Smart Education System Based on Automatic Image Content Generation

Abstract

The present invention relates to a smart education system based on automatic generation of image content that can provide users with speaking learning services based on an image generation model and an evaluation solution in the field of artificial intelligence-based education platforms. More specifically, the present invention relates to a smart education system based on automatic generation of image content that allows users to view image content provided by a smart education platform server, compose sentences (including English, Korean, and other languages) to create similar images, and provide the sentences to a smart education platform. The platform then generates and provides images based on the user's sentences, evaluates pronunciation fluency so that users can learn to speak using the sentences, and provides feedback accordingly.

Description

[Technical Field]

[0001] The present invention relates to a smart education system based on automatic generation of image content, and more particularly, to a smart education system based on automatic generation of image content that can provide users with speaking learning services based on an image generation model and an evaluation solution in the field of artificial intelligence-based education platforms. [Background technology]

[0002] In recent years, with the rapid development of artificial intelligence technology, there has been a trend in the education sector as well, where innovative AI-based educational services are rapidly developing.

[0003] However, in the field of language education (various language services such as Korean conversation education services and English conversation services), AI technology has limitations in voice recognition functions, and the creation and evaluation of various content still relies mainly on passive system structures that rely on pre-constructed data and experts (lecturers, teachers, etc.).

[0004] In this context, this invention proposes an innovative system and service that actively utilizes artificial intelligence technology in areas such as content generation, speaking fluency assessment, and sentence construction ability assessment to provide learners (users) with a variety of speaking training. Technological developments in recent years have brought about revolutionary changes in online education and learning methods. Online education platforms have greatly increased the accessibility of education and played an important role in expanding the learning experience. This has given learners the opportunity to learn a variety of subjects and improve their skills without being bound by time or place.

[0005] However, maintaining learner participation and engagement has emerged as a major challenge in online education. Language learning, especially speaking practice, is seen as one of these challenges. Speaking practice plays an important role in improving language skills, but effectively assessing learners' pronunciation accuracy, fluency, and speaking rate and providing feedback in an online environment is technically very complex.

[0006] Furthermore, image-based teaching methods are effective in promoting learners' interest and participation through visual stimulation and helping them understand concepts. However, the interaction between images and text, where learners see pictures and explain them in text, or generate images based on text, is an area that existing technology has not been able to adequately address.

[0007] Therefore, the present invention seeks to overcome such problems and present an innovative way to increase learner participation and engagement and improve language and speaking skills. Summary of the Invention [Problem to be solved by the invention]

[0008] The technical problem to be solved by the present invention is to provide a smart education system based on automatic image content generation that can induce learner participation and engagement and provide an effective method for improving language learning and speaking skills.

[0009] Another technical problem that the present invention aims to solve is to provide a smart education system based on automatic image content generation that can make learning experiences more interesting and effective through interactions between images and text, thereby allowing learners to participate more actively, improve their language and speaking skills, and maximize learning effectiveness in an online education environment.

[0010] Another technical problem that the present invention aims to solve is to provide a smart education system based on automatic image content generation that can provide an image-based speaking learning system and service based on a variety of AI-based content generation solutions, a variety of sentence evaluation and proofreading solutions, and a speaking fluency solution.

[0011] Another technical problem that the present invention aims to solve is to provide a smart education system based on automatic image content generation, which includes a service for registering and sharing images created by learners (users) in order to provide efficient educational services and learning motivation to learners (users).

[0012] The technical problems to be solved by the present invention are not limited to those mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art from the following description. [Means for solving the problem]

[0013] To achieve the above technical objectives, one embodiment of the present invention provides a smart education system based on automatic generation of image content, which includes a smart education platform that provides first image content, evaluates the learning results of a learner performed based on the provided first image content, and provides the evaluated results to the learner; and a learner platform that generates text or records audio based on the first image content provided from the smart education platform, transmits the generated text or audio to the smart education platform, and receives the evaluation results for the text or audio.

