Artificial intelligence-based system for personalized text transformation and method of operating the same

Abstract

A method of operation of a user-customized text conversion system is disclosed. A method of operation of a user-customized text conversion system according to one aspect of the technical concept of the present disclosure comprises: collecting metadata regarding a user and original text for which the user requests analysis; generating at least one query related to the original text or the user; dynamically generating literacy data of the user using a first artificial intelligence model that takes as input the at least one query and a user response to the at least one query; determining a difficulty parameter of a customized text using the literacy data; generating the customized text using a second artificial intelligence model that takes as input the difficulty parameter; and providing the customized text to the user through a user interface.

Description

Technology Field

[0001] The technical concept of the present disclosure relates to an artificial intelligence-based user-customized text conversion system and a method of operation thereof. More specifically, it relates to a method of providing a service that dynamically identifies literacy through conversational interaction with a user and converts text into an optimal individual form in real time accordingly. Background Technology

[0003] With the recent acceleration of information digitization, the importance of delivering information tailored to the user's level of understanding is emerging across various fields. In particular, in areas involving complex documents such as education, public administration, healthcare, and finance, accessibility and comprehension can vary significantly depending on the recipient's literacy level. In these fields, the vocabulary, sentence structure, and explanatory style of the delivered text must be appropriately aligned with the recipient's comprehension to ensure the accuracy and efficiency of information transmission.

[0004] Natural Language Processing (NLP) technology is utilized as a means to achieve these objectives, and in particular, technologies based on Large Language Models (LLM), such as text analysis, summarization, rewriting, and leveling, have been rapidly advancing recently. Along with this, techniques for personalizing information based on user responses or characteristics are also being applied in various fields. For instance, educational platforms provide content tailored to the learner's level, while public institutions provide documents that consider the learner's understanding of civil complaint notices or terms and conditions. The problem to be solved

[0006] Existing text transformation and summarization technologies primarily focus on static, rule-based processing and are often limited to text length reduction, key keyword extraction, and formatting. Because this approach fails to consider the user's actual literacy level or state of comprehension, it leads to difficulties in the practical understanding of information.

[0007] Furthermore, existing adaptive content delivery systems are limited to personalizing learning paths, problem difficulty, and content recommendations, and do not provide the functionality to change the difficulty or presentation style of the original text itself in real time to match the user's level. The technology for existing adaptive content delivery systems to diagnose a user's current literacy status through real-time interactive communication and rewrite text accordingly is very limited.

[0008] Accordingly, the present disclosure is conceived in response to the aforementioned background technology and existing text conversion and summarization technologies, and relates to a user-customized text conversion system capable of precisely and dynamically diagnosing the level of literacy through real-time conversation with a user and, accordingly, converting and providing text in a customized manner in real-time.

[0009] However, the problems to be solved in this disclosure are not limited to those mentioned above, and other unmentioned problems may be clearly understood based on the description below. means of solving the problem

[0011] A method of operation of a user-customized text conversion system according to an embodiment of the present disclosure for realizing the aforementioned objectives is disclosed. The method comprises the steps of: collecting metadata regarding a user and original text for which the user requests analysis; generating at least one query related to the original text or the user; dynamically generating literacy data of the user using a first artificial intelligence model that takes as input the at least one query and a user response to the at least one query; determining a difficulty parameter of the customized text using the literacy data; generating the customized text using a second artificial intelligence model that takes as input the difficulty parameter; and providing the customized text to the user through a user interface.

[0012] According to one embodiment, the metadata includes information regarding at least one of the user's age, occupation, educational background, work area, degree of multilingual exposure, or type of documents created, viewed, or downloaded during a certain period.

[0013] According to one embodiment, the first artificial intelligence model includes a natural language processing model and a machine learning model, and the literacy data may be data calculated based on at least one of the accuracy of the user response, the response time, the words included in the user response, and the response pattern by type of at least one query.

[0014] According to one embodiment, the difficulty parameter may be a value representing the difficulty of at least one of the words, sentence length, and sentence structure type of the custom text.

