KR102586799B1 - Method, device and system for automatically processing creation of web book based on web novel using artificial intelligence model - Google Patents

Abstract

According to an embodiment, a method for automatically processing the creation of a web book based on a web novel using an artificial intelligence (AI) model comprises the steps of: obtaining text of a web novel from a user terminal; inputting the text of the web novel into a pre-trained first AI model, and obtaining a text set in which the text of the web novel is divided into dialogue and text, as an output of the input of the first AI model; inputting a fingerprint text distinguished as a fingerprint from the text set into a pre-trained second AI model, and obtaining a first image rendered with fingerprint content using the fingerprint text, as an output for the input of the second AI model; generating a web book based on dialogue text separated into dialogues in the text set and the first image; and uploading and registering the web book on a web book platform. Therefore, the present invention can automatically create and provide web book content.

Description

Web novel-based web book creation automated processing method, device, and system using an artificial intelligence model {METHOD, DEVICE AND SYSTEM FOR AUTOMATICALLY PROCESSING CREATION OF WEB BOOK BASED ON WEB NOVEL USING ARTIFICIAL INTELLIGENCE MODEL}

The examples below relate to technology for automatically processing the creation of web books based on web novels using artificial intelligence models.

One-Source Multi-Use, which maximizes added value by using a single original content and transforming it into various genres such as movies, games, records, cartoons, animations, character products, toys, and publications, etc. It is becoming the basic strategy.

In particular, by using web novels or webtoons as original content, the added value of the content can be maximized by transforming and releasing it into content of various genres.

Accordingly, the number of works on web novels and webtoons is rapidly increasing, but web novels consist only of text, which limits the freedom of use of the content by consumers who are accustomed to video. Webtoons consist of images divided into multiple cuts, so cartoons are There are limitations to producing them in a short period of time.

Therefore, the demand for content in the middle area between web novels and webtoons is increasing, and there is a need to implement technology that can automatically generate the content and increase the efficiency of content creation work.

Korean Patent Publication No. 10-2019-0027645 Korean Patent Publication No. 10-2014-0097668 Korean Patent No. 10-1499052 Korean Patent No. 10-1087732

According to one embodiment, the purpose is to provide a method, device, and system for automatically processing the creation of a web book based on a web novel using an artificial intelligence model.

The object of the present invention is not limited to the object mentioned above, and other objects not mentioned can be clearly understood from the description below.

According to one embodiment, an automated processing method for creating a web novel-based web book using an artificial intelligence model, performed by a device, includes the steps of obtaining text of a web novel from a user terminal; Inputting the text of the web novel into a pre-trained first artificial intelligence model, and obtaining, as an output of the input of the first artificial intelligence model, a text set in which the text of the web novel is divided into dialogue and fingerprints; The fingerprint text classified into fingerprints in the text set is input to a pre-learned second artificial intelligence model, and as an output of the input of the second artificial intelligence model, the first image is rendered by using the fingerprint text to render the fingerprint contents. Obtaining a; generating a webbook based on the dialogue text divided into dialogues in the text set and the first image; An automated processing method for creating a web novel-based web book using an artificial intelligence model is provided, including the step of uploading and registering the web book on a web book platform.

The automated processing method for creating a web novel-based web book using the artificial intelligence model includes, after obtaining the text set, generating first audio by converting the dialogue content into audio using the dialogue text; When the first image is acquired, generating an audiobook based on the first audio and the first image; And it may further include uploading and registering the audiobook on an audiobook platform.

The automated processing method for creating a web novel-based web book using the artificial intelligence model includes, after the step of obtaining the text set, translating the dialogue text and the fingerprint text into multiple languages to generate translated dialogue text and translated fingerprint text. step; generating second audio by converting the dialogue content into audio using the translated dialogue text; and generating a webbook container including the dialogue text, the fingerprint text, the first image, the translated dialogue text, the translated fingerprint text, the first audio, and the second audio. .

According to one embodiment, the text of the web novel is divided into dialogue and fingerprints, an image rendering the contents of the fingerprint is obtained, and a web book is created based on the dialogue and image, thereby creating a corresponding web book in the intermediate area between the web novel and the webtoon. It has the effect of automatically generating and providing content.

Meanwhile, the effects according to the embodiments are not limited to those mentioned above, and other effects not mentioned can be clearly understood by those skilled in the art from the description below.

1 is a diagram schematically showing the configuration of a system according to an embodiment.
Figure 2 is a diagram illustrating the configuration of a pipeline tool for the process of automating the creation of web books and audio books based on web novels using an artificial intelligence model according to an embodiment.
Figure 3 is a flow chart to explain the process of creating and registering a web book based on a web novel according to an embodiment.
Figure 4 is a flow chart to explain the process of creating and registering an audiobook based on a web novel according to an embodiment.
Figure 5 is a flowchart explaining the process of creating a webbook container according to an embodiment.
Figure 6 is a flowchart for explaining the process of distinguishing between lines and passages in a text according to an embodiment.
Figure 7 is a flowchart explaining the process of providing an artificial intelligence model recommendation platform according to an embodiment.
Figure 8 is an exemplary diagram of the configuration of a device according to an embodiment.

Hereinafter, embodiments will be described in detail with reference to the attached drawings. However, various changes can be made to the embodiments, so the scope of the patent application is not limited or limited by these embodiments. It should be understood that all changes, equivalents, or substitutes for the embodiments are included in the scope of rights.

Specific structural or functional descriptions of the embodiments are disclosed for illustrative purposes only and may be modified and implemented in various forms. Accordingly, the embodiments are not limited to the specific disclosed form, and the scope of the present specification includes changes, equivalents, or substitutes included in the technical spirit.

Terms such as first or second may be used to describe various components, but these terms should be interpreted only for the purpose of distinguishing one component from another component. For example, a first component may be named a second component, and similarly, the second component may also be named a first component.

When a component is referred to as being “connected” to another component, it should be understood that it may be directly connected or connected to the other component, but that other components may exist in between.

The terms used in the examples are for descriptive purposes only and should not be construed as limiting. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this specification, terms such as “comprise” or “have” are intended to designate the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, but are not intended to indicate the presence of one or more other features. It should be understood that this does not exclude in advance the possibility of the existence or addition of elements, numbers, steps, operations, components, parts, or combinations thereof.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by a person of ordinary skill in the technical field to which the embodiments belong. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related technology, and unless explicitly defined in the present application, should not be interpreted in an ideal or excessively formal sense. No.

