KR20200011795A - Quiz creation system and method for language learning - Google Patents

Abstract

Disclosed are a quiz generation system for language learning and a method thereof. According to an embodiment of the present invention, the quiz generation system for language learning comprises: a text extraction unit extracting full text of a file including language text; a text summary unit summarizing content of the full text to generate a summary statement; an image generation unit generating a summary statement image corresponding to the summary statement; and a quiz setting unit providing a quiz by using the summary statement and the summary statement image.

Description

QUIZ CREATION SYSTEM AND METHOD FOR LANGUAGE LEARNING}

The present invention relates to a problem generation system and method for language learning, and more particularly, to summarize the paragraphs describing the images contained in the e-book file to generate a summary and match the summary with the image of the reader A problem generating system and method for language learning configured to generate problems that can enhance book comprehension.

Common methods for learning a foreign language include using a foreign language school, using a landline or video phone, or using an online class. Among these, as the Internet-related technology develops recently, the number of people who want to learn a foreign language using online lectures is increasing rapidly because of the limitation of time and space.

In this regard, companies that provide foreign language learning using internet lectures make various foreign language learning materials using computers as tools, but there are limitations in the technology of mechanizing foreign language translation. Generating data requires a lot of manpower, time and money.

For example, conventionally, a learning system provider directly selects main images included in a book, and selects the selected main images in order to make a question about the contents of the book in order to improve the understanding of an e-book in a foreign language. After generating the corresponding summaries, a method of using the main images and the summaries to question the user was used.

Therefore, in the related industry, continuous development of methods and technologies for effectively creating and presenting foreign language learning-related problems in the foreign language learning providing system using the Internet is required.

The present invention has been made to solve the above problems, the main technical problem to be achieved by the present invention is to summarize the paragraphs describing the images contained in the e-book file to generate a summary and match the image and the summary together It is to provide a problem generation system and method for language learning that is configured to generate a problem that can improve the reader's understanding.

The technical problem to be achieved by the present invention is not limited to the technical problem mentioned above, and other technical problems not mentioned above may be clearly understood by those skilled in the art from the following description. There will be.

In order to solve the technical problem, an embodiment of the present invention, a text extraction unit for extracting the full text of the file containing the language text, a text summary unit for generating a summary by summarizing the contents of the full text, Provided is a language learning problem generation system including an image generation unit for generating a summary image corresponding to the summary sentence, and a problem questionnaire for providing a problem using the summary sentence and the summary sentence image.

In the present embodiment, the file including the language text includes one or more pages, each of the one or more pages includes an image and a plurality of sentences corresponding to the image, and the text summary unit includes the plurality of sentences. Among them, a summary sentence may be generated to include one sentence including a word having the highest occurrence frequency, and the summary sentence may be generated for each of the one or more pages.

In the present embodiment, the image generation unit may be generated by extracting an image associated with a word having a high frequency among words included in the summary based on the summary generated for each of the one or more pages in the file, or by using an external image database. Can be generated via

In the present embodiment, a plurality of the summary and the summary image is generated, and the question-producing unit displays a problem formed to randomly display the plurality of the summary and the plurality of the summary images and to connect the arranged summary and the images. Can provide.

In the present embodiment, a plurality of the summary sentence and the summary image are generated, and the question-producing unit displays one summary image and the plurality of summary sentences, and corresponds to one summary image provided among the plurality of summary sentences provided. Provide questions that are designed to select a summary.

In the present exemplary embodiment, the problem questionnaire may provide a voice corresponding to the summary sentence or a voice corresponding to the summary sentence image together with the problem.

In the present exemplary embodiment, the file including the language text includes a plurality of pages, the linked page including a plurality of sentences that are displayed to be linked to one epic image of the plurality of pages and corresponding to the epic image. The text summarizing unit may generate a summary sentence to include one sentence including a word having the highest occurrence frequency among a plurality of sentences corresponding to the epic image, and the image generating unit may include words included in the summary sentence. An image associated with a word having a high frequency of occurrence may be generated by editing a specific region of the epic image.

In addition, another embodiment of the present invention to solve the technical problem is a language learning problem generation method using a language learning problem generation system according to an embodiment of the present invention, the language learning problem generation system includes a language text A text extracting step of extracting the entire text of a file, a text summarizing step of generating a summary by summarizing the contents of the entire text, and the language learning problem generating system generating a summary image corresponding to the summary It provides an image generation step, and a language learning problem generation method comprising a problem question step that the language learning problem generation system provides a problem using the summary and the summary image.