[0015] According to one embodiment, the method may further include the step of analyzing the subject and sentence structure of the original text.

[0016] According to one embodiment, the second artificial intelligence model includes a natural language generation model, and the second artificial intelligence model may take the topic and difficulty parameter of the original text as input.

[0017] According to one embodiment, the customized text may be text in which the words or sentence structures included in the original text are changed or example sentences are added.

[0018] According to one embodiment, the method may further include the step of receiving the user response to the at least one query or user feedback regarding the customized text, and the step of dynamically generating the user's literacy data using a first artificial intelligence model that takes the at least one query, the user response to the at least one query, and the user feedback as inputs.

[0019] A user-customized text conversion device according to an embodiment of the present disclosure is disclosed for realizing the aforementioned objectives. The device comprises a processor including at least one core, a memory including program codes executable on the processor, metadata regarding a user, a network unit receiving original text for which the user requests analysis, and a user interface for displaying customized text. The processor is configured to generate at least one query related to the original text or the user, dynamically generate literacy data of the user using a first artificial intelligence model that takes the at least one query and a user response to the at least one query as input, determine a difficulty parameter of the customized text using the literacy data, generate the customized text using a second artificial intelligence model that takes the difficulty parameter as input, and provide the customized text to the user through the user interface. Effects of the invention

[0021] According to the method of operation of a user-customized text conversion system of the technical concept of the present disclosure, the limitations of static evaluation methods can be overcome to provide user-customized text to the user through real-time conversation-based literacy inference.

[0022] According to the method of operation of a user-customized text conversion system of the technical concept of the present disclosure, the user's understanding of the text can be improved by utilizing natural language processing and machine learning technologies to precisely infer the user's literacy level and rewriting (i.e., converting) the text into an optimized form including vocabulary, sentences, and explanation methods.

[0023] According to the method of operation of a user-customized text conversion system of the technical concept of the present disclosure, by providing a complex text conversion algorithm that adjusts sentence structure, vocabulary level, explanation method, etc. while maintaining the core meaning of the original text, the accessibility and usability of text information can be maximized.

[0024] According to the method of operation of a user-customized text conversion system of the technical concept of the present disclosure, through a user feedback loop, it is possible to continuously adapt to the changing literacy of the user and further ensure system adaptability.

[0025] According to the method of operation of a user-customized text conversion system of the technical concept of the present disclosure, it is applicable to various industrial fields such as education, media, public documents, finance, and medical care, and can contribute to bridging the information gap and improving information access for the digitally marginalized. Brief explanation of the drawing

[0027] FIG. 1 is a conceptual diagram of a user-customized text conversion system according to one embodiment of the present disclosure. FIG. 2 is a block diagram of a user-customized text conversion device according to one embodiment of the present disclosure. FIG. 3 is a block diagram of a user-customized text conversion device according to one embodiment of the present disclosure. FIG. 4 is an exemplary diagram illustrating a literacy dynamic reasoning algorithm and a user interface according to one embodiment of the present disclosure. FIG. 5 is an exemplary diagram showing a user interface displaying original test and custom text according to one embodiment of the present disclosure. FIG. 6 is a flowchart illustrating the operation method of a user-customized text conversion device according to one embodiment of the present disclosure. Specific details for implementing the invention

[0028] Specific structural or functional descriptions of embodiments according to the concept of the present invention disclosed herein are provided merely for the purpose of explaining embodiments according to the concept of the present invention, and embodiments according to the concept of the present invention may be implemented in various forms and are not limited to the embodiments described herein.

[0029] Embodiments according to the concept of the present invention may be subject to various modifications and may take various forms; therefore, embodiments are illustrated in the drawings and described in detail in this specification. However, this is not intended to limit the embodiments according to the concept of the present invention to specific disclosed forms, and includes modifications, equivalents, or substitutions that fall within the spirit and scope of the present invention.

[0030] Terms such as "first" or "second" may be used to describe various components, but said components shall not be limited by said terms. For the sole purpose of distinguishing one component from another, for example, without departing from the scope of rights according to the concept of the present invention, the first component may be named the second component, and similarly, the second component may be named the first component.