In addition, when describing with reference to the accompanying drawings, identical components will be assigned the same reference numerals regardless of the reference numerals, and overlapping descriptions thereof will be omitted. In describing the embodiments, if it is determined that detailed descriptions of related known technologies may unnecessarily obscure the gist of the embodiments, the detailed descriptions are omitted.

Embodiments may be implemented in various types of products such as personal computers, laptop computers, tablet computers, smart phones, televisions, smart home appliances, intelligent vehicles, kiosks, and wearable devices.

In an embodiment, an artificial intelligence (AI) system is a computer system that implements human-level intelligence, and unlike existing rule-based smart systems, it is a system in which machines learn and make decisions on their own. As artificial intelligence systems are used, recognition rates improve and sellers' tastes can be more accurately understood, and existing rule-based smart systems are gradually being replaced by deep learning-based artificial intelligence systems.

Artificial intelligence technology consists of machine learning and element technologies using machine learning. Machine learning is an algorithmic technology that classifies/learns the characteristics of input data on its own, and elemental technology is a technology that mimics the functions of the human brain such as cognition and judgment by utilizing machine learning algorithms such as deep learning, including linguistic understanding and visual It consists of technical areas such as understanding, reasoning/prediction, knowledge expression, and motion control.

The various fields where artificial intelligence technology is applied are as follows. Linguistic understanding is a technology that recognizes and applies/processes human language/characters and includes natural language processing, machine translation, conversation systems, question and answer, and voice recognition/synthesis. Visual understanding is a technology that recognizes and processes objects like human vision, and includes object recognition, object tracking, image search, person recognition, scene understanding, spatial understanding, and image improvement. Inferential prediction is a technology that judges information to make logical inferences and predictions, and includes knowledge/probability-based reasoning, optimization prediction, preference-based planning, and recommendations. Knowledge expression is a technology that automatically processes human experience information into knowledge data, and includes knowledge construction (data creation/classification) and knowledge management (data utilization). Motion control is a technology that controls the autonomous driving of vehicles and the movement of robots, and includes motion control (navigation, collision, driving), operation control (behavior control), etc.

Generally, in order to apply machine learning algorithms to real life, learning is performed using a trial and error method due to the nature of the basic methodology of machine learning. In particular, deep learning requires hundreds of thousands of iterations. It is impossible to execute this in an actual physical external environment, so instead, the actual physical external environment is virtually implemented on a computer and learning is performed through simulation.

1 is a diagram schematically showing the configuration of a system according to an embodiment.

Referring to FIG. 1, a system according to one embodiment may include a user terminal 10 and a device 20.

First, the user terminal 10 and the device 20 can be connected through a communication network, and the communication network is configured regardless of the communication mode, such as wired or wireless, so that communication between servers and between servers and terminals is performed. It can be implemented in various forms.

The user terminal 10 may be implemented as a computing device with a communication function, and may be implemented as, for example, a mobile phone, a desktop PC, a laptop PC, a tablet PC, a smartphone, etc., but is not limited thereto, and is not limited to external devices. It can also be implemented as various types of communication devices that can be connected to a server.

The user terminal 10 may be configured to perform all or part of the calculation function, storage/reference function, input/output function, and control function of a typical computer. The user terminal 10 may be configured to communicate with the device 20 wired or wirelessly.

The user terminal 10 is connected to a web page operated by a person or organization providing services using the device 20, or an application developed and distributed by a person or organization providing services using the device 20. Can be installed. The user terminal 10 may be linked to the device 20 through a web page or application.

The device 20 may be an own server owned by a person or organization that provides services using the device 20, a cloud server, or a p2p (peer-to-peer) collection of distributed nodes. It may be possible. The device 20 may be configured to perform all or part of the calculation function, storage/reference function, input/output function, and control function of a typical computer. The device 20 may be equipped with at least one artificial intelligence model that performs an inference function.

The device 20 may be configured to communicate wired or wirelessly with the user terminal 10, control the operation of the user terminal 10, and control which information to display on the screen of the user terminal 10. .

The device 20 can be implemented as a server that creates and automatically processes webbooks and audiobooks based on web novels, and can operate and manage a webbook-only platform and an audiobook-only platform, respectively.

According to one embodiment, a webbook is content that falls between a web novel and a webtoon, and can be created by combining images composed of illustrations and text, and an audiobook is produced so that the book can be listened to with the ears instead of read with the eyes. As one piece of content, text can be converted into audio and created.

The device 20 can upload and register a webbook to a webbook-only platform, and upload and register an audiobook to an audio-only platform. Through this, platform users can receive webbooks through the webbook-only platform, You can receive audiobooks through an audio-only platform.

Meanwhile, for convenience of explanation, only the user terminal 10 is shown in FIG. 1, but the number of terminals may vary depending on the embodiment. As long as the processing capacity of the device 20 allows, the number of terminals is not particularly limited.

According to one embodiment, the device 20 can automatically process the creation of web books and audio books based on web novels using an artificial intelligence model.

In the present invention, artificial intelligence (AI) refers to technology that imitates human learning ability, reasoning ability, perception ability, etc. and implements this with a computer, and includes concepts such as machine learning and symbolic logic. may include. Machine Learning (ML) is an algorithmic technology that classifies or learns the characteristics of input data on its own. Artificial intelligence technology is a machine learning algorithm that analyzes input data, learns the results of the analysis, and makes judgments or predictions based on the results of the learning. Additionally, technologies that mimic the functions of the human brain, such as cognition and judgment, using machine learning algorithms can also be understood as the category of artificial intelligence. For example, technical fields such as verbal understanding, visual understanding, reasoning/prediction, knowledge representation, and motion control may be included.

Machine learning can refer to the process of training a neural network model using experience processing data. Machine learning can mean that computer software improves its own data processing capabilities. A neural network model is built by modeling the correlation between data, and the correlation can be expressed by a plurality of parameters. A neural network model extracts and analyzes features from given data to derive correlations between data. Repeating this process to optimize the parameters of the neural network model can be called machine learning. For example, a neural network model can learn the mapping (correlation) between input and output for data given as input-output pairs. Alternatively, a neural network model may learn the relationships by deriving regularities between given data even when only input data is given.

