System

Abstract

A system is provided.SOLUTION: A system including means for receiving and storing novel data, means for passing the stored novel data to a text analysis module and causing the text analysis module to analyze a structure of a story, a description of a character, a style of writing, a progress of a plot, and the like, means for inputting an analysis result to a plurality of generation AI models and causing the generation AI models to evaluate the novel based on respective evaluation criteria, means for integrating evaluation results of the respective generation AI models and calculating an overall evaluation score, and means for providing the overall evaluation score and evaluation contents.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] In recent years, advances in generative AI have made it easier for many authors to create and publish novels. While this has dramatically increased the number of novels published, it has also led to a mix of high-quality and low-quality works, making it difficult for readers to discover hidden masterpieces. Furthermore, an increasing number of readers are wasting their money and time on poor works, resulting in a decline in the overall reputation of literary works. In this situation, there is a need to provide an environment where masterpieces are not buried but are properly evaluated, and where readers can discover even better works. [Means for solving the problem]

[0005] To solve the above-mentioned problems, the present invention provides the following means. First, it includes a means for receiving and saving novel data. Next, it includes a means for passing the saved novel data to a text analysis module and analyzing the story structure, character descriptions, writing style, plot progression, etc. Based on the analysis results, it includes a means for inputting the analysis results into multiple generative AI models and having them evaluate the novel based on their respective evaluation criteria. It also includes a means for integrating the evaluation results of each generative AI model and calculating an overall evaluation score. Finally, it configures a system including a means for providing an overall evaluation score and evaluation content. It also includes a means for providing an interface for accepting novel data uploads and sending them to a server, a means for visually displaying the evaluation results to users, and a means for collecting user feedback and sending it to a server. As a result, it includes a means for automatically generating new catchphrases, introductions, and jacket text based on the novel evaluation results. This allows for efficient evaluation of high-quality novels and providing readers with hidden masterpieces.

[0006] "Novel data" is digital data that includes information such as the text of the novel, author information, genre, and plot.

[0007] The "text analysis module" is software that analyzes novel data and extracts elements such as story structure, character descriptions, writing style, and plot progression.

[0008] A "generative AI model" is an artificial intelligence system that evaluates novels using various evaluation criteria based on given data.

[0009] The "analysis results" are the analysis information of the novel data obtained by the text analysis module.

[0010] "Evaluation criteria" are the criteria that the generative AI model uses to evaluate novels, including, for example, story coherence, character appeal, and stylistic sophistication.

[0011] The "overall evaluation score" is a comprehensive evaluation value calculated by integrating the evaluation results of multiple generative AI models.

[0012] The "interface" is an operation screen that allows users to upload novel data, view evaluation results, submit feedback, and so on.

[0013] "Feedback" is information that allows readers to provide their impressions and evaluations of a novel.

[0014] A "catchphrase" is a short phrase that succinctly expresses the content of a novel and attracts the reader's interest.

[0015] An "introduction" is a piece of writing that provides a detailed explanation of the contents of a novel.

[0016] "Obi text" is a short introduction or catch phrase that is printed on the cover or obi of a book. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8]FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] server

[0039] 1. Data Receipt and Storage

[0040] The server receives novel data sent via the Internet from authors or publishers. This data includes the text of the novel, author information, genre, plot summary, etc. The received data is immediately stored in a database.

[0041] 2. Text Analysis

[0042] The server sends the stored novel data to the text analysis module, which performs the following analysis:

[0043] Story structure analysis: Analyzes the beginning, development, twist, and conclusion of a story, scene transitions, and consistency of the timeline.

[0044] Character description analysis: Analyze the characters' personalities, backgrounds, and relationships with each other.

[0045] Stylistic analysis: Evaluating the rhythm of the writing, vocabulary, grammatical accuracy, etc.

[0046] Plot progression analysis: Evaluating whether the story unfolds logically and coherently.

[0047] 3. AI Evaluation

[0048] The server inputs the text analysis results into multiple generative AI models. Each AI model evaluates the analysis results based on its own criteria. For example, one AI model may emphasize story coherence, while another emphasizes character depth. Each AI model generates a specific score and a detailed review based on its own criteria.

[0049] 4. Evaluation Integration

[0050] The server integrates the evaluation results obtained from multiple generative AI models. At this time, it calculates the average of the evaluations to calculate an overall evaluation score. For example, if the individual AI evaluations are 9.0, 8.5, and 8.0, respectively, the overall evaluation score will be 8.5.

[0051] 5. Providing results

[0052] The server then notifies the author or publisher of the calculated overall score and detailed evaluation results. This information may be used as marketing material, and is also used to generate new taglines, introductions, and obi text. The generated text is then provided to the author or publisher, who can revise it as needed.

[0053] Terminal

[0054] 1. Providing an interface

[0055] The terminal provides an interface for users to access and operate. Through this interface, users can:

[0056] Uploading novel data

[0057] Viewing evaluation results

[0058] Submitting Feedback

[0059] 2. Display of evaluation results

[0060] The evaluation results sent from the server are visually displayed on the device, allowing users to select an appropriate novel based on this. Individual evaluation results from each AI model are also displayed, allowing users to use this information to help them select evaluation criteria that best suit their preferences.

[0061] 3. Gathering Feedback

[0062] After reading a novel, readers submit their ratings and impressions through a feedback form. This feedback is sent to the server and used to improve the evaluation algorithm of the generative AI model.

[0063] User

[0064] 1. Uploading a Novel

[0065] Authors or publishers upload novel data through the device's interface, which is then sent to the server and stored.

[0066] 2. Viewing the evaluation results

[0067] Authors and publishers can check the evaluation results sent from the server on their devices, allowing them to understand how their work has been evaluated and identify areas for improvement.

[0068] 3. Providing Feedback

[0069] After finishing a novel, readers can provide feedback via their devices, which will help the AI ​​make a more accurate assessment.

[0070] Specific examples

[0071] For example, when a well-known author writes a new novel and uploads it to the system through a publisher, the novel data is first received and stored on the server. It is then analyzed by a text analysis module, which performs a detailed analysis of the story structure, character descriptions, writing style, etc. The analysis results are input into multiple generative AI models, each of which evaluates the novel based on its own evaluation criteria. As a result, an overall evaluation score is calculated, and the evaluation results are notified to the author and publisher. Based on this evaluation result, new catchphrases and introductions are automatically generated and used in promotional activities. Readers can use the evaluation results as a reference when selecting a novel, and provide feedback after reading, contributing to improving the accuracy of the AI ​​evaluation.

[0072] In this way, the present invention realizes an environment in which hidden masterpieces can be easily discovered by efficiently evaluating high-quality works and providing them to readers amidst the proliferation of novels.

[0073] The processing flow will be explained below.

[0074] Step 1:

[0075] The server receives novel data sent via the Internet from authors or publishers. This data includes the text of the novel, author information, genre, plot summary, etc. The received data is immediately stored in a database.

[0076] Step 2:

[0077] The server sends the saved novel data to the text analysis module, which performs grammatical analysis, sentiment analysis, keyword extraction, etc. of the novel, and generates and returns the analysis results to the server.

[0078] Step 3:

[0079] The server inputs the results of the text analysis into multiple generative AI models. Each AI model evaluates the novel data based on criteria such as story coherence, character depth, and stylistic clarity. Each AI model generates a rating score and a detailed review.

[0080] Step 4:

[0081] The server integrates the evaluation results from each generative AI model. At this time, it calculates the average of each evaluation to calculate an overall evaluation score. For example, if AI model A evaluates 8.0, AI model B evaluates 7.0, and AI model C evaluates 9.0, the average is calculated and the overall evaluation score is 8.0.

[0082] Step 5:

[0083] The server notifies the author or publisher of the calculated overall evaluation score and detailed evaluation results. The notification also includes the individual evaluation results of each AI model and the evaluation criteria. Based on the evaluation results, the server automatically generates new catchphrases, introductions, and obi text and provides them to the author or publisher.

[0084] Step 6:

[0085] The terminal provides an interface for users (authors, publishers, and readers) to access and operate, through which users can upload novel data, view evaluation results, and submit feedback.

[0086] Step 7:

[0087] The device visually displays the evaluation results sent from the server to the user. It displays not only the overall evaluation score but also the detailed evaluation results from each AI model. This allows the user to select novels based on evaluation criteria that best suit their preferences.

[0088] Step 8:

[0089] The device collects feedback from readers about the novels they have read, and sends the information submitted through a feedback form to a server, which then reflects the collected feedback in the generative AI model, thereby contributing to improving the accuracy of the evaluation algorithm.

[0090] Step 9:

[0091] Users (authors, publishers, and readers) can use the device to check the new catchphrases and introductions, decide whether they are appropriate, and, if necessary, revise the automatically generated text to use as the final marketing material.

[0092] Step 10:

[0093] The server analyzes the collected feedback and uses it to improve the evaluation criteria of the generative AI model, which will improve the accuracy of future novel evaluations and enable better recommendations.

[0094] Example 1

[0095] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0096] Conventional literary evaluation systems often lack uniformity and fairness in their evaluations, and do not evaluate works from a variety of perspectives, making it difficult to determine their true value. Furthermore, there is no efficient way to collect feedback from many users, resulting in a lack of reference information for revising and releasing works.

[0097] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0098] In this invention, the server includes means for receiving and saving literary data, means for passing the saved literary data to a natural language analysis module to analyze the narrative structure, character traits, writing style, and story progression, means for inputting the analysis results into a plurality of AI models to evaluate the literary work based on their respective evaluation criteria, means for integrating the evaluation results of each AI model to calculate an overall evaluation score, and means for providing the overall evaluation score and the evaluation content, thereby enabling high-quality literary evaluation and detailed feedback from a variety of perspectives.

[0099] "Literary data" refers to data that includes information such as the text of a work, author information, genre, and plot.

[0100] A "natural language analysis module" is a program that analyzes text data and evaluates the structure of the story, the characteristics of the characters, the writing style, the progression of the story, etc.

[0101] A "generative artificial intelligence model" is an artificial intelligence program that evaluates text data according to specific evaluation criteria based on previously learned data.

[0102] The "overall evaluation score" is a numerical value that indicates the overall evaluation by integrating the individual evaluation results obtained from multiple generating artificial intelligence models.

[0103] "Upload Interface" is a platform through which users can submit literary data to the system.

[0104] The "visual display means" is a mechanism for displaying the evaluation results to the user as graphs or text.

[0105] The "feedback collection means" is a means for receiving evaluations and impressions from users and transmitting them to the server.

[0106] A "catchphrase" is a short, catchy phrase used to introduce a work to the market.

[0107] An "introduction" is a short sentence that explains the outline and characteristics of the work.

[0108] "Obi text" refers to short sentences or catchphrases printed on the book's obi, and serves to stimulate purchasing desire.

[0109] server

[0110] 1. Data Receipt and Storage

[0111] The server receives literary data sent by connected authors or publishers via the Internet. This data includes the text of the work, author information, genre, plot summary, etc. The received data is immediately stored in the database. For example, when an author uploads a new work, the data is sent to the server and stored.

[0112] 2. Text Analysis

[0113] The server sends the stored literary data to a natural language analysis module, which analyzes the narrative structure, character traits, writing style, and story progression. For example, it analyzes the beginning, development, climax, and conclusion of a story and detects how each part is structured.

[0114] 3. AI Evaluation

[0115] The server then feeds the analysis results into multiple artificial intelligence models, which evaluate literary works based on their own criteria: for example, one AI model focuses on story coherence, while another evaluates character portrayals.

[0116] 4. Evaluation Integration

[0117] The server integrates the evaluation results obtained from each AI model and calculates an overall evaluation score. For example, if model A is evaluated as 8.5, model B as 9.0, and model C as 8.0, the server calculates the average of these scores and uses this as the overall evaluation score.

[0118] 5. Providing results

[0119] The server then notifies the author or publisher of the calculated overall score and detailed evaluation. This information is used as marketing material and is also utilized to generate new catchphrases, descriptions, and obi text. For example, the server may notify the author or publisher of the evaluation result, saying, "This work has been evaluated for its story consistency, with an overall score of 8.5."

[0120] Terminal

[0121] 1. Providing an interface

[0122] The terminal provides an interface for users to access and operate, through which users can upload literary data, view evaluation results, and provide feedback. For example, a user can submit a work using a form for uploading a novel.

[0123] 2. Display of evaluation results

[0124] The evaluation results sent from the server are visually displayed on the device, allowing users to select an appropriate novel based on this information. Individual evaluation results from each generated AI model are also displayed, helping users choose evaluation criteria that best suit their preferences. For example, the dashboard displays the overall evaluation score and detailed evaluation results in graphs and text.

[0125] 3. Gathering Feedback

[0126] After a reader finishes reading a novel, they submit their rating and thoughts through a feedback form. This feedback is sent to the server and used to improve the evaluation algorithm of the AI ​​model that generates it. For example, reader comments such as "The story development was fascinating" are collected.

[0127] User

[0128] 1. Uploading a Novel

[0129] Authors or publishers upload literary data through the device interface. The uploaded data is sent to the server and stored. For example, when uploading a new novel, they enter the necessary information and press the submit button, and the data is stored on the server.

[0130] 2. Viewing the evaluation results

[0131] Authors and publishers can check the evaluation results sent from the server on their devices. This allows them to understand how their work has been evaluated and identify areas for improvement. For example, they can check the evaluation score and detailed feedback on a dashboard.

[0132] 3. Providing Feedback

[0133] After finishing a novel, readers can provide feedback via their devices, which will help the AI ​​model to generate a more accurate evaluation. For example, after finishing a novel, readers can fill out a feedback form and press the submit button, which will send the feedback to the server.

[0134] Specific prompt examples

[0135] "Please enter the text of the novel."

[0136] Analyze the characters' personalities

[0137] "Evaluate the coherence of the story."

[0138] This makes it possible to efficiently evaluate high-quality works from among many literary works and provide them to readers, creating an environment in which hidden masterpieces can be easily discovered.

[0139] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0140] Step 1: Receiving and storing data

[0141] The server receives literary data sent by connected authors or publishers via the Internet. The input includes data such as the novel text, author information, genre, and plot summary. The server verifies that the data has been received correctly, and if successful, it is stored in a database. For example, when a new work is uploaded, all of its data arrives at the server and is immediately stored in the database.

[0142] Step 2: Text analysis

[0143] The server sends the stored literary data to a natural language analysis module. The literary data is used as input. The natural language analysis module analyzes the structure of the story (beginning, development, climax, conclusion, etc.), the characteristics of the characters (personalities, background, etc.), the writing style (rhythm, vocabulary, etc.), and the progression of the story (consistency of the timeline, etc.), and outputs the results of these analyses. For example, it identifies and analyzes the beginning, middle, climax, and conclusion of a story.

[0144] Step 3: AI evaluation

[0145] The server inputs the analysis results into multiple AI models. The text analysis results are used as input. The AI ​​models evaluate literary works based on their respective evaluation criteria (e.g., story coherence, character depth, etc.). Each AI model outputs a specific score and a detailed review. For example, an AI model that emphasizes story coherence will evaluate the work based on that criteria and output its results.

[0146] Step 4: Consolidating the assessments

[0147] The server integrates the evaluation results obtained from each generated AI model. Evaluation results from multiple AI models are used as input. The server calculates the average of these evaluation results and outputs an overall evaluation score. For example, if the evaluation scores are 9.0, 8.5, and 8.0, the average of these, 9.0, is calculated as the overall evaluation score.

[0148] Step 5: Delivering results

[0149] The server notifies the author or publisher of the calculated overall rating score and detailed rating content. The overall rating score and detailed rating content are used as input. The rating result is notified to the author or publisher as output. For example, a notification may be sent saying, "This work has an overall rating score of 8.5."

[0150] Step 6: Providing an Interface

[0151] The terminal provides an interface for users to access and operate. User operations are used as input. The terminal provides and outputs a form for users to upload literary data and a dashboard for viewing evaluation results. For example, when a user clicks the upload button, the following page is displayed.

[0152] Step 7: View the evaluation results

[0153] The terminal visually displays the evaluation results sent from the server. The evaluation results from the server are used as input. The evaluation results are output in graph and text format on the dashboard, helping users to select the appropriate novel. For example, the terminal displays the overall evaluation score and detailed evaluations by each AI model.

[0154] Step 8: Gather feedback

[0155] The terminal provides a means for the reader user to submit their evaluation and thoughts through a feedback form after finishing reading the novel. The user's feedback is used as input. The submitted feedback is sent to the server and used to improve the evaluation algorithm of the generated artificial intelligence model. For example, a comment such as "The story development was very satisfying" can be entered and submitted in the feedback form.

[0156] Through these steps, this system is able to evaluate literary works from multiple perspectives and provide readers with high-quality works.

[0157] (Application example 1)

[0158] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0159] This invention relates to a system that efficiently evaluates high-quality works amidst the proliferation of novels and provides them to readers. Conventional evaluation methods make it difficult for authors and publishers to quickly and accurately grasp the quality of works, and readers lack the information necessary to select appropriate works. Furthermore, the collection and utilization of feedback is inefficient, resulting in a lack of consistency in the evaluation of works. It is necessary to solve these issues and improve the process of evaluating and providing novels.

[0160] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0161] In this invention, the server includes: [means for receiving and saving novel data; [means for passing the saved novel data to a text analysis module and having it analyze the story structure, character descriptions, writing style, plot progression, etc.; and [means for inputting the analysis results into multiple generative AI models and having them evaluate the novel based on their respective evaluation criteria.] This makes it possible [to integrate the evaluation results of each generative AI model, calculate an overall evaluation score, and provide the overall evaluation score and evaluation content].

[0162] "Novel data" refers to data such as the text of a novel, author information, genre, and plot summary provided by the author or publisher.

[0163] A "text analysis module" is software or hardware used to analyze novel data and evaluate the story structure, character descriptions, writing style, plot progression, etc.

[0164] A "generative AI model" is an artificial intelligence model that evaluates novels based on the results of analyzing novel data and each evaluation criterion.

[0165] The "overall evaluation score" is a number calculated by combining the evaluation results from multiple generative AI models, and is used to comprehensively evaluate the quality of the entire novel.

[0166] A "smartphone application" is software that runs on a smartphone and provides functions such as uploading novel data, displaying evaluation results, and collecting feedback.

[0167] "Feedback" refers to the impressions and evaluations that readers provide after finishing a novel, and is information that is sent to the server and contributes to improving the accuracy of the generative AI model.

[0168] The "interface" is the UI (user interface) that users can operate, allowing them to upload novel data, view evaluation results, and submit feedback.

[0169] A "catchphrase" is a short phrase used in marketing and promotional activities to effectively convey the appeal of a novel.

[0170] An "introduction" is a text that explains the content and characteristics of a novel and is used to convey an overview of the work to customers.

[0171] "Book cover text" refers to advertising slogans or catch phrases printed on a piece of paper attached to the outside of a book's cover, intended to motivate customers to purchase the book.

[0172] In this invention, the server receives, stores, analyzes, evaluates, and provides results of novel data using the following means.

[0173] server

[0174] 1. Data Receipt and Storage

[0175] The server receives novel data sent via the Internet from authors or publishers. This data includes the text of the novel, author information, genre, plot summary, etc. The received data is immediately stored in a database.

[0176] 2. Text Analysis

[0177] The server sends the saved novel data to the text analysis module, which uses a Python natural language processing library (e.g., NLTK or spaCy). The text analysis module performs the following analysis:

[0178] Story structure analysis: Analyzes the beginning, development, twist, and conclusion of a story, scene transitions, and consistency of the timeline.

[0179] Character description analysis: Analyze the characters' personalities, backgrounds, and relationships with each other.

[0180] Stylistic analysis: Evaluating the rhythm of the writing, vocabulary, grammatical accuracy, etc.

[0181] Plot progression analysis: Evaluating whether the story unfolds logically and coherently.

[0182] 3. AI Evaluation

[0183] The server inputs the text analysis results into multiple generative AI models. Each generative AI model evaluates the analysis results based on its own evaluation criteria. Examples of AI models used include OpenAI's GPT-3 (registered trademark). Each AI model generates a specific score and a detailed review based on its own evaluation criteria.

[0184] 4. Evaluation Integration

[0185] The server integrates the evaluation results obtained from multiple generative AI models, calculating the average of the evaluations and deriving an overall evaluation score.

[0186] 5. Providing results

[0187] The server then notifies the author or publisher of the calculated overall score and detailed evaluation results. This information is used as marketing material and is also used to generate new taglines, introductions, and obi text. The generated text is then provided to the author or publisher, who can revise it as needed.

[0188] Terminal

[0189] 1. Providing an interface

[0190] The terminal provides an interface for users to access and operate. Through this interface, users can:

[0191] Uploading novel data

[0192] Viewing evaluation results

[0193] Submitting Feedback

[0194] 2. Display of evaluation results

[0195] The evaluation results sent from the server are visually displayed on the device, allowing users to select an appropriate novel based on this. Individual evaluation results from each AI model are also displayed, allowing users to use this information to help them select evaluation criteria that best suit their preferences.

[0196] 3. Gathering Feedback

[0197] After reading a novel, readers submit their ratings and impressions through a feedback form. This feedback is sent to the server and used to improve the evaluation algorithm of the generative AI model.

[0198] User

[0199] 1. Uploading a Novel

[0200] Authors or publishers upload novel data through the device's interface, which is then sent to the server and stored.

[0201] 2. Viewing the evaluation results

[0202] Authors and publishers can check the evaluation results sent from the server on their devices, allowing them to understand how their work has been evaluated and identify areas for improvement.

[0203] 3. Providing Feedback

[0204] After finishing a novel, readers provide feedback through their devices, which helps the AI ​​to more accurately evaluate it.

[0205] Specific examples

[0206] For example, when an author writes a new novel and uploads it to the system via their device, the novel data is first received and stored on the server. The text analysis module then analyzes the story structure, character descriptions, writing style, and other aspects, and the analysis results are input into multiple generative AI models. The evaluation results are then integrated to calculate an overall evaluation score. The author and publisher are notified of this evaluation result, and a new catchphrase and introduction are automatically generated based on it.

[0207] Prompt Sentence Examples

[0208] Please rate the following novel data in terms of plot coherence, character depth, stylistic rhythm, etc.

[0209] Novel Title: New Novel

[0210] Author: Famous Author

[0211] Genre: Fantasy

[0212] Synopsis: This is a sample story

[0213] Novel content: The main text of the novel...