In the present embodiment, the file including the language text includes one or more pages, wherein each of the one or more pages includes an image and a plurality of sentences corresponding to the images, and the text summarizing step includes the language learning. The problem generating system may generate the summary sentence to include one sentence including the word having the highest frequency of occurrence among the plurality of sentences, and generate the summary sentence for each of the one or more pages.

In the present embodiment, the image generation step, the language learning problem generation system, based on the summary statement generated for each of the one or more pages of the image included in the summary word associated with the word occurring frequently in the file in the file The extraction may be performed or generated through an external image database.

In the present embodiment, a plurality of the summary and the summary image is generated, and in the question-producing step, the language learning problem generation system randomly displays the plurality of the summary and the plurality of the summary image and arranges the summary. It may be a step of providing a problem formed to connect the images and the images.

In the present embodiment, a plurality of the summary and the summary image is generated, and in the question-producing step, the language learning problem generation system displays one summary image and the plurality of summary statements, and provides a plurality of summary statements. It may be a step of providing a problem formed to select a summary corresponding to one of the summary image provided.

In the present embodiment, the question-producing step may be a step in which the language learning problem generation system provides a voice corresponding to the summary sentence or a voice corresponding to the summary sentence image together with the problem.

In the present exemplary embodiment, the file including the language text includes a plurality of pages, the linked page including a plurality of sentences that are displayed to be linked to one epic image of the plurality of pages and corresponding to the epic image. The text summarizing step may include generating a summary sentence by the language learning problem generation system to include one sentence including a word having the highest occurrence frequency among a plurality of sentences corresponding to the narrative image. The image generating step may be a step in which the language learning problem generation system generates an image associated with a word having a high frequency among words included in the summary by editing a specific region of the epic image.

According to the present invention, the paragraph describing the image included in the e-book can be automatically summarized to generate a summary, and the problem can be automatically generated by matching the image and the summary together to enhance the reader's understanding.

In addition, according to the present invention, the content summary of the text including the language may be performed first, and then the image may be generated for the summary to increase the relevance of the summary to the image.

In addition, according to the present invention, even when the narrative image is displayed on two pages, the sentences corresponding to the narrative image are summarized, and the image corresponding to the summary is displayed by editing and extracting some of the narrative images to display the related images. The degree can be further increased.

In addition, according to the present invention, in addition to the above effects, it is possible to reduce the manpower, time and cost required for the question of language learning through online, and can increase the work productivity in this regard.

The effects of the present invention are not limited to the above-described effects, but should be understood to include all the effects deduced from the configuration of the invention described in the detailed description or claims of the present invention.

1 is a block diagram showing the configuration of a problem generation system for language learning according to an embodiment of the present invention.
2 is a diagram illustrating a problem generation system for language learning, a database, a terminal, and the like interoperable with the problem generation system according to an embodiment of the present invention.
3 is a diagram illustrating the types of problems created and provided according to an embodiment of the present invention.
4 is a diagram illustrating a process of extracting an epic image according to an embodiment of the present invention.
5 is a flowchart illustrating a procedure of a problem generating method for language learning according to another embodiment of the present invention.
FIG. 6 is a diagram illustrating images included in an e-book illustrated to explain an embodiment of the present invention.

Hereinafter, with reference to the accompanying drawings will be described in detail the present invention. As those skilled in the art would realize, the described embodiments may be modified in various different ways, all without departing from the spirit or scope of the present invention. In addition, the accompanying drawings are only for easily understanding the embodiments disclosed in the present specification, the technical idea disclosed in the specification by the accompanying drawings are not limited, and all changes included in the spirit and scope of the present invention. It is to be understood to include water, equivalents and substitutes. And the part not related to the description in order to clearly describe the present invention in the drawings are omitted, the size, shape, shape of each component shown in the drawings may be variously modified, the same / similar parts for the entire specification Identical / similar reference numerals are used.

The suffixes "module" and "unit" for components used in the following description are given or mixed in consideration of ease of specification, and do not have distinct meanings or roles. In addition, in describing the embodiments disclosed herein, when it is determined that the detailed description of the related known technology may obscure the gist of the embodiments disclosed herein, the detailed description thereof is omitted.