[0031] When it is stated that one component is "connected" or "connected" to another component, it should be understood that while it may be directly connected or connected to that other component, there may also be other components in between. Conversely, when it is stated that one component is "directly connected" or "directly connected" to another component, it should be understood that there are no other components in between. Expressions describing the relationships between components, such as "between," "exactly between," or "directly adjacent to," should be interpreted in the same way.

[0032] The terms used herein are used merely to describe specific embodiments and are not intended to limit the invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this specification, terms such as “comprising” or “having” are intended to specify the existence of the described features, numbers, steps, actions, components, parts, or combinations thereof, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0033] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art to which the present invention pertains. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in this specification.

[0035] In this specification, the term "processor" may refer to hardware capable of performing functions and operations according to each name described in this specification, computer program code capable of performing specific functions and operations, or an electronic recording medium loaded with computer program code capable of performing specific functions and operations.

[0036] In other words, the term "processor" may refer to a functional and / or structural combination of hardware for carrying out the technical concept of the present invention and / or software for driving said hardware.

[0038] Hereinafter, embodiments will be described in detail with reference to the attached drawings. However, the scope of the patent application is not limited or restricted by these embodiments. Identical reference numerals in each drawing indicate identical components.

[0040] FIG. 1 is a conceptual diagram of a user-customized text conversion system according to one embodiment of the present disclosure.

[0041] Referring to FIG. 1, a user-customized text conversion system (1000) according to one embodiment of the present disclosure includes a user device (100), a user interface providing device (200) (hereinafter, user-customized text conversion device (200)), and / or a literacy status database (20). According to an embodiment, the user-customized text conversion system (1000) may include a plurality of users.

[0042] A user-customized text conversion device (200) according to one embodiment of the present disclosure may receive metadata regarding the user and / or original text for which the user requests analysis from the user through a user device (100).

[0043] For example, metadata received from a user through a user device (100) may include basic information about the user, such as age, occupation, and educational background. Additionally, 'metadata' received from a user through a user device (100) may include information related to the user's occupation, such as work area, degree of multilingual exposure, and / or types of documents created, viewed, or downloaded during a certain period. This is merely an example and may include other information depending on the user's choice or service request, and does not limit the scope of the rights of the present invention. 'Degree of multilingual exposure' may refer to the level of exposure based on the frequency, scope, or duration of encounters with foreign languages ​​other than Korean (e.g., English, Japanese, Chinese, etc.) during daily or professional activities. For example, it may refer to a history of viewing documents, emails, reports, news articles, etc., written in a foreign language; the frequency of interactions such as messages, chats, and meetings with foreign language users; or the time or usage rate of foreign language-based systems, applications, and websites.

[0044] The 'original text' for which the user requests analysis may consist of at least one word, at least one phrase, or at least one sentence.

[0045] A user-customized text conversion device (200) according to one embodiment of the present disclosure can generate original text and / or a query related to the user and can transmit it to a user device (100). The user can respond by inputting an answer to the query provided by the user-customized text conversion device (200) into the user device (100). The user-customized text conversion device (200) can dynamically generate user literacy data using a first artificial intelligence model that takes at least one query and at least one user response to the query as input.

[0046] "Literacy data" refers to information that quantitatively or qualitatively expresses a user's text comprehension ability, and includes data calculated based on at least one of the following factors: accuracy of user responses, response time, words included in user responses, response patterns by question type, and feedback evaluation values. Literacy data may be values ​​analyzed or predicted by one or more artificial intelligence models.

[0047] A user-customized text conversion device (200) according to one embodiment of the present disclosure can determine a difficulty parameter of the customized text using literacy data. 'Customized text' refers to text modified while maintaining the meaning of the original text based on user literacy data, and may be composed in the form of at least one word, at least one phrase, or at least one sentence. The customized text may be text in which the word or sentence structure included in the original text is changed or example sentences are added; however, this is merely an example and may include text in other forms depending on the algorithm, and does not limit the scope of the present invention. 'Difficulty parameter' refers to a value determined based on user literacy data, representing the difficulty of at least one of the word, sentence length, and sentence structure type of the customized text that affects the expression method of the customized text. The difficulty parameter can be utilized to control the linguistic complexity or comprehensibility of the customized text.