[0014] The smart education platform also includes a learning content management unit that generates text and the first image content to be provided to the learner and transmits them to the learner platform; and a similarity evaluation unit that evaluates the accuracy of the text and voice generated by the learner based on the first image content transmitted to the learner platform.

[0015] The smart education platform further includes a learner image generation unit that generates second image content based on text or voice generated by the learner, and the similarity evaluation unit compares the first image content with the second image content to evaluate accuracy.

[0016] The smart education platform also includes a text proofreading / recommendation unit that provides the learner with proofread text for the learner's text generated based on the text or voice generated by the learner, recommended text extended based on the learner's text, and correct text for the first image content.

[0017] The system further includes a speaking evaluation unit that selects one of the sentences generated through the learner's voice, the proofread sentence, the recommended sentence, and the correct answer sentence, and when the learner records the selected sentence, evaluates the learner's speaking fluency based on the selected sentence and the recording file.

[0018] The smart education platform also includes a personal content management unit that stores all matters carried out through the learner platform.

[0019] The learner platform further includes a learner text generation unit that generates text or voice generated by the learner based on the first image content transmitted from the learning content management unit and transmits the generated text or voice to the smart education platform; and a learner image expression unit that receives the evaluation result transmitted through the similarity evaluation unit.

[0020] The learner platform also includes a speaking learning unit that checks the sentences generated by the learner, the proofread sentences, the recommended sentences, and the correct answer sentences, selects one of the sentences for speaking practice, and then records the selected sentence in audio; and an evaluation screen management unit that receives feedback on the evaluation results through the speaking evaluation unit and receives guidance on whether to re-study, finish learning, save the learning results, and share the learning results.

[0021] The above aspects of the present invention are only some of the preferred embodiments of the present invention, and various embodiments reflecting the technical features of the present invention can be derived and understood by those having ordinary skill in the art based on the detailed description of the present invention set forth below. [Effects of the Invention]

[0022] The present invention has the following advantages.

[0023] First, the present invention provides a service that evaluates a learner's explanatory writing based on an image generated by AI, and conversely, generates an image based on the learner's written sentence and evaluates how well it matches. In addition, it provides a service that evaluates the pronunciation fluency of the learner's written sentence and provides feedback to improve pronunciation for practical speaking (free speech), thereby combining sentence construction for image generation with speaking practice to improve the learner's sentence construction ability and speaking skills.

[0024] In addition, by interacting images and sentences, students' imaginations for writing practice are enhanced and their ability to compose sentences is improved. By repeating this process, students' language skills can be maximized and developed.

[0025] In addition, the present invention provides a personalized learning experience, i.e., a customized learning path is provided by utilizing the learner's voice and text data, and an opportunity is provided to grasp and improve the learner's development direction, thereby providing a learning experience optimized for each learner's abilities and requirements and maximizing learning efficiency.

[0026] Furthermore, the present invention promotes learners' interest and participation through a learning method that utilizes images, and by using visual stimuli to stimulate learners' interest and increase the enjoyment of learning, it can have a positive impact on providing motivation to learn and improving learning outcomes.

[0027] In addition, the present invention provides a picture-based vocabulary learning solution and supports effective learning through images and sentences during language test preparation.

[0028] Furthermore, the present invention can bring about revolutionary changes in the field of language education by providing learners with a variety of language education services, thereby improving learning efficiency and providing a more engaging learning experience.

