination-based English practice service for learning reading and speaking of FIG. 1 according to an embodiment of the present invention. Hereinafter, an example of a process in which data is transmitted/received between each component will be described with reference to FIG. 4, but the present application is not limitedly interpreted as such an embodiment, and is illustrated in FIG. 4 according to various embodiments described above. It is apparent to those skilled in the art that the process of transmitting and receiving data may be changed.

Referring to FIG. 4, the English practice service providing server 300 matches an English sentence format and a Korean sentence format to form a database (S4100), and stores at least one type of tag, a female word, and a Korean word by mapping. (S4200). And, the English practice service providing server 300, when the learner terminal 100 is registered, assigns a student to the instructor terminal 400 (S4300), and starts learning from the learner terminal 100 (S4400) start page Is provided (S4410), and the Korean sentence in the randomly combined Korean sentence format is output, and at the same time, the English sentence may be output together (S4500). Of course, it is possible to output only the Korean sentence and speak it in English (English writing and speaking), and whether or not the answer is correct can be proceeded with a voice recognition and automatic scoring algorithm, or it is possible to output only the English sentence and interpret it as a Korean sentence (S4610 , S4630). And, when the English practice service providing server 300 does not automatically analyze or give feedback, it is possible to receive the feedback from the instructor terminal 400 and transmit the feedback to the learner terminal 100 (S4700), and this is the learner terminal 100 After output from (S4800), it is possible to repeat learning by selecting a tag again (S4900, S4920).

The order between the above-described steps S4100 to S4920 is only an example and is not limited thereto. That is, the order of the above-described steps (S4100 to S4920) may be mutually changed, and some of the steps may be simultaneously executed or deleted.

The matters that are not described about the method of providing a random word combination-based English practice service for learning reading and speaking of FIG. 4 are described above through FIGS. 1 to 3 as a method for providing a random word combination-based English practice service for reading and speaking learning. Since the contents are the same as those described for or can be easily inferred from the described contents, the following description will be omitted.

5 is a flowchart illustrating a method of providing a random word combination-based English practice service for reading and speaking learning according to an embodiment of the present invention. Referring to FIG. 5, the English practice service providing server maps and stores at least one type of tag and at least one type of word to randomly output at least one type of word to a predetermined position (S5100), When at least one tag is selected in the learner's terminal, at least one type of word previously mapped to at least one tag and stored is set to be randomly output (S5200).

In addition, the English practice service providing server, when at least one type of tag is selected in the learner terminal, randomly outputs at least one type of word previously mapped to at least one type of tag and stored, but in English sentence format and Korean The random words outputted in the sentence format are matched and output (S5300).

The matters not described about the method of providing a random word combination-based English practice service for learning reading and speaking of FIG. 5 are described above through FIGS. 1 to 4 as a method for providing a random word combination-based English practice service for reading and speaking learning. Since the contents are the same as those described for or can be easily inferred from the described contents, the following description will be omitted.

A method of providing a random word combination-based English practice service for learning reading and speaking according to an embodiment described with reference to FIG. 5 is a recording medium including a computer-executable instruction such as an application or program module executed by a computer. It can also be implemented in the form of. Computer-readable media can be any available media that can be accessed by a computer, and includes both volatile and nonvolatile media, removable and non-removable media. Further, the computer-readable medium may include all computer storage media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data.

The method for providing English practice services based on random word combinations for learning reading and speaking according to an embodiment of the present invention described above includes an application basically installed in a terminal (this includes a program included in a platform or operating system basically installed in the terminal). It may be executed by an application store server, an application, or an application (that is, a program) directly installed on the master terminal through an application providing server such as a web server related to the service. In this sense, the method for providing English practice services based on random word combinations for reading and speaking learning according to an embodiment of the present invention described above is implemented as an application (i.e., a program) installed in a terminal or directly installed by a user. It can be recorded on a computer-readable recording medium such as a terminal.

The above description of the present invention is for illustrative purposes only, and those of ordinary skill in the art to which the present invention pertains will be able to understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not limiting. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as being distributed may also be implemented in a combined form.

The scope of the present invention is indicated by the claims to be described later rather than the detailed description, and all changes or modified forms derived from the meaning and scope of the claims and their equivalent concepts should be interpreted as being included in the scope of the present invention. do.

Claims (7)

A Korean sentence format and an English sentence format in which at least one type of word is randomly output at a predetermined position are output, and when at least one type of tag is selected, the word corresponding to the tag is the English sentence format and the Korean sentence A learner terminal 100 output to a predetermined location in the format; And
A database conversion unit 310 for mapping and storing at least one type of tag and at least one type of word to randomly output at least one type of word to a predetermined position, and the at least one tag is the learner terminal 100 ), a setting unit 320 configured to randomly output at least one type of word previously mapped to the at least one tag and stored, and at least one type of tag is selected from the learner terminal 100 In this case, an output unit 330 that randomly outputs at least one type of word previously mapped to and stored in the at least one type of tag, and matches the outputted random word in the English sentence format and the Korean sentence format. Includes; English practice service providing server 300; including,
The setting unit 320 extracts words based on bag-of-words (BoW) so that the order of words is not taken into account when randomly extracting words, and is mainly extracted based on frequency of occurrence of words,
The English practice service providing server 300, when receiving an English sentence in the English sentence format output from the learner terminal 100 through voice recognition from the learner terminal 100, to read and speak the English sentence Analyzing unit 340 for analyzing by processing NLP (Natural Language Processing) and transmitting the result to the learner terminal 100; further includes,
An instructor terminal 400 interworking with the learner terminal 100 to share the voice and text input from the learner terminal 100 and transmit a feedback to the learner terminal 100; further includes,
The at least one type of tag is matched with at least one Korean word and an English word, and the at least one English word is matched with and stored with a Korean word corresponding to the English word, and the at least one type of tag is stored. When a tag is selected, the at least one Korean word is randomly selected, and an English word corresponding to the randomly selected Korean word is located in the English sentence format,
The English sentence format includes a first format in which only a subject exists, a second format including a subject and a general verb, a third format including a subject and the verb be, and a fourth format including the subject, be verb, and adjective. , The subject includes Korean words and English words corresponding to the indicating pronoun tags, personal pronoun tags, and other pronoun tags, and the general verb includes Korean words and English words corresponding to plain preface tags, negative sentences and interrogative tags. And the verb be includes Korean words and English words corresponding to plain preface tags, negative sentence tags, and interrogative tags,
The English training service providing server 300, after randomly providing Korean sentences in the Korean sentence format as a combination of Korean words, receiving an English sentence corresponding to the Korean sentence from the learner terminal 100, and receiving the English sentence A writing-learning unit 360 that determines a degree of correspondence with a sentence and an English sentence stored in correspondence with the Korean sentence and transmits it to the learner terminal 100;
A system for providing English practice services based on random word combinations for reading and speaking learning, characterized in that it further comprises.
delete delete delete delete The method of claim 1,
The English practice service providing server 300,
Consonant Vowel Consonant (CVC), Consonant Vowel Consonant Vowel (CVCV), Consonant Consonant Vowel Consonant Vowel (CCVCV) and Consonant Consonant Vowel Consonant Vowel Consonant (CCVVCVC) in English words, Korean words, and at least one phonics syllable structure A phonics learning unit 350 for mapping and storing phonetic symbols;
A system for providing English practice services based on random word combinations for reading and speaking learning, characterized in that it further comprises.
delete

Images