[0048] A user-customized text conversion device (200) according to one embodiment of the present disclosure can generate customized text using a second artificial intelligence model that takes a difficulty parameter as input. The generated customized text can be provided to a user through a user interface.

[0049] The user device (100) is an electronic device capable of capturing and / or outputting images or videos, and can be implemented as a laptop computer, mobile phone, smartphone, tablet PC, mobile internet device (MID), PDA (personal digital assistant), EDA (enterprise digital assistant), digital still camera, digital video camera, PMP (portable multimedia player), PND (personal navigation device or portable navigation device), handheld game console, e-book, or smart device. The smart device can be implemented as a smart watch, smart band, or smart ring.

[0050] A literacy status database (20) according to one embodiment of the present disclosure can store a user's literacy data. The user's literacy data can be updated in real time and dynamically.

[0051] According to the present disclosure, personalized text can be provided to a user through real-time conversation-based literacy inference, and the user's understanding of the text can be improved by utilizing natural language processing and machine learning technologies to precisely infer the level of literacy and converting the text into an optimized form including vocabulary, sentences, and explanation methods.

[0053] FIG. 2 is a block diagram of a user-customized text conversion device according to one embodiment of the present disclosure.

[0054] A user-customized text conversion device (200) according to one embodiment of the present disclosure may be a hardware device or part of a hardware device that performs comprehensive processing and computation of data, or it may be a software-based computing environment connected to a communication network. For example, the user-customized text conversion device (200) may be a server that performs intensive data processing functions and is an entity that shares resources, or it may be a client that shares resources through interaction with the server. Additionally, the user-customized text conversion device (200) may be a cloud system that enables multiple servers and clients to interact to comprehensively process data. Since the above description is merely one example regarding the type of user-customized text conversion device (200), the type of user-customized text conversion device (200) may be configured in various ways within a range understandable to those skilled in the art based on the contents of the present disclosure.

[0055] Referring to FIG. 2, a user-customized text conversion device (200) according to one embodiment of the present disclosure may include a processor (210), a memory (220), and / or a network unit (230). However, since FIG. 2 is merely an example, the user-customized text conversion device (200) may include other configurations for implementing a computing environment. Additionally, only some of the disclosed configurations may be included in the user-customized text conversion device (200).

[0056] A processor (210) according to one embodiment of the present disclosure may be understood as a constituent unit comprising hardware and / or software for performing computing operations. For example, the processor (210) may read a computer program and perform data processing for machine learning. The processor (210) may perform user literacy data generation or customized text generation by executing a first artificial intelligence model and / or a second artificial intelligence model stored in memory (220). An artificial neural network (or neural network) model that may be implemented by the processor (210) may include a statistical learning algorithm that mimics biological neurons in machine learning and cognitive science. According to one embodiment, an artificial intelligence model that may be implemented by the processor (210) according to an embodiment of the present disclosure may include a natural language processing model and / or a natural language generation model. An artificial intelligence model according to one embodiment of the present disclosure may be a pre-trained natural language processing model and / or natural language generation model. The processor (210) can process computational processes such as processing input data for machine learning, extracting features for machine learning, and calculating errors based on backpropagation.

[0057] A processor (210) for performing such data processing may include a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), a tensor processing unit (TPU), an application specific integrated circuit (ASIC), or a field programmable gate array (FPGA). Since the above-described type of processor (210) is merely an example, the type of processor (210) may be configured in various ways within a range understandable to those skilled in the art based on the contents of this disclosure.

[0058] A processor (210) according to one embodiment of the present disclosure can control a series of processes for generating customized text using metadata received from a user, original text, user response to a query, etc. Specific details of the operation of the processor (210) are described later in FIG. 3.