[0214] Please provide your evaluation in the following format:

[0215] 1. Overall evaluation score

[0216] 2. Detailed evaluation of story coherence

[0217] 3. Detailed evaluation of character depth

[0218] 4. Detailed evaluation of stylistic rhythm

[0219] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0220] Step 1:

[0221] The device receives novel data from the author or publisher. The novel data includes the text, author information, genre, and synopsis. The device uses this data as input and sends an HTTP POST request to the server. This sends the novel data to the server and stores it in a database.

[0222] Step 2:

[0223] The server sends the saved novel data to the text analysis module, which uses a Python natural language processing library (such as NLTK or spaCy). Here, the following data processing is performed and the analysis results are output:

[0224] Story structure analysis (beginning, development, twist, conclusion, scene transitions, etc.)

[0225] Character description analysis (personality, background, relationships, etc.)

[0226] Stylistic analysis (rhythm, vocabulary, grammatical accuracy, etc.)

[0227] Plot progression analysis (logic of development, consistency, etc.)

[0228] Step 3:

[0229] The server inputs the text analysis results into multiple generative AI models, such as OpenAI's GPT-3. Each generative AI model performs the following data calculations and outputs an individual rating score and detailed review:

[0230] Story consistency

[0231] Character depth

[0232] Stylistic rhythm and variety

[0233] Overall rating score

[0234] Step 4:

[0235] The server integrates the evaluation results obtained from multiple generative AI models. Specifically, it calculates the average of the evaluation scores of each model and outputs an overall evaluation score. It also integrates detailed evaluation reviews to generate a single evaluation report. These results are stored in the server database.

[0236] Step 5:

[0237] The server outputs the evaluation results—namely, the overall evaluation score and a detailed evaluation report—in JSON format via an API endpoint to provide them to the user's device, where the user (author or publisher) can visually check these evaluation results.

[0238] Step 6:

[0239] The terminal provides a GUI (Graphical User Interface) to visually display the evaluation results. Users can view the evaluation scores and detailed evaluation reviews through this interface, which allows them to deepen their understanding of their work and identify areas for improvement.

[0240] Step 7:

[0241] After finishing reading a novel, users (readers) provide their ratings and impressions using a feedback form. The device sends this feedback to the server and stores it as data used to improve the evaluation algorithm of the generative AI model.

[0242] Prompt Sentence Examples

[0243] Please rate the following novel data in terms of plot coherence, character depth, stylistic rhythm, etc.

[0244] Novel Title: New Novel

[0245] Author: Famous Author

[0246] Genre: Fantasy

[0247] Synopsis: This is a sample story

[0248] Novel content: The main text of the novel...

[0249] Please provide your evaluation in the following format:

[0250] 1. Overall evaluation score

[0251] 2. Detailed evaluation of story coherence

[0252] 3. Detailed evaluation of character depth

[0253] 4. Detailed evaluation of stylistic rhythm

[0254] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0255] The present invention relates to a system for receiving and storing novel data, a system for analyzing and rating novel data, and a method for improving the accuracy and personalization of novel ratings by combining an emotion engine that analyzes user emotions.

[0256] server

[0257] 1. Data Receipt and Storage

[0258] The server receives novel data sent via the Internet from authors or publishers. This data includes the text of the novel, author information, genre, plot summary, etc. The received data is immediately stored in a database.

[0259] 2. Text Analysis

[0260] The server sends the stored novel data to the text analysis module, which performs the following analysis:

[0261] Story structure analysis: Analyzes the beginning, development, twist, and conclusion of a story, scene transitions, and consistency of the timeline.

[0262] Character description analysis: Analyze the characters' personalities, backgrounds, and relationships with each other.

[0263] Stylistic analysis: Evaluating the rhythm of the writing, vocabulary, grammatical accuracy, etc.

[0264] Plot progression analysis: Evaluating whether the story unfolds logically and coherently.

[0265] 3. AI Evaluation

[0266] The server inputs the text analysis results into multiple generative AI models. Each AI model evaluates the analysis results based on its own criteria. For example, one AI model may emphasize story coherence, while another emphasizes character depth. Each AI model generates a specific score and a detailed review based on its own criteria.

[0267] 4. Evaluation Integration

[0268] The server integrates the evaluation results obtained from each generative AI model. At this time, it calculates the average of the evaluations to calculate an overall evaluation score. For example, if the individual AI evaluations are 9.0, 8.5, and 8.0, respectively, the overall evaluation score will be 8.5.

[0269] 5. Providing results

[0270] The server notifies the author or publisher of the calculated overall evaluation score and detailed evaluation results. It also automatically generates new catchphrases, introductions, and obi text based on the evaluation results and provides them to the author or publisher.

[0271] Terminal

[0272] 1. Providing an interface

[0273] The terminal provides an interface for users to access and operate. Through this interface, users can:

[0274] Uploading novel data

[0275] Viewing evaluation results

[0276] Submitting Feedback

[0277] 2. Display of evaluation results

[0278] The terminal visually displays the evaluation results sent from the server to the user, allowing the user to select novels based on evaluation criteria that are closest to their preferences.

[0279] 3. Gathering Feedback

[0280] The device collects feedback on the novels that users have read and sends their impressions and evaluations to the server, thereby contributing to improving the accuracy of the AI ​​evaluation.

[0281] Introducing the Emotion Engine

[0282] 1. Emotion recognition

[0283] The server uses an emotion engine to perform sentiment analysis of the feedback provided by the user, for example, automatically classifying it as positive, negative, or neutral.

[0284] 2. Real-time analysis

[0285] The device analyzes the user's emotional state in real time as they read the novel, and sends the results to the emotion engine. For example, if the user is using a smartphone or tablet, the device recognizes their emotions by utilizing their operation patterns and facial recognition technology.

[0286] 3. Personalized evaluation

[0287] The server personalizes the novel evaluation results based on the emotional data obtained from the emotion engine. For example, if a user typically provides many positive reviews, the server will make recommendations that match that emotional pattern.

[0288] 4. Accumulation of emotional history

[0289] The server accumulates users' emotional history data and adjusts the novel recommendation algorithm based on their past emotional patterns, enabling more accurate recommendations in the future.

[0290] Specific examples

[0291] For example, suppose a user purchases a newly released novel through a device and begins reading it. The novel data is uploaded and stored on a server by the author or publisher. The server sends the novel data to a text analysis module, which generates analysis results. The results are then input into multiple generative AI models, which evaluate the novel on factors such as story coherence, character depth, and stylistic clarity. The evaluation results are then combined to calculate an overall evaluation score.

[0292] The evaluation results are provided to the user via their device. Furthermore, while the user is reading the novel, their emotions are analyzed in real time and their emotional state is recorded. The emotion engine uses this real-time data to personalize the evaluation results and make optimal recommendations to the user. After finishing reading, the feedback provided by the user is also analyzed by the emotion engine and sent to the server.

[0293] Through this series of processes, the present invention can efficiently evaluate high-quality works from a wide variety of novels and make optimal recommendations based on the user's emotional state. Furthermore, by continuously improving the evaluation algorithm based on collected emotional data, it will be possible to provide a more accurate novel evaluation system in the future.

[0294] The processing flow will be explained below.

[0295] server

[0296] Step 1:

[0297] The server receives novel data uploaded by authors or publishers. The novel data includes information such as the text, author information, genre, and plot. After receiving the data, it stores it in a database.

[0298] Step 2:

[0299] The server sends the saved novel data to the text analysis module, which performs story structure analysis, character portrayal analysis, stylistic analysis, and plot progression analysis to generate analysis results, which are then sent back to the server.

[0300] Step 3:

[0301] The server inputs the results of the text analysis into multiple generative AI models. Each generative AI model analyzes the novel data based on criteria such as story coherence, character depth, and stylistic beauty. Each AI model generates a specific evaluation score and a detailed review.

[0302] Step 4:

[0303] The server combines the evaluation results returned by each generative AI model. It calculates the average of each evaluation and calculates the overall evaluation score. For example, if AI model A evaluates the score as 8.0, AI model B as 7.5, and AI model C as 9.0, the overall evaluation score will be 8.2.

[0304] Step 5:

[0305] The server notifies the author or publisher of the overall evaluation score and detailed evaluation results. It also automatically generates new catchphrases, introductions, and obi text based on the evaluation results and notifies the author or publisher of these texts.

[0306] Terminal

[0307] Step 6:

[0308] The terminal provides an interface for users to access and operate, through which users can upload novel data, view evaluation results, and submit feedback.

[0309] Step 7:

[0310] The device visually displays the evaluation results sent from the server to the user. Not only the overall evaluation score but also the detailed evaluation results from each generative AI model are displayed. This allows the user to select novels based on evaluation criteria that best suit their preferences.

[0311] Step 8:

[0312] The device collects feedback on the novels the user has read, which is then sent to a server, which uses this information to improve the evaluation algorithm of the generative AI model.

[0313] Introducing the Emotion Engine

[0314] Step 9:

[0315] The server performs sentiment analysis of the feedback provided by the user using an emotion engine, which categorizes the feedback into positive, negative, and neutral categories and sends the analysis results back to the server.

[0316] Step 10:

[0317] The device analyzes the user's emotional state in real time as they read the novel and sends the results to the emotion engine. For example, if the user is using a smartphone or tablet, the device uses their operation patterns and facial recognition technology to recognize their emotions.

[0318] Step 11:

[0319] The server personalizes the novel evaluation results based on real-time emotional data obtained from the emotion engine, and recommends novels that are optimal for the user's emotional state. For example, if the user is feeling sad, it will recommend novels that will soothe the emotions.

[0320] Step 12:

[0321] The server will accumulate the user's emotional history and adjust the novel recommendation algorithm based on past emotional patterns, which will enable more accurate novel evaluation and recommendation in the future.

[0322] Specific examples

[0323] For example, an author of a new novel uploads the novel data to the system through a publisher. The server receives and stores the data. The novel data is then sent to the text analysis module for detailed analysis. Based on the analysis results, each generative AI model evaluates the novel according to its own evaluation criteria. The evaluation results are then integrated to calculate an overall evaluation score.

[0324] The evaluation results are provided to the user via their device. As the user reads the novel, the emotion engine analyzes the user's emotions in real time and sends the data to the server. Personalized evaluation results and recommendations are made based on the user's emotional state, and feedback after reading is also analyzed by the emotion engine.

[0325] The data collected in this way will continuously improve the evaluation algorithms of the generative AI model, ensuring that users always have the best possible novels to choose from, as well as ensuring that authors and publishers have their work properly evaluated.

[0326] Example 2

[0327] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0328] Conventional novel evaluation systems have limited means for objectively evaluating the quality of novels, making it difficult to provide personalized recommendations that take the user's emotional state into account. Furthermore, they lack the means to appropriately utilize user feedback and improve the overall evaluation accuracy of the system. Therefore, a new system is needed that can effectively achieve high-quality novel evaluations and personalized recommendations that reflect the user's emotional state.

[0329] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0330] In this invention, the server includes means for receiving and saving novel data, means for passing the saved novel data to a text analysis module to analyze the story structure, character descriptions, writing style, plot progression, etc., means for inputting the analysis results into multiple generative AI models and evaluating the novel based on their respective evaluation criteria, means for integrating the evaluation results of each generative AI model to calculate an overall evaluation score, means for providing the overall evaluation score and evaluation details, means for analyzing feedback provided by the user with an emotion engine and personalizing the novel evaluation results based on the emotion data, and means for accumulating the user's emotion history and adjusting the novel recommendation algorithm based on past emotion patterns. This enables high-quality novel evaluations and personalized recommendations according to the user's emotional state.

[0331] "Novel data" is digital data that includes the text of the novel, author information, genre, plot summary, etc.

[0332] The "text analysis module" is a software module that analyzes novel data to evaluate the story structure, character descriptions, writing style, plot progression, etc.

[0333] A "generative AI model" is an artificial intelligence model used to evaluate novels based on analysis results. Specifically, it refers to a model that utilizes natural language processing technology.

[0334] The "evaluation criteria" are items that serve as indicators for evaluating a novel, such as the consistency of the story, the depth of the characters, and the clarity of the writing style.

[0335] The "overall evaluation score" is a number that indicates the overall evaluation of a novel, calculated by combining the evaluation results obtained from multiple generative AI models.

[0336] The "emotion engine" is a software engine that analyzes emotions based on user-provided feedback and real-time operational data.

[0337] "Personalization" refers to providing an optimized experience for a user by adjusting the system's behavior and recommendations based on the user's individual attributes and emotional state.

[0338] "Emotion history" is data that records and accumulates a user's past emotional data. This data will improve the accuracy of the recommendation algorithm from the next time onwards.

[0339] "Interface" refers to the means of providing a screen and a set of functions for users to operate a system.

[0340] "Feedback" refers to the user's impressions and evaluations of the novels they have read. It is used to improve the accuracy of the system's evaluations.

[0341] The present invention relates to a system for receiving and storing novel data, a system for analyzing and rating novel data, and a method for improving the accuracy and personalization of novel ratings by combining an emotion engine for analyzing user emotions.

[0342] server

[0343] The server receives novel data sent over the internet from authors or publishers. This data includes the novel's text, author information, genre, and synopsis. The received data is immediately stored in a database. The server uses libraries such as NLTK (Natural Language Toolkit) and SpaCy, which use the Python language, to send the novel data to a text analysis module for analysis. This analyzes the story structure, character descriptions, writing style, and plot progression. The text analysis results are input into multiple generative AI models, which evaluate the story's coherence and character depth. This is done using prompts such as, "Please rate the story coherence and character depth of this newly released novel." The evaluation results from each generative AI model are combined to calculate an overall evaluation score. The calculated overall evaluation score and detailed evaluation results are then notified to the author or publisher. Automatically generated taglines, introductions, and obi text are also provided.

[0344] Terminal

[0345] The terminal provides an interface for users to access and operate the system. This includes uploading novel data, viewing evaluation results, and submitting feedback through a web browser or dedicated application. The evaluation results sent from the server are visually displayed to the user via the terminal. As the user reads the novel, their emotions are analyzed in real time and sent to the emotion engine. This allows emotions to be recognized using the user's operation patterns and facial recognition technology when using a smartphone or tablet. Feedback and impressions provided by the user are also sent from the terminal to the server.

[0346] Emotion Engine

[0347] The emotion engine performs sentiment analysis on feedback provided by users and categorizes them as positive, negative, or neutral. It uses sentiment analysis APIs such as Microsoft® Azure®'s Text Analytics API. It analyzes the user's emotional state in real time and personalizes the novel evaluation results based on this. For example, if a user has a lot of positive thoughts, it will recommend novels that match their emotions. Emotion data is stored on the server, and the novel recommendation algorithm is adjusted based on past emotional patterns.

[0348] Specific examples

[0349] For example, a user purchases a newly released novel through a device and begins reading it. This novel data is uploaded and stored on a server by the author or publisher. The server then sends the novel data to a text analysis module, which evaluates the story's coherence, character depth, and writing style. The analysis results are input into multiple generative AI models, which then perform an evaluation. The evaluation results are integrated to calculate an overall evaluation score. This score and detailed evaluation results are provided to the user through the device. Furthermore, emotions are analyzed in real time as the user reads the novel, and the user's emotional state is recorded. The emotion engine then personalizes the evaluation results based on this real-time data and makes optimal recommendations to the user. After reading, feedback provided by the user is also analyzed by the emotion engine and sent to the server. Through this series of processes, the present invention can achieve high-quality novel evaluations and personalized recommendations based on the user's emotional state.

[0350] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0351] Step 1:

[0352] The server receives novel data sent from an author or a publisher via the Internet.

[0353] Input: Digital data including the text of the novel, author information, genre, plot summary, etc.

[0354] Data processing: Decodes the received data and converts it into the appropriate format.

[0355] Output: Decoded novel data.

[0356] Specific operation: The server receives data through a specific API endpoint and stores it in a database.

[0357] Step 2:

[0358] The server transmits the stored novel data to a text analysis module.

[0359] Input: Novel data stored in the database.

[0360] Data Computing: Perform natural language analysis using libraries such as Python's NLTK and SpaCy.

[0361] Output: Analysis of narrative structure, characterization, writing style, and plot progression.

[0362] Specific operation: The server passes the data to the analysis module, which analyzes the structure, character, and style of the text.

[0363] Step 3:

[0364] The server inputs the results of the text analysis into multiple generative AI models, which then evaluate the novel based on their respective evaluation criteria.

[0365] Input: Analysis results output from the text analysis module.

[0366] Data calculation: The analysis results are input into each generative AI model and evaluated using prompt statements.

[0367] Output: Evaluation results from each generative AI model.

[0368] Specific behavior: The server generates a prompt statement such as "Please rate the story coherence and character depth of a newly released novel" and gives it to each AI model.

[0369] Step 4:

[0370] The server integrates the evaluation results obtained from each generative AI model and calculates an overall evaluation score.

[0371] Input: Evaluation scores for each generative AI model.

[0372] Data calculation: The evaluation scores are averaged and combined.

[0373] Output: Overall evaluation score.

[0374] Specific operation: The server aggregates the evaluation scores of each AI model, calculates the average value, and derives the overall evaluation score.

[0375] Step 5:

[0376] The server notifies the author or publisher of the detailed evaluation results and the overall evaluation score.

[0377] Input: Overall assessment score and detailed assessment results.

[0378] Data processing: converting the results into a format for notification.

[0379] Output: Notification of evaluation results.

[0380] Specific operation: The server notifies the user of the evaluation results via email or dashboard, and also automatically generates and provides a catchy slogan, introduction, and obi text.

[0381] Step 6:

[0382] The terminal provides an interface for the user to access and operate.

[0383] Input: User operation request.

[0384] Data processing: Generate and display the user interface.

[0385] Output: The interface that is displayed to the user.

[0386] Specific operation: The device provides a UI for uploading, viewing evaluation results, and submitting feedback via a web browser or dedicated app.

[0387] Step 7:

[0388] The terminal visually displays the evaluation results sent from the server to the user.

[0389] Input: The evaluation result sent from the server.

[0390] Data processing: Convert the evaluation results into a visually easy-to-read format.

[0391] Output: The evaluation results that are displayed to the user.

[0392] Specific operation: The device displays the evaluation results in graphs and text, making it easy for the user to understand.

[0393] Step 8:

[0394] The terminal collects feedback from the user and sends it to the server.

[0395] Input: User feedback.

[0396] Data Processing: Collect feedback and convert it into a format that can be sent to the server.

[0397] Output: Feedback data to the server.

[0398] Specific operation: The device accepts feedback via an input form and sends it to the server's feedback API.

[0399] Step 9:

[0400] The server uses an emotion engine to perform emotion analysis of the feedback provided by the user.

[0401] Input: User feedback data.

[0402] Data Computation: Perform sentiment analysis using the sentiment engine.

[0403] Output: Positive, negative, or neutral sentiment classification results.

[0404] Specific operation: The server uses a sentiment analysis API (e.g., Microsoft Azure's Text Analytics API) to perform sentiment classification.

[0405] Step 10:

[0406] The device analyzes the user's emotional state in real time and transmits it to the emotion engine.

[0407] Input: Real-time user operation data.

[0408] Data calculation: Analyzes operational data and recognizes real-time emotional states.

[0409] Output: Emotion state data to the emotion engine.

[0410] Specific operation: The device estimates the user's emotional state using facial recognition and operation patterns, and transmits the information to the server in real time.

[0411] Step 11:

[0412] The server personalizes the evaluation results of the novel based on the emotional data obtained from the emotion engine.

[0413] Input: Emotion data from the emotion engine.

[0414] Data calculation: Emotional data is used to individually optimize evaluation results.

[0415] Output: Personalized assessment results.

[0416] Specific operation: The server analyzes the emotion data and adjusts the evaluation results based on the user's emotion patterns.

[0417] Step 12:

[0418] The server accumulates the user's emotional history data and adjusts the novel recommendation algorithm based on past emotional patterns.

[0419] Input: Emotion history data.

[0420] Data calculation: Emotional data is accumulated and used to adjust algorithms.

[0421] Output: The adjusted recommendation algorithm.

[0422] Specific operation: The server stores the emotion history data in a database and optimizes the next recommendation based on past patterns.

[0423] (Application example 2)

[0424] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0425] Conventional novel rating systems rely on fixed evaluation criteria and have the problem of not being able to fully reflect the individual feelings and preferences of users. This makes it difficult to recommend novels that truly interest users and are personalized. Furthermore, because it is not possible to check feelings in real time and update evaluation results accordingly, users' reading experience is uniform, which can lead to a decrease in satisfaction.

[0426] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: [means for receiving and saving novel data;] [means for passing the saved novel data to a text analysis module and analyzing the story structure, character descriptions, writing style, plot progression, etc.;] [means for inputting the analysis results into multiple generative AI models and evaluating the novel based on their respective evaluation criteria;] [means for integrating the evaluation results of each generative AI model and calculating an overall evaluation score;] [means for providing the overall evaluation score and evaluation content;] [means for analyzing the user's emotions in real time and personalizing the evaluation results based on the emotional state; and] [means for accumulating the user's emotional history data and adjusting the evaluation algorithm.] This enables highly accurate personalized evaluation and recommendations based on the user's emotions and preferences.

[0427] "Novel data" refers to data sent by the author or publisher that includes the text of the novel, author information, genre, plot summary, etc.

[0428] The "text analysis module" is a software module for analyzing the narrative structure, character descriptions, writing style, plot progression, etc. of novel data.

[0429] A "generative AI model" is an artificial intelligence model that has multiple different evaluation criteria for evaluating novels based on the results of text analysis.

[0430] "Evaluation results" is a collective term for scores and detailed reviews based on each evaluation criterion applied to the novel data analyzed by the generative AI model.

[0431] The "overall evaluation score" is an overall evaluation score calculated by integrating the evaluation results from multiple generative AI models.

[0432] An "emotion engine" is a software engine that analyzes users' emotions and reflects the results in rating and recommending novels.

[0433] "Personalized ratings" refer to ratings or recommendations that are tailored based on a user's emotional state and preferences.

[0434] "Emotion history data" is data about a user's past emotional patterns, information that is used to adjust future rating algorithms.

[0435] An "interface" is an operation screen or operation means that allows users to upload novel data, view evaluation results, submit feedback, and so on.

[0436] The present invention relates to a system for receiving and storing novel data, a system for analyzing and evaluating novel data, and a method for combining an emotion engine that analyzes user emotions to improve the accuracy and personalization of evaluations.

[0437] Server Roles

[0438] The server has the following functions:

[0439] Data reception and storage

[0440] The server receives novel data sent from authors or publishers via the Internet. This data includes the novel's text, author information, genre, plot summary, etc. The received data is immediately stored in a database.