[0029] The effects that can be obtained by the present invention are not limited to those mentioned above, and other effects not mentioned will be clearly understood by those having ordinary skill in the art to which the present invention pertains from the following description. [Brief explanation of the drawings]

[0030] [Figure 1] 1 is a diagram illustrating a procedure configuration according to an embodiment of a smart education system based on automatic image content generation according to the present invention. [Figure 2] 1 is a conceptual diagram illustrating a configuration of an embodiment of a smart education system based on automatic image content generation according to the present invention. [Figure 3] FIG. 2 is a configuration diagram of a learning content management unit according to the present invention. [Figure 4] FIG. 2 is a configuration diagram of a learner image generation unit according to the present invention. [Figure 5]FIG. 2 is a configuration diagram of a similarity evaluation unit according to the present invention. [Figure 6] FIG. 2 is a block diagram of a text proofreading / recommendation unit according to the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0031] Hereinafter, some embodiments of the present invention will be described in detail with reference to the drawings. When assigning reference numerals to components in each drawing, it should be noted that the same components are assigned the same numerals as much as possible even if they are displayed in different drawings. Furthermore, in describing the embodiments of the present invention, if a detailed description of related well-known structures or functions is deemed to hinder understanding of the embodiments of the present invention, the detailed description will be omitted.

[0032] Furthermore, when describing components of an embodiment of the present invention, terms such as first, second, A, B, (a), (b), etc. may be used. These terms are merely used to distinguish a component from other components, and do not limit the nature, order, or sequence of the components. When a component is described as being "coupled," "coupled," or "connected" to another component, it should be understood that the component may be directly coupled or connected to the other component, but that other components may also be "coupled," "coupled," or "connected" between them.

[0033] Figure 1 is a procedural configuration diagram for one embodiment of a smart education system based on automatic image content generation of the present invention, Figure 2 is a conceptual configuration diagram for one embodiment of a smart education system based on automatic image content generation of the present invention, Figure 3 is a configuration diagram of a learning content management unit according to the present invention, Figure 4 is a configuration diagram of a learner image generation unit according to the present invention, Figure 5 is a configuration diagram of a similarity evaluation unit according to the present invention, and Figure 6 is a configuration diagram of a sentence proofreading / recommendation unit according to the present invention.

[0034] The smart education system based on automatic image content generation according to the present invention will now be described with reference to FIGS.

[0035] The present invention relates to a smart education system based on automatic generation of image content, which is an image generation-based learner speaking service for solving problems that arise in online education systems and education services and for learner participation.

[0036] The procedure and concept of the service proposed in the present invention are as shown in FIG. 1, and the functions of the smart education platform server and terminal for providing the service are as shown in FIG.

[0037] First, referring to FIG. 1, the procedure for the smart education system based on automatic image content generation according to the present invention will be described as follows.

[0038] A learner can select a picture to study from among the pictures provided by the service of the present invention.

[0039] Learners can view the displayed picture (first image content) through the device and interpret it in sentences. At this time, they can input the interpreted sentence, for example, "cat and tree," using text, voice recording, or other input methods.

[0040] The sentences composed by the learner are transmitted to the smart education platform server, and the server evaluates the similarity between the image (second image content) generated based on the sentences composed by the learner and the exposed picture (first image content) and provides it to the learner.

[0041] Learners can look at the images and sentences they have created and choose whether to create images again or practice speaking.

[0042] When choosing to try again to create an image, the learner can return to the step of creating a sentence that interprets the picture, with the picture again exposed on the terminal, and create a sentence that describes the picture exposed on the terminal.

[0043] When a learner selects speaking learning, the screen of the terminal may present a proofread sentence in which incorrect parts of the sentence composed by the learner have been corrected, a recommended sentence expanded based on the sentence composed by the learner, and a correct sentence for the question.

[0044] The learner can select a sentence for speaking practice from the proofread sentence, the recommended sentence, and the correct answer sentence. Once a sentence is selected, the learner can read and record the selected sentence.

[0045] The learner's recorded voice and the sentences selected by the learner are transmitted to the smart education platform server, and the server can show the results of the speaking assessment (including assessment of pronunciation, fluency, speaking speed, rhythm, accent, etc.) to the learner through the terminal.