[0059] A memory (220) according to one embodiment of the present disclosure may be understood as a configuration unit comprising hardware and / or software for storing and managing data processed by a user-customized text conversion device (200). That is, the memory (220) may store data of any form generated or determined by the processor (210) and data of any form received by the network unit (230). For example, the memory (220) may include at least one type of storage medium among a flash memory type, a hard disk type, a multimedia card micro type, a card type memory, RAM (random access memory), SRAM (static random access memory), ROM (read-only memory), EEPROM (electrically erasable programmable read-only memory), PROM (programmable read-only memory), magnetic memory, a magnetic disk, or an optical disk. Additionally, the memory (220) may include a database system that controls and manages data in a predetermined system. Since the above-described type of memory (220) is merely an example, the type of memory (220) can be configured in various ways within a range understandable to those skilled in the art based on the contents of the present disclosure.

[0060] A network unit (230) according to one embodiment of the present disclosure may be understood as a configuration unit that transmits and receives data through any known form of wired or wireless communication system. For example, the network unit (230) may perform data transmission and reception using wired or wireless communication systems such as a local area network (LAN), wideband code division multiple access (WCDMA), long term evolution (LTE), wireless broadband internet (WiBro), 5th generation mobile communication (5G), ultrawide-band wireless communication, ZigBee, radio frequency (RF) communication, wireless LAN, wireless fidelity (Wi-Fi), near field communication (NFC), or Bluetooth. Since the communication systems described above are merely examples, wired or wireless communication systems for data transmission and reception of the network unit (230) may be applied in various ways other than those described above.

[0061] According to one embodiment, the network unit (230) may receive metadata regarding a user, original text for which the user requests analysis, a user response to a query, and / or user feedback from the user device. The network unit (230) may transmit at least one query and / or custom text to the user device.

[0063] FIG. 3 is a block diagram of a user-customized text conversion device according to one embodiment of the present disclosure. FIG. 4 is an example diagram showing a literacy dynamic inference algorithm and a user interface according to one embodiment of the present disclosure.

[0064] Referring to FIGS. 2 and FIGS. 3, the user-customized text converter (300) of FIG. 3 can be applied to the user-customized text converter (200) of FIG. 2.

[0065] Referring to FIG. 3, a user-customized text conversion device (300) according to one embodiment of the present disclosure may include a data collection module (310), a text analysis module (320), a literacy inference module (330), a difficulty parameter determination module (340), a text conversion module (350), and / or a user interface module (360).

[0066] The data collection module (310) can collect and store metadata that can be used for literacy inference, such as user's personal information, learning history, and service usage records (e.g., age, occupation, educational background, work area, degree of multilingual exposure, or types of documents viewed over a certain period). Referring to FIG. 4, the data collection module (410) can transmit the collected and stored metadata to the text analysis module (420).

[0067] According to an embodiment in which a user-customized text conversion device (400) provides a web-based learning support service, the user inputs user metadata such as name, age, occupation, and preferences (e.g., Hong Gil-dong, 34 years old, PM, likes Squid Game) through a user device, and the original text that the user requests analysis of can be provided in the form of a PDF, URL, copied text, etc. The user-customized text conversion device can generate and deliver a query about the user (e.g., “What is step 1 in a recipe for making spaghetti?”) to the user, and can receive user responses (e.g., preparing ingredients) and response times (e.g., 8 seconds). The user-customized text conversion device can calculate the user’s literacy level using the response content or response speed, and can rewrite the original text that the user requests analysis of to suit the user’s level. It can show the converted customized text to the user and request feedback on whether the customized text is easy to read and suitable for the level. Upon receiving user feedback, the user-customized text conversion device can provide the user-customized text in an optimized form by repeating the process described above.

[0068] Referring to FIG. 3, the text analysis module (320) can analyze and extract key meanings, topics, major concepts, sentence structures, etc. from the original text received from the user. Referring to FIG. 4, the original text (42) received from the user can be displayed on the user interface module (460). The topic of the original text may be 'Article 1 of the Constitution of the Republic of Korea'. The text analysis module (420) can transmit the analysis data of the original text to the literacy inference module (430).