[0441] Text analytics

[0442] The server passes the saved novel data to the text analysis module, which performs the following analysis:

[0443] Story structure analysis: Analyze the beginning, development, twist, and conclusion of a story, scene transitions, and consistency of the timeline.

[0444] Character description analysis: Analyze the characters' personalities, backgrounds, and relationships with each other.

[0445] Stylistic analysis: Evaluating the rhythm of the writing, vocabulary, grammatical accuracy, etc.

[0446] Plot progression analysis: Evaluating whether the story unfolds logically and coherently.

[0447] AI evaluation

[0448] The server inputs the text analysis results into multiple generative AI models. Each AI model evaluates the analysis results based on its own criteria. For example, one AI model may emphasize story coherence, while another emphasizes character depth. Each AI model generates a specific score and a detailed review based on its own criteria.

[0449] Evaluation Integration

[0450] The server integrates the evaluation results obtained from each generative AI model. At this time, it calculates the average of the evaluations to calculate an overall evaluation score. For example, if the individual AI evaluations are 9.0, 8.5, and 8.0, respectively, the overall evaluation score will be 8.5.

[0451] Emotion Recognition and Real-Time Analysis

[0452] The server uses an emotion engine to perform an emotional analysis of the feedback provided by the user. For example, it automatically classifies feedback into positive, negative, and neutral. Furthermore, the device analyzes the user's emotional state in real time as they read the novel, and transmits the results to the emotion engine. For example, if the user is using a smartphone, their emotions are recognized by utilizing their operation patterns and facial recognition technology.

[0453] Personalized Evaluation

[0454] The server personalizes the evaluation results of novels based on the emotional data obtained from the emotion engine. For example, if a user typically provides many positive reviews, the server will make recommendations that match that emotional pattern. This enables highly accurate personalized evaluations and recommendations based on the user's emotions and preferences.

[0455] Accumulation of emotional history

[0456] The server accumulates users' emotional history data and adjusts the novel recommendation algorithm based on their past emotional patterns, enabling more accurate recommendations in the future.

[0457] Device Role

[0458] The terminal has the following functions:

[0459] Providing an interface

[0460] The terminal provides an interface for users to access and operate, through which users can perform the following operations:

[0461] Uploading novel data

[0462] Viewing evaluation results

[0463] Submitting Feedback

[0464] Displaying the evaluation results

[0465] The terminal visually displays the evaluation results sent from the server to the user, allowing the user to select novels based on evaluation criteria that are closest to their preferences.

[0466] Gathering feedback

[0467] The device collects feedback on the novels that users have read and sends their impressions and evaluations to the server, thereby contributing to improving the accuracy of the AI ​​evaluation.

[0468] emotion recognition

[0469] The terminal uses the input device of the smart device to recognize the user's emotional state in real time and transmits the emotional data to the server.

[0470] Specific examples

[0471] For example, suppose a user purchases a newly released novel through a device and begins reading it. The novel data is uploaded and stored on a server by the author or publisher. The server sends the novel data to a text analysis module, which generates analysis results. The results are then input into multiple generative AI models, which evaluate the novel on factors such as story coherence, character depth, and stylistic clarity. The evaluation results are then combined to calculate an overall evaluation score.

[0472] The evaluation results are provided to the user via their device. Furthermore, while the user is reading the novel, their emotions are analyzed in real time and their emotional state is recorded. The emotion engine uses this real-time data to personalize the evaluation results and make optimal recommendations to the user. After finishing reading, the feedback provided by the user is also analyzed by the emotion engine and sent to the server.

[0473] Example prompts to input to the generative AI model

[0474] 1. If the user expresses positive sentiment:

[0475] "How entertaining is this paragraph if it makes the user smile?"

[0476] 2. If the user expresses negative sentiment:

[0477] "If users frowned, what was their criticism of the work?"

[0478] Through this series of processes, the present invention can efficiently evaluate high-quality works from a wide variety of novels and make optimal recommendations based on the user's emotional state. Furthermore, by continuously improving the evaluation algorithm based on collected emotional data, it will be possible to provide a more accurate novel evaluation system in the future.

[0479] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0480] Step 1:

[0481] The server receives novel data from authors or publishers via the Internet and stores the data in a database. Specifically, when a user sends novel data, the server receives the data, extracts metadata such as the text, author information, genre, and plot, and stores the data in a database. The input is the novel data, and the output is the stored novel data.

[0482] Step 2:

[0483] The server sends the saved novel data to the text analysis module. The text analysis module performs the following analyses: story structure analysis, character description analysis, writing style analysis, and plot progression analysis. The data obtained from these analyses becomes the respective analysis results. The input is the saved novel data, and the output is each analysis result.

[0484] Step 3:

[0485] The server inputs the text analysis results into multiple generative AI models. Each AI model evaluates the analysis results based on its own evaluation criteria and generates a specific score and detailed review. The input is each analysis result, and the output is the evaluation score and review.

[0486] Step 4:

[0487] The server integrates the evaluation results obtained from each generative AI model and calculates an overall evaluation score. At this time, it calculates the average of the evaluations to calculate the overall evaluation score. For example, if the AI ​​evaluations are 9.0, 8.5, and 8.0 respectively, the overall evaluation score will be 8.5. The input is each evaluation result, and the output is the overall evaluation score.

[0488] Step 5:

[0489] The server notifies the author or publisher of the calculated overall evaluation score and detailed evaluation results. It also automatically generates new catchphrases, introductions, and obi text based on the evaluation results and provides them to the author or publisher. The input is the overall evaluation score and each evaluation result, and the output is the notification and the generated text.

[0490] Step 6:

[0491] The terminal provides an interface for users to upload novel data. When a user uploads novel data, the terminal sends the data to the server. The input is the novel data entered by the user, and the output is the novel data sent to the server.

[0492] Step 7:

[0493] The terminal visually displays the evaluation results sent from the server to the user, allowing the user to select novels based on evaluation criteria that best suit their preferences. The input is the evaluation results from the server, and the output is the displayed evaluation results.

[0494] Step 8:

[0495] As the user reads the novel, the device uses the smartphone's camera and microphone to recognize the user's emotional state in real time and transmits the emotional data to the server. The input is data from the emotion recognition device (camera and microphone), and the output is the emotional data transmitted to the server.

[0496] Step 9:

[0497] The server uses an emotion engine to analyze the user's emotional data and personalize the evaluation results in real time. If the user expresses positive emotions, the evaluation results are adjusted to lean more positively. The input is the user's real-time emotional data, and the output is the personalized evaluation results.

[0498] Step 10:

[0499] Based on the emotion data obtained from the emotion engine and the user's past emotion history data, the server adjusts the novel recommendation algorithm and recommends the most suitable novel for the user. The input is the emotion history data and real-time emotion data, and the output is the adjusted recommendation algorithm and the recommended novel.

[0500] The above processing steps enable highly accurate personalized evaluation and recommendations based on the user's emotions and preferences.

[0501] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0502] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0503] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0504] [Second embodiment]

[0505] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0506] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0507] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0508] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0509] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0510] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0511] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0512] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0513] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0514] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0515] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0516] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0517] server

[0518] 1. Data Receipt and Storage

[0519] The server receives novel data sent via the Internet from authors or publishers. This data includes the text of the novel, author information, genre, plot summary, etc. The received data is immediately stored in a database.

[0520] 2. Text Analysis

[0521] The server sends the stored novel data to the text analysis module, which performs the following analysis:

[0522] Story structure analysis: Analyzes the beginning, development, twist, and conclusion of a story, scene transitions, and consistency of the timeline.

[0523] Character description analysis: Analyze the characters' personalities, backgrounds, and relationships with each other.

[0524] Stylistic analysis: Evaluating the rhythm of the writing, vocabulary, grammatical accuracy, etc.

[0525] Plot progression analysis: Evaluating whether the story unfolds logically and coherently.

[0526] 3. AI Evaluation

[0527] The server inputs the text analysis results into multiple generative AI models. Each AI model evaluates the analysis results based on its own criteria. For example, one AI model may emphasize story coherence, while another emphasizes character depth. Each AI model generates a specific score and a detailed review based on its own criteria.

[0528] 4. Evaluation Integration

[0529] The server integrates the evaluation results obtained from multiple generative AI models. At this time, it calculates the average of the evaluations to calculate an overall evaluation score. For example, if the individual AI evaluations are 9.0, 8.5, and 8.0, respectively, the overall evaluation score will be 8.5.

[0530] 5. Providing results

[0531] The server then notifies the author or publisher of the calculated overall score and detailed evaluation results. This information may be used as marketing material, and is also used to generate new taglines, introductions, and obi text. The generated text is then provided to the author or publisher, who can revise it as needed.

[0532] Terminal

[0533] 1. Providing an interface

[0534] The terminal provides an interface for users to access and operate. Through this interface, users can:

[0535] Uploading novel data

[0536] Viewing evaluation results

[0537] Submitting Feedback

[0538] 2. Display of evaluation results

[0539] The evaluation results sent from the server are visually displayed on the device, allowing users to select an appropriate novel based on this. Individual evaluation results from each AI model are also displayed, allowing users to use this information to help them select evaluation criteria that best suit their preferences.

[0540] 3. Gathering Feedback

[0541] After reading a novel, readers submit their ratings and impressions through a feedback form. This feedback is sent to the server and used to improve the evaluation algorithm of the generative AI model.

[0542] User

[0543] 1. Uploading a Novel

[0544] Authors or publishers upload novel data through the device's interface, which is then sent to the server and stored.

[0545] 2. Viewing the evaluation results

[0546] Authors and publishers can check the evaluation results sent from the server on their devices, allowing them to understand how their work has been evaluated and identify areas for improvement.

[0547] 3. Providing Feedback

[0548] After finishing a novel, readers can provide feedback via their devices, which will help the AI ​​make a more accurate assessment.

[0549] Specific examples

[0550] For example, when a well-known author writes a new novel and uploads it to the system through a publisher, the novel data is first received and stored on the server. It is then analyzed by a text analysis module, which performs a detailed analysis of the story structure, character descriptions, writing style, etc. The analysis results are input into multiple generative AI models, each of which evaluates the novel based on its own evaluation criteria. As a result, an overall evaluation score is calculated, and the evaluation results are notified to the author and publisher. Based on this evaluation result, new catchphrases and introductions are automatically generated and used in promotional activities. Readers can use the evaluation results as a reference when selecting a novel, and provide feedback after reading, contributing to improving the accuracy of the AI ​​evaluation.

[0551] In this way, the present invention realizes an environment in which hidden masterpieces can be easily discovered by efficiently evaluating high-quality works and providing them to readers amidst the proliferation of novels.

[0552] The processing flow will be explained below.

[0553] Step 1:

[0554] The server receives novel data sent via the Internet from authors or publishers. This data includes the text of the novel, author information, genre, plot summary, etc. The received data is immediately stored in a database.

[0555] Step 2:

[0556] The server sends the saved novel data to the text analysis module, which performs grammatical analysis, sentiment analysis, keyword extraction, etc. of the novel, and generates and returns the analysis results to the server.

[0557] Step 3:

[0558] The server inputs the results of the text analysis into multiple generative AI models. Each AI model evaluates the novel data based on criteria such as story coherence, character depth, and stylistic clarity. Each AI model generates a rating score and a detailed review.

[0559] Step 4:

[0560] The server integrates the evaluation results from each generative AI model. At this time, it calculates the average of each evaluation to calculate an overall evaluation score. For example, if AI model A evaluates 8.0, AI model B evaluates 7.0, and AI model C evaluates 9.0, the average is calculated and the overall evaluation score is 8.0.

[0561] Step 5:

[0562] The server notifies the author or publisher of the calculated overall evaluation score and detailed evaluation results. The notification also includes the individual evaluation results of each AI model and the evaluation criteria. Based on the evaluation results, the server automatically generates new catchphrases, introductions, and obi text and provides them to the author or publisher.

[0563] Step 6:

[0564] The terminal provides an interface for users (authors, publishers, and readers) to access and operate, through which users can upload novel data, view evaluation results, and submit feedback.

[0565] Step 7:

[0566] The device visually displays the evaluation results sent from the server to the user. It displays not only the overall evaluation score but also the detailed evaluation results from each AI model. This allows the user to select novels based on evaluation criteria that best suit their preferences.

[0567] Step 8:

[0568] The device collects feedback from readers about the novels they have read, and sends the information submitted through a feedback form to a server, which then reflects the collected feedback in the generative AI model, thereby contributing to improving the accuracy of the evaluation algorithm.

[0569] Step 9:

[0570] Users (authors, publishers, and readers) can use the device to check the new catchphrases and introductions, decide whether they are appropriate, and, if necessary, revise the automatically generated text to use as the final marketing material.

[0571] Step 10:

[0572] The server analyzes the collected feedback and uses it to improve the evaluation criteria of the generative AI model, which will improve the accuracy of future novel evaluations and enable better recommendations.

[0573] Example 1

[0574] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0575] Conventional literary evaluation systems often lack uniformity and fairness in their evaluations, and do not evaluate works from a variety of perspectives, making it difficult to determine their true value. Furthermore, there is no efficient way to collect feedback from many users, resulting in a lack of reference information for revising and releasing works.

[0576] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0577] In this invention, the server includes means for receiving and saving literary data, means for passing the saved literary data to a natural language analysis module to analyze the narrative structure, character traits, writing style, and story progression, means for inputting the analysis results into a plurality of AI models to evaluate the literary work based on their respective evaluation criteria, means for integrating the evaluation results of each AI model to calculate an overall evaluation score, and means for providing the overall evaluation score and the evaluation content, thereby enabling high-quality literary evaluation and detailed feedback from a variety of perspectives.

[0578] "Literary data" refers to data that includes information such as the text of a work, author information, genre, and plot.

[0579] A "natural language analysis module" is a program that analyzes text data and evaluates the structure of the story, the characteristics of the characters, the writing style, the progression of the story, etc.

[0580] A "generative artificial intelligence model" is an artificial intelligence program that evaluates text data according to specific evaluation criteria based on previously learned data.

[0581] The "overall evaluation score" is a numerical value that indicates the overall evaluation by integrating the individual evaluation results obtained from multiple generating artificial intelligence models.

[0582] "Upload Interface" is a platform through which users can submit literary data to the system.

[0583] The "visual display means" is a mechanism for displaying the evaluation results to the user as graphs or text.

[0584] The "feedback collection means" is a means for receiving evaluations and impressions from users and transmitting them to the server.

[0585] A "catchphrase" is a short, catchy phrase used to introduce a work to the market.

[0586] An "introduction" is a short sentence that explains the outline and characteristics of the work.

[0587] "Obi text" refers to short sentences or catchphrases printed on the book's obi, and serves to stimulate purchasing desire.

[0588] server

[0589] 1. Data Receipt and Storage

[0590] The server receives literary data sent by connected authors or publishers via the Internet. This data includes the text of the work, author information, genre, plot summary, etc. The received data is immediately stored in the database. For example, when an author uploads a new work, the data is sent to the server and stored.

[0591] 2. Text Analysis

[0592] The server sends the stored literary data to a natural language analysis module, which analyzes the narrative structure, character traits, writing style, and story progression. For example, it analyzes the beginning, development, climax, and conclusion of a story and detects how each part is structured.

[0593] 3. AI Evaluation

[0594] The server then feeds the analysis results into multiple artificial intelligence models, which evaluate literary works based on their own criteria: for example, one AI model focuses on story coherence, while another evaluates character portrayals.

[0595] 4. Evaluation Integration

[0596] The server integrates the evaluation results obtained from each AI model and calculates an overall evaluation score. For example, if model A is evaluated as 8.5, model B as 9.0, and model C as 8.0, the server calculates the average of these scores and uses this as the overall evaluation score.

[0597] 5. Providing results

[0598] The server then notifies the author or publisher of the calculated overall score and detailed evaluation. This information is used as marketing material and is also utilized to generate new catchphrases, descriptions, and obi text. For example, the server may notify the author or publisher of the evaluation result, saying, "This work has been evaluated for its story consistency, with an overall score of 8.5."

[0599] Terminal

[0600] 1. Providing an interface

[0601] The terminal provides an interface for users to access and operate, through which users can upload literary data, view evaluation results, and provide feedback. For example, a user can submit a work using a form for uploading a novel.

[0602] 2. Display of evaluation results

[0603] The evaluation results sent from the server are visually displayed on the device, allowing users to select an appropriate novel based on this information. Individual evaluation results from each generated AI model are also displayed, helping users choose evaluation criteria that best suit their preferences. For example, the dashboard displays the overall evaluation score and detailed evaluation results in graphs and text.

[0604] 3. Gathering Feedback

[0605] After a reader finishes reading a novel, they submit their rating and thoughts through a feedback form. This feedback is sent to the server and used to improve the evaluation algorithm of the AI ​​model that generates it. For example, reader comments such as "The story development was fascinating" are collected.

[0606] User

[0607] 1. Uploading a Novel

[0608] Authors or publishers upload literary data through the device interface. The uploaded data is sent to the server and stored. For example, when uploading a new novel, they enter the necessary information and press the submit button, and the data is stored on the server.

[0609] 2. Viewing the evaluation results

[0610] Authors and publishers can check the evaluation results sent from the server on their devices. This allows them to understand how their work has been evaluated and identify areas for improvement. For example, they can check the evaluation score and detailed feedback on a dashboard.

[0611] 3. Providing Feedback

[0612] After finishing a novel, readers can provide feedback via their devices, which will help the AI ​​model to generate a more accurate evaluation. For example, after finishing a novel, readers can fill out a feedback form and press the submit button, which will send the feedback to the server.

[0613] Specific prompt examples

[0614] "Please enter the text of the novel."

[0615] Analyze the characters' personalities

[0616] "Evaluate the coherence of the story."

[0617] This makes it possible to efficiently evaluate high-quality works from among many literary works and provide them to readers, creating an environment in which hidden masterpieces can be easily discovered.

[0618] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0619] Step 1: Receiving and storing data

[0620] The server receives literary data sent by connected authors or publishers via the Internet. The input includes data such as the novel text, author information, genre, and plot summary. The server verifies that the data has been received correctly, and if successful, it is stored in a database. For example, when a new work is uploaded, all of its data arrives at the server and is immediately stored in the database.

[0621] Step 2: Text analysis

[0622] The server sends the stored literary data to a natural language analysis module. The literary data is used as input. The natural language analysis module analyzes the structure of the story (beginning, development, climax, conclusion, etc.), the characteristics of the characters (personalities, background, etc.), the writing style (rhythm, vocabulary, etc.), and the progression of the story (consistency of the timeline, etc.), and outputs the results of these analyses. For example, it identifies and analyzes the beginning, middle, climax, and conclusion of a story.

[0623] Step 3: AI evaluation

[0624] The server inputs the analysis results into multiple AI models. The text analysis results are used as input. The AI ​​models evaluate literary works based on their respective evaluation criteria (e.g., story coherence, character depth, etc.). Each AI model outputs a specific score and a detailed review. For example, an AI model that emphasizes story coherence will evaluate the work based on that criteria and output its results.

[0625] Step 4: Consolidating the assessments

[0626] The server integrates the evaluation results obtained from each generated AI model. Evaluation results from multiple AI models are used as input. The server calculates the average of these evaluation results and outputs an overall evaluation score. For example, if the evaluation scores are 9.0, 8.5, and 8.0, the average of these, 9.0, is calculated as the overall evaluation score.

[0627] Step 5: Delivering results

[0628] The server notifies the author or publisher of the calculated overall rating score and detailed rating content. The overall rating score and detailed rating content are used as input. The rating result is notified to the author or publisher as output. For example, a notification may be sent saying, "This work has an overall rating score of 8.5."

[0629] Step 6: Providing an Interface

[0630] The terminal provides an interface for users to access and operate. User operations are used as input. The terminal provides and outputs a form for users to upload literary data and a dashboard for viewing evaluation results. For example, when a user clicks the upload button, the following page is displayed.

[0631] Step 7: View the evaluation results

[0632] The terminal visually displays the evaluation results sent from the server. The evaluation results from the server are used as input. The evaluation results are output in graph and text format on the dashboard, helping users to select the appropriate novel. For example, the terminal displays the overall evaluation score and detailed evaluations by each AI model.

[0633] Step 8: Gather feedback

[0634] The terminal provides a means for the reader user to submit their evaluation and thoughts through a feedback form after finishing reading the novel. The user's feedback is used as input. The submitted feedback is sent to the server and used to improve the evaluation algorithm of the generated artificial intelligence model. For example, a comment such as "The story development was very satisfying" can be entered and submitted in the feedback form.

[0635] Through these steps, this system is able to evaluate literary works from multiple perspectives and provide readers with high-quality works.

[0636] (Application example 1)

[0637] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0638] This invention relates to a system that efficiently evaluates high-quality works amidst the proliferation of novels and provides them to readers. Conventional evaluation methods make it difficult for authors and publishers to quickly and accurately grasp the quality of works, and readers lack the information necessary to select appropriate works. Furthermore, the collection and utilization of feedback is inefficient, resulting in a lack of consistency in the evaluation of works. It is necessary to solve these issues and improve the process of evaluating and providing novels.

[0639] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0640] In this invention, the server includes: [means for receiving and saving novel data; [means for passing the saved novel data to a text analysis module and having it analyze the story structure, character descriptions, writing style, plot progression, etc.; and [means for inputting the analysis results into multiple generative AI models and having them evaluate the novel based on their respective evaluation criteria.] This makes it possible [to integrate the evaluation results of each generative AI model, calculate an overall evaluation score, and provide the overall evaluation score and evaluation content].

[0641] "Novel data" refers to data such as the text of a novel, author information, genre, and plot summary provided by the author or publisher.

[0642] A "text analysis module" is software or hardware used to analyze novel data and evaluate the story structure, character descriptions, writing style, plot progression, etc.

[0643] A "generative AI model" is an artificial intelligence model that evaluates novels based on the results of analyzing novel data and each evaluation criterion.

[0644] The "overall evaluation score" is a number calculated by combining the evaluation results from multiple generative AI models, and is used to comprehensively evaluate the quality of the entire novel.

[0645] A "smartphone application" is software that runs on a smartphone and provides functions such as uploading novel data, displaying evaluation results, and collecting feedback.

[0646] "Feedback" refers to the impressions and evaluations that readers provide after finishing a novel, and is information that is sent to the server and contributes to improving the accuracy of the generative AI model.

[0647] The "interface" is the UI (user interface) that users can operate, allowing them to upload novel data, view evaluation results, and submit feedback.