An artificial intelligence learning model or neural network model may be designed to implement the human brain structure on a computer, and may include a plurality of network nodes with weights that simulate neurons of a human neural network. A plurality of network nodes may have a connection relationship with each other by simulating the synaptic activity of neurons in which neurons exchange signals through synapses. In an artificial intelligence learning model, multiple network nodes are located in layers of different depths and can exchange data according to convolutional connection relationships. The artificial intelligence learning model may be, for example, an artificial neural network model (Artificial Neural Network), a convolution neural network (CNN) model, etc. As an example, an artificial intelligence learning model may be machine-learned according to methods such as supervised learning, unsupervised learning, and reinforcement learning. Machine learning algorithms for performing machine learning include Decision Tree, Bayesian Network, Support Vector Machine, Artificial Neural Network, and Ada-boost. , Perceptron, Genetic Programming, Clustering, etc. can be used.

Among them, CNN is a type of multilayer perceptrons designed to use minimal preprocessing. CNN consists of one or several convolution layers and general artificial neural network layers on top of them, and additionally utilizes weights and pooling layers. Thanks to this structure, CNN can fully utilize input data with a two-dimensional structure. Compared to other deep learning structures, CNN shows good performance in both video and audio fields. CNNs can also be trained via standard back propagation. CNNs have the advantage of being easier to train and using fewer parameters than other feedforward artificial neural network techniques.

Convolutional networks are neural networks that contain sets of nodes with bound parameters. The increasing size of available training data and the availability of computational power, combined with algorithmic advances such as piecewise linear unit and dropout training, have led to significant improvements in many computer vision tasks. For extremely large data sets, such as those available for many tasks today, overfitting is not critical, and increasing the size of the network improves test accuracy. Optimal use of computing resources becomes a limiting factor. For this purpose, distributed, scalable implementations of deep neural networks can be used.

Figure 2 is a diagram illustrating the configuration of a pipeline tool for the process of automating the creation of web books and audio books based on web novels using an artificial intelligence model according to an embodiment.

Each step shown in FIG. 2 can be performed by device 20.

Referring to Figure 2, first, step 110 is the Input Text step, where the text of a web novel can be input. At this time, the text of the web novel can be input through the user terminal 10.

Step 120 is the Input Image step, where an image file with text written on it can be input. At this time, the image file can be input through the user terminal 10.

Step 130 is the Image To Text step, where the image entered in step 120 can be converted to text. At this time, text can be created by analyzing the text in the image through artificial intelligence. The artificial intelligence used in step 130 may be trained to use images as input data and text as output data, and to generate and output text matching the images through analysis of the input images.

Step 140 is the GTP (Generative Pre-Training) step, which receives the text input at step 110 and the converted text at step 120 and can distinguish between fingerprints and dialogue. At this time, artificial intelligence can be used to separate fingerprints and dialogue within the text. The artificial intelligence used in step 140 can be composed of two model sets: a dialogue artificial intelligence model learned based on the original text and fingerprint removal data, and a fingerprint artificial intelligence model learned based on the original text and dialogue removal data. It can be configured.

In other words, the dialogue artificial intelligence model uses text as input data and dialogue as output data, and is trained to select and output dialogue within the text through analysis of the input text, and the fingerprint artificial intelligence model uses text as input data. With the fingerprint as the output data, it is learned to select and output the fingerprint within the text through analysis of the input text.

Step 150 is the GPT Result step, and through step 140, a text set divided into dialogue and fingerprint can be obtained. In other words, if fingerprints and lines are separated within a text using GPT, a set of texts divided into lines and fingerprints can be created by combining the text separated by lines and the text separated by fingerprints.

Step 160 is the Text To Image step, where text separated by fingerprints can be converted to an image. At this time, images can be created by analyzing text through artificial intelligence. The artificial intelligence used in step 160 may be trained to generate and output a rendered image through analysis of the input text, using text as input data and an image as output data.

Step 170 is the Text To i18n-Text step, and a text set obtained by translating the text set obtained through step 150 into multiple languages can be created. At this time, it is possible to create a set of translated texts by translating the dialogue and fingerprint text through artificial intelligence. The artificial intelligence used in step 170 may be trained to use text as input data and translated text as output data, and to generate and output translated text in multiple languages through analysis of the input text.

Step 180 is the i18n-Text To i18n-Audio step, and the text set translated into multiple languages created through step 170 can be converted into audio to create an audio set converted into multiple languages. At this time, an audio set can be created by converting a text set translated into multiple languages into audio through artificial intelligence. The artificial intelligence used in step 180 uses text converted into multiple languages as input data and a set of audio converted into multiple languages as output data, and generates a set of audio converted into multiple languages through analysis of the text translated into multiple languages. It may be in a state where it has been learned to output.

Step 190 is the WebBook Container step, which can create a webbook container containing the results generated through steps 150, 160, 170, and 180. Here, the webbook container may be composed of dialogue, fingerprints, images, text sets translated into multiple languages, audio sets converted into multiple languages, etc.

Based on the webbook container, webbooks and audiobooks can be created, and a webbook can be composed of a set of multiple blocks with an order.

Step 200 is the Platform Upload step. When a webbook is created based on a webbook container, the webbook can be uploaded and registered on a dedicated webbook platform.

Step 210 is the AudioBook Upload step. When an audiobook is created based on a webbook container, the audiobook can be uploaded and registered on an audiobook-specific platform.

Figure 3 is a flow chart to explain the process of creating and registering a web book based on a web novel according to an embodiment.

Referring to FIG. 3, first, in step S301, the device 20 may obtain the text of the web novel from the user terminal 10.

That is, when the user selects a web novel that he or she wants to create as a web book through the user terminal 10, the user terminal 10 can transmit the text of the selected web novel to the device 20, and the device 20 can transmit the text of the selected web novel to the device 20. You can obtain the text of the web novel from (10).

In step S302, the device 20 may input the text of the web novel into the first artificial intelligence model. Here, the first artificial intelligence model is the artificial intelligence used in step 140 and may be pre-trained to distinguish between lines and fingerprints within the text.