[0046] The learner can select another sentence and decide whether to start a new speaking practice, and if they select to resume speaking practice, they can return to the content display screen and start learning. The content display screen refers to a state in which a proofread sentence in which an incorrect part of a sentence written by the learner has been corrected, a recommended sentence expanded based on the sentence written by the learner, and a correct sentence for the question are presented on the screen of the terminal.

[0047] After completing their speaking practice, learners can register (save) and manage the sentences and images they have created in an album, and can share the images and sentences they have created. An album can be a space where users can save and manage images and other media content. This is a function provided within certain apps or platforms, and allows users to save images on their computers, smartphones, tablets, etc. and easily access them when needed.

[0048] Sharing images and text in an album can be done in a variety of ways.

[0049] First, learners can select images and texts they have created within the learning platform and share them with other users or groups using the internal sharing (in-app) function. Through this, they can share materials with users of the same platform.

[0050] After completing their study, learners can upload the images and text saved in their album to social media platforms (e.g., Facebook, Instagram, Twitter, etc.) or generate a sharing link to share with others.

[0051] After completing their study, learners can also create a sharing link for the images and text they have created and share it with others. This allows people who are not subscribed to the learner's album or a specific platform to view the shared content.

[0052] Once learners have completed their learning, they can also share the images and text they have created with others via email or messaging apps.

[0053] Information included when registering or sharing may include the learner's written text (or proofread text), image, learner information, date and time, sharing settings, sharing link, feedback or comments, social media information, similarity score, speaking fluency score, etc.

[0054] Next, a description will be given with reference to FIGS.

[0055] FIG. 2 is a conceptual diagram of a system configuration according to the present invention for providing the service shown in FIG.

[0056] First, the smart education system based on automatic image content generation according to the present invention may include a smart education platform and a learner platform.

[0057] The smart education platform can provide first image content, evaluate the learner's learning results based on the provided first image content, and provide the evaluated results to the learner. The smart education platform can include a learning content management unit, a learner sentence processing unit, a learner image generation unit, a similarity evaluation unit, a sentence proofreading / recommendation unit, a speaking evaluation unit, and a personal content management unit.

[0058] The learner platform may generate text or record audio based on the first image content provided by the smart education platform, transmit the generated text or audio to the smart education platform, and receive an evaluation result for the text or audio. The learner platform may include an image content management unit, a learner sentence generation unit, a learner image expression unit, a speaking learning unit, and an evaluation screen management unit.

[0059] The learning content management unit is a content generation unit for providing the service of the present invention, and may be configured as shown in Figure 3. The learning content management unit may periodically generate sentences and images (first image content) to be provided to learners.

[0060] Figure 3 shows the main function of the learning content management unit, which includes the function of generating periodic content. If a sentence for a learner is created in advance and registered as a learning sentence, the registered text (learning sentence) is provided to an AI-based image generation model to generate an image, and the text and image can be transmitted to the learning data storage unit and managed.

[0061] In addition, a database for storing images and texts can be built, and new content can be created using pre-prepared text templates and image data. Various types of learning content can be created by combining texts and images in the database.

[0062] It also uses natural language processing technology to analyze text related to an image and generate sentences that fit it, such as a description of the image or a sentence based on the objects and features in the image.

[0063] In addition, registered content text (including English, Korean, and other foreign languages) can be transmitted to a local image generation model to generate an image, or it can include a part that transmits text and image style to an external image generation model (e.g., Dall-e) to generate and store images externally. It can also use natural language processing technology to analyze text related to an image and generate corresponding text. For example, it can generate an explanation for the image or generate text based on the objects and features in the image.

[0064] External API processing conforms to external API standards, and the present invention may include a part that generates commands and sentences for API utilization. If the image generation result through external API processing is transmitted via a non-image path, the invention may include a function to receive and save the image via the path.

[0065] You can also develop scripts to automate the image and text generation process. For example, you can run a script at a specific interval (daily, weekly, etc.) to generate and distribute text and images to learners.