[0648] A "catchphrase" is a short phrase used in marketing and promotional activities to effectively convey the appeal of a novel.

[0649] An "introduction" is a text that explains the content and characteristics of a novel and is used to convey an overview of the work to customers.

[0650] "Book cover text" refers to advertising slogans or catch phrases printed on a piece of paper attached to the outside of a book's cover, intended to motivate customers to purchase the book.

[0651] In this invention, the server receives, stores, analyzes, evaluates, and provides results of novel data using the following means.

[0652] server

[0653] 1. Data Receipt and Storage

[0654] The server receives novel data sent via the Internet from authors or publishers. This data includes the text of the novel, author information, genre, plot summary, etc. The received data is immediately stored in a database.

[0655] 2. Text Analysis

[0656] The server sends the saved novel data to the text analysis module, which uses a Python natural language processing library (e.g., NLTK or spaCy). The text analysis module performs the following analysis:

[0657] Story structure analysis: Analyzes the beginning, development, twist, and conclusion of a story, scene transitions, and consistency of the timeline.

[0658] Character description analysis: Analyze the characters' personalities, backgrounds, and relationships with each other.

[0659] Stylistic analysis: Evaluating the rhythm of the writing, vocabulary, grammatical accuracy, etc.

[0660] Plot progression analysis: Evaluating whether the story unfolds logically and coherently.

[0661] 3. AI Evaluation

[0662] The server inputs the text analysis results into multiple generative AI models. Each generative AI model evaluates the analysis results based on its own evaluation criteria. Examples of AI models used include OpenAI's GPT-3. Each AI model generates a specific score and a detailed review based on its own evaluation criteria.

[0663] 4. Evaluation Integration

[0664] The server integrates the evaluation results obtained from multiple generative AI models, calculating the average of the evaluations and deriving an overall evaluation score.

[0665] 5. Providing results

[0666] The server then notifies the author or publisher of the calculated overall score and detailed evaluation results. This information is used as marketing material and is also used to generate new taglines, introductions, and obi text. The generated text is then provided to the author or publisher, who can revise it as needed.

[0667] Terminal

[0668] 1. Providing an interface

[0669] The terminal provides an interface for users to access and operate. Through this interface, users can:

[0670] Uploading novel data

[0671] Viewing evaluation results

[0672] Submitting Feedback

[0673] 2. Display of evaluation results

[0674] The evaluation results sent from the server are visually displayed on the device, allowing users to select an appropriate novel based on this. Individual evaluation results from each AI model are also displayed, allowing users to use this information to help them select evaluation criteria that best suit their preferences.

[0675] 3. Gathering Feedback

[0676] After reading a novel, readers submit their ratings and impressions through a feedback form. This feedback is sent to the server and used to improve the evaluation algorithm of the generative AI model.

[0677] User

[0678] 1. Uploading a Novel

[0679] Authors or publishers upload novel data through the device's interface, which is then sent to the server and stored.

[0680] 2. Viewing the evaluation results

[0681] Authors and publishers can check the evaluation results sent from the server on their devices, allowing them to understand how their work has been evaluated and identify areas for improvement.

[0682] 3. Providing Feedback

[0683] After finishing a novel, readers provide feedback through their devices, which helps the AI ​​to more accurately evaluate it.

[0684] Specific examples

[0685] For example, when an author writes a new novel and uploads it to the system via their device, the novel data is first received and stored on the server. The text analysis module then analyzes the story structure, character descriptions, writing style, and other aspects, and the analysis results are input into multiple generative AI models. The evaluation results are then integrated to calculate an overall evaluation score. The author and publisher are notified of this evaluation result, and a new catchphrase and introduction are automatically generated based on it.

[0686] Prompt Sentence Examples

[0687] Please rate the following novel data in terms of plot coherence, character depth, stylistic rhythm, etc.

[0688] Novel Title: New Novel

[0689] Author: Famous Author

[0690] Genre: Fantasy

[0691] Synopsis: This is a sample story

[0692] Novel content: The main text of the novel...

[0693] Please provide your evaluation in the following format:

[0694] 1. Overall evaluation score

[0695] 2. Detailed evaluation of story coherence

[0696] 3. Detailed evaluation of character depth

[0697] 4. Detailed evaluation of stylistic rhythm

[0698] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0699] Step 1:

[0700] The device receives novel data from the author or publisher. The novel data includes the text, author information, genre, and synopsis. The device uses this data as input and sends an HTTP POST request to the server. This sends the novel data to the server and stores it in a database.

[0701] Step 2:

[0702] The server sends the saved novel data to the text analysis module, which uses a Python natural language processing library (such as NLTK or spaCy). Here, the following data processing is performed and the analysis results are output:

[0703] Story structure analysis (beginning, development, twist, conclusion, scene transitions, etc.)

[0704] Character description analysis (personality, background, relationships, etc.)

[0705] Stylistic analysis (rhythm, vocabulary, grammatical accuracy, etc.)

[0706] Plot progression analysis (logic of development, consistency, etc.)

[0707] Step 3:

[0708] The server inputs the text analysis results into multiple generative AI models, such as OpenAI's GPT-3. Each generative AI model performs the following data calculations and outputs an individual rating score and detailed review:

[0709] Story consistency

[0710] Character depth

[0711] Stylistic rhythm and variety

[0712] Overall rating score

[0713] Step 4:

[0714] The server integrates the evaluation results obtained from multiple generative AI models. Specifically, it calculates the average of the evaluation scores of each model and outputs an overall evaluation score. It also integrates detailed evaluation reviews to generate a single evaluation report. These results are stored in the server database.

[0715] Step 5:

[0716] The server outputs the evaluation results—namely, the overall evaluation score and a detailed evaluation report—in JSON format via an API endpoint to provide them to the user's device, where the user (author or publisher) can visually check these evaluation results.

[0717] Step 6:

[0718] The terminal provides a GUI (Graphical User Interface) to visually display the evaluation results. Users can view the evaluation scores and detailed evaluation reviews through this interface, which allows them to deepen their understanding of their work and identify areas for improvement.

[0719] Step 7:

[0720] After finishing reading a novel, users (readers) provide their ratings and impressions using a feedback form. The device sends this feedback to the server and stores it as data used to improve the evaluation algorithm of the generative AI model.

[0721] Prompt Sentence Examples

[0722] Please rate the following novel data in terms of plot coherence, character depth, stylistic rhythm, etc.

[0723] Novel Title: New Novel

[0724] Author: Famous Author

[0725] Genre: Fantasy

[0726] Synopsis: This is a sample story

[0727] Novel content: The main text of the novel...

[0728] Please provide your evaluation in the following format:

[0729] 1. Overall evaluation score

[0730] 2. Detailed evaluation of story coherence

[0731] 3. Detailed evaluation of character depth

[0732] 4. Detailed evaluation of stylistic rhythm

[0733] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0734] The present invention relates to a system for receiving and storing novel data, a system for analyzing and rating novel data, and a method for improving the accuracy and personalization of novel ratings by combining an emotion engine that analyzes user emotions.

[0735] server

[0736] 1. Data Receipt and Storage

[0737] The server receives novel data sent via the Internet from authors or publishers. This data includes the text of the novel, author information, genre, plot summary, etc. The received data is immediately stored in a database.

[0738] 2. Text Analysis

[0739] The server sends the stored novel data to the text analysis module, which performs the following analysis:

[0740] Story structure analysis: Analyzes the beginning, development, twist, and conclusion of a story, scene transitions, and consistency of the timeline.

[0741] Character description analysis: Analyze the characters' personalities, backgrounds, and relationships with each other.

[0742] Stylistic analysis: Evaluating the rhythm of the writing, vocabulary, grammatical accuracy, etc.

[0743] Plot progression analysis: Evaluating whether the story unfolds logically and coherently.

[0744] 3. AI Evaluation

[0745] The server inputs the text analysis results into multiple generative AI models. Each AI model evaluates the analysis results based on its own criteria. For example, one AI model may emphasize story coherence, while another emphasizes character depth. Each AI model generates a specific score and a detailed review based on its own criteria.

[0746] 4. Evaluation Integration

[0747] The server integrates the evaluation results obtained from each generative AI model. At this time, it calculates the average of the evaluations to calculate an overall evaluation score. For example, if the individual AI evaluations are 9.0, 8.5, and 8.0, respectively, the overall evaluation score will be 8.5.

[0748] 5. Providing results

[0749] The server notifies the author or publisher of the calculated overall evaluation score and detailed evaluation results. It also automatically generates new catchphrases, introductions, and obi text based on the evaluation results and provides them to the author or publisher.

[0750] Terminal

[0751] 1. Providing an interface

[0752] The terminal provides an interface for users to access and operate. Through this interface, users can:

[0753] Uploading novel data

[0754] Viewing evaluation results

[0755] Submitting Feedback

[0756] 2. Display of evaluation results

[0757] The terminal visually displays the evaluation results sent from the server to the user, allowing the user to select novels based on evaluation criteria that are closest to their preferences.

[0758] 3. Gathering Feedback

[0759] The device collects feedback on the novels that users have read and sends their impressions and evaluations to the server, thereby contributing to improving the accuracy of the AI ​​evaluation.

[0760] Introducing the Emotion Engine

[0761] 1. Emotion recognition

[0762] The server uses an emotion engine to perform sentiment analysis of the feedback provided by the user, for example, automatically classifying it as positive, negative, or neutral.

[0763] 2. Real-time analysis

[0764] The device analyzes the user's emotional state in real time as they read the novel, and sends the results to the emotion engine. For example, if the user is using a smartphone or tablet, the device recognizes their emotions by utilizing their operation patterns and facial recognition technology.

[0765] 3. Personalized evaluation

[0766] The server personalizes the novel evaluation results based on the emotional data obtained from the emotion engine. For example, if a user typically provides many positive reviews, the server will make recommendations that match that emotional pattern.

[0767] 4. Accumulation of emotional history

[0768] The server accumulates users' emotional history data and adjusts the novel recommendation algorithm based on their past emotional patterns, enabling more accurate recommendations in the future.

[0769] Specific examples

[0770] For example, suppose a user purchases a newly released novel through a device and begins reading it. The novel data is uploaded and stored on a server by the author or publisher. The server sends the novel data to a text analysis module, which generates analysis results. The results are then input into multiple generative AI models, which evaluate the novel on factors such as story coherence, character depth, and stylistic clarity. The evaluation results are then combined to calculate an overall evaluation score.

[0771] The evaluation results are provided to the user via their device. Furthermore, while the user is reading the novel, their emotions are analyzed in real time and their emotional state is recorded. The emotion engine uses this real-time data to personalize the evaluation results and make optimal recommendations to the user. After finishing reading, the feedback provided by the user is also analyzed by the emotion engine and sent to the server.

[0772] Through this series of processes, the present invention can efficiently evaluate high-quality works from a wide variety of novels and make optimal recommendations based on the user's emotional state. Furthermore, by continuously improving the evaluation algorithm based on collected emotional data, it will be possible to provide a more accurate novel evaluation system in the future.

[0773] The processing flow will be explained below.

[0774] server

[0775] Step 1:

[0776] The server receives novel data uploaded by authors or publishers. The novel data includes information such as the text, author information, genre, and plot. After receiving the data, it stores it in a database.

[0777] Step 2:

[0778] The server sends the saved novel data to the text analysis module, which performs story structure analysis, character portrayal analysis, stylistic analysis, and plot progression analysis to generate analysis results, which are then sent back to the server.

[0779] Step 3:

[0780] The server inputs the results of the text analysis into multiple generative AI models. Each generative AI model analyzes the novel data based on criteria such as story coherence, character depth, and stylistic beauty. Each AI model generates a specific evaluation score and a detailed review.

[0781] Step 4:

[0782] The server combines the evaluation results returned by each generative AI model. It calculates the average of each evaluation and calculates the overall evaluation score. For example, if AI model A evaluates the score as 8.0, AI model B as 7.5, and AI model C as 9.0, the overall evaluation score will be 8.2.

[0783] Step 5:

[0784] The server notifies the author or publisher of the overall evaluation score and detailed evaluation results. It also automatically generates new catchphrases, introductions, and obi text based on the evaluation results and notifies the author or publisher of these texts.

[0785] Terminal

[0786] Step 6:

[0787] The terminal provides an interface for users to access and operate, through which users can upload novel data, view evaluation results, and submit feedback.

[0788] Step 7:

[0789] The device visually displays the evaluation results sent from the server to the user. Not only the overall evaluation score but also the detailed evaluation results from each generative AI model are displayed. This allows the user to select novels based on evaluation criteria that best suit their preferences.

[0790] Step 8:

[0791] The device collects feedback on the novels the user has read, which is then sent to a server, which uses this information to improve the evaluation algorithm of the generative AI model.

[0792] Introducing the Emotion Engine

[0793] Step 9:

[0794] The server performs sentiment analysis of the feedback provided by the user using an emotion engine, which categorizes the feedback into positive, negative, and neutral categories and sends the analysis results back to the server.

[0795] Step 10:

[0796] The device analyzes the user's emotional state in real time as they read the novel and sends the results to the emotion engine. For example, if the user is using a smartphone or tablet, the device uses their operation patterns and facial recognition technology to recognize their emotions.

[0797] Step 11:

[0798] The server personalizes the novel evaluation results based on real-time emotional data obtained from the emotion engine, and recommends novels that are optimal for the user's emotional state. For example, if the user is feeling sad, it will recommend novels that will soothe the emotions.

[0799] Step 12:

[0800] The server will accumulate the user's emotional history and adjust the novel recommendation algorithm based on past emotional patterns, which will enable more accurate novel evaluation and recommendation in the future.

[0801] Specific examples

[0802] For example, an author of a new novel uploads the novel data to the system through a publisher. The server receives and stores the data. The novel data is then sent to the text analysis module for detailed analysis. Based on the analysis results, each generative AI model evaluates the novel according to its own evaluation criteria. The evaluation results are then integrated to calculate an overall evaluation score.

[0803] The evaluation results are provided to the user via their device. As the user reads the novel, the emotion engine analyzes the user's emotions in real time and sends the data to the server. Personalized evaluation results and recommendations are made based on the user's emotional state, and feedback after reading is also analyzed by the emotion engine.

[0804] The data collected in this way will continuously improve the evaluation algorithms of the generative AI model, ensuring that users always have the best possible novels to choose from, as well as ensuring that authors and publishers have their work properly evaluated.

[0805] Example 2

[0806] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0807] Conventional novel evaluation systems have limited means for objectively evaluating the quality of novels, making it difficult to provide personalized recommendations that take the user's emotional state into account. Furthermore, they lack the means to appropriately utilize user feedback and improve the overall evaluation accuracy of the system. Therefore, a new system is needed that can effectively achieve high-quality novel evaluations and personalized recommendations that reflect the user's emotional state.

[0808] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0809] In this invention, the server includes means for receiving and saving novel data, means for passing the saved novel data to a text analysis module to analyze the story structure, character descriptions, writing style, plot progression, etc., means for inputting the analysis results into multiple generative AI models and evaluating the novel based on their respective evaluation criteria, means for integrating the evaluation results of each generative AI model to calculate an overall evaluation score, means for providing the overall evaluation score and evaluation details, means for analyzing feedback provided by the user with an emotion engine and personalizing the novel evaluation results based on the emotion data, and means for accumulating the user's emotion history and adjusting the novel recommendation algorithm based on past emotion patterns. This enables high-quality novel evaluations and personalized recommendations according to the user's emotional state.

[0810] "Novel data" is digital data that includes the text of the novel, author information, genre, plot summary, etc.

[0811] The "text analysis module" is a software module that analyzes novel data to evaluate the story structure, character descriptions, writing style, plot progression, etc.

[0812] A "generative AI model" is an artificial intelligence model used to evaluate novels based on analysis results. Specifically, it refers to a model that utilizes natural language processing technology.

[0813] The "evaluation criteria" are items that serve as indicators for evaluating a novel, such as the consistency of the story, the depth of the characters, and the clarity of the writing style.

[0814] The "overall evaluation score" is a number that indicates the overall evaluation of a novel, calculated by combining the evaluation results obtained from multiple generative AI models.

[0815] The "emotion engine" is a software engine that analyzes emotions based on user-provided feedback and real-time operational data.

[0816] "Personalization" refers to providing an optimized experience for a user by adjusting the system's behavior and recommendations based on the user's individual attributes and emotional state.

[0817] "Emotion history" is data that records and accumulates a user's past emotional data. This data will improve the accuracy of the recommendation algorithm from the next time onwards.

[0818] "Interface" refers to the means of providing a screen and a set of functions for users to operate a system.

[0819] "Feedback" refers to the user's impressions and evaluations of the novels they have read. It is used to improve the accuracy of the system's evaluations.

[0820] The present invention relates to a system for receiving and storing novel data, a system for analyzing and rating novel data, and a method for improving the accuracy and personalization of novel ratings by combining an emotion engine for analyzing user emotions.

[0821] server

[0822] The server receives novel data sent over the internet from authors or publishers. This data includes the novel's text, author information, genre, and synopsis. The received data is immediately stored in a database. The server uses libraries such as NLTK (Natural Language Toolkit) and SpaCy, which use the Python language, to send the novel data to a text analysis module for analysis. This analyzes the story structure, character descriptions, writing style, and plot progression. The text analysis results are input into multiple generative AI models, which evaluate the story's coherence and character depth. This is done using prompts such as, "Please rate the story coherence and character depth of this newly released novel." The evaluation results from each generative AI model are combined to calculate an overall evaluation score. The calculated overall evaluation score and detailed evaluation results are then notified to the author or publisher. Automatically generated taglines, introductions, and obi text are also provided.

[0823] Terminal

[0824] The terminal provides an interface for users to access and operate the system. This includes uploading novel data, viewing evaluation results, and submitting feedback through a web browser or dedicated application. The evaluation results sent from the server are visually displayed to the user via the terminal. As the user reads the novel, their emotions are analyzed in real time and sent to the emotion engine. This allows emotions to be recognized using the user's operation patterns and facial recognition technology when using a smartphone or tablet. Feedback and impressions provided by the user are also sent from the terminal to the server.

[0825] Emotion Engine

[0826] The emotion engine performs sentiment analysis on feedback provided by users and categorizes them as positive, negative, or neutral. It uses sentiment analysis APIs such as Microsoft Azure's Text Analytics API. It analyzes the user's emotional state in real time and personalizes the novel evaluation results based on this. For example, if a user has a lot of positive comments, it will recommend novels based on those emotions. Emotion data is stored on the server, and the novel recommendation algorithm is adjusted based on past emotional patterns.

[0827] Specific examples

[0828] For example, a user purchases a newly released novel through a device and begins reading it. This novel data is uploaded and stored on a server by the author or publisher. The server then sends the novel data to a text analysis module, which evaluates the story's coherence, character depth, and writing style. The analysis results are input into multiple generative AI models, which then perform an evaluation. The evaluation results are integrated to calculate an overall evaluation score. This score and detailed evaluation results are provided to the user through the device. Furthermore, emotions are analyzed in real time as the user reads the novel, and the user's emotional state is recorded. The emotion engine then personalizes the evaluation results based on this real-time data and makes optimal recommendations to the user. After reading, feedback provided by the user is also analyzed by the emotion engine and sent to the server. Through this series of processes, the present invention can achieve high-quality novel evaluations and personalized recommendations based on the user's emotional state.

[0829] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0830] Step 1:

[0831] The server receives novel data sent from an author or a publisher via the Internet.

[0832] Input: Digital data including the text of the novel, author information, genre, plot summary, etc.

[0833] Data processing: Decodes the received data and converts it into the appropriate format.

[0834] Output: Decoded novel data.

[0835] Specific operation: The server receives data through a specific API endpoint and stores it in a database.

[0836] Step 2:

[0837] The server transmits the stored novel data to a text analysis module.

[0838] Input: Novel data stored in the database.

[0839] Data Computing: Perform natural language analysis using libraries such as Python's NLTK and SpaCy.

[0840] Output: Analysis of narrative structure, characterization, writing style, and plot progression.

[0841] Specific operation: The server passes the data to the analysis module, which analyzes the structure, character, and style of the text.

[0842] Step 3:

[0843] The server inputs the results of the text analysis into multiple generative AI models, which then evaluate the novel based on their respective evaluation criteria.

[0844] Input: Analysis results output from the text analysis module.

[0845] Data calculation: The analysis results are input into each generative AI model and evaluated using prompt statements.

[0846] Output: Evaluation results from each generative AI model.

[0847] Specific behavior: The server generates a prompt statement such as "Please rate the story coherence and character depth of a newly released novel" and gives it to each AI model.

[0848] Step 4:

[0849] The server integrates the evaluation results obtained from each generative AI model and calculates an overall evaluation score.

[0850] Input: Evaluation scores for each generative AI model.

[0851] Data calculation: The evaluation scores are averaged and combined.

[0852] Output: Overall evaluation score.

[0853] Specific operation: The server aggregates the evaluation scores of each AI model, calculates the average value, and derives the overall evaluation score.

[0854] Step 5:

[0855] The server notifies the author or publisher of the detailed evaluation results and the overall evaluation score.

[0856] Input: Overall assessment score and detailed assessment results.

[0857] Data processing: converting the results into a format for notification.

[0858] Output: Notification of evaluation results.

[0859] Specific operation: The server notifies the user of the evaluation results via email or dashboard, and also automatically generates and provides a catchy slogan, introduction, and obi text.

[0860] Step 6:

[0861] The terminal provides an interface for the user to access and operate.

[0862] Input: User operation request.

[0863] Data processing: Generate and display the user interface.

[0864] Output: The interface that is displayed to the user.

[0865] Specific operation: The device provides a UI for uploading, viewing evaluation results, and submitting feedback via a web browser or dedicated app.

[0866] Step 7:

[0867] The terminal visually displays the evaluation results sent from the server to the user.

[0868] Input: The evaluation result sent from the server.

[0869] Data processing: Convert the evaluation results into a visually easy-to-read format.

[0870] Output: The evaluation results that are displayed to the user.

[0871] Specific operation: The device displays the evaluation results in graphs and text, making it easy for the user to understand.

[0872] Step 8:

[0873] The terminal collects feedback from the user and sends it to the server.

[0874] Input: User feedback.

[0875] Data Processing: Collect feedback and convert it into a format that can be sent to the server.

[0876] Output: Feedback data to the server.

[0877] Specific operation: The device accepts feedback via an input form and sends it to the server's feedback API.