In step S303, the device 20 may obtain a text set in which the text of the web novel is divided into dialogue and fingerprints as an output for the input of the first artificial intelligence model. Here, the text set may be composed of dialogue text divided into lines and fingerprint text divided into fingerprints within the text of the web novel. A detailed explanation of the process by which the first artificial intelligence model distinguishes between dialogue and fingerprints within the text will be described later with reference to FIG. 6.

For example, the first artificial intelligence model may be composed of a dialogue artificial intelligence model and a fingerprint artificial intelligence model, and when the text of a web novel is input, the dialogue artificial intelligence model selects the dialogue within the text of the web novel and creates the dialogue text. can be output, and the fingerprint artificial intelligence model can select fingerprints within the text of a web novel and output fingerprint text.

The first artificial intelligence model may generate a text set by combining the dialogue text and the fingerprint text and output the generated text set. Through this, the device 20 may output the text as an output for the input of the first artificial intelligence model. A set can be obtained.

The first artificial intelligence model can distinguish between dialogue and fingerprints through various methods. Text mining technology is used to extract specific patterns for dialogue and fingerprints, and based on this, dialogue and fingerprints can be distinguished.

For example, dialogue is a part of a character's speech that includes the character's name or has a special pattern that marks the dialogue, such as quotation marks or parentheses, so the dialogue can be distinguished by learning these patterns.

In addition, the fingerprint is a part that contains additional explanations other than the dialogue, and explains the character's behavior, background explanation, emotions, etc., so the fingerprint can be distinguished by learning keywords representing these.

According to one embodiment, the first artificial intelligence can be learned by fine tuning an artificial intelligence model that understands the meaning of language into an artificial intelligence model that distinguishes between lines and fingerprints. At this time, the learning device may be the same device as the device 20 or may be a separate device.

Specifically, the learning device can select a pre-trained model to use to implement the language model. For example, models such as BERT, GPT, and RoBERTa can be used.

Afterwards, the learning device can collect data corresponding to dialogue and fingerprints and preprocess it. In the preprocessing stage, you can go through processes such as removing special characters or unnecessary words or unifying uppercase and lowercase letters.

Afterwards, the learning device can fine-tune the model that distinguishes between dialogue and fingerprints using the weights of the pre-trained language model. There can be various ways to distinguish between lines and fingerprints. For example, lines can be distinguished using features such as speaker name, line marking, and text mining.

Afterwards, the learning device can evaluate the performance of the learned model. To this end, you can use test data to examine indicators such as model accuracy, precision, and recall.

Afterwards, the learning device can apply the learned model to actual applications. For example, a function to distinguish between dialogue and text in a movie script can be implemented.

In the same way as above, you can fine-tune the artificial intelligence model that distinguishes between dialogue and fingerprints using a pre-trained language model. Through this, various applications can be possible in the field of natural language processing, such as conversation.

In step S304, the device 20 may input the fingerprint text divided into fingerprints from the text set into the second artificial intelligence model. Here, the second artificial intelligence model is the artificial intelligence used in step 160 and may be pre-trained to generate a rendered image through analysis of text.

In step S305, the device 20 may obtain a first image in which fingerprint content is rendered using fingerprint text as an output in response to the input of the second artificial intelligence model.

The second artificial intelligence model is an artificial intelligence model that analyzes text and creates an image. It is a model that receives text as input and outputs an image that expresses the text content in a visual form.

The second artificial intelligence model can be mainly used in the field of natural language processing and can extract important information from text content and create an image appropriate for it. For example, if you enter the sentence “cat resting under a tree,” it can be analyzed to generate an image of a tree and a cat.

The second artificial intelligence model is one of the generative models, a type of deep learning model. GAN (Generative Adversarial Networks) can be used as a representative example, and it uses two neural networks, a generator and a discriminator, to generate images. You can create and learn a discriminator neural network that distinguishes generated images from real images. In this process, the generator neural network can generate various images to train the discriminator neural network.

In this way, the second artificial intelligence model can be used to convert text into images for effective visual expression.

According to one embodiment, the second artificial intelligence model can be learned by fine tuning an image processing model that generates text into images into an image processing model that generates images necessary for the movie making process. At this time, the learning device may be the same device as the device 20 or may be a separate device.

Specifically, the learning device can prepare a pre-trained text image generation model using a deep learning model such as GAN (Generative Adversarial Networks) as a basic model for image generation. The text image generation model has the basic ability to convert text into images.

Afterwards, the learning device can collect the image dataset needed for filmmaking. This dataset may include images of movie scenes and characters.

Afterwards, the learning device can preprocess the collected dataset to convert the size and format of the image into a format that can be used by the text image creation model.

Afterwards, the learning device can perform fine-tuning on the second artificial intelligence model using the text image generation model and the preprocessed movie dataset. In this process, the second artificial intelligence model can generate images necessary for the filmmaking process based on the text image generation model. At this time, fine-tuning can be performed to adjust the second artificial intelligence model so that the generated image is created to suit the purpose of filmmaking.

Afterwards, the learning device may evaluate the second artificial intelligence model. At this time, it is possible to check whether the image generated through the second artificial intelligence model is at a level that can be used in the filmmaking process and modify the second artificial intelligence model as necessary.

Afterwards, the learning device can apply the second artificial intelligence model in the movie making process. Through this, you can convert text into images and create the images needed to make a movie.

Through this method, the model that generates text into images can be fine-tuned into a model that generates images needed in the filmmaking process. Through this, the second artificial intelligence model can more effectively generate the images needed in the filmmaking process. You can.

In step S306, the device 20 may create a webbook based on the first image and the dialogue text divided into dialogues in the text set.

That is, the device 20 can distinguish dialogue and fingerprints from the text of a web novel, create an image related to the fingerprint, and then combine the dialogue and images to create a web book. At this time, the dialogue can be inserted into the webbook in text format, and the images can be inserted into the webbook in illustration format.

In step S307, the device 20 may upload and register a webbook on the webbook platform.

That is, when a webbook is created, the device 20 can upload the webbook to a webbook-specific platform in step 200 so that platform users can receive the newly created webbook.

Figure 4 is a flow chart to explain the process of creating and registering an audiobook based on a web novel according to an embodiment.