[0066] Additionally, machine learning models can be used to analyze a learner's previous activities and tendencies and predict appropriate sentences and images for that learner.

[0067] The learning content (images) generated by the learning content management unit can be provided to the learner platform (terminal). At this time, information such as the learning level and difficulty of the image, the creation date, and the image style (e.g., cartoon style, illustration style, watercolor style, sketch style, etc.) can be transmitted together. The image content management unit of the learner platform can filter and display images to the learner by difficulty level, creation date, and image style based on the information provided by the smart education platform (server side). Here, the user can select the image they want to study and start learning.

[0068] By viewing an image (first image content) selected in the image content management unit, the learner can create a sentence for creating the same image through the learner sentence creation unit. Here, the sentence creation method can include both voice recording using the device's microphone and text input using the device's typing function. Through the learner sentence creation unit, the learner can create a sentence using voice or text by selecting an input method and transmit the voice file or text to the learner sentence processing unit of the smart education platform on the server.

[0069] When a voice file is transmitted from the terminal, the learner's text processing unit can generate a voice recognition result (text) through a voice recognition function and transmit it to the learner's image generating unit. Also, when only text is provided from the terminal, the provided text can be transmitted to the learner's image generating unit.

[0070] Referring to Figure 4, the learner image generation unit can generate an image (second image content) based on the text or voice transmitted from the learner sentence processing unit. Here, a text- or voice-based image can be generated using a local image generation model, and an image can be generated by connecting to an external API and transmitting text and commands, if necessary. The learner image and learner sentence generated by the learner image generation unit can be transmitted to a similarity evaluation unit.

[0071] The similarity evaluation unit can evaluate the mutual similarity between the image (second image content) generated by the learner and the learning content image (first image content). Here, when evaluating the similarity, two methods can be used as shown in FIG. 5.

[0072] The first method is to evaluate the similarity between learner-generated images and the correct image by calculating the distance through correlation analysis. In other words, this method calculates the distance by analyzing the correlation between images. This can be done by comparing the similarity of image characteristics or pixel values. For example, the learner-generated image and the correct image can each be expressed as a number, and the correlation between these numbers can be analyzed to determine the similarity between the images, and the degree of similarity can be evaluated numerically through correlation analysis.

[0073] Alternatively, the similarity to the correct image may be evaluated through training of an artificial intelligence model. That is, the similarity between images can be evaluated by training an artificial intelligence model that evaluates images. For example, after providing many images and their corresponding correct images as training data to train an artificial intelligence model, the trained model can be used to evaluate the similarity between a new image and the correct image. This model automatically learns the characteristics of images and can determine the similarity between images based on that information.

[0074] The second method is a method of evaluating the similarity between a learner's sentence and a correct answer sentence, and can include both a method that uses word similarity and a method that evaluates the semantic similarity of sentences through learning an artificial intelligence model.

[0075] First, we can use a method to compare the similarity between the words in the sentences created by the learner and the correct sentences. For example, we can compare the meanings and usage of the words used in the sentences to evaluate how similar they are. We can measure the similarity between sentences by grasping the semantic similarity between words.

[0076] Another method is to train an artificial intelligence model to assess the semantic similarity between sentences. The model is trained using information needed to understand the structure and meaning of sentences, and can then predict the semantic similarity between new sentences.

[0077] These two methods can be used to evaluate the similarity between the sentence generated by the learner and the correct answer sentence. Furthermore, depending on the learner's situation and the situation of the evaluation system, the evaluation results of the two methods can be used independently. Alternatively, the evaluation scores obtained by the two methods can be combined and used to finally evaluate the similarity of the learner's sentence. In this way, it is possible to evaluate how similar the learner's sentence is to the correct answer sentence.