Throughout the specification, when a part is said to be "connected (connected, contacted or coupled) with another part, it is not only when it is" directly connected (connected, contacted or coupled) ", but also in between. This includes cases in which the connection is indirectly connected (connected, contacted or coupled). In addition, when a part is said to "include (or prepare)" a component, it will not "exclude (or prepare)" another component rather than to exclude other components unless specifically stated otherwise. That means you can.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. In this specification, terms such as "comprise" or "have" are intended to indicate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, and one or more other features. It is to be understood that the present invention does not exclude the possibility of the presence or the addition of numbers, steps, operations, components, components, or a combination thereof.

1 is a block diagram illustrating a configuration of a problem generation system for language learning according to an embodiment of the present invention, and FIG. 2 is a problem generation system for language learning according to an embodiment of the present invention (hereinafter, “language”). Learning problem generation system 100 ") and a database, a terminal, and the like interoperable therewith.

As shown in FIG. 1, the language learning problem generating system 100 includes a text extracting unit 110, a text summarizing unit 120, an image generating unit 130, and a problem generating unit 140.

The text extraction unit 110 extracts the entire text of the file containing the language text. here. The language text may be an e-book type file including foreign language text other than Korean, and may be obtained through a separate language file database 210.

The text summarizing unit 120 generates a summary by summarizing the contents of the entire text extracted by the text extracting unit 100.

The image generator 130 generates a summary image image corresponding to the summary sentence.

As an example, the file including the language text may include one or more pages, and each of the one or more pages may include an image and a plurality of sentences corresponding to the image. In this case, the text summary unit 120 may generate a summary sentence to include one sentence including a word having the highest occurrence frequency among the plurality of sentences, but generate the summary sentence for each of the one or more pages. In addition, the image generator 130 extracts an image associated with a word having a high occurrence frequency among the words included in the summary sentence based on the summary sentence generated for each of the one or more pages in the file, or generates an external image database 220. Can be generated via

Problem question unit 140 provides a problem using the summary and the summary image. The problem generated in this way may be provided to the user terminal 300 formed in the form of a smart phone, a desktop, or the like.

Referring to FIG. 3, which shows an example of providing a problem of the problem question unit 140, the problem question unit 140 allows the user to connect the summary statements and the corresponding summary image images as shown in FIGS. 3A and 3B. Can create problems. In other words, the question generating unit 140 may randomly display the plurality of summaries and the plurality of summarization images and provide a problem formed to connect the arranged summaries and images.

In addition, as shown in (c) of FIG. 3, the question question unit 140 displays one summary image and a plurality of the summary sentences, and selects a summary sentence corresponding to one summary image provided from the plurality of summary statements provided. Problems formed can be provided.

In addition, the question question unit 140 may provide a voice corresponding to the summary sentence or a voice corresponding to the summary sentence image to the user.

As such, the language learning problem generation system 100 automatically generates a summary by summarizing paragraphs describing an image included in the e-book, and automatically generates a problem that can increase the reader's understanding by matching the image and the summary together. can do.

In addition, the language learning problem generation system 100 may first perform a summary of the contents of the text including the language, and then generate an image for the summary to increase the relevance of the summary to the image.

4 is a diagram illustrating a process of extracting an epic image according to an embodiment of the present invention.

As shown in 401 of FIG. 4, when every page is composed of a single image and sentences corresponding to each page, the sentences are summarized to generate a summary sentence, and the image corresponding to the summary sentence is located on the same page as the summary sentence so that it is smoothly extracted and It can be created.

However, in the case of a file in which one linked narrative image is displayed on a plurality of pages (pages 3 and 4) as shown in 402 of FIG. 4 and the sentences corresponding thereto are divided into a plurality of pages, the sentences are summarized to generate a summary sentence. The image corresponding to the summary may then be shown on page 3 or may appear on page 4. Therefore, since it is not necessary to extract and / or generate all of one narrative image as an image corresponding to the summary sentence, the image generator 130 may generate or extract an image corresponding to the summary sentence from the narrative image in this case. Can be.

In other words, as an embodiment of the language learning problem generating system 100 described above, as shown in 402 of FIG. 4, the file including the language text includes a plurality of pages but an epic image of one of the plurality of pages. May include a linked page that is displayed to be linked and includes a plurality of sentences corresponding to the epic image. In the above embodiment, the text summary unit 120 may generate a summary sentence to include one sentence including a word having the highest occurrence frequency among a plurality of sentences corresponding to the narrative image. In addition, in the same embodiment, the image generator 130 may generate an image associated with a word having a high frequency among words included in the summary by editing and / or extracting a specific region of the epic image. .