Referring to FIG. 4, first, in step S401, when the device 20 obtains a text set in which the text of the web novel is divided into dialogue and fingerprints, the dialogue content is converted into audio using the dialogue text divided into dialogue in the text set. The first audio converted to can be generated. At this time, the device 20 can convert the dialogue content into audio using an artificial intelligence model, and the artificial intelligence model used here is the artificial intelligence used in step 180 and is pre-trained to convert text into audio. You can.

In step S402, when the first image is acquired, the device 20 may generate an audiobook based on the first audio and the first image.

That is, the device 20 can distinguish dialogue and fingerprints from the text of a web novel, convert the dialogue into audio, generate an image related to the fingerprint, and then combine the audio and images to create an audiobook. At this time, dialogue can be inserted into the audiobook in audio format, and images can be inserted into the audiobook in illustration format.

In step S403, the device 20 may upload and register the audiobook on the audiobook platform.

That is, when an audiobook is created, the device 20 uploads the audiobook to an audiobook-only platform, as in step 210, so that platform users can receive the newly created audiobook.

Figure 5 is a flowchart explaining the process of creating a webbook container according to an embodiment.

Referring to FIG. 5, first, in step S501, when a text set that divides the text of the web novel into dialogue and fingerprints is obtained, the device 20 translates the dialogue text and fingerprint text into multiple languages to produce the translated dialogue text and translation. can generate fingerprint text. At this time, the device 20 may utilize an artificial intelligence model to translate the dialogue text to generate a translated dialogue text and translate the fingerprint text to generate a translated fingerprint text. The artificial intelligence model used here is used in step 180. The artificial intelligence used may be pre-trained to translate text into multiple languages.

In step S502, the device 20 may generate second audio by converting the dialogue content into audio using the translated dialogue text. At this time, the device 20 can convert the dialogue content into audio using an artificial intelligence model, and the artificial intelligence model used here is the artificial intelligence used in step 180 and is pre-trained to convert text into audio. You can.

In step S503, the device 20 may create a webbook container including dialogue text, fingerprint text, first image, translated dialogue text, translated fingerprint text, first audio, and second audio.

That is, the device 20 may create a webbook container including dialogue, fingerprints, images, translated dialogue, translated fingerprints, audio, translated audio, etc., as in step 190.

When the webbook container is created, the device 20 can create a webbook and an audiobook based on the webbook container, and when the webbook is created, the webbook can be uploaded and registered on the webbook platform as in step 200, and audio Once the book is created, the audiobook can be uploaded and registered on the audiobook platform, as in step 210.

Figure 6 is a flowchart for explaining the process of distinguishing between lines and passages in a text according to an embodiment.

Referring to Figure 6, first, in step S601, when the text of the web novel is input, the first artificial intelligence model can extract the first sentence, which is one of the texts of the web novel.

In step S602, the first artificial intelligence model may recognize the first keyword in the first sentence.

When multiple keywords are recognized in the first sentence, the first artificial intelligence model can calculate the importance of each keyword and recognize the keyword with the highest importance as the first keyword.

Specifically, the first artificial intelligence model performs morphological analysis, syntactic analysis, semantic analysis, and pragmatic analysis on the first sentence and performs keywords in the first sentence. can be recognized, and by checking how often the recognized keyword is used in web novels, the importance of the keyword can be calculated according to the number of uses. To this end, the database connected to the first artificial intelligence model stores information on the number of uses for each keyword in the web novel, and the first artificial intelligence model can check the number of uses for each keyword by searching the database.

In step S603, the first artificial intelligence model may set the probability that the first keyword will be used as a dialogue as a first ratio, and the probability that the first keyword will be used as a fingerprint may be set as a second ratio.

Specifically, the database connected to the first artificial intelligence model stores information on the number of times each keyword is used as a dialogue, and information on the number of times each keyword is used as a fingerprint is stored, and the first artificial intelligence model stores Search the database to check the number of times the first keyword is used as a line and the number of times the first keyword is used as a fingerprint, set the first ratio in proportion to the number of times the first keyword is used as a line, and set the first ratio in proportion to the number of times the first keyword is used as a line. 1 The second ratio can be set in proportion to the number of times the keyword is used as a fingerprint.

For example, if the standard number of times is set to 100, and the first artificial intelligence model confirms that the number of times the first keyword has been used as a line is 30, it uses the number of times the first keyword has been used as a line as the standard number. As a divided value, the first ratio can be set to 30%, and if the number of times the first keyword is used as a fingerprint is confirmed to be 70, the number of times the first keyword is used as a fingerprint is divided by the standard number, 2 The ratio can be set to 70%. At this time, the reference number of times may be set differently depending on the embodiment.

In step S604, the first artificial intelligence model may calculate the difference between the first ratio and the second ratio as the first difference ratio. At this time, the first artificial intelligence model may compare the first ratio and the second ratio and calculate the first difference ratio by subtracting the smaller value from the larger value as a result of the comparison.

In step S605, the first artificial intelligence model may check whether the first difference ratio is higher than the reference ratio. At this time, the reference ratio may be set differently depending on the embodiment.

If the first difference ratio is confirmed to be higher than the reference ratio in step S605, the first artificial intelligence model may check whether the first ratio is higher than the second ratio in step S606.

If the first rate is confirmed to be higher than the second rate in step S606, the first artificial intelligence model may classify the first sentence as a line in step S613.

That is, the first artificial intelligence model can classify the first sentence as a line if the first difference ratio is confirmed to be higher than the standard ratio and the first ratio is confirmed to be higher than the second ratio.

For example, if the reference ratio is set to 20%, the first ratio is set to 70%, and the second ratio is set to 30%, the first artificial intelligence model compares the first ratio and the second ratio, 40%, which is the value obtained by subtracting the second ratio from the first ratio, can be calculated as the first difference ratio, and the first difference ratio, 40%, is higher than the standard ratio of 20%, and the first ratio, 70%, is the second ratio. Since it is confirmed to be higher than 30%, the first sentence can be classified as a line.

If it is confirmed in step S606 that the first rate is not higher than the second rate, but that the second rate is higher than the first rate, in step S614, the first artificial intelligence model may classify the first sentence as a fingerprint.

That is, the first artificial intelligence model can classify the first sentence as a fingerprint if the first difference ratio is confirmed to be higher than the reference ratio and the second ratio is confirmed to be higher than the first ratio.