[0878] Step 9:

[0879] The server uses an emotion engine to perform emotion analysis of the feedback provided by the user.

[0880] Input: User feedback data.

[0881] Data Computation: Perform sentiment analysis using the sentiment engine.

[0882] Output: Positive, negative, or neutral sentiment classification results.

[0883] Specific operation: The server uses a sentiment analysis API (e.g., Microsoft Azure's Text Analytics API) to perform sentiment classification.

[0884] Step 10:

[0885] The device analyzes the user's emotional state in real time and transmits it to the emotion engine.

[0886] Input: Real-time user operation data.

[0887] Data calculation: Analyzes operational data and recognizes real-time emotional states.

[0888] Output: Emotion state data to the emotion engine.

[0889] Specific operation: The device estimates the user's emotional state using facial recognition and operation patterns, and transmits the information to the server in real time.

[0890] Step 11:

[0891] The server personalizes the evaluation results of the novel based on the emotional data obtained from the emotion engine.

[0892] Input: Emotion data from the emotion engine.

[0893] Data calculation: Emotional data is used to individually optimize evaluation results.

[0894] Output: Personalized assessment results.

[0895] Specific operation: The server analyzes the emotion data and adjusts the evaluation results based on the user's emotion patterns.

[0896] Step 12:

[0897] The server accumulates the user's emotional history data and adjusts the novel recommendation algorithm based on past emotional patterns.

[0898] Input: Emotion history data.

[0899] Data calculation: Emotional data is accumulated and used to adjust algorithms.

[0900] Output: The adjusted recommendation algorithm.

[0901] Specific operation: The server stores the emotion history data in a database and optimizes the next recommendation based on past patterns.

[0902] (Application example 2)

[0903] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0904] Conventional novel rating systems rely on fixed evaluation criteria and have the problem of not being able to fully reflect the individual feelings and preferences of users. This makes it difficult to recommend novels that truly interest users and are personalized. Furthermore, because it is not possible to check feelings in real time and update evaluation results accordingly, users' reading experience is uniform, which can lead to a decrease in satisfaction.

[0905] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: [means for receiving and saving novel data;] [means for passing the saved novel data to a text analysis module and analyzing the story structure, character descriptions, writing style, plot progression, etc.;] [means for inputting the analysis results into multiple generative AI models and evaluating the novel based on their respective evaluation criteria;] [means for integrating the evaluation results of each generative AI model and calculating an overall evaluation score;] [means for providing the overall evaluation score and evaluation content;] [means for analyzing the user's emotions in real time and personalizing the evaluation results based on the emotional state; and] [means for accumulating the user's emotional history data and adjusting the evaluation algorithm.] This enables highly accurate personalized evaluation and recommendations based on the user's emotions and preferences.

[0906] "Novel data" refers to data sent by the author or publisher that includes the text of the novel, author information, genre, plot summary, etc.

[0907] The "text analysis module" is a software module for analyzing the narrative structure, character descriptions, writing style, plot progression, etc. of novel data.

[0908] A "generative AI model" is an artificial intelligence model that has multiple different evaluation criteria for evaluating novels based on the results of text analysis.

[0909] "Evaluation results" is a collective term for scores and detailed reviews based on each evaluation criterion applied to the novel data analyzed by the generative AI model.

[0910] The "overall evaluation score" is an overall evaluation score calculated by integrating the evaluation results from multiple generative AI models.

[0911] An "emotion engine" is a software engine that analyzes users' emotions and reflects the results in rating and recommending novels.

[0912] "Personalized ratings" refer to ratings or recommendations that are tailored based on a user's emotional state and preferences.

[0913] "Emotion history data" is data about a user's past emotional patterns, information that is used to adjust future rating algorithms.

[0914] An "interface" is an operation screen or operation means that allows users to upload novel data, view evaluation results, submit feedback, and so on.

[0915] The present invention relates to a system for receiving and storing novel data, a system for analyzing and evaluating novel data, and a method for combining an emotion engine that analyzes user emotions to improve the accuracy and personalization of evaluations.

[0916] Server Roles

[0917] The server has the following functions:

[0918] Data reception and storage

[0919] The server receives novel data sent from authors or publishers via the Internet. This data includes the novel's text, author information, genre, plot summary, etc. The received data is immediately stored in a database.

[0920] Text analytics

[0921] The server passes the saved novel data to the text analysis module, which performs the following analysis:

[0922] Story structure analysis: Analyze the beginning, development, twist, and conclusion of a story, scene transitions, and consistency of the timeline.

[0923] Character description analysis: Analyze the characters' personalities, backgrounds, and relationships with each other.

[0924] Stylistic analysis: Evaluating the rhythm of the writing, vocabulary, grammatical accuracy, etc.

[0925] Plot progression analysis: Evaluating whether the story unfolds logically and coherently.

[0926] AI evaluation

[0927] The server inputs the text analysis results into multiple generative AI models. Each AI model evaluates the analysis results based on its own criteria. For example, one AI model may emphasize story coherence, while another emphasizes character depth. Each AI model generates a specific score and a detailed review based on its own criteria.

[0928] Evaluation Integration

[0929] The server integrates the evaluation results obtained from each generative AI model. At this time, it calculates the average of the evaluations to calculate an overall evaluation score. For example, if the individual AI evaluations are 9.0, 8.5, and 8.0, respectively, the overall evaluation score will be 8.5.

[0930] Emotion Recognition and Real-Time Analysis

[0931] The server uses an emotion engine to perform an emotional analysis of the feedback provided by the user. For example, it automatically classifies feedback into positive, negative, and neutral. Furthermore, the device analyzes the user's emotional state in real time as they read the novel, and transmits the results to the emotion engine. For example, if the user is using a smartphone, their emotions are recognized by utilizing their operation patterns and facial recognition technology.

[0932] Personalized Evaluation

[0933] The server personalizes the evaluation results of novels based on the emotional data obtained from the emotion engine. For example, if a user typically provides many positive reviews, the server will make recommendations that match that emotional pattern. This enables highly accurate personalized evaluations and recommendations based on the user's emotions and preferences.

[0934] Accumulation of emotional history

[0935] The server accumulates users' emotional history data and adjusts the novel recommendation algorithm based on their past emotional patterns, enabling more accurate recommendations in the future.

[0936] Device Role

[0937] The terminal has the following functions:

[0938] Providing an interface

[0939] The terminal provides an interface for users to access and operate, through which users can perform the following operations:

[0940] Uploading novel data

[0941] Viewing evaluation results

[0942] Submitting Feedback

[0943] Displaying the evaluation results

[0944] The terminal visually displays the evaluation results sent from the server to the user, allowing the user to select novels based on evaluation criteria that are closest to their preferences.

[0945] Gathering feedback

[0946] The device collects feedback on the novels that users have read and sends their impressions and evaluations to the server, thereby contributing to improving the accuracy of the AI ​​evaluation.

[0947] emotion recognition

[0948] The terminal uses the input device of the smart device to recognize the user's emotional state in real time and transmits the emotional data to the server.

[0949] Specific examples

[0950] For example, suppose a user purchases a newly released novel through a device and begins reading it. The novel data is uploaded and stored on a server by the author or publisher. The server sends the novel data to a text analysis module, which generates analysis results. The results are then input into multiple generative AI models, which evaluate the novel on factors such as story coherence, character depth, and stylistic clarity. The evaluation results are then combined to calculate an overall evaluation score.

[0951] The evaluation results are provided to the user via their device. Furthermore, while the user is reading the novel, their emotions are analyzed in real time and their emotional state is recorded. The emotion engine uses this real-time data to personalize the evaluation results and make optimal recommendations to the user. After finishing reading, the feedback provided by the user is also analyzed by the emotion engine and sent to the server.

[0952] Example prompts to input to the generative AI model

[0953] 1. If the user expresses positive sentiment:

[0954] "How entertaining is this paragraph if it makes the user smile?"

[0955] 2. If the user expresses negative sentiment:

[0956] "If users frowned, what was their criticism of the work?"

[0957] Through this series of processes, the present invention can efficiently evaluate high-quality works from a wide variety of novels and make optimal recommendations based on the user's emotional state. Furthermore, by continuously improving the evaluation algorithm based on collected emotional data, it will be possible to provide a more accurate novel evaluation system in the future.

[0958] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0959] Step 1:

[0960] The server receives novel data from authors or publishers via the Internet and stores the data in a database. Specifically, when a user sends novel data, the server receives the data, extracts metadata such as the text, author information, genre, and plot, and stores the data in a database. The input is the novel data, and the output is the stored novel data.

[0961] Step 2:

[0962] The server sends the saved novel data to the text analysis module. The text analysis module performs the following analyses: story structure analysis, character description analysis, writing style analysis, and plot progression analysis. The data obtained from these analyses becomes the respective analysis results. The input is the saved novel data, and the output is each analysis result.

[0963] Step 3:

[0964] The server inputs the text analysis results into multiple generative AI models. Each AI model evaluates the analysis results based on its own evaluation criteria and generates a specific score and detailed review. The input is each analysis result, and the output is the evaluation score and review.

[0965] Step 4:

[0966] The server integrates the evaluation results obtained from each generative AI model and calculates an overall evaluation score. At this time, it calculates the average of the evaluations to calculate the overall evaluation score. For example, if the AI ​​evaluations are 9.0, 8.5, and 8.0 respectively, the overall evaluation score will be 8.5. The input is each evaluation result, and the output is the overall evaluation score.

[0967] Step 5:

[0968] The server notifies the author or publisher of the calculated overall evaluation score and detailed evaluation results. It also automatically generates new catchphrases, introductions, and obi text based on the evaluation results and provides them to the author or publisher. The input is the overall evaluation score and each evaluation result, and the output is the notification and the generated text.

[0969] Step 6:

[0970] The terminal provides an interface for users to upload novel data. When a user uploads novel data, the terminal sends the data to the server. The input is the novel data entered by the user, and the output is the novel data sent to the server.

[0971] Step 7:

[0972] The terminal visually displays the evaluation results sent from the server to the user, allowing the user to select novels based on evaluation criteria that best suit their preferences. The input is the evaluation results from the server, and the output is the displayed evaluation results.

[0973] Step 8:

[0974] As the user reads the novel, the device uses the smartphone's camera and microphone to recognize the user's emotional state in real time and transmits the emotional data to the server. The input is data from the emotion recognition device (camera and microphone), and the output is the emotional data transmitted to the server.

[0975] Step 9:

[0976] The server uses an emotion engine to analyze the user's emotional data and personalize the evaluation results in real time. If the user expresses positive emotions, the evaluation results are adjusted to lean more positively. The input is the user's real-time emotional data, and the output is the personalized evaluation results.

[0977] Step 10:

[0978] Based on the emotion data obtained from the emotion engine and the user's past emotion history data, the server adjusts the novel recommendation algorithm and recommends the most suitable novel for the user. The input is the emotion history data and real-time emotion data, and the output is the adjusted recommendation algorithm and the recommended novel.

[0979] The above processing steps enable highly accurate personalized evaluation and recommendations based on the user's emotions and preferences.

[0980] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0981] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0982] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0983] [Third embodiment]

[0984] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0985] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0986] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0987] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0988] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0989] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0990] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0991] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0992] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0993] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0994] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0995] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0996] server

[0997] 1. Data Receipt and Storage

[0998] The server receives novel data sent via the Internet from authors or publishers. This data includes the text of the novel, author information, genre, plot summary, etc. The received data is immediately stored in a database.

[0999] 2. Text Analysis

[1000] The server sends the stored novel data to the text analysis module, which performs the following analysis:

[1001] Story structure analysis: Analyzes the beginning, development, twist, and conclusion of a story, scene transitions, and consistency of the timeline.

[1002] Character description analysis: Analyze the characters' personalities, backgrounds, and relationships with each other.

[1003] Stylistic analysis: Evaluating the rhythm of the writing, vocabulary, grammatical accuracy, etc.

[1004] Plot progression analysis: Evaluating whether the story unfolds logically and coherently.

[1005] 3. AI Evaluation

[1006] The server inputs the text analysis results into multiple generative AI models. Each AI model evaluates the analysis results based on its own criteria. For example, one AI model may emphasize story coherence, while another emphasizes character depth. Each AI model generates a specific score and a detailed review based on its own criteria.

[1007] 4. Evaluation Integration

[1008] The server integrates the evaluation results obtained from multiple generative AI models. At this time, it calculates the average of the evaluations to calculate an overall evaluation score. For example, if the individual AI evaluations are 9.0, 8.5, and 8.0, respectively, the overall evaluation score will be 8.5.

[1009] 5. Providing results

[1010] The server then notifies the author or publisher of the calculated overall score and detailed evaluation results. This information may be used as marketing material, and is also used to generate new taglines, introductions, and obi text. The generated text is then provided to the author or publisher, who can revise it as needed.

[1011] Terminal

[1012] 1. Providing an interface

[1013] The terminal provides an interface for users to access and operate. Through this interface, users can:

[1014] Uploading novel data

[1015] Viewing evaluation results

[1016] Submitting Feedback

[1017] 2. Display of evaluation results

[1018] The evaluation results sent from the server are visually displayed on the device, allowing users to select an appropriate novel based on this. Individual evaluation results from each AI model are also displayed, allowing users to use this information to help them select evaluation criteria that best suit their preferences.

[1019] 3. Gathering Feedback

[1020] After reading a novel, readers submit their ratings and impressions through a feedback form. This feedback is sent to the server and used to improve the evaluation algorithm of the generative AI model.

[1021] User

[1022] 1. Uploading a Novel

[1023] Authors or publishers upload novel data through the device's interface, which is then sent to the server and stored.

[1024] 2. Viewing the evaluation results

[1025] Authors and publishers can check the evaluation results sent from the server on their devices, allowing them to understand how their work has been evaluated and identify areas for improvement.

[1026] 3. Providing Feedback

[1027] After finishing a novel, readers can provide feedback via their devices, which will help the AI ​​make a more accurate assessment.

[1028] Specific examples

[1029] For example, when a well-known author writes a new novel and uploads it to the system through a publisher, the novel data is first received and stored on the server. It is then analyzed by a text analysis module, which performs a detailed analysis of the story structure, character descriptions, writing style, etc. The analysis results are input into multiple generative AI models, each of which evaluates the novel based on its own evaluation criteria. As a result, an overall evaluation score is calculated, and the evaluation results are notified to the author and publisher. Based on this evaluation result, new catchphrases and introductions are automatically generated and used in promotional activities. Readers can use the evaluation results as a reference when selecting a novel, and provide feedback after reading, contributing to improving the accuracy of the AI ​​evaluation.

[1030] In this way, the present invention realizes an environment in which hidden masterpieces can be easily discovered by efficiently evaluating high-quality works and providing them to readers amidst the proliferation of novels.

[1031] The processing flow will be explained below.

[1032] Step 1:

[1033] The server receives novel data sent via the Internet from authors or publishers. This data includes the text of the novel, author information, genre, plot summary, etc. The received data is immediately stored in a database.

[1034] Step 2:

[1035] The server sends the saved novel data to the text analysis module, which performs grammatical analysis, sentiment analysis, keyword extraction, etc. of the novel, and generates and returns the analysis results to the server.

[1036] Step 3:

[1037] The server inputs the results of the text analysis into multiple generative AI models. Each AI model evaluates the novel data based on criteria such as story coherence, character depth, and stylistic clarity. Each AI model generates a rating score and a detailed review.

[1038] Step 4:

[1039] The server integrates the evaluation results from each generative AI model. At this time, it calculates the average of each evaluation to calculate an overall evaluation score. For example, if AI model A evaluates 8.0, AI model B evaluates 7.0, and AI model C evaluates 9.0, the average is calculated and the overall evaluation score is 8.0.

[1040] Step 5:

[1041] The server notifies the author or publisher of the calculated overall evaluation score and detailed evaluation results. The notification also includes the individual evaluation results of each AI model and the evaluation criteria. Based on the evaluation results, the server automatically generates new catchphrases, introductions, and obi text and provides them to the author or publisher.

[1042] Step 6:

[1043] The terminal provides an interface for users (authors, publishers, and readers) to access and operate, through which users can upload novel data, view evaluation results, and submit feedback.

[1044] Step 7:

[1045] The device visually displays the evaluation results sent from the server to the user. It displays not only the overall evaluation score but also the detailed evaluation results from each AI model. This allows the user to select novels based on evaluation criteria that best suit their preferences.

[1046] Step 8:

[1047] The device collects feedback from readers about the novels they have read, and sends the information submitted through a feedback form to a server, which then reflects the collected feedback in the generative AI model, thereby contributing to improving the accuracy of the evaluation algorithm.

[1048] Step 9:

[1049] Users (authors, publishers, and readers) can use the device to check the new catchphrases and introductions, decide whether they are appropriate, and, if necessary, revise the automatically generated text to use as the final marketing material.

[1050] Step 10:

[1051] The server analyzes the collected feedback and uses it to improve the evaluation criteria of the generative AI model, which will improve the accuracy of future novel evaluations and enable better recommendations.

[1052] Example 1

[1053] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1054] Conventional literary evaluation systems often lack uniformity and fairness in their evaluations, and do not evaluate works from a variety of perspectives, making it difficult to determine their true value. Furthermore, there is no efficient way to collect feedback from many users, resulting in a lack of reference information for revising and releasing works.

[1055] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1056] In this invention, the server includes means for receiving and saving literary data, means for passing the saved literary data to a natural language analysis module to analyze the narrative structure, character traits, writing style, and story progression, means for inputting the analysis results into a plurality of AI models to evaluate the literary work based on their respective evaluation criteria, means for integrating the evaluation results of each AI model to calculate an overall evaluation score, and means for providing the overall evaluation score and the evaluation content, thereby enabling high-quality literary evaluation and detailed feedback from a variety of perspectives.

[1057] "Literary data" refers to data that includes information such as the text of a work, author information, genre, and plot.

[1058] A "natural language analysis module" is a program that analyzes text data and evaluates the structure of the story, the characteristics of the characters, the writing style, the progression of the story, etc.

[1059] A "generative artificial intelligence model" is an artificial intelligence program that evaluates text data according to specific evaluation criteria based on previously learned data.

[1060] The "overall evaluation score" is a numerical value that indicates the overall evaluation by integrating the individual evaluation results obtained from multiple generating artificial intelligence models.

[1061] "Upload Interface" is a platform through which users can submit literary data to the system.

[1062] The "visual display means" is a mechanism for displaying the evaluation results to the user as graphs or text.

[1063] The "feedback collection means" is a means for receiving evaluations and impressions from users and transmitting them to the server.

[1064] A "catchphrase" is a short, catchy phrase used to introduce a work to the market.

[1065] An "introduction" is a short sentence that explains the outline and characteristics of the work.

[1066] "Obi text" refers to short sentences or catchphrases printed on the book's obi, and serves to stimulate purchasing desire.

[1067] server

[1068] 1. Data Receipt and Storage

[1069] The server receives literary data sent by connected authors or publishers via the Internet. This data includes the text of the work, author information, genre, plot summary, etc. The received data is immediately stored in the database. For example, when an author uploads a new work, the data is sent to the server and stored.

[1070] 2. Text Analysis

[1071] The server sends the stored literary data to a natural language analysis module, which analyzes the narrative structure, character traits, writing style, and story progression. For example, it analyzes the beginning, development, climax, and conclusion of a story and detects how each part is structured.

[1072] 3. AI Evaluation

[1073] The server then feeds the analysis results into multiple artificial intelligence models, which evaluate literary works based on their own criteria: for example, one AI model focuses on story coherence, while another evaluates character portrayals.

[1074] 4. Evaluation Integration

[1075] The server integrates the evaluation results obtained from each AI model and calculates an overall evaluation score. For example, if model A is evaluated as 8.5, model B as 9.0, and model C as 8.0, the server calculates the average of these scores and uses this as the overall evaluation score.

[1076] 5. Providing results

[1077] The server then notifies the author or publisher of the calculated overall score and detailed evaluation. This information is used as marketing material and is also utilized to generate new catchphrases, descriptions, and obi text. For example, the server may notify the author or publisher of the evaluation result, saying, "This work has been evaluated for its story consistency, with an overall score of 8.5."

[1078] Terminal

[1079] 1. Providing an interface

[1080] The terminal provides an interface for users to access and operate, through which users can upload literary data, view evaluation results, and provide feedback. For example, a user can submit a work using a form for uploading a novel.

[1081] 2. Display of evaluation results

[1082] The evaluation results sent from the server are visually displayed on the device, allowing users to select an appropriate novel based on this information. Individual evaluation results from each generated AI model are also displayed, helping users choose evaluation criteria that best suit their preferences. For example, the dashboard displays the overall evaluation score and detailed evaluation results in graphs and text.

[1083] 3. Gathering Feedback

[1084] After a reader finishes reading a novel, they submit their rating and thoughts through a feedback form. This feedback is sent to the server and used to improve the evaluation algorithm of the AI ​​model that generates it. For example, reader comments such as "The story development was fascinating" are collected.

[1085] User

[1086] 1. Uploading a Novel

[1087] Authors or publishers upload literary data through the device interface. The uploaded data is sent to the server and stored. For example, when uploading a new novel, they enter the necessary information and press the submit button, and the data is stored on the server.

[1088] 2. Viewing the evaluation results

[1089] Authors and publishers can check the evaluation results sent from the server on their devices. This allows them to understand how their work has been evaluated and identify areas for improvement. For example, they can check the evaluation score and detailed feedback on a dashboard.

[1090] 3. Providing Feedback

[1091] After finishing a novel, readers can provide feedback via their devices, which will help the AI ​​model to generate a more accurate evaluation. For example, after finishing a novel, readers can fill out a feedback form and press the submit button, which will send the feedback to the server.

[1092] Specific prompt examples

[1093] "Please enter the text of the novel."

[1094] Analyze the characters' personalities

[1095] "Evaluate the coherence of the story."

[1096] This makes it possible to efficiently evaluate high-quality works from among many literary works and provide them to readers, creating an environment in which hidden masterpieces can be easily discovered.

[1097] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1098] Step 1: Receiving and storing data

[1099] The server receives literary data sent by connected authors or publishers via the Internet. The input includes data such as the novel text, author information, genre, and plot summary. The server verifies that the data has been received correctly, and if successful, it is stored in a database. For example, when a new work is uploaded, all of its data arrives at the server and is immediately stored in the database.

[1100] Step 2: Text analysis

[1101] The server sends the stored literary data to a natural language analysis module. The literary data is used as input. The natural language analysis module analyzes the structure of the story (beginning, development, climax, conclusion, etc.), the characteristics of the characters (personalities, background, etc.), the writing style (rhythm, vocabulary, etc.), and the progression of the story (consistency of the timeline, etc.), and outputs the results of these analyses. For example, it identifies and analyzes the beginning, middle, climax, and conclusion of a story.