[0069] User metadata can be provided by the user selecting from the items in the view in response to a query provided by the user-customized text conversion device (300) as shown in [Table 1] below. 'Information to be identified' refers to the information that the user-customized text conversion device (300) intends to identify by receiving the user's response to the query.

[0070]

[0071] Referring again to FIG. 3, the literacy inference module (330) can dynamically generate the user's literacy data by executing a first artificial intelligence model based on the user's query and user response. The first artificial intelligence model may include a natural language processing model and / or a machine learning model. Referring to FIG. 4, the literacy inference module (430) can transmit the generated literacy data to the literacy status DB (40). The literacy status DB (40) can store the user's literacy data.

[0072] In the user interface module (460), questions and responses (44) to the user can be displayed in a conversational format. An example of questions and responses to the user for generating literacy data is shown in [Table 2] below.

[0073]

[0074] Referring again to FIG. 3, the difficulty parameter determination module (340) can calculate difficulty parameters such as vocabulary level, sentence length, and sentence structure type for generating customized text based on literacy data. Referring to FIG. 4, the difficulty parameter determination module (440) can transmit the difficulty parameters to the text conversion module (450).

[0075] Referring again to FIG. 3, the text conversion module (350) can execute a second artificial intelligence model that takes as input the analysis data of the original text analyzed by the text analysis module (320) and the difficulty parameter calculated by the difficulty parameter determination module (340), and generate customized text that can be provided to the user. The second artificial intelligence model may include a natural language generation (NLG) model.

[0076] The user interface module (360) can receive original text from a user device, provide a question / answer-based interface, output generated custom text to the user, and collect user feedback. The user feedback may include user opinions on understanding to evaluate how much the user understands the custom text.

[0078] FIG. 5 is an exemplary diagram showing a user interface displaying original test and custom text according to one embodiment of the present disclosure.

[0079] Referring to FIG. 5, a user interface module (560) according to one embodiment of the present disclosure may display the original text (50) before conversion and / or the customized text (52) after conversion. According to an embodiment, the user-customized text conversion device may provide a plurality of customized texts. The user-customized text conversion device may provide a customized text corresponding to a 'low' level and a customized text corresponding to a 'medium' level, in accordance with the diagnosed literacy level of the user.

[0080] According to the user-customized text conversion device of the present disclosure, the user's current state of understanding can be captured and analyzed in real time through natural conversation induced during the process of reading the source text. In addition, the text can be reconstructed by optimizing vocabulary, sentence structure, and explanation methods in real time to match the inferred dynamic literacy level of each individual user.

[0082] FIG. 6 is a flowchart illustrating the operation method of a user-customized text conversion device according to one embodiment of the present disclosure.

[0083] A user-customized text conversion device according to one embodiment of the present disclosure may collect metadata regarding a user and original text for which the user requests analysis (S600). The metadata may include information regarding at least one of the user's age, occupation, educational background, work area, degree of multilingual exposure, or types of documents created, viewed, or downloaded during a certain period.

[0084] A user-customized text conversion device according to one embodiment of the present disclosure can analyze the subject and sentence structure of the original text.

[0085] A user-customized text conversion device according to one embodiment of the present disclosure can generate at least one query related to the original text or the user (S602).

[0086] A user-customized text conversion device according to one embodiment of the present disclosure can dynamically generate user literacy data using a first artificial intelligence model that takes at least one query and a user response to at least one query as input (S604). The first artificial intelligence model may include a natural language processing model and a machine learning model. The literacy data may be data calculated based on at least one of the accuracy of the user response, the response time, words included in the user response, and the response pattern by type of at least one query.

[0087] A user-customized text conversion device according to one embodiment of the present disclosure can determine a difficulty parameter of the customized text using literacy data (S606). The difficulty parameter may be a value representing the difficulty of at least one of the words, sentence length, and sentence structure type of the customized text.

[0088] A user-customized text conversion device according to one embodiment of the present disclosure can generate customized text using a second artificial intelligence model that takes a difficulty parameter as input (S608). The second artificial intelligence model may include a natural language generation model. The second artificial intelligence model may take the topic and difficulty parameter of the original text as input. The customized text may be text in which the words or sentence structures included in the original text are modified, or example sentences are added.