Using the above-described method, the language learning problem generation system 100 may summarize sentences corresponding to the narrative image even when the narrative image is displayed over two pages, and edit and extract some of the narrative image from the image corresponding to the summary. By presenting, the relevance between the image and the summary can be further enhanced.

5 is a flowchart illustrating a procedure of a problem generating method for language learning according to another embodiment of the present invention. The problem generating method for language learning according to the present embodiment is described with reference to FIGS. 1 to 4. A language learning problem generation method using the learning problem generation system 100. Therefore, hereinafter, descriptions overlapping with the above description will be omitted.

In the method for generating a language learning problem according to the present embodiment, the text learning step of extracting the entire text of the file including the language text by the language learning problem generating system (s510), and the language learning problem generating system generates the contents of the whole text. A text summarizing step (s520) of generating a summary by summarizing, an image generating step (s530) of generating a summary image corresponding to the summary by the language learning problem generating system, and the language learning problem generating system by the summary and the summary image It includes a problem question step (s540) that provides a problem using.

In the present embodiment, the file including the language text may include one or more pages, and each of the one or more pages may include an image and a plurality of sentences corresponding to the images, wherein the text summarization step (s520) ), The language learning problem generating system may generate a summary sentence to include one sentence including a word having the highest occurrence frequency among the plurality of sentences, but generating the summary sentence for each of the one or more pages. .

In addition, the image generation step (s530), the language learning problem generation system, based on the summary generated for each of the one or more pages extracted from the image associated with the word with a high frequency among the words included in the summary sentence in the file Or may be generated through an external image database.

In addition, a plurality of the summary sentence and the summary sentence image may be generated. In this case, in the question question step s540, the language learning problem generation system randomly displays the plurality of the summary sentence and the plurality of the summary sentence images, It may be a step of providing a problem formed to connect the arranged abstracts and images.

In addition, a plurality of the summary sentence and the summary sentence image may be generated. Here, in the problem question step s540, the language learning problem generating system may display one summary sentence image and the plurality of summary sentences, and provide a plurality of summary sentences. It may be a step of providing a problem formed to select a summary corresponding to the one summary image provided of the summary.

In addition, the question generation step s540 may be a step in which the language learning problem generation system provides a voice corresponding to the summary sentence or a voice corresponding to the summary sentence image together with the problem.

In the present exemplary embodiment, the file including the language text includes a plurality of pages, the linked page including a plurality of sentences that are displayed to be linked to one epic image of the plurality of pages and corresponding to the epic image. In the text summarizing step s520, the language learning problem generation system may generate a summary sentence to include one sentence including a word having the highest occurrence frequency among a plurality of sentences corresponding to the epic image. The image generation step (s530) may include generating, by the language learning problem generation system, an image associated with a word having a high frequency among words included in the summary by editing a specific region of the epic image. Can be.

For convenience of understanding, one embodiment of the various embodiments of the present invention described above will be described as an example.

According to an embodiment of the present invention, i) the entire text of the e-book (ebook) may be summarized into 11 sentences (paragraphs) by first summarizing. Ii) Next, text corresponding to each image may be extracted using the image of each page for eleven sentences (paragraphs). Iii) Next, three sentences (paragraphs) having high similarity can be selected by comparing the extracted sentences with 11 sentences (paragraphs). Iv) Next, the question can be asked in three sentences (paragraphs) with high verified similarity.

For example, the full text included in the e-book (Full Story [ORT "A Monster Mistake"] (334 words)) is as follows and the image shown on each page of the e-book may be the same as the images shown in FIG.