For example, if the reference ratio is set to 20%, the first ratio is set to 30%, and the second ratio is set to 70%, the first artificial intelligence model compares the first ratio and the second ratio, 40%, which is the value obtained by subtracting the first ratio from the second ratio, can be calculated as the first difference ratio, and the first difference ratio, 40%, is higher than the standard ratio of 20%, and the second ratio, 70%, is the first ratio. Since it is confirmed to be higher than 30%, the first sentence can be classified as a fingerprint.

Meanwhile, if it is confirmed in step S605 that the first difference ratio is not higher than the reference rate, but that the first difference rate is lower than the reference rate, in step S607, the first artificial intelligence model adds the first keyword in the first sentence. It can be recognized as

Specifically, the first artificial intelligence model can recognize a plurality of keywords in the first sentence, calculate the importance of each keyword, recognize the keyword with the highest importance among the keywords as the first keyword, and Next, the keyword with high importance can be recognized as the second keyword.

In step S608, the first artificial intelligence model may set the probability that the second keyword will be used as a dialogue as a third ratio, and the probability that the second keyword will be used as a fingerprint may be set as a fourth ratio.

In step S609, the first artificial intelligence model may calculate the average value of the first ratio and the third ratio as the fifth ratio, and calculate the average value of the second ratio and the fourth ratio as the sixth ratio.

In step S610, the first artificial intelligence model may calculate the difference between the fifth ratio and the sixth ratio as the second difference ratio. At this time, the first artificial intelligence model may compare the fifth ratio and the sixth ratio and calculate the second difference ratio by subtracting the smaller value from the larger value as a result of the comparison.

In step S611, the first artificial intelligence model can check whether the second difference ratio is higher than the reference ratio.

If it is confirmed in step S611 that the second difference ratio is not higher than the reference rate, but that the second difference rate is lower than the reference rate, returning to step S607, the first artificial intelligence model adds the third keyword in the first sentence. You can start again from the recognition process.

If the second difference ratio is confirmed to be higher than the reference ratio in step S611, in step S612, the first artificial intelligence model can check whether the fifth ratio is higher than the sixth ratio.

If the fifth ratio is confirmed to be higher than the sixth ratio in step S612, the first artificial intelligence model may classify the first sentence as a line in step S613.

That is, the first artificial intelligence model can classify the first sentence as a line if the second difference ratio is confirmed to be higher than the standard ratio and the fifth ratio is confirmed to be higher than the sixth ratio.

If it is confirmed in step S612 that the fifth ratio is not higher than the sixth ratio, but that the sixth ratio is higher than the fifth ratio, in step S614, the first artificial intelligence model may classify the first sentence as a fingerprint.

That is, the first artificial intelligence model can classify the first sentence as a fingerprint if the second difference ratio is confirmed to be higher than the reference ratio and the sixth ratio is confirmed to be higher than the fifth ratio.

If the text of the input web novel consists of a plurality of sentences, the first artificial intelligence model can classify each of the plurality of sentences into dialogue and fingerprints by repeatedly performing each step shown in Figure 6, and classifies them into dialogue. You can generate a dialogue text based on a given sentence, create a fingerprint text based on a sentence classified as a fingerprint, and then output a text set that combines the dialogue text and the fingerprint text.

According to one embodiment, the device 20 determines the user's intention within the web novel, extracts a recommended artificial intelligence model from the artificial intelligence model database based on the user's intention, and sends the recommended artificial intelligence model to the user terminal ( 10) can be provided. A detailed description regarding this will be provided later with reference to FIG. 7 .

Figure 7 is a flowchart explaining the process of providing an artificial intelligence model recommendation platform according to an embodiment.

Referring to FIG. 7, first, in step S701, the device 20 may obtain selection information about the first section that is part of the audiobook from the user terminal 10.

Specifically, the device 20 may obtain selection information for the first section from the user terminal 10 when the user selects the first section in the audiobook, and from the first audio used to create the audiobook. The part corresponding to the first section can be extracted as the audio of the first section.

In step S702, the device 20 may obtain selection information about the second section that is part of the webbook from the user terminal 10.

Specifically, the device 20 may obtain selection information about the second section from the user terminal 10 when the user selects the second section in the webbook, and select the second section from the dialogue text used to create the webbook. The part corresponding to can be extracted as the text of the second section.

In step S703, the device 20 may convert the audio of the first section into first text. At this time, when the audio of the first section is extracted through the audiobook, the device 20 may convert the audio of the first section into the first text using voice recognition technology.

In step S704, the device 20 may set the text of the second section as the second text. At this time, when the text of the second section is extracted through the webbook, the device 20 may set the text of the second section as the second text.

In step S705, the device 20 may extract a keyword based on at least one of the first text and the second text.

That is, when the device 20 acquires at least one of the first text and the second text, it can extract key keywords through words and morphemes included in at least one of the obtained first text and the second text.

In step S706, the device 20 can determine the user's intention by analyzing the extracted keywords.

In other words, when a keyword is extracted, the extracted keyword can be classified as a factor or a result, and the user's intention can be determined through the classified keyword.

Below, we will explain in detail the details of identifying the user's intention.

Specifically, the device 20 may classify at least one of the first text and the second text into words and morphemes. At this time, when the audio in the first section is converted to the first text and the text in the second section is set to the second text, the device 20 classifies at least one of the first text and the second text into words and morphemes. You can.

Afterwards, the device 20 can acquire key keywords by identifying the association between each word and morpheme based on the classified words and morphemes. At this time, the device 20 may include a word database including a thesaurus that can confirm the association between words, and determine the association between words and morphemes extracted using the word database and use the word database to determine the association between words. , can be selected as key keywords. Here, the core keyword may be a word that has the most correlation between words as a result of identifying the correlation between words, and words that are included more than a preset standard through the first and second texts may be selected as the core keyword. Alternatively, words that can be used as core keywords can be set in advance in the word database, and if the word is included in the first text and the second text, the word can be selected as the core keyword.

Afterwards, the device 20 can classify the obtained key keywords into factors and results. At this time, the device 20 may check words surrounding the core keyword obtained from at least one of the first text and the second text and classify the core keyword into factors and results. That is, the device 20 checks surrounding words of the core keyword included in at least one of the first text and the second text, and determines whether words related to factors such as input, factor, cause, reason, from, through, etc. When included, the core keyword can be classified as a factor, and surrounding words of the core keyword included in at least one of the first text and the second text are checked to produce results such as output, result, conclusion, conclusion, etc. If words related to are included, the corresponding core keyword can be classified as a result. Here, the surrounding words may be words included in the text within a preset range based on the core keyword. Additionally, words related to factors and words related to results may be preset words, and as the embodiment increases, words related to factors and words related to results may increase.