[1102] Step 3: AI evaluation

[1103] The server inputs the analysis results into multiple AI models. The text analysis results are used as input. The AI ​​models evaluate literary works based on their respective evaluation criteria (e.g., story coherence, character depth, etc.). Each AI model outputs a specific score and a detailed review. For example, an AI model that emphasizes story coherence will evaluate the work based on that criteria and output its results.

[1104] Step 4: Consolidating the assessments

[1105] The server integrates the evaluation results obtained from each generated AI model. Evaluation results from multiple AI models are used as input. The server calculates the average of these evaluation results and outputs an overall evaluation score. For example, if the evaluation scores are 9.0, 8.5, and 8.0, the average of these, 9.0, is calculated as the overall evaluation score.

[1106] Step 5: Delivering results

[1107] The server notifies the author or publisher of the calculated overall rating score and detailed rating content. The overall rating score and detailed rating content are used as input. The rating result is notified to the author or publisher as output. For example, a notification may be sent saying, "This work has an overall rating score of 8.5."

[1108] Step 6: Providing an Interface

[1109] The terminal provides an interface for users to access and operate. User operations are used as input. The terminal provides and outputs a form for users to upload literary data and a dashboard for viewing evaluation results. For example, when a user clicks the upload button, the following page is displayed.

[1110] Step 7: View the evaluation results

[1111] The terminal visually displays the evaluation results sent from the server. The evaluation results from the server are used as input. The evaluation results are output in graph and text format on the dashboard, helping users to select the appropriate novel. For example, the terminal displays the overall evaluation score and detailed evaluations by each AI model.

[1112] Step 8: Gather feedback

[1113] The terminal provides a means for the reader user to submit their evaluation and thoughts through a feedback form after finishing reading the novel. The user's feedback is used as input. The submitted feedback is sent to the server and used to improve the evaluation algorithm of the generated artificial intelligence model. For example, a comment such as "The story development was very satisfying" can be entered and submitted in the feedback form.

[1114] Through these steps, this system is able to evaluate literary works from multiple perspectives and provide readers with high-quality works.

[1115] (Application example 1)

[1116] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1117] This invention relates to a system that efficiently evaluates high-quality works amidst the proliferation of novels and provides them to readers. Conventional evaluation methods make it difficult for authors and publishers to quickly and accurately grasp the quality of works, and readers lack the information necessary to select appropriate works. Furthermore, the collection and utilization of feedback is inefficient, resulting in a lack of consistency in the evaluation of works. It is necessary to solve these issues and improve the process of evaluating and providing novels.

[1118] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1119] In this invention, the server includes: [means for receiving and saving novel data; [means for passing the saved novel data to a text analysis module and having it analyze the story structure, character descriptions, writing style, plot progression, etc.; and [means for inputting the analysis results into multiple generative AI models and having them evaluate the novel based on their respective evaluation criteria.] This makes it possible [to integrate the evaluation results of each generative AI model, calculate an overall evaluation score, and provide the overall evaluation score and evaluation content].

[1120] "Novel data" refers to data such as the text of a novel, author information, genre, and plot summary provided by the author or publisher.

[1121] A "text analysis module" is software or hardware used to analyze novel data and evaluate the story structure, character descriptions, writing style, plot progression, etc.

[1122] A "generative AI model" is an artificial intelligence model that evaluates novels based on the results of analyzing novel data and each evaluation criterion.

[1123] The "overall evaluation score" is a number calculated by combining the evaluation results from multiple generative AI models, and is used to comprehensively evaluate the quality of the entire novel.

[1124] A "smartphone application" is software that runs on a smartphone and provides functions such as uploading novel data, displaying evaluation results, and collecting feedback.

[1125] "Feedback" refers to the impressions and evaluations that readers provide after finishing a novel, and is information that is sent to the server and contributes to improving the accuracy of the generative AI model.

[1126] The "interface" is the UI (user interface) that users can operate, allowing them to upload novel data, view evaluation results, and submit feedback.

[1127] A "catchphrase" is a short phrase used in marketing and promotional activities to effectively convey the appeal of a novel.

[1128] An "introduction" is a text that explains the content and characteristics of a novel and is used to convey an overview of the work to customers.

[1129] "Book cover text" refers to advertising slogans or catch phrases printed on a piece of paper attached to the outside of a book's cover, intended to motivate customers to purchase the book.

[1130] In this invention, the server receives, stores, analyzes, evaluates, and provides results of novel data using the following means.

[1131] server

[1132] 1. Data Receipt and Storage

[1133] The server receives novel data sent via the Internet from authors or publishers. This data includes the text of the novel, author information, genre, plot summary, etc. The received data is immediately stored in a database.

[1134] 2. Text Analysis

[1135] The server sends the saved novel data to the text analysis module, which uses a Python natural language processing library (e.g., NLTK or spaCy). The text analysis module performs the following analysis:

[1136] Story structure analysis: Analyzes the beginning, development, twist, and conclusion of a story, scene transitions, and consistency of the timeline.

[1137] Character description analysis: Analyze the characters' personalities, backgrounds, and relationships with each other.

[1138] Stylistic analysis: Evaluating the rhythm of the writing, vocabulary, grammatical accuracy, etc.

[1139] Plot progression analysis: Evaluating whether the story unfolds logically and coherently.

[1140] 3. AI Evaluation

[1141] The server inputs the text analysis results into multiple generative AI models. Each generative AI model evaluates the analysis results based on its own evaluation criteria. Examples of AI models used include OpenAI's GPT-3. Each AI model generates a specific score and a detailed review based on its own evaluation criteria.

[1142] 4. Evaluation Integration

[1143] The server integrates the evaluation results obtained from multiple generative AI models, calculating the average of the evaluations and deriving an overall evaluation score.

[1144] 5. Providing results

[1145] The server then notifies the author or publisher of the calculated overall score and detailed evaluation results. This information is used as marketing material and is also used to generate new taglines, introductions, and obi text. The generated text is then provided to the author or publisher, who can revise it as needed.

[1146] Terminal

[1147] 1. Providing an interface

[1148] The terminal provides an interface for users to access and operate. Through this interface, users can:

[1149] Uploading novel data

[1150] Viewing evaluation results

[1151] Submitting Feedback

[1152] 2. Display of evaluation results

[1153] The evaluation results sent from the server are visually displayed on the device, allowing users to select an appropriate novel based on this. Individual evaluation results from each AI model are also displayed, allowing users to use this information to help them select evaluation criteria that best suit their preferences.

[1154] 3. Gathering Feedback

[1155] After reading a novel, readers submit their ratings and impressions through a feedback form. This feedback is sent to the server and used to improve the evaluation algorithm of the generative AI model.

[1156] User

[1157] 1. Uploading a Novel

[1158] Authors or publishers upload novel data through the device's interface, which is then sent to the server and stored.

[1159] 2. Viewing the evaluation results

[1160] Authors and publishers can check the evaluation results sent from the server on their devices, allowing them to understand how their work has been evaluated and identify areas for improvement.

[1161] 3. Providing Feedback

[1162] After finishing a novel, readers provide feedback through their devices, which helps the AI ​​to more accurately evaluate it.

[1163] Specific examples

[1164] For example, when an author writes a new novel and uploads it to the system via their device, the novel data is first received and stored on the server. The text analysis module then analyzes the story structure, character descriptions, writing style, and other aspects, and the analysis results are input into multiple generative AI models. The evaluation results are then integrated to calculate an overall evaluation score. The author and publisher are notified of this evaluation result, and a new catchphrase and introduction are automatically generated based on it.

[1165] Prompt Sentence Examples

[1166] Please rate the following novel data in terms of plot coherence, character depth, stylistic rhythm, etc.

[1167] Novel Title: New Novel

[1168] Author: Famous Author

[1169] Genre: Fantasy

[1170] Synopsis: This is a sample story

[1171] Novel content: The main text of the novel...

[1172] Please provide your evaluation in the following format:

[1173] 1. Overall evaluation score

[1174] 2. Detailed evaluation of story coherence

[1175] 3. Detailed evaluation of character depth

[1176] 4. Detailed evaluation of stylistic rhythm

[1177] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1178] Step 1:

[1179] The device receives novel data from the author or publisher. The novel data includes the text, author information, genre, and synopsis. The device uses this data as input and sends an HTTP POST request to the server. This sends the novel data to the server and stores it in a database.

[1180] Step 2:

[1181] The server sends the saved novel data to the text analysis module, which uses a Python natural language processing library (such as NLTK or spaCy). Here, the following data processing is performed and the analysis results are output:

[1182] Story structure analysis (beginning, development, twist, conclusion, scene transitions, etc.)

[1183] Character description analysis (personality, background, relationships, etc.)

[1184] Stylistic analysis (rhythm, vocabulary, grammatical accuracy, etc.)

[1185] Plot progression analysis (logic of development, consistency, etc.)

[1186] Step 3:

[1187] The server inputs the text analysis results into multiple generative AI models, such as OpenAI's GPT-3. Each generative AI model performs the following data calculations and outputs an individual rating score and detailed review:

[1188] Story consistency

[1189] Character depth

[1190] Stylistic rhythm and variety

[1191] Overall rating score

[1192] Step 4:

[1193] The server integrates the evaluation results obtained from multiple generative AI models. Specifically, it calculates the average of the evaluation scores of each model and outputs an overall evaluation score. It also integrates detailed evaluation reviews to generate a single evaluation report. These results are stored in the server database.

[1194] Step 5:

[1195] The server outputs the evaluation results—namely, the overall evaluation score and a detailed evaluation report—in JSON format via an API endpoint to provide them to the user's device, where the user (author or publisher) can visually check these evaluation results.

[1196] Step 6:

[1197] The terminal provides a GUI (Graphical User Interface) to visually display the evaluation results. Users can view the evaluation scores and detailed evaluation reviews through this interface, which allows them to deepen their understanding of their work and identify areas for improvement.

[1198] Step 7:

[1199] After finishing reading a novel, users (readers) provide their ratings and impressions using a feedback form. The device sends this feedback to the server and stores it as data used to improve the evaluation algorithm of the generative AI model.

[1200] Prompt Sentence Examples

[1201] Please rate the following novel data in terms of plot coherence, character depth, stylistic rhythm, etc.

[1202] Novel Title: New Novel

[1203] Author: Famous Author

[1204] Genre: Fantasy

[1205] Synopsis: This is a sample story

[1206] Novel content: The main text of the novel...

[1207] Please provide your evaluation in the following format:

[1208] 1. Overall evaluation score

[1209] 2. Detailed evaluation of story coherence

[1210] 3. Detailed evaluation of character depth

[1211] 4. Detailed evaluation of stylistic rhythm

[1212] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1213] The present invention relates to a system for receiving and storing novel data, a system for analyzing and rating novel data, and a method for improving the accuracy and personalization of novel ratings by combining an emotion engine that analyzes user emotions.

[1214] server

[1215] 1. Data Receipt and Storage

[1216] The server receives novel data sent via the Internet from authors or publishers. This data includes the text of the novel, author information, genre, plot summary, etc. The received data is immediately stored in a database.

[1217] 2. Text Analysis

[1218] The server sends the stored novel data to the text analysis module, which performs the following analysis:

[1219] Story structure analysis: Analyzes the beginning, development, twist, and conclusion of a story, scene transitions, and consistency of the timeline.

[1220] Character description analysis: Analyze the characters' personalities, backgrounds, and relationships with each other.

[1221] Stylistic analysis: Evaluating the rhythm of the writing, vocabulary, grammatical accuracy, etc.

[1222] Plot progression analysis: Evaluating whether the story unfolds logically and coherently.

[1223] 3. AI Evaluation

[1224] The server inputs the text analysis results into multiple generative AI models. Each AI model evaluates the analysis results based on its own criteria. For example, one AI model may emphasize story coherence, while another emphasizes character depth. Each AI model generates a specific score and a detailed review based on its own criteria.

[1225] 4. Evaluation Integration

[1226] The server integrates the evaluation results obtained from each generative AI model. At this time, it calculates the average of the evaluations to calculate an overall evaluation score. For example, if the individual AI evaluations are 9.0, 8.5, and 8.0, respectively, the overall evaluation score will be 8.5.

[1227] 5. Providing results

[1228] The server notifies the author or publisher of the calculated overall evaluation score and detailed evaluation results. It also automatically generates new catchphrases, introductions, and obi text based on the evaluation results and provides them to the author or publisher.

[1229] Terminal

[1230] 1. Providing an interface

[1231] The terminal provides an interface for users to access and operate. Through this interface, users can:

[1232] Uploading novel data

[1233] Viewing evaluation results

[1234] Submitting Feedback

[1235] 2. Display of evaluation results

[1236] The terminal visually displays the evaluation results sent from the server to the user, allowing the user to select novels based on evaluation criteria that are closest to their preferences.

[1237] 3. Gathering Feedback

[1238] The device collects feedback on the novels that users have read and sends their impressions and evaluations to the server, thereby contributing to improving the accuracy of the AI ​​evaluation.

[1239] Introducing the Emotion Engine

[1240] 1. Emotion recognition

[1241] The server uses an emotion engine to perform sentiment analysis of the feedback provided by the user, for example, automatically classifying it as positive, negative, or neutral.

[1242] 2. Real-time analysis

[1243] The device analyzes the user's emotional state in real time as they read the novel, and sends the results to the emotion engine. For example, if the user is using a smartphone or tablet, the device recognizes their emotions by utilizing their operation patterns and facial recognition technology.

[1244] 3. Personalized evaluation

[1245] The server personalizes the novel evaluation results based on the emotional data obtained from the emotion engine. For example, if a user typically provides many positive reviews, the server will make recommendations that match that emotional pattern.

[1246] 4. Accumulation of emotional history

[1247] The server accumulates users' emotional history data and adjusts the novel recommendation algorithm based on their past emotional patterns, enabling more accurate recommendations in the future.

[1248] Specific examples

[1249] For example, suppose a user purchases a newly released novel through a device and begins reading it. The novel data is uploaded and stored on a server by the author or publisher. The server sends the novel data to a text analysis module, which generates analysis results. The results are then input into multiple generative AI models, which evaluate the novel on factors such as story coherence, character depth, and stylistic clarity. The evaluation results are then combined to calculate an overall evaluation score.

[1250] The evaluation results are provided to the user via their device. Furthermore, while the user is reading the novel, their emotions are analyzed in real time and their emotional state is recorded. The emotion engine uses this real-time data to personalize the evaluation results and make optimal recommendations to the user. After finishing reading, the feedback provided by the user is also analyzed by the emotion engine and sent to the server.

[1251] Through this series of processes, the present invention can efficiently evaluate high-quality works from a wide variety of novels and make optimal recommendations based on the user's emotional state. Furthermore, by continuously improving the evaluation algorithm based on collected emotional data, it will be possible to provide a more accurate novel evaluation system in the future.

[1252] The processing flow will be explained below.

[1253] server

[1254] Step 1:

[1255] The server receives novel data uploaded by authors or publishers. The novel data includes information such as the text, author information, genre, and plot. After receiving the data, it stores it in a database.

[1256] Step 2:

[1257] The server sends the saved novel data to the text analysis module, which performs story structure analysis, character portrayal analysis, stylistic analysis, and plot progression analysis to generate analysis results, which are then sent back to the server.

[1258] Step 3:

[1259] The server inputs the results of the text analysis into multiple generative AI models. Each generative AI model analyzes the novel data based on criteria such as story coherence, character depth, and stylistic beauty. Each AI model generates a specific evaluation score and a detailed review.

[1260] Step 4:

[1261] The server combines the evaluation results returned by each generative AI model. It calculates the average of each evaluation and calculates the overall evaluation score. For example, if AI model A evaluates the score as 8.0, AI model B as 7.5, and AI model C as 9.0, the overall evaluation score will be 8.2.

[1262] Step 5:

[1263] The server notifies the author or publisher of the overall evaluation score and detailed evaluation results. It also automatically generates new catchphrases, introductions, and obi text based on the evaluation results and notifies the author or publisher of these texts.

[1264] Terminal

[1265] Step 6:

[1266] The terminal provides an interface for users to access and operate, through which users can upload novel data, view evaluation results, and submit feedback.

[1267] Step 7:

[1268] The device visually displays the evaluation results sent from the server to the user. Not only the overall evaluation score but also the detailed evaluation results from each generative AI model are displayed. This allows the user to select novels based on evaluation criteria that best suit their preferences.

[1269] Step 8:

[1270] The device collects feedback on the novels the user has read, which is then sent to a server, which uses this information to improve the evaluation algorithm of the generative AI model.

[1271] Introducing the Emotion Engine

[1272] Step 9:

[1273] The server performs sentiment analysis of the feedback provided by the user using an emotion engine, which categorizes the feedback into positive, negative, and neutral categories and sends the analysis results back to the server.

[1274] Step 10:

[1275] The device analyzes the user's emotional state in real time as they read the novel and sends the results to the emotion engine. For example, if the user is using a smartphone or tablet, the device uses their operation patterns and facial recognition technology to recognize their emotions.

[1276] Step 11:

[1277] The server personalizes the novel evaluation results based on real-time emotional data obtained from the emotion engine, and recommends novels that are optimal for the user's emotional state. For example, if the user is feeling sad, it will recommend novels that will soothe the emotions.

[1278] Step 12:

[1279] The server will accumulate the user's emotional history and adjust the novel recommendation algorithm based on past emotional patterns, which will enable more accurate novel evaluation and recommendation in the future.

[1280] Specific examples

[1281] For example, an author of a new novel uploads the novel data to the system through a publisher. The server receives and stores the data. The novel data is then sent to the text analysis module for detailed analysis. Based on the analysis results, each generative AI model evaluates the novel according to its own evaluation criteria. The evaluation results are then integrated to calculate an overall evaluation score.

[1282] The evaluation results are provided to the user via their device. As the user reads the novel, the emotion engine analyzes the user's emotions in real time and sends the data to the server. Personalized evaluation results and recommendations are made based on the user's emotional state, and feedback after reading is also analyzed by the emotion engine.

[1283] The data collected in this way will continuously improve the evaluation algorithms of the generative AI model, ensuring that users always have the best possible novels to choose from, as well as ensuring that authors and publishers have their work properly evaluated.

[1284] Example 2

[1285] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1286] Conventional novel evaluation systems have limited means for objectively evaluating the quality of novels, making it difficult to provide personalized recommendations that take the user's emotional state into account. Furthermore, they lack the means to appropriately utilize user feedback and improve the overall evaluation accuracy of the system. Therefore, a new system is needed that can effectively achieve high-quality novel evaluations and personalized recommendations that reflect the user's emotional state.

[1287] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1288] In this invention, the server includes means for receiving and saving novel data, means for passing the saved novel data to a text analysis module to analyze the story structure, character descriptions, writing style, plot progression, etc., means for inputting the analysis results into multiple generative AI models and evaluating the novel based on their respective evaluation criteria, means for integrating the evaluation results of each generative AI model to calculate an overall evaluation score, means for providing the overall evaluation score and evaluation details, means for analyzing feedback provided by the user with an emotion engine and personalizing the novel evaluation results based on the emotion data, and means for accumulating the user's emotion history and adjusting the novel recommendation algorithm based on past emotion patterns. This enables high-quality novel evaluations and personalized recommendations according to the user's emotional state.

[1289] "Novel data" is digital data that includes the text of the novel, author information, genre, plot summary, etc.

[1290] The "text analysis module" is a software module that analyzes novel data to evaluate the story structure, character descriptions, writing style, plot progression, etc.

[1291] A "generative AI model" is an artificial intelligence model used to evaluate novels based on analysis results. Specifically, it refers to a model that utilizes natural language processing technology.

[1292] The "evaluation criteria" are items that serve as indicators for evaluating a novel, such as the consistency of the story, the depth of the characters, and the clarity of the writing style.

[1293] The "overall evaluation score" is a number that indicates the overall evaluation of a novel, calculated by combining the evaluation results obtained from multiple generative AI models.

[1294] The "emotion engine" is a software engine that analyzes emotions based on user-provided feedback and real-time operational data.

[1295] "Personalization" refers to providing an optimized experience for a user by adjusting the system's behavior and recommendations based on the user's individual attributes and emotional state.

[1296] "Emotion history" is data that records and accumulates a user's past emotional data. This data will improve the accuracy of the recommendation algorithm from the next time onwards.

[1297] "Interface" refers to the means of providing a screen and a set of functions for users to operate a system.

[1298] "Feedback" refers to the user's impressions and evaluations of the novels they have read. It is used to improve the accuracy of the system's evaluations.

[1299] The present invention relates to a system for receiving and storing novel data, a system for analyzing and rating novel data, and a method for improving the accuracy and personalization of novel ratings by combining an emotion engine for analyzing user emotions.

[1300] server

[1301] The server receives novel data sent over the internet from authors or publishers. This data includes the novel's text, author information, genre, and synopsis. The received data is immediately stored in a database. The server uses libraries such as NLTK (Natural Language Toolkit) and SpaCy, which use the Python language, to send the novel data to a text analysis module for analysis. This analyzes the story structure, character descriptions, writing style, and plot progression. The text analysis results are input into multiple generative AI models, which evaluate the story's coherence and character depth. This is done using prompts such as, "Please rate the story coherence and character depth of this newly released novel." The evaluation results from each generative AI model are combined to calculate an overall evaluation score. The calculated overall evaluation score and detailed evaluation results are then notified to the author or publisher. Automatically generated taglines, introductions, and obi text are also provided.

[1302] Terminal

[1303] The terminal provides an interface for users to access and operate the system. This includes uploading novel data, viewing evaluation results, and submitting feedback through a web browser or dedicated application. The evaluation results sent from the server are visually displayed to the user via the terminal. As the user reads the novel, their emotions are analyzed in real time and sent to the emotion engine. This allows emotions to be recognized using the user's operation patterns and facial recognition technology when using a smartphone or tablet. Feedback and impressions provided by the user are also sent from the terminal to the server.

[1304] Emotion Engine

[1305] The emotion engine performs sentiment analysis on feedback provided by users and categorizes them as positive, negative, or neutral. It uses sentiment analysis APIs such as Microsoft Azure's Text Analytics API. It analyzes the user's emotional state in real time and personalizes the novel evaluation results based on this. For example, if a user has a lot of positive comments, it will recommend novels based on those emotions. Emotion data is stored on the server, and the novel recommendation algorithm is adjusted based on past emotional patterns.