“Mum and Gran went on holiday. They went to Scotland. They took the children. They stayed in a cottage. The cottage was by a lake. It had a boat. "I like it here," said Biff. "We can go sailing." "And fishing," said Kipper. Everyone had a good time. Biff and Kipper went fishing. Gran and Chip painted a picture. Mum sat in the sun and read a book. "This is fun," she said. Everyone looked at Gran's picture. "Oh Gran!" said Chip. She had painted a monster. Kipper looked at the monster. Gran laughed. "There's no such thing," she said. Mum went shopping. She took Kipper. Biff and Chip stayed with Gran. Mum looked at the shops. "Let's get Dad a postcard," she said. Kipper went into a shop. "I want a monster for me and a postcard for Dad," he said. Kipper posted the card to Dad. "I wish Dad was here," he said. Gran wanted to play a joke on Mum. "Let's make a monster," she said. "I don't get it," said Biff. "Wait and see," said Gran. They put the monster in the lake. It made the children laugh. "It looks brilliant!" said Chip. "What a good joke," said Biff. "What a good joke to play on Mum." Mum and Kipper came back. Gran pulled the rope. The monster went across the lake. "A real monster," said Kipper. "I don't believe it," said Mum. "There's no such thing." Some people saw Gran's monster. They were amazed. They took photographs. The children watched television. "Gran's monster!" sand Chip. "Oh no!" groaned Biff. The next day lots of people came. There were lots and lots and lots of people. They wanted to see the monster. "Oh Gran!" said Mum. "Now look what you've done." Gran told everyone about the monster. "It was just a joke," she said. A man from the television came. Mum was cross with Gran but everyone laughed. Gran was sorry. "A monster?" she said. "There is no such thing."

Here, according to the process i) it can be summarized as follows. The reduction ratio can be preset in various ways.

"(page1) Mum and Gran went on holiday.They went to Scotland.They took the children.

(page2) They stayed in a cottage. The cottage was by a lake. It had a boat.

(page 4) Everyone had a good time. Biff and Kipper went fishing. Gran and Chip painted a picture.

(page8) Mum went shopping. She took Kipper. Biff and Chip stayed with Gran.

(page9) Mum looked at the shops. "get Dad a postcard,"

(page12) Gran wanted to play a joke on Mum. "make a monster,"

(page17) "don't believe it,"

(page18) Some people saw Gran's monster. They were amazed. They took photographs.

(page 19) The children watched television. "monster!"

(page22) Gran told everyone about the monster. "It was just a joke," she said.

(page24) Gran was sorry. ”

Next, text may be extracted as in step ii). Here, when the image is divided into two sheets, texts corresponding to the entire image may be extracted.

“(Page1) Family Member Going Inside House.

(page2,3) Woman Standing On Dock Beside Row Boat On Body Of Water Near House.

(page4,5) Girl And Boy Fishing.

(page8) Grandmother And Two Children Waving Goodbye To People Inside Car

(page9) Boy Standing Near Woman Wearing Yellow Jacket

(page12,13) Girl And Boy Holding Gray Rocks

(page17) Women's Gray Long-Sleeved Shirt

(page18) Group Of People Standing Near Vehicles And Taking Photographs.

(page19) Three Children Watching Television

(page22,23) A Woman Talking To Group Of People

(page24) Green Crocodile On Body Of Water ”

Next, the process of iii) comparing the sentences obtained through the process ii) with each sentence (11 lines in total) and confirming the similarity may be performed as follows.

For example, the length 11 matrix below may represent the similarity between the sentences of each page of the main body and the sentences obtained through the process ii).

“(Page1)" Family Member Going Inside House. "

[0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

Accordingly, the sentence may mean that the similarity with the text is low, and thus may not be selected.

(page2,3) "Woman Standing On Dock Beside Row Boat On Body Of Water Near House."

[0.19467834 0.15053424 0.0 0.0 0.19897093 0.0 0.0 0.12144983 0.0]

Accordingly, the sentence may mean that the similarity with the text is low and may not be selected.

(page4,5) "Girl And Boy Fishing." An example of similarity detection when comparing with each sentence of the main text is as follows.

[0.20926994 0. 0.3611502 0.24730484 0.0 0.0 0.0 0.0 0.0]

Accordingly, the sentence may mean that the similarity with the page4 sentence is the highest in the text, and may be selected.

(page8) "Grandmother And Two Children Waving Goodbye To People Inside Car"

[0.37448663 0.0 0.14545763 0.09960502 0.0 0.14829972 0.0 0.13909829 0.18300696 0.0]

Accordingly, the sentence is similar to the page1 sentence in the text, but may not be selected because it does not match the image page.

(page9) "Boy Standing Near Woman Wearing Yellow Jacket"

[0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

Accordingly, the sentence may not be selected because of similarity with the text.

(page12,13) "Girl And Boy Holding Gray Rocks"

[0.20926994 0.0 0.3611502 0.24730484 0.0 0.0 0.0 0.0 0.0] ”

Accordingly, the sentence is similar to the page4 sentence in the text, but may not be selected because it does not match the image page.