Afterwards, the device 20 may store key keywords classified as factors as first input data. At this time, the device 20 may classify key keywords into factors and results, and store the key keywords classified into factors as first input data.

Afterwards, the device 20 may store the key keywords classified as results as first output data. At this time, the device 20 may classify the core keywords into factors and results, and store the core keywords classified as core as first output data.

Due to this, the device 20 has the effect of identifying the user's intention by extracting key keywords from the text and dividing the key keywords into first input data or first output data.

In step S707, the device 20 may select a recommended artificial intelligence model from the artificial intelligence model database based on the user's intention.

That is, the device 20 may have an artificial intelligence model database or communicate wired or wirelessly with a separate artificial intelligence model database, and the artificial intelligence model database includes an artificial intelligence model, and information about the artificial intelligence model is stored in the artificial intelligence model database. It may be matched to an intelligence model and stored. The device 20 may extract a recommended artificial intelligence model needed by the user from an artificial intelligence model database based on the user's intention.

Below, we will explain in detail the details of selecting a recommended artificial intelligence model.

Specifically, the device 20 may select a candidate artificial intelligence model using input data whose category matches the first input data and output data whose category matches the first output data from the artificial intelligence model database. . Here, the category may be information about the format or value in which the input data and output data were input and output. For example, the category of the input data may include user images, user information, etc., and the output data The category may include scores, probability values, etc. for each keyword.

That is, the device 20 may have an artificial intelligence model database or communicate wired or wirelessly with a separate artificial intelligence model database, and the artificial intelligence model database stores an artificial intelligence model, input data for the artificial intelligence model, Information about the artificial intelligence model including output data may be matched and stored. At this time, the device 20 may extract core keywords based on the text acquired through the user terminal 10, and store the extracted core keywords as first input data or first output data, and the device 20 Through the artificial intelligence model database, a candidate artificial intelligence model using input data whose category matches the first input data and output data whose category matches the first output data can be selected.

Thereafter, when only one artificial intelligence model is selected as the candidate artificial intelligence model, the device 20 may set the selected candidate artificial intelligence model as the recommended artificial intelligence model.

When a plurality of artificial intelligence models are selected as candidate artificial intelligence models, the device 20 may input first input data for each selected candidate artificial intelligence model and compare the output value with the first output data. At this time, the device 20 selects a candidate artificial intelligence model from the artificial intelligence model database based on the first input data and the first output data, and if there are multiple selected candidate artificial intelligence models, each candidate artificial intelligence model A value output by inputting first input data may be compared with the first output data.

That is, the device 20 inputs the first input data into the selected candidate artificial intelligence model to determine whether the selected candidate artificial intelligence model is suitable for the user, and compares the output value and the first output data to generate an error. Through this, users can check whether the artificial intelligence model they need is correct.

Afterwards, the device 20 inputs first input data for each selected candidate artificial intelligence model and compares the output value with the first output data to analyze the comparison result. As a result of the comparison, the candidate artificial intelligence model with the smallest difference value is selected. can be selected as a recommended artificial intelligence model.

That is, the device 20 may input first input data for each candidate artificial intelligence model, compare the output value with the first output data, and select the candidate artificial intelligence model with the smallest difference value as the recommended artificial intelligence model.

For example, if the first artificial intelligence model, the second artificial intelligence model, and the third artificial intelligence model are selected as the candidate artificial intelligence models, and the candidate artificial intelligence model with the smallest difference value is selected as the recommended artificial intelligence model, The device 20 can obtain a first output value by inputting first input data to the first artificial intelligence model, and compare the first output value and the first output data to confirm that the difference value is 5%. And, by inputting the first input data to the second artificial intelligence model, the second output value can be obtained, and by comparing the second output value and the first output data, it can be confirmed that the difference value is 20%, 3 By inputting the first input data to the artificial intelligence model, the third output value can be obtained, and by comparing the third output value and the first output data, it can be confirmed that the difference is 10%. At this time, the device 20 may select the first artificial intelligence model as the recommended artificial intelligence model because the first artificial intelligence model has the smallest difference value of 5%.

For this reason, the device 20 selects a candidate artificial intelligence model from the artificial intelligence model database, inputs first input data for each selected candidate artificial intelligence model, and compares the output value with the first output data to obtain the highest difference value. A small number of candidate AI models can be selected as a recommended AI model, which has the effect of selecting an AI model that is more suitable for the user's intention.

In step S708, the device 20 may provide a recommended artificial intelligence model to the user terminal 10.

Specifically, the device 20 extracts text from the first section and the second section set by the user, determines the user's intention through the extracted text, and based on the user's intention, retrieves the user from the artificial intelligence model database. The required recommended artificial intelligence model can be extracted and the extracted recommended recommended artificial intelligence model can be provided to the user terminal 10.

Due to this, the device 20 can extract the artificial intelligence model needed by the user just by setting the section, even if the user does not know about the artificial intelligence model he needs, and sends the extracted artificial intelligence model to the user terminal. It can be provided as (10).

Figure 8 is an exemplary diagram of the configuration of a device according to an embodiment.

Device 20 according to one embodiment includes a processor 21 and memory 22. The processor 21 may include at least one device described above with reference to FIGS. 1 to 7 or may perform at least one method described above with reference to FIGS. 1 to 7 . A person or organization using device 20 may provide services related to some or all of the methods described above with reference to FIGS. 1 to 7 .

The memory 22 may store information related to the methods described above or store a program in which methods described later are implemented. Memory 22 may be volatile memory or non-volatile memory.

The processor 21 can execute programs and control the device 20. The code of the program executed by the processor 21 may be stored in the memory 22. The device 20 is connected to an external device (eg, a personal computer or a network) through an input/output device (not shown) and can exchange data through wired or wireless communication.

The device 20 may be used to train an artificial intelligence model or use a learned artificial intelligence model. Memory 22 may include an artificial intelligence model that is being trained or has been trained. The processor 21 can learn or execute the algorithm of the artificial intelligence model stored in the memory 22. The learning device that trains the artificial intelligence model and the device 20 that uses the learned artificial intelligence model may be the same or may be separate.