[0089] A user-customized text conversion device according to one embodiment of the present disclosure can provide customized text to a user through a user interface (S610).

[0090] A user-customized text conversion device according to one embodiment of the present disclosure may receive a user response to at least one query or user feedback regarding customized text. A user-customized text conversion device according to one embodiment of the present disclosure may dynamically generate user literacy data by using a first artificial intelligence model that takes at least one query, a user response to at least one query, and user feedback as input.

[0092] As described above, exemplary embodiments have been disclosed in the drawings and specification. Although specific terms have been used to describe the embodiments in this specification, they are used only for the purpose of explaining the technical concept of this disclosure and are not intended to limit the meaning or the scope of this disclosure as defined in the claims. Therefore, those skilled in the art will understand that various modifications and equivalent alternative embodiments are possible therefrom. Accordingly, the true technical scope of protection of this disclosure should be determined by the technical concept of the appended claims.

Claims

Claim 1 A step of collecting metadata regarding a user and the original text for which the user requests analysis; a step of analyzing the subject and sentence structure of the original text; a step of generating at least one query related to the original text or the user; a step of dynamically generating the user's literacy data using a first artificial intelligence model that takes the at least one query and the user's response to the at least one query as input; a step of determining a difficulty parameter of a customized text using the literacy data; and a step of generating the customized text using a second artificial intelligence model that takes the original text and the difficulty parameter as input. A method of operation of a user-customized text conversion device, comprising the step of providing the customized text to the user through a user interface; wherein the customized text is text in which words or sentence structures included in the original text are changed or example sentences are added while maintaining the meaning and subject of the original text; wherein the metadata includes information on at least one of the user's age, occupation, education level, work area, degree of multilingual exposure, or type of document written, viewed, or downloaded during a certain period; wherein the literacy data is quantitative data calculated based on at least one of the accuracy of the user response, response time, words included in the user response, and response patterns by type of at least one query; and wherein the difficulty parameter is a value representing the difficulty of at least one of the words, sentence length, and sentence structure type of the customized text. Claim 2 delete Claim 3 A method of operation of a user-customized text conversion device according to claim 1, wherein the first artificial intelligence model includes a natural language processing model and a machine learning model. Claim 4 delete Claim 5 delete Claim 6 A method of operation of a user-customized text conversion device according to claim 1, wherein the second artificial intelligence model includes a natural language generation model, and the second artificial intelligence model takes the subject and difficulty parameter of the original text as input. Claim 7 delete Claim 8 A method of operation of a user-customized text conversion device according to claim 1, further comprising: receiving the user response to the at least one query or user feedback to the customized text; and dynamically generating the user's literacy data using a first artificial intelligence model that takes the at least one query, the user response to the at least one query, and the user feedback as inputs. Claim 9 A user-customized text conversion device comprising: a processor including at least one core; a memory including program code executable on said processor; metadata regarding a user and a network unit receiving original text for which said user requests analysis; The system includes a user interface that displays customized text; wherein the processor analyzes the subject and sentence structure of the original text, generates at least one query related to the original text or the user, and dynamically generates the user's literacy data using a first artificial intelligence model that takes the at least one query and the user's response to the at least one query as input, determines a difficulty parameter of the customized text using the literacy data, generates the customized text using a second artificial intelligence model that takes the original text and the difficulty parameter as input, and is configured to provide the customized text to the user through the user interface; wherein the customized text is text in which words or sentence structures included in the original text are modified or example sentences are added while maintaining the meaning and subject of the original text, and the metadata includes information on at least one of the user's age, occupation, education level, work area, degree of multilingual exposure, or types of documents written, viewed, or downloaded during a certain period, and the literacy data is based on at least one of the accuracy of the user response, response time, words included in the user response, and response patterns by type of the at least one query. A device comprising quantitative data that is produced, wherein the difficulty parameter is a value representing the difficulty of at least one of the word, sentence length, and sentence structure type of the custom text.

Images