(Page 17) Women's Gray Long-Sleeved Shirt

[0. 0.0 0.0 0.0 0.12029144 0.1297936290.11364595 0.12174041 0.08008489 0.0.

Accordingly, the sentence may not be selected because of low similarity.

(page18) Group Of People Standing Near Vehicles And Taking Picture

[0.0677762 0.0 0.11696561 0.08009455 0.0 0.0 0.333153 0.21915913 0.0]

Accordingly, the sentence may be selected to have the highest similarity with the page18 sentence in the text.

(page19) Three Children Watching Television

[0.15909743 0.0 0.0 0.0 0.0 0.0 0.0 0.29883584 0.0]

Accordingly, the sentence may be selected to have the highest similarity with the page19 sentence in the text.

(page 22,23) A Woman Talking To Group Of People

(0.1341005 0.06726596 0.04950481 0. 0.02717189 0.19569391

0. 0.12855348 0.25188357 0.03149408 0.] ”

Accordingly, the sentence is similar to the page19 sentence in the text, but may not be selected because it does not match the image page.

“(Page24) Green Crocodile On Body Of Water

[0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.] ”

Accordingly, the sentence may not be selected because of its similarity to the text.

Next, a question may be asked using the following sentence selected through the above step iv) and the image shown in FIG. 6.

“(Page4) Everyone had a good time. Biff and Kipper went fishing. Gran and Chip painted a picture.

(page18) Some people saw Gran's monster. They were amazed. They's took photographs.

(page 19) The children watched television. “

Finally, if the number of selected pages is less than the number of image-phrases (paragraphs) required for the question, then after adjusting the reduction ratio (e.g. from 40% to 60%) in the summary step of step i) above, The present invention can be implemented such that the problem is solved in the same manner as described above by performing image and text matching on the page.

In addition, when the number of the last selected pages is larger than the number of image-phrases (paragraphs) required for the question, the present invention may be implemented such that the questions are selected by selecting the order of the similarity between the image and the sentence (paragraphs).

As described above, various embodiments of the present invention may be implemented to measure the similarity between sentences using various techniques in addition to the method of evaluating the similarity between sentences using a matrix technique.

In addition, the language learning problem generation system 100 and method as described above may be implemented through a mobile PC and a mobile application, respectively. For example, the language learning problem generation system 100 may be implemented in a form such as a smartphone, and each function of the system may be implemented through a wireless communication technology, an application processor, and a liquid crystal display mounted on the smartphone. Each procedure can be performed through a smartphone application built-in or downloaded.

In addition, the embodiments described above may be implemented as a combination of hardware components, software components, hardware components, and software components. For example, the devices, methods, and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, an FPGA ( It may be implemented using one or more general purpose or special purpose computers, such as a field programmable gate array, a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions. In addition, the method according to various embodiments of the present disclosure may be implemented in the form of program instructions that may be executed by various computer means, and may be recorded on a computer readable medium.

According to various embodiments of the present invention described so far, it is possible to reduce the manpower, time and cost required to solve language learning problems online, and increase work productivity in this regard.

The description of the present invention described above is for illustrative purposes, and it will be understood by those skilled in the art that the present invention may be easily modified in 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 exemplary in all respects and not restrictive. The scope of the present invention is represented by the following claims, and it should be construed that all changes or modifications derived from the meaning and scope of the claims and their equivalents are included in the scope of the present invention.

Claims (15)