[1306] Specific examples

[1307] For example, a user purchases a newly released novel through a device and begins reading it. This novel data is uploaded and stored on a server by the author or publisher. The server then sends the novel data to a text analysis module, which evaluates the story's coherence, character depth, and writing style. The analysis results are input into multiple generative AI models, which then perform an evaluation. The evaluation results are integrated to calculate an overall evaluation score. This score and detailed evaluation results are provided to the user through the device. Furthermore, emotions are analyzed in real time as the user reads the novel, and the user's emotional state is recorded. The emotion engine then personalizes the evaluation results based on this real-time data and makes optimal recommendations to the user. After reading, feedback provided by the user is also analyzed by the emotion engine and sent to the server. Through this series of processes, the present invention can achieve high-quality novel evaluations and personalized recommendations based on the user's emotional state.

[1308] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1309] Step 1:

[1310] The server receives novel data sent from an author or a publisher via the Internet.

[1311] Input: Digital data including the text of the novel, author information, genre, plot summary, etc.

[1312] Data processing: Decodes the received data and converts it into the appropriate format.

[1313] Output: Decoded novel data.

[1314] Specific operation: The server receives data through a specific API endpoint and stores it in a database.

[1315] Step 2:

[1316] The server transmits the stored novel data to a text analysis module.

[1317] Input: Novel data stored in the database.

[1318] Data Computing: Perform natural language analysis using libraries such as Python's NLTK and SpaCy.

[1319] Output: Analysis of narrative structure, characterization, writing style, and plot progression.

[1320] Specific operation: The server passes the data to the analysis module, which analyzes the structure, character, and style of the text.

[1321] Step 3:

[1322] The server inputs the results of the text analysis into multiple generative AI models, which then evaluate the novel based on their respective evaluation criteria.

[1323] Input: Analysis results output from the text analysis module.

[1324] Data calculation: The analysis results are input into each generative AI model and evaluated using prompt statements.

[1325] Output: Evaluation results from each generative AI model.

[1326] Specific behavior: The server generates a prompt statement such as "Please rate the story coherence and character depth of a newly released novel" and gives it to each AI model.

[1327] Step 4:

[1328] The server integrates the evaluation results obtained from each generative AI model and calculates an overall evaluation score.

[1329] Input: Evaluation scores for each generative AI model.

[1330] Data calculation: The evaluation scores are averaged and combined.

[1331] Output: Overall evaluation score.

[1332] Specific operation: The server aggregates the evaluation scores of each AI model, calculates the average value, and derives the overall evaluation score.

[1333] Step 5:

[1334] The server notifies the author or publisher of the detailed evaluation results and the overall evaluation score.

[1335] Input: Overall assessment score and detailed assessment results.

[1336] Data processing: converting the results into a format for notification.

[1337] Output: Notification of evaluation results.

[1338] Specific operation: The server notifies the user of the evaluation results via email or dashboard, and also automatically generates and provides a catchy slogan, introduction, and obi text.

[1339] Step 6:

[1340] The terminal provides an interface for the user to access and operate.

[1341] Input: User operation request.

[1342] Data processing: Generate and display the user interface.

[1343] Output: The interface that is displayed to the user.

[1344] Specific operation: The device provides a UI for uploading, viewing evaluation results, and submitting feedback via a web browser or dedicated app.

[1345] Step 7:

[1346] The terminal visually displays the evaluation results sent from the server to the user.

[1347] Input: The evaluation result sent from the server.

[1348] Data processing: Convert the evaluation results into a visually easy-to-read format.

[1349] Output: The evaluation results that are displayed to the user.

[1350] Specific operation: The device displays the evaluation results in graphs and text, making it easy for the user to understand.

[1351] Step 8:

[1352] The terminal collects feedback from the user and sends it to the server.

[1353] Input: User feedback.

[1354] Data Processing: Collect feedback and convert it into a format that can be sent to the server.

[1355] Output: Feedback data to the server.

[1356] Specific operation: The device accepts feedback via an input form and sends it to the server's feedback API.

[1357] Step 9:

[1358] The server uses an emotion engine to perform emotion analysis of the feedback provided by the user.

[1359] Input: User feedback data.

[1360] Data Computation: Perform sentiment analysis using the sentiment engine.

[1361] Output: Positive, negative, or neutral sentiment classification results.

[1362] Specific operation: The server uses a sentiment analysis API (e.g., Microsoft Azure's Text Analytics API) to perform sentiment classification.

[1363] Step 10:

[1364] The device analyzes the user's emotional state in real time and transmits it to the emotion engine.

[1365] Input: Real-time user operation data.

[1366] Data calculation: Analyzes operational data and recognizes real-time emotional states.

[1367] Output: Emotion state data to the emotion engine.

[1368] Specific operation: The device estimates the user's emotional state using facial recognition and operation patterns, and transmits the information to the server in real time.

[1369] Step 11:

[1370] The server personalizes the evaluation results of the novel based on the emotional data obtained from the emotion engine.

[1371] Input: Emotion data from the emotion engine.

[1372] Data calculation: Emotional data is used to individually optimize evaluation results.

[1373] Output: Personalized assessment results.

[1374] Specific operation: The server analyzes the emotion data and adjusts the evaluation results based on the user's emotion patterns.

[1375] Step 12:

[1376] The server accumulates the user's emotional history data and adjusts the novel recommendation algorithm based on past emotional patterns.

[1377] Input: Emotion history data.

[1378] Data calculation: Emotional data is accumulated and used to adjust algorithms.

[1379] Output: The adjusted recommendation algorithm.

[1380] Specific operation: The server stores the emotion history data in a database and optimizes the next recommendation based on past patterns.

[1381] (Application example 2)

[1382] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1383] Conventional novel rating systems rely on fixed evaluation criteria and have the problem of not being able to fully reflect the individual feelings and preferences of users. This makes it difficult to recommend novels that truly interest users and are personalized. Furthermore, because it is not possible to check feelings in real time and update evaluation results accordingly, users' reading experience is uniform, which can lead to a decrease in satisfaction.

[1384] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: [means for receiving and saving novel data;] [means for passing the saved novel data to a text analysis module and analyzing the story structure, character descriptions, writing style, plot progression, etc.;] [means for inputting the analysis results into multiple generative AI models and evaluating the novel based on their respective evaluation criteria;] [means for integrating the evaluation results of each generative AI model and calculating an overall evaluation score;] [means for providing the overall evaluation score and evaluation content;] [means for analyzing the user's emotions in real time and personalizing the evaluation results based on the emotional state; and] [means for accumulating the user's emotional history data and adjusting the evaluation algorithm.] This enables highly accurate personalized evaluation and recommendations based on the user's emotions and preferences.

[1385] "Novel data" refers to data sent by the author or publisher that includes the text of the novel, author information, genre, plot summary, etc.

[1386] The "text analysis module" is a software module for analyzing the narrative structure, character descriptions, writing style, plot progression, etc. of novel data.

[1387] A "generative AI model" is an artificial intelligence model that has multiple different evaluation criteria for evaluating novels based on the results of text analysis.

[1388] "Evaluation results" is a collective term for scores and detailed reviews based on each evaluation criterion applied to the novel data analyzed by the generative AI model.

[1389] The "overall evaluation score" is an overall evaluation score calculated by integrating the evaluation results from multiple generative AI models.

[1390] An "emotion engine" is a software engine that analyzes users' emotions and reflects the results in rating and recommending novels.

[1391] "Personalized ratings" refer to ratings or recommendations that are tailored based on a user's emotional state and preferences.

[1392] "Emotion history data" is data about a user's past emotional patterns, information that is used to adjust future rating algorithms.

[1393] An "interface" is an operation screen or operation means that allows users to upload novel data, view evaluation results, submit feedback, and so on.

[1394] The present invention relates to a system for receiving and storing novel data, a system for analyzing and evaluating novel data, and a method for combining an emotion engine that analyzes user emotions to improve the accuracy and personalization of evaluations.

[1395] Server Roles

[1396] The server has the following functions:

[1397] Data reception and storage

[1398] The server receives novel data sent from authors or publishers via the Internet. This data includes the novel's text, author information, genre, plot summary, etc. The received data is immediately stored in a database.

[1399] Text analytics

[1400] The server passes the saved novel data to the text analysis module, which performs the following analysis:

[1401] Story structure analysis: Analyze the beginning, development, twist, and conclusion of a story, scene transitions, and consistency of the timeline.

[1402] Character description analysis: Analyze the characters' personalities, backgrounds, and relationships with each other.

[1403] Stylistic analysis: Evaluating the rhythm of the writing, vocabulary, grammatical accuracy, etc.

[1404] Plot progression analysis: Evaluating whether the story unfolds logically and coherently.

[1405] AI evaluation

[1406] The server inputs the text analysis results into multiple generative AI models. Each AI model evaluates the analysis results based on its own criteria. For example, one AI model may emphasize story coherence, while another emphasizes character depth. Each AI model generates a specific score and a detailed review based on its own criteria.

[1407] Evaluation Integration

[1408] The server integrates the evaluation results obtained from each generative AI model. At this time, it calculates the average of the evaluations to calculate an overall evaluation score. For example, if the individual AI evaluations are 9.0, 8.5, and 8.0, respectively, the overall evaluation score will be 8.5.

[1409] Emotion Recognition and Real-Time Analysis

[1410] The server uses an emotion engine to perform an emotional analysis of the feedback provided by the user. For example, it automatically classifies feedback into positive, negative, and neutral. Furthermore, the device analyzes the user's emotional state in real time as they read the novel, and transmits the results to the emotion engine. For example, if the user is using a smartphone, their emotions are recognized by utilizing their operation patterns and facial recognition technology.

[1411] Personalized Evaluation

[1412] The server personalizes the evaluation results of novels based on the emotional data obtained from the emotion engine. For example, if a user typically provides many positive reviews, the server will make recommendations that match that emotional pattern. This enables highly accurate personalized evaluations and recommendations based on the user's emotions and preferences.

[1413] Accumulation of emotional history

[1414] The server accumulates users' emotional history data and adjusts the novel recommendation algorithm based on their past emotional patterns, enabling more accurate recommendations in the future.

[1415] Device Role

[1416] The terminal has the following functions:

[1417] Providing an interface

[1418] The terminal provides an interface for users to access and operate, through which users can perform the following operations:

[1419] Uploading novel data

[1420] Viewing evaluation results

[1421] Submitting Feedback

[1422] Displaying the evaluation results

[1423] The terminal visually displays the evaluation results sent from the server to the user, allowing the user to select novels based on evaluation criteria that are closest to their preferences.

[1424] Gathering feedback

[1425] The device collects feedback on the novels that users have read and sends their impressions and evaluations to the server, thereby contributing to improving the accuracy of the AI ​​evaluation.

[1426] emotion recognition

[1427] The terminal uses the input device of the smart device to recognize the user's emotional state in real time and transmits the emotional data to the server.

[1428] Specific examples

[1429] For example, suppose a user purchases a newly released novel through a device and begins reading it. The novel data is uploaded and stored on a server by the author or publisher. The server sends the novel data to a text analysis module, which generates analysis results. The results are then input into multiple generative AI models, which evaluate the novel on factors such as story coherence, character depth, and stylistic clarity. The evaluation results are then combined to calculate an overall evaluation score.

[1430] The evaluation results are provided to the user via their device. Furthermore, while the user is reading the novel, their emotions are analyzed in real time and their emotional state is recorded. The emotion engine uses this real-time data to personalize the evaluation results and make optimal recommendations to the user. After finishing reading, the feedback provided by the user is also analyzed by the emotion engine and sent to the server.

[1431] Example prompts to input to the generative AI model

[1432] 1. If the user expresses positive sentiment:

[1433] "How entertaining is this paragraph if it makes the user smile?"

[1434] 2. If the user expresses negative sentiment:

[1435] "If users frowned, what was their criticism of the work?"

[1436] Through this series of processes, the present invention can efficiently evaluate high-quality works from a wide variety of novels and make optimal recommendations based on the user's emotional state. Furthermore, by continuously improving the evaluation algorithm based on collected emotional data, it will be possible to provide a more accurate novel evaluation system in the future.

[1437] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1438] Step 1:

[1439] The server receives novel data from authors or publishers via the Internet and stores the data in a database. Specifically, when a user sends novel data, the server receives the data, extracts metadata such as the text, author information, genre, and plot, and stores the data in a database. The input is the novel data, and the output is the stored novel data.

[1440] Step 2:

[1441] The server sends the saved novel data to the text analysis module. The text analysis module performs the following analyses: story structure analysis, character description analysis, writing style analysis, and plot progression analysis. The data obtained from these analyses becomes the respective analysis results. The input is the saved novel data, and the output is each analysis result.

[1442] Step 3:

[1443] The server inputs the text analysis results into multiple generative AI models. Each AI model evaluates the analysis results based on its own evaluation criteria and generates a specific score and detailed review. The input is each analysis result, and the output is the evaluation score and review.

[1444] Step 4:

[1445] The server integrates the evaluation results obtained from each generative AI model and calculates an overall evaluation score. At this time, it calculates the average of the evaluations to calculate the overall evaluation score. For example, if the AI ​​evaluations are 9.0, 8.5, and 8.0 respectively, the overall evaluation score will be 8.5. The input is each evaluation result, and the output is the overall evaluation score.

[1446] Step 5:

[1447] The server notifies the author or publisher of the calculated overall evaluation score and detailed evaluation results. It also automatically generates new catchphrases, introductions, and obi text based on the evaluation results and provides them to the author or publisher. The input is the overall evaluation score and each evaluation result, and the output is the notification and the generated text.

[1448] Step 6:

[1449] The terminal provides an interface for users to upload novel data. When a user uploads novel data, the terminal sends the data to the server. The input is the novel data entered by the user, and the output is the novel data sent to the server.

[1450] Step 7:

[1451] The terminal visually displays the evaluation results sent from the server to the user, allowing the user to select novels based on evaluation criteria that best suit their preferences. The input is the evaluation results from the server, and the output is the displayed evaluation results.

[1452] Step 8:

[1453] As the user reads the novel, the device uses the smartphone's camera and microphone to recognize the user's emotional state in real time and transmits the emotional data to the server. The input is data from the emotion recognition device (camera and microphone), and the output is the emotional data transmitted to the server.

[1454] Step 9:

[1455] The server uses an emotion engine to analyze the user's emotional data and personalize the evaluation results in real time. If the user expresses positive emotions, the evaluation results are adjusted to lean more positively. The input is the user's real-time emotional data, and the output is the personalized evaluation results.

[1456] Step 10:

[1457] Based on the emotion data obtained from the emotion engine and the user's past emotion history data, the server adjusts the novel recommendation algorithm and recommends the most suitable novel for the user. The input is the emotion history data and real-time emotion data, and the output is the adjusted recommendation algorithm and the recommended novel.

[1458] The above processing steps enable highly accurate personalized evaluation and recommendations based on the user's emotions and preferences.

[1459] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1460] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1461] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1462] [Fourth embodiment]

[1463] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1464] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1465] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1466] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1467] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1468] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1469] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1470] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1471] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1472] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1473] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1474] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1475] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1476] server

[1477] 1. Data Receipt and Storage

[1478] The server receives novel data sent via the Internet from authors or publishers. This data includes the text of the novel, author information, genre, plot summary, etc. The received data is immediately stored in a database.

[1479] 2. Text Analysis

[1480] The server sends the stored novel data to the text analysis module, which performs the following analysis:

[1481] Story structure analysis: Analyzes the beginning, development, twist, and conclusion of a story, scene transitions, and consistency of the timeline.

[1482] Character description analysis: Analyze the characters' personalities, backgrounds, and relationships with each other.

[1483] Stylistic analysis: Evaluating the rhythm of the writing, vocabulary, grammatical accuracy, etc.

[1484] Plot progression analysis: Evaluating whether the story unfolds logically and coherently.

[1485] 3. AI Evaluation

[1486] The server inputs the text analysis results into multiple generative AI models. Each AI model evaluates the analysis results based on its own criteria. For example, one AI model may emphasize story coherence, while another emphasizes character depth. Each AI model generates a specific score and a detailed review based on its own criteria.

[1487] 4. Evaluation Integration

[1488] The server integrates the evaluation results obtained from multiple generative AI models. At this time, it calculates the average of the evaluations to calculate an overall evaluation score. For example, if the individual AI evaluations are 9.0, 8.5, and 8.0, respectively, the overall evaluation score will be 8.5.

[1489] 5. Providing results

[1490] The server then notifies the author or publisher of the calculated overall score and detailed evaluation results. This information may be used as marketing material, and is also used to generate new taglines, introductions, and obi text. The generated text is then provided to the author or publisher, who can revise it as needed.

[1491] Terminal

[1492] 1. Providing an interface

[1493] The terminal provides an interface for users to access and operate. Through this interface, users can:

[1494] Uploading novel data

[1495] Viewing evaluation results

[1496] Submitting Feedback

[1497] 2. Display of evaluation results

[1498] The evaluation results sent from the server are visually displayed on the device, allowing users to select an appropriate novel based on this. Individual evaluation results from each AI model are also displayed, allowing users to use this information to help them select evaluation criteria that best suit their preferences.

[1499] 3. Gathering Feedback

[1500] After reading a novel, readers submit their ratings and impressions through a feedback form. This feedback is sent to the server and used to improve the evaluation algorithm of the generative AI model.

[1501] User

[1502] 1. Uploading a Novel

[1503] Authors or publishers upload novel data through the device's interface, which is then sent to the server and stored.

[1504] 2. Viewing the evaluation results

[1505] Authors and publishers can check the evaluation results sent from the server on their devices, allowing them to understand how their work has been evaluated and identify areas for improvement.

[1506] 3. Providing Feedback

[1507] After finishing a novel, readers can provide feedback via their devices, which will help the AI ​​make a more accurate assessment.

[1508] Specific examples

[1509] For example, when a well-known author writes a new novel and uploads it to the system through a publisher, the novel data is first received and stored on the server. It is then analyzed by a text analysis module, which performs a detailed analysis of the story structure, character descriptions, writing style, etc. The analysis results are input into multiple generative AI models, each of which evaluates the novel based on its own evaluation criteria. As a result, an overall evaluation score is calculated, and the evaluation results are notified to the author and publisher. Based on this evaluation result, new catchphrases and introductions are automatically generated and used in promotional activities. Readers can use the evaluation results as a reference when selecting a novel, and provide feedback after reading, contributing to improving the accuracy of the AI ​​evaluation.

[1510] In this way, the present invention realizes an environment in which hidden masterpieces can be easily discovered by efficiently evaluating high-quality works and providing them to readers amidst the proliferation of novels.

[1511] The processing flow will be explained below.

[1512] Step 1:

[1513] The server receives novel data sent via the Internet from authors or publishers. This data includes the text of the novel, author information, genre, plot summary, etc. The received data is immediately stored in a database.

[1514] Step 2:

[1515] The server sends the saved novel data to the text analysis module, which performs grammatical analysis, sentiment analysis, keyword extraction, etc. of the novel, and generates and returns the analysis results to the server.

[1516] Step 3:

[1517] The server inputs the results of the text analysis into multiple generative AI models. Each AI model evaluates the novel data based on criteria such as story coherence, character depth, and stylistic clarity. Each AI model generates a rating score and a detailed review.

[1518] Step 4:

[1519] The server integrates the evaluation results from each generative AI model. At this time, it calculates the average of each evaluation to calculate an overall evaluation score. For example, if AI model A evaluates 8.0, AI model B evaluates 7.0, and AI model C evaluates 9.0, the average is calculated and the overall evaluation score is 8.0.

[1520] Step 5:

[1521] The server notifies the author or publisher of the calculated overall evaluation score and detailed evaluation results. The notification also includes the individual evaluation results of each AI model and the evaluation criteria. Based on the evaluation results, the server automatically generates new catchphrases, introductions, and obi text and provides them to the author or publisher.

[1522] Step 6:

[1523] The terminal provides an interface for users (authors, publishers, and readers) to access and operate, through which users can upload novel data, view evaluation results, and submit feedback.

[1524] Step 7:

[1525] The device visually displays the evaluation results sent from the server to the user. It displays not only the overall evaluation score but also the detailed evaluation results from each AI model. This allows the user to select novels based on evaluation criteria that best suit their preferences.

[1526] Step 8:

[1527] The device collects feedback from readers about the novels they have read, and sends the information submitted through a feedback form to a server, which then reflects the collected feedback in the generative AI model, thereby contributing to improving the accuracy of the evaluation algorithm.

[1528] Step 9:

[1529] Users (authors, publishers, and readers) can use the device to check the new catchphrases and introductions, decide whether they are appropriate, and, if necessary, revise the automatically generated text to use as the final marketing material.

[1530] Step 10:

[1531] The server analyzes the collected feedback and uses it to improve the evaluation criteria of the generative AI model, which will improve the accuracy of future novel evaluations and enable better recommendations.

[1532] Example 1

[1533] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1534] Conventional literary evaluation systems often lack uniformity and fairness in their evaluations, and do not evaluate works from a variety of perspectives, making it difficult to determine their true value. Furthermore, there is no efficient way to collect feedback from many users, resulting in a lack of reference information for revising and releasing works.

[1535] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1536] In this invention, the server includes means for receiving and saving literary data, means for passing the saved literary data to a natural language analysis module to analyze the narrative structure, character traits, writing style, and story progression, means for inputting the analysis results into a plurality of AI models to evaluate the literary work based on their respective evaluation criteria, means for integrating the evaluation results of each AI model to calculate an overall evaluation score, and means for providing the overall evaluation score and the evaluation content, thereby enabling high-quality literary evaluation and detailed feedback from a variety of perspectives.

[1537] "Literary data" refers to data that includes information such as the text of a work, author information, genre, and plot.

[1538] A "natural language analysis module" is a program that analyzes text data and evaluates the structure of the story, the characteristics of the characters, the writing style, the progression of the story, etc.

[1539] A "generative artificial intelligence model" is an artificial intelligence program that evaluates text data according to specific evaluation criteria based on previously learned data.

[1540] The "overall evaluation score" is a numerical value that indicates the overall evaluation by integrating the individual evaluation results obtained from multiple generating artificial intelligence models.

[1541] "Upload Interface" is a platform through which users can submit literary data to the system.

[1542] The "visual display means" is a mechanism for displaying the evaluation results to the user as graphs or text.

[1543] The "feedback collection means" is a means for receiving evaluations and impressions from users and transmitting them to the server.