The embodiments described above may be implemented with hardware components, software components, and/or a combination of 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, and a field programmable gate (FPGA). It may be implemented using one or more general-purpose or special-purpose computers, such as an array, programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions. A processing device may execute an operating system (OS) and one or more software applications that run on the operating system. Additionally, a processing device may access, store, manipulate, process, and generate data in response to the execution of software. For ease of understanding, a single processing device may be described as being used; however, those skilled in the art will understand that a processing device includes multiple processing elements and/or multiple types of processing elements. It can be seen that it may include. For example, a processing device may include a plurality of processors or one processor and one controller. Additionally, other processing configurations, such as parallel processors, are possible.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., singly or in combination. Program instructions recorded on the medium may be specially designed and configured for the embodiment or may be known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. -Includes optical media (magneto-optical media) and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, etc. Examples of program instructions include machine language code, such as that produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

Software may include a computer program, code, instructions, or a combination of one or more of these, which may configure a processing unit to operate as desired, or may be processed independently or collectively. You can command the device. Software and/or data may be used on any type of machine, component, physical device, virtual equipment, computer storage medium or device to be interpreted by or to provide instructions or data to a processing device. , or may be permanently or temporarily embodied in a transmitted signal wave. Software may be distributed over networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

Although the embodiments have been described with limited drawings as described above, those skilled in the art can apply various technical modifications and variations based on the above. For example, the described techniques are performed in a different order than the described method, and/or components of the described system, structure, device, circuit, etc. are combined or combined in a different form than the described method, or other components are used. Alternatively, appropriate results may be achieved even if substituted or substituted by an equivalent.

Therefore, other implementations, other embodiments, and equivalents of the claims also fall within the scope of the following claims.

Claims (3)

In the automated processing method of creating a web novel-based web book using an artificial intelligence model performed by a device,
Obtaining the text of a web novel from a user terminal;
Inputting the text of the web novel into a pre-trained first artificial intelligence model, and obtaining, as an output of the input of the first artificial intelligence model, a text set in which the text of the web novel is divided into dialogue and fingerprints;
The fingerprint text classified into fingerprints in the text set is input to a pre-learned second artificial intelligence model, and as an output of the input of the second artificial intelligence model, the first image is rendered by using the fingerprint text to render the fingerprint contents. Obtaining a;
generating a webbook based on the dialogue text divided into dialogues in the text set and the first image; and
Including the step of uploading and registering the webbook on a webbook platform,
After acquiring the first image,
generating first audio by converting the dialogue content into audio using the dialogue text;
When the first image is acquired, generating an audiobook based on the first audio and the first image; and
Further comprising the step of uploading and registering the audiobook on an audiobook platform,
Obtaining selection information about a first section that is part of the audiobook from the user terminal;
Obtaining selection information about a second section that is part of the webbook from the user terminal;
converting the audio of the first section into first text;
setting the text of the second section as a second text;
Extracting a keyword based on at least one of the first text and the second text and analyzing the extracted keyword to determine the user's intention;
Selecting a recommended artificial intelligence model from an artificial intelligence model database based on the user's intention; and
Further comprising providing the recommended artificial intelligence model to the user terminal,
The step of determining the user's intention is,
Classifying at least one of the first text and the second text into words and morphemes;
Based on the classified words and morphemes, obtaining key keywords by identifying associations between each word and morpheme;
Classifying the obtained key keywords into factors and results; and
Comprising the steps of storing key keywords classified by the factors as first input data and storing key keywords classified by the results as first output data,
The step of selecting the recommended artificial intelligence model is,
Selecting a candidate artificial intelligence model using input data whose category matches the first input data and output data whose category matches the first output data from an artificial intelligence model database,
When one of the first artificial intelligence model and the second artificial intelligence model is selected as the candidate artificial intelligence model, setting the selected candidate artificial intelligence model as a recommended artificial intelligence model; and
When the first artificial intelligence model and the second artificial intelligence model are selected as the candidate artificial intelligence model, the first input data is input for each selected candidate artificial intelligence model and the output value is compared with the first output data. Analyzing the comparison results, and selecting the candidate artificial intelligence model with the smallest difference value as the recommended artificial intelligence model as a result of the comparison,
The first artificial intelligence model is,
Extract the first sentence from the text of the web novel,
Recognize the first keyword in the first sentence,
The probability that the first keyword will be used as a dialogue is set as a first ratio, and the probability that the first keyword will be used as a fingerprint is set as a second ratio,
Calculating the difference between the first ratio and the second ratio as a first difference ratio,
When the first difference ratio is confirmed to be higher than the preset reference ratio, if the first ratio is confirmed to be higher than the second ratio, the first sentence is classified as a dialogue, and the second ratio is determined to be higher than the first ratio. If confirmed to be higher than the ratio, classify the first sentence as a fingerprint,
If the first difference ratio is confirmed to be lower than the reference ratio, additionally recognize a second keyword in the first sentence,
The probability that the second keyword will be used as a dialogue is set as a third ratio, and the probability that the second keyword will be used as a fingerprint is set as a fourth ratio,
Calculating the average of the first ratio and the third ratio as the fifth ratio, and calculating the average of the second ratio and the fourth ratio as the sixth ratio,
Calculating the difference between the fifth ratio and the sixth ratio as a second difference ratio,
If the second difference ratio is confirmed to be higher than the reference ratio, and the fifth ratio is confirmed to be higher than the sixth ratio, the first sentence is classified as a dialogue, and the sixth ratio is determined to be higher than the fifth ratio. If confirmed to be higher, classifying the first sentence as a fingerprint,
Automation processing method for web novel-based web book creation using an artificial intelligence model. delete According to paragraph 1,
After acquiring the first image,
Translating the dialogue text and the fingerprint text into multiple languages to generate translated dialogue text and translated fingerprint text;
generating second audio by converting the dialogue content into audio using the translated dialogue text; and
Further comprising generating a webbook container including the dialogue text, the fingerprint text, the first image, the translated dialogue text, the translated fingerprint text, the first audio, and the second audio,
Automation processing method for web novel-based web book creation using an artificial intelligence model.