A text extraction unit for extracting the entire text of the file including the language text;
A text summarizing unit configured to generate a summary by summarizing the contents of the entire text;
An image generator which generates a summary image image corresponding to the summary sentence; And
And a question questionnaire that provides a problem using the summary and the summary image.
The method of claim 1,
The file including the language text includes one or more pages, each of the one or more pages includes an image and a plurality of sentences corresponding to the image,
The text summarizing unit generates a summary sentence to include one sentence including a word having the highest occurrence frequency among the plurality of sentences, and generates the summary sentence for each of the one or more pages.
The method of claim 2,
The image generating unit,
Language learning problem, characterized in that for extracting the image associated with the word with a high frequency among the words included in the summary based on the summary generated for each of the one or more pages in the file or generated through an external image database Generating system.
The method of claim 1,
A plurality of the summary and the summary image is generated,
The problem question generating unit, wherein the plurality of summaries and a plurality of the summary images are displayed randomly, and a language learning problem generation system, characterized in that for providing a problem formed to connect the arranged summary and the image.
The method of claim 1,
A plurality of the summary and the summary image is generated,
The problem question generating unit generates a language learning problem, characterized in that for displaying a summary image and a plurality of the summary statements, and providing a problem formed to select a summary sentence corresponding to the one summary image provided from the plurality of summary statements provided. system.
The method of claim 1,
The question questions section,
And a speech corresponding to the summary sentence or a speech corresponding to the summary sentence image together with the question.
The method of claim 1,
The file including the language text includes a plurality of pages, the linked page including a plurality of sentences that are displayed to be linked to one epic image of the plurality of pages and corresponding to the epic image,
The text summarizing unit generates a summary sentence to include one sentence including a word having the highest occurrence frequency among a plurality of sentences corresponding to the epic image.
The image generating unit,
And generating an image associated with a word having a high frequency among words included in the summary by editing a specific region of the narrative image.
A language learning problem generating method using a language learning problem generating system according to any one of claims 1 to 7,
A text extracting step of extracting, by the language learning problem generating system, the entire text of the file including the language text;
A text summarizing step of generating, by the language learning problem generating system, a summary sentence by summarizing contents of the entire text;
An image generation step of generating, by the language learning problem generation system, a summary sentence image corresponding to the summary sentence; And
And a problem question step of the language learning problem generation system providing a problem using the summary sentence and the summary sentence image.
The method of claim 8,
The file including the language text includes one or more pages, each of the one or more pages includes an image and a plurality of sentences corresponding to the image,
The text summary step,
The language learning problem generating system generates a summary sentence to include one sentence including a word having the highest frequency of occurrence among the plurality of sentences, wherein the summary sentence is generated for each of the one or more pages. How to create a learning problem.
The method of claim 9,
The image generation step,
The language learning problem generating system extracts and generates an image associated with a word having a high frequency among words included in the summary in the file based on the summary generated for each of the one or more pages, or through an external image database. Method for generating a language learning problem, characterized in that the step.

The method of claim 8,
A plurality of the summary and the summary image is generated,
The problem question step,
And the language learning problem generating system is configured to randomly display the plurality of summaries and the plurality of summaries images and provide a problem formed to connect the arranged summaries and images.
The method of claim 8,
A plurality of the summary and the summary image is generated,
The problem question step,
The language learning problem generating system is configured to display a single summary image and a plurality of the summary sentences and provide a problem configured to select a summary sentence corresponding to the provided summary image from among the plurality of provided summary sentences. How to create language learning questions.
The method of claim 8,
The problem question step,
And generating, by the language learning problem generation system, a voice corresponding to the summary sentence or a voice corresponding to the summary sentence image together with the problem.
The method of claim 8,
The file including the language text includes a plurality of pages, the linked page including a plurality of sentences that are displayed to be linked to one epic image of the plurality of pages and corresponding to the epic image,
In the text summarizing step, the language learning problem generation system generates a summary sentence to include one sentence including a word having the highest occurrence frequency among a plurality of sentences corresponding to the narrative image.
The image generation step is a language learning step, the language learning problem generation system, the language learning, characterized in that for generating an image associated with a word with a high occurrence frequency among the words included in the summary by editing a specific region of the narrative image How to create a problem.
A text extraction unit for extracting the entire text of the file including the language text;
A text summarizing unit configured to generate a summary by summarizing the contents of the entire text;
An image generator which generates a summary image image corresponding to the summary sentence; And
Including a question questionnaire that provides a problem using the summary and the summary image,
The file including the language text includes one or more pages, each of the one or more pages includes an image and a plurality of sentences corresponding to the image,
The text summary unit generates a summary sentence to include one sentence including a word having the highest frequency of occurrence among the plurality of sentences, and generates the summary sentence for each of the one or more pages.
The image generating unit may generate an image associated with a word having a high frequency among words included in the summary sentence based on the summary sentence generated for each of the one or more pages in the file or generate the image through an external image database,
A plurality of the summary and the summary image is generated,
The question-producing unit may provide a problem configured to randomly display the plurality of summaries and the plurality of summaries images and connect the arranged summaries and images, or display and display one of the summary images and the plurality of summaries. And a problem configured to select a summary that corresponds to the provided summary image of the one of six summaries.

Images