[1544] A "catchphrase" is a short, catchy phrase used to introduce a work to the market.

[1545] An "introduction" is a short sentence that explains the outline and characteristics of the work.

[1546] "Obi text" refers to short sentences or catchphrases printed on the book's obi, and serves to stimulate purchasing desire.

[1547] server

[1548] 1. Data Receipt and Storage

[1549] The server receives literary data sent by connected authors or publishers via the Internet. This data includes the text of the work, author information, genre, plot summary, etc. The received data is immediately stored in the database. For example, when an author uploads a new work, the data is sent to the server and stored.

[1550] 2. Text Analysis

[1551] The server sends the stored literary data to a natural language analysis module, which analyzes the narrative structure, character traits, writing style, and story progression. For example, it analyzes the beginning, development, climax, and conclusion of a story and detects how each part is structured.

[1552] 3. AI Evaluation

[1553] The server then feeds the analysis results into multiple artificial intelligence models, which evaluate literary works based on their own criteria: for example, one AI model focuses on story coherence, while another evaluates character portrayals.

[1554] 4. Evaluation Integration

[1555] The server integrates the evaluation results obtained from each AI model and calculates an overall evaluation score. For example, if model A is evaluated as 8.5, model B as 9.0, and model C as 8.0, the server calculates the average of these scores and uses this as the overall evaluation score.

[1556] 5. Providing results

[1557] The server then notifies the author or publisher of the calculated overall score and detailed evaluation. This information is used as marketing material and is also utilized to generate new catchphrases, descriptions, and obi text. For example, the server may notify the author or publisher of the evaluation result, saying, "This work has been evaluated for its story consistency, with an overall score of 8.5."

[1558] Terminal

[1559] 1. Providing an interface

[1560] The terminal provides an interface for users to access and operate, through which users can upload literary data, view evaluation results, and provide feedback. For example, a user can submit a work using a form for uploading a novel.

[1561] 2. Display of evaluation results

[1562] The evaluation results sent from the server are visually displayed on the device, allowing users to select an appropriate novel based on this information. Individual evaluation results from each generated AI model are also displayed, helping users choose evaluation criteria that best suit their preferences. For example, the dashboard displays the overall evaluation score and detailed evaluation results in graphs and text.

[1563] 3. Gathering Feedback

[1564] After a reader finishes reading a novel, they submit their rating and thoughts through a feedback form. This feedback is sent to the server and used to improve the evaluation algorithm of the AI ​​model that generates it. For example, reader comments such as "The story development was fascinating" are collected.

[1565] User

[1566] 1. Uploading a Novel

[1567] Authors or publishers upload literary data through the device interface. The uploaded data is sent to the server and stored. For example, when uploading a new novel, they enter the necessary information and press the submit button, and the data is stored on the server.

[1568] 2. Viewing the evaluation results

[1569] Authors and publishers can check the evaluation results sent from the server on their devices. This allows them to understand how their work has been evaluated and identify areas for improvement. For example, they can check the evaluation score and detailed feedback on a dashboard.

[1570] 3. Providing Feedback

[1571] After finishing a novel, readers can provide feedback via their devices, which will help the AI ​​model to generate a more accurate evaluation. For example, after finishing a novel, readers can fill out a feedback form and press the submit button, which will send the feedback to the server.

[1572] Specific prompt examples

[1573] "Please enter the text of the novel."

[1574] Analyze the characters' personalities

[1575] "Evaluate the coherence of the story."

[1576] This makes it possible to efficiently evaluate high-quality works from among many literary works and provide them to readers, creating an environment in which hidden masterpieces can be easily discovered.

[1577] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1578] Step 1: Receiving and storing data

[1579] The server receives literary data sent by connected authors or publishers via the Internet. The input includes data such as the novel text, author information, genre, and plot summary. The server verifies that the data has been received correctly, and if successful, it is stored in a database. For example, when a new work is uploaded, all of its data arrives at the server and is immediately stored in the database.

[1580] Step 2: Text analysis

[1581] The server sends the stored literary data to a natural language analysis module. The literary data is used as input. The natural language analysis module analyzes the structure of the story (beginning, development, climax, conclusion, etc.), the characteristics of the characters (personalities, background, etc.), the writing style (rhythm, vocabulary, etc.), and the progression of the story (consistency of the timeline, etc.), and outputs the results of these analyses. For example, it identifies and analyzes the beginning, middle, climax, and conclusion of a story.

[1582] Step 3: AI evaluation

[1583] The server inputs the analysis results into multiple AI models. The text analysis results are used as input. The AI ​​models evaluate literary works based on their respective evaluation criteria (e.g., story coherence, character depth, etc.). Each AI model outputs a specific score and a detailed review. For example, an AI model that emphasizes story coherence will evaluate the work based on that criteria and output its results.

[1584] Step 4: Consolidating the assessments

[1585] The server integrates the evaluation results obtained from each generated AI model. Evaluation results from multiple AI models are used as input. The server calculates the average of these evaluation results and outputs an overall evaluation score. For example, if the evaluation scores are 9.0, 8.5, and 8.0, the average of these, 9.0, is calculated as the overall evaluation score.

[1586] Step 5: Delivering results

[1587] The server notifies the author or publisher of the calculated overall rating score and detailed rating content. The overall rating score and detailed rating content are used as input. The rating result is notified to the author or publisher as output. For example, a notification may be sent saying, "This work has an overall rating score of 8.5."

[1588] Step 6: Providing an Interface

[1589] The terminal provides an interface for users to access and operate. User operations are used as input. The terminal provides and outputs a form for users to upload literary data and a dashboard for viewing evaluation results. For example, when a user clicks the upload button, the following page is displayed.

[1590] Step 7: View the evaluation results

[1591] The terminal visually displays the evaluation results sent from the server. The evaluation results from the server are used as input. The evaluation results are output in graph and text format on the dashboard, helping users to select the appropriate novel. For example, the terminal displays the overall evaluation score and detailed evaluations by each AI model.

[1592] Step 8: Gather feedback

[1593] The terminal provides a means for the reader user to submit their evaluation and thoughts through a feedback form after finishing reading the novel. The user's feedback is used as input. The submitted feedback is sent to the server and used to improve the evaluation algorithm of the generated artificial intelligence model. For example, a comment such as "The story development was very satisfying" can be entered and submitted in the feedback form.

[1594] Through these steps, this system is able to evaluate literary works from multiple perspectives and provide readers with high-quality works.

[1595] (Application example 1)

[1596] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1597] This invention relates to a system that efficiently evaluates high-quality works amidst the proliferation of novels and provides them to readers. Conventional evaluation methods make it difficult for authors and publishers to quickly and accurately grasp the quality of works, and readers lack the information necessary to select appropriate works. Furthermore, the collection and utilization of feedback is inefficient, resulting in a lack of consistency in the evaluation of works. It is necessary to solve these issues and improve the process of evaluating and providing novels.

[1598] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1599] In this invention, the server includes: [means for receiving and saving novel data; [means for passing the saved novel data to a text analysis module and having it analyze the story structure, character descriptions, writing style, plot progression, etc.; and [means for inputting the analysis results into multiple generative AI models and having them evaluate the novel based on their respective evaluation criteria.] This makes it possible [to integrate the evaluation results of each generative AI model, calculate an overall evaluation score, and provide the overall evaluation score and evaluation content].

[1600] "Novel data" refers to data such as the text of a novel, author information, genre, and plot summary provided by the author or publisher.

[1601] A "text analysis module" is software or hardware used to analyze novel data and evaluate the story structure, character descriptions, writing style, plot progression, etc.

[1602] A "generative AI model" is an artificial intelligence model that evaluates novels based on the results of analyzing novel data and each evaluation criterion.

[1603] The "overall evaluation score" is a number calculated by combining the evaluation results from multiple generative AI models, and is used to comprehensively evaluate the quality of the entire novel.

[1604] A "smartphone application" is software that runs on a smartphone and provides functions such as uploading novel data, displaying evaluation results, and collecting feedback.

[1605] "Feedback" refers to the impressions and evaluations that readers provide after finishing a novel, and is information that is sent to the server and contributes to improving the accuracy of the generative AI model.

[1606] The "interface" is the UI (user interface) that users can operate, allowing them to upload novel data, view evaluation results, and submit feedback.

[1607] A "catchphrase" is a short phrase used in marketing and promotional activities to effectively convey the appeal of a novel.

[1608] An "introduction" is a text that explains the content and characteristics of a novel and is used to convey an overview of the work to customers.

[1609] "Book cover text" refers to advertising slogans or catch phrases printed on a piece of paper attached to the outside of a book's cover, intended to motivate customers to purchase the book.

[1610] In this invention, the server receives, stores, analyzes, evaluates, and provides results of novel data using the following means.

[1611] server

[1612] 1. Data Receipt and Storage

[1613] The server receives novel data sent via the Internet from authors or publishers. This data includes the text of the novel, author information, genre, plot summary, etc. The received data is immediately stored in a database.

[1614] 2. Text Analysis

[1615] The server sends the saved novel data to the text analysis module, which uses a Python natural language processing library (e.g., NLTK or spaCy). The text analysis module performs the following analysis:

[1616] Story structure analysis: Analyzes the beginning, development, twist, and conclusion of a story, scene transitions, and consistency of the timeline.

[1617] Character description analysis: Analyze the characters' personalities, backgrounds, and relationships with each other.

[1618] Stylistic analysis: Evaluating the rhythm of the writing, vocabulary, grammatical accuracy, etc.

[1619] Plot progression analysis: Evaluating whether the story unfolds logically and coherently.

[1620] 3. AI Evaluation

[1621] The server inputs the text analysis results into multiple generative AI models. Each generative AI model evaluates the analysis results based on its own evaluation criteria. Examples of AI models used include OpenAI's GPT-3. Each AI model generates a specific score and a detailed review based on its own evaluation criteria.

[1622] 4. Evaluation Integration

[1623] The server integrates the evaluation results obtained from multiple generative AI models, calculating the average of the evaluations and deriving an overall evaluation score.

[1624] 5. Providing results

[1625] The server then notifies the author or publisher of the calculated overall score and detailed evaluation results. This information is used as marketing material and is also used to generate new taglines, introductions, and obi text. The generated text is then provided to the author or publisher, who can revise it as needed.

[1626] Terminal

[1627] 1. Providing an interface

[1628] The terminal provides an interface for users to access and operate. Through this interface, users can:

[1629] Uploading novel data

[1630] Viewing evaluation results

[1631] Submitting Feedback

[1632] 2. Display of evaluation results

[1633] The evaluation results sent from the server are visually displayed on the device, allowing users to select an appropriate novel based on this. Individual evaluation results from each AI model are also displayed, allowing users to use this information to help them select evaluation criteria that best suit their preferences.

[1634] 3. Gathering Feedback

[1635] After reading a novel, readers submit their ratings and impressions through a feedback form. This feedback is sent to the server and used to improve the evaluation algorithm of the generative AI model.

[1636] User

[1637] 1. Uploading a Novel

[1638] Authors or publishers upload novel data through the device's interface, which is then sent to the server and stored.

[1639] 2. Viewing the evaluation results

[1640] Authors and publishers can check the evaluation results sent from the server on their devices, allowing them to understand how their work has been evaluated and identify areas for improvement.

[1641] 3. Providing Feedback

[1642] After finishing a novel, readers provide feedback through their devices, which helps the AI ​​to more accurately evaluate it.

[1643] Specific examples

[1644] For example, when an author writes a new novel and uploads it to the system via their device, the novel data is first received and stored on the server. The text analysis module then analyzes the story structure, character descriptions, writing style, and other aspects, and the analysis results are input into multiple generative AI models. The evaluation results are then integrated to calculate an overall evaluation score. The author and publisher are notified of this evaluation result, and a new catchphrase and introduction are automatically generated based on it.

[1645] Prompt Sentence Examples

[1646] Please rate the following novel data in terms of plot coherence, character depth, stylistic rhythm, etc.

[1647] Novel Title: New Novel

[1648] Author: Famous Author

[1649] Genre: Fantasy

[1650] Synopsis: This is a sample story

[1651] Novel content: The main text of the novel...

[1652] Please provide your evaluation in the following format:

[1653] 1. Overall evaluation score

[1654] 2. Detailed evaluation of story coherence

[1655] 3. Detailed evaluation of character depth

[1656] 4. Detailed evaluation of stylistic rhythm

[1657] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1658] Step 1:

[1659] The device receives novel data from the author or publisher. The novel data includes the text, author information, genre, and synopsis. The device uses this data as input and sends an HTTP POST request to the server. This sends the novel data to the server and stores it in a database.

[1660] Step 2:

[1661] The server sends the saved novel data to the text analysis module, which uses a Python natural language processing library (such as NLTK or spaCy). Here, the following data processing is performed and the analysis results are output:

[1662] Story structure analysis (beginning, development, twist, conclusion, scene transitions, etc.)

[1663] Character description analysis (personality, background, relationships, etc.)

[1664] Stylistic analysis (rhythm, vocabulary, grammatical accuracy, etc.)

[1665] Plot progression analysis (logic of development, consistency, etc.)

[1666] Step 3:

[1667] The server inputs the text analysis results into multiple generative AI models, such as OpenAI's GPT-3. Each generative AI model performs the following data calculations and outputs an individual rating score and detailed review:

[1668] Story consistency

[1669] Character depth

[1670] Stylistic rhythm and variety

[1671] Overall rating score

[1672] Step 4:

[1673] The server integrates the evaluation results obtained from multiple generative AI models. Specifically, it calculates the average of the evaluation scores of each model and outputs an overall evaluation score. It also integrates detailed evaluation reviews to generate a single evaluation report. These results are stored in the server database.

[1674] Step 5:

[1675] The server outputs the evaluation results—namely, the overall evaluation score and a detailed evaluation report—in JSON format via an API endpoint to provide them to the user's device, where the user (author or publisher) can visually check these evaluation results.

[1676] Step 6:

[1677] The terminal provides a GUI (Graphical User Interface) to visually display the evaluation results. Users can view the evaluation scores and detailed evaluation reviews through this interface, which allows them to deepen their understanding of their work and identify areas for improvement.

[1678] Step 7:

[1679] After finishing reading a novel, users (readers) provide their ratings and impressions using a feedback form. The device sends this feedback to the server and stores it as data used to improve the evaluation algorithm of the generative AI model.

[1680] Prompt Sentence Examples

[1681] Please rate the following novel data in terms of plot coherence, character depth, stylistic rhythm, etc.

[1682] Novel Title: New Novel

[1683] Author: Famous Author

[1684] Genre: Fantasy

[1685] Synopsis: This is a sample story

[1686] Novel content: The main text of the novel...

[1687] Please provide your evaluation in the following format:

[1688] 1. Overall evaluation score

[1689] 2. Detailed evaluation of story coherence

[1690] 3. Detailed evaluation of character depth

[1691] 4. Detailed evaluation of stylistic rhythm

[1692] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1693] The present invention relates to a system for receiving and storing novel data, a system for analyzing and rating novel data, and a method for improving the accuracy and personalization of novel ratings by combining an emotion engine that analyzes user emotions.

[1694] server

[1695] 1. Data Receipt and Storage

[1696] The server receives novel data sent via the Internet from authors or publishers. This data includes the text of the novel, author information, genre, plot summary, etc. The received data is immediately stored in a database.

[1697] 2. Text Analysis

[1698] The server sends the stored novel data to the text analysis module, which performs the following analysis:

[1699] Story structure analysis: Analyzes the beginning, development, twist, and conclusion of a story, scene transitions, and consistency of the timeline.

[1700] Character description analysis: Analyze the characters' personalities, backgrounds, and relationships with each other.

[1701] Stylistic analysis: Evaluating the rhythm of the writing, vocabulary, grammatical accuracy, etc.

[1702] Plot progression analysis: Evaluating whether the story unfolds logically and coherently.

[1703] 3. AI Evaluation

[1704] The server inputs the text analysis results into multiple generative AI models. Each AI model evaluates the analysis results based on its own criteria. For example, one AI model may emphasize story coherence, while another emphasizes character depth. Each AI model generates a specific score and a detailed review based on its own criteria.

[1705] 4. Evaluation Integration

[1706] The server integrates the evaluation results obtained from each generative AI model. At this time, it calculates the average of the evaluations to calculate an overall evaluation score. For example, if the individual AI evaluations are 9.0, 8.5, and 8.0, respectively, the overall evaluation score will be 8.5.

[1707] 5. Providing results

[1708] The server notifies the author or publisher of the calculated overall evaluation score and detailed evaluation results. It also automatically generates new catchphrases, introductions, and obi text based on the evaluation results and provides them to the author or publisher.

[1709] Terminal

[1710] 1. Providing an interface

[1711] The terminal provides an interface for users to access and operate. Through this interface, users can:

[1712] Uploading novel data

[1713] Viewing evaluation results

[1714] Submitting Feedback

[1715] 2. Display of evaluation results

[1716] The terminal visually displays the evaluation results sent from the server to the user, allowing the user to select novels based on evaluation criteria that are closest to their preferences.

[1717] 3. Gathering Feedback

[1718] The device collects feedback on the novels that users have read and sends their impressions and evaluations to the server, thereby contributing to improving the accuracy of the AI ​​evaluation.

[1719] Introducing the Emotion Engine

[1720] 1. Emotion recognition

[1721] The server uses an emotion engine to perform sentiment analysis of the feedback provided by the user, for example, automatically classifying it as positive, negative, or neutral.

[1722] 2. Real-time analysis

[1723] The device analyzes the user's emotional state in real time as they read the novel, and sends the results to the emotion engine. For example, if the user is using a smartphone or tablet, the device recognizes their emotions by utilizing their operation patterns and facial recognition technology.

[1724] 3. Personalized evaluation

[1725] The server personalizes the novel evaluation results based on the emotional data obtained from the emotion engine. For example, if a user typically provides many positive reviews, the server will make recommendations that match that emotional pattern.

[1726] 4. Accumulation of emotional history

[1727] The server accumulates users' emotional history data and adjusts the novel recommendation algorithm based on their past emotional patterns, enabling more accurate recommendations in the future.

[1728] Specific examples

[1729] For example, suppose a user purchases a newly released novel through a device and begins reading it. The novel data is uploaded and stored on a server by the author or publisher. The server sends the novel data to a text analysis module, which generates analysis results. The results are then input into multiple generative AI models, which evaluate the novel on factors such as story coherence, character depth, and stylistic clarity. The evaluation results are then combined to calculate an overall evaluation score.

[1730] The evaluation results are provided to the user via their device. Furthermore, while the user is reading the novel, their emotions are analyzed in real time and their emotional state is recorded. The emotion engine uses this real-time data to personalize the evaluation results and make optimal recommendations to the user. After finishing reading, the feedback provided by the user is also analyzed by the emotion engine and sent to the server.

[1731] Through this series of processes, the present invention can efficiently evaluate high-quality works from a wide variety of novels and make optimal recommendations based on the user's emotional state. Furthermore, by continuously improving the evaluation algorithm based on collected emotional data, it will be possible to provide a more accurate novel evaluation system in the future.

[1732] The processing flow will be explained below.

[1733] server

[1734] Step 1:

[1735] The server receives novel data uploaded by authors or publishers. The novel data includes information such as the text, author information, genre, and plot. After receiving the data, it stores it in a database.

[1736] Step 2:

[1737] The server sends the saved novel data to the text analysis module, which performs story structure analysis, character portrayal analysis, stylistic analysis, and plot progression analysis to generate analysis results, which are then sent back to the server.

[1738] Step 3:

[1739] The server inputs the results of the text analysis into multiple generative AI models. Each generative AI model analyzes the novel data based on criteria such as story coherence, character depth, and stylistic beauty. Each AI model generates a specific evaluation score and a detailed review.

[1740] Step 4:

[1741] The server combines the evaluation results returned by each generative AI model. It calculates the average of each evaluation and calculates the overall evaluation score. For example, if AI model A evaluates the score as 8.0, AI model B as 7.5, and AI model C as 9.0, the overall evaluation score will be 8.2.

[1742] Step 5:

[1743] The server notifies the author or publisher of the overall evaluation score and detailed evaluation results. It also automatically generates new catchphrases, introductions, and obi text based on the evaluation results and notifies the author or publisher of these texts.

[1744] Terminal

[1745] Step 6:

[1746] The terminal provides an interface for users to access and operate, through which users can upload novel data, view evaluation results, and submit feedback.

[1747] Step 7:

[1748] The device visually displays the evaluation results sent from the server to the user. Not only the overall evaluation score but also the detailed evaluation results from each generative AI model are displayed. This allows the user to select novels based on evaluation criteria that best suit their preferences.

[1749] Step 8:

[1750] The device collects feedback on the novels the user has read, which is then sent to a server, which uses this information to improve the evaluation algorithm of the generative AI model.

[1751] Introducing the Emotion Engine

[1752] Step 9:

[1753] The server performs sentiment analysis of the feedback provided by the user using an emotion engine, which categorizes the feedback into positive, negative, and neutral categories and sends the analysis results back to the server.

[1754] Step 10:

[1755] The device analyzes the user's emotional state in real time as they read the novel and sends the results to the emotion engine. For example, if the user is using a smartphone or tablet, the device uses their operation patterns and facial recognition technology to recognize their emotions.

[1756] Step 11:

[1757] The server personalizes the novel evaluation results based on real-time emotional data obtained from the emotion engine, and recommends novels that are optimal for the user's emotional state. For example, if the user is feeling sad, it will recommend novels that will soothe the emotions.

[1758] Step 12:

[1759] The server will accumulate the user's emotional history and adjust the novel recommendation algorithm based on past emotional patterns, which will enable more accurate novel evaluation and recommendation in the future.

[1760] Specific examples

[1761] For example, an author of a new novel uploads the novel data to the system through a publisher. The server receives and stores the data. The novel data is then sent to the text analysis module for detailed analysis. Based on the analysis results, each generative AI model evaluates the novel according to its own evaluation criteria. The evaluation results are then integrated to calculate an overall evaluation score.

[1762] The evaluation results are provided to the user via their device. As the user reads the novel, the emotion engine analyzes the user's emotions in real time and sends the data to the server. Personalized evaluation results and recommendations are made based on the user's emotional state, and feedback after reading is also analyzed by the emotion engine.

[1763] The data collected in this way will continuously improve the evaluation algorithms of the generative AI model, ensuring that users always have the best possible novels to choose from, as well as ensuring that authors and publishers have their work properly evaluated.

[1764] Example 2

[1765] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1766] Conventional novel evaluation systems have limited means for objectively evaluating the quality