[0078] The similarity evaluation of the final learner can be evaluated using the following formula:

[0079] (Formula) Similarity evaluation = (1 - α) × image similarity + (α × sentence similarity)

[0080] Here, α (alpha) is a constant that can be determined between 0 and 1, and serves to adjust the weight of the image similarity and text similarity indexes.

[0081] The image similarity obtained by measuring the similarity between images indicates the similarity between the image generated by the learner and the correct image.

[0082] The sentence similarity obtained by measuring the similarity between the sentence generated by the learner and the correct sentence indicates the semantic similarity between the sentences obtained through the above-mentioned method.

[0083] Then, (1-α) represents the weighting value of image similarity, and “α” represents the weighting value of text similarity. The “α” value can be adjusted to adjust the relative importance between the two similarity indices.

[0084] In this way, the similarity between the image and the text can be combined to perform the final similarity evaluation. Through the above formula, the similarity between the image and the text of the content created by the learner can be independently evaluated and adjusted.

[0085] Additionally, image similarity and text similarity each range from '0' to '1', with values ​​closer to 1 indicating greater similarity. The final similarity evaluation can be performed by combining the image and text similarity values ​​using the above formula.

[0086] The similarity score and learner image generated by the similarity evaluation unit are provided to the learner image display unit of the learner platform (terminal), and the learner can view the image and similarity score provided through the learner image display unit and choose whether to generate an image again or to continue speaking practice.

[0087] If the learner wants to create an image again, the process can return to the processing step of the learner sentence creation unit described above.

[0088] When a learner selects speaking learning, the smart education platform (server side) can generate recommended sentences based on the learner's sentences and proofread sentences that are generated by proofreading the learner's spoken sentences, and transmit them to the learner platform. Here, the proofreading / recommending unit that generates the proofread sentences and recommended sentences can be configured as shown in Figure 6.

[0089] Referring to Figure 6, the text proofreading / recommendation unit can transmit a proofreading command and the learner's text to an external API processing unit (e.g., ChatGPT) to transmit the proofread text. It can also generate recommended text based on the learner's text by transmitting a recommended text command and the learner's text to generate recommended text. To receive recommendations for text related to the learning content, the unit can transmit both the learner's text and the correct answer text when generating recommended text, thereby receiving more complete recommendations related to the learning problem.

[0090] Through the speaking learning module, learners can review the sentences they have spoken, the proofread sentences, recommended sentences, and correct answer sentences, and select the sentence they want to practice speaking. They can record the selected sentence and send the audio file and the selected learning sentence to the speaking evaluation module. That is, learners can review the sentences they have spoken through the speaking learning module. The content that can be reviewed here may include the sentences they have spoken, the proofread sentences, recommended sentences, and correct answer sentences. Learners can select the sentences they want to practice speaking from among these. They can actually record the selected sentences and send the audio file and the selected learning sentences to the speaking evaluation module. In this way, learners can pronounce the selected sentences aloud, and their pronunciation and speaking ability can be evaluated and they can receive feedback.

[0091] The speaking assessment unit provides the audio file and the correct answer file to a speaking fluency assessment unit (artificial intelligence model), generates speaking learning results (fluency score, pronunciation accuracy score, rhythm, accent, speed score, etc.), and transmits them to the learner's assessment screen management unit. That is, the speaking assessment unit receives the learner's audio file and correct answer file and uses the artificial intelligence model to evaluate speaking fluency, pronunciation accuracy, rhythm, accent, speed, etc. Thereafter, such assessment results can be generated and sent to the learner's assessment screen management unit. The assessment results include various scores that indicate the learner's speaking ability, so the learner can check them and determine their own direction of development.

[0092] Learners can view their speaking assessment results through the assessment screen management unit. After receiving feedback on the assessment results, they can choose to study again for better learning, or to end the study and save or share the results with others. Through this selection process, learners can determine the direction for their own development and utilize their learning results as they wish.

[0093] In order for learners to save and share their learning results, their devices (e.g., smartphones) can request registration on the smart education platform (server side).The personal content management unit that makes up the smart education platform then accepts information related to the learner's personal content and stores and manages images, sentences written by the learner, similarity scores, and study dates in a database (DB).This allows the learner's learning results and information to be safely stored and accessed by the learner or shared with those who need it when needed.

[0094] This invention overcomes existing limitations in the field of language education, provides learners with an innovative and effective learning experience, and contributes to revolutionizing the entire education system and helping learners improve their language skills.

[0095] Although all components constituting the embodiments of the present invention have been described above as being combined or operating in combination, the present invention is not necessarily limited to such embodiments. That is, all components may be selectively combined and operate in combination as long as it is within the scope of the present invention. Furthermore, unless otherwise specified, the terms "comprise," "comprise," "have," etc., used above, mean that the corresponding component may be present, and should be interpreted as including other components rather than excluding other components. All terms, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the art to which the present invention pertains, unless otherwise defined. Commonly used terms, such as dictionary-defined terms, should be interpreted in accordance with the context of the relevant art and should not be interpreted in an idealized or overly formal sense unless expressly defined in the present invention.

[0096] The above description is merely illustrative of the technical concept of the present invention, and various modifications and variations may be made by those skilled in the art without departing from the essential characteristics of the present invention. Therefore, the examples presented in the present invention are for illustrative purposes only, and are not intended to limit the technical concept of the present invention. The scope of the present invention should be interpreted by the following claims, and all technical concepts within the scope equivalent thereto should be interpreted as being within the scope of the present invention.

Claims

1. A smart education platform that provides first image content, evaluates the learning results of the learners performed based on the provided first image content, and provides the evaluated results to the learners; and A smart education system based on automatic generation of image content, including a learner platform that generates text or records audio based on the first image content provided by the smart education platform, transmits the generated text or audio to the smart education platform, and receives an evaluation result for the text or audio.

2. The smart education platform includes: a learning content management unit that generates text and the first image content to be provided to the learner and transmits the content to the learner platform; and 2. The smart education system according to claim 1, further comprising a similarity evaluation unit that evaluates the accuracy of text and voice generated by a learner based on the first image content transmitted to the learner platform.

3. The smart education platform includes: further comprising a learner image generating unit that generates second image content based on the text or voice generated by the learner; The smart education system based on automatic image content generation according to claim 2 , wherein the similarity evaluation unit compares the first image content with the second image content to evaluate accuracy.

4. The smart education platform includes:

2. The smart education system based on automatic image content generation according to claim 1, further comprising a sentence proofreading / recommendation unit that provides the learner with proofread sentences for learner sentences generated based on text or voice generated by the learner, recommended sentences extended based on the learner sentences, and correct sentences for the first image content.

5. 5. The smart education system according to claim 4, further comprising a speaking evaluation unit that selects one of the sentence generated through the learner's voice, the proofread sentence, the recommended sentence, and the correct answer sentence, and when the learner records the selected sentence, evaluates the learner's speaking fluency based on the selected sentence and the recording file.

6. The smart education platform includes:

10. The smart education system according to claim 1, further comprising a personal content management unit for storing all matters performed through the learner platform.

7. The learner platform includes: a learner text generation unit that generates learner-generated text or voice based on the first image content transmitted from the learning content management unit and transmits the generated text or voice to the smart education platform; and The smart education system according to claim 3, further comprising a learner image expression unit that receives the evaluation result from the similarity evaluation unit.

8. The learner platform includes: a speaking learning unit that checks the sentence generated by the user, the proofread sentence, the recommended sentence, and the correct sentence, selects one sentence for speaking practice, and then records the selected sentence; and 6. The smart education system based on automatic image content generation according to claim 5, further comprising an evaluation screen management unit that receives feedback of the evaluation results through the speaking evaluation unit and receives guidance on whether to re-study, finish learning, save learning results, and share learning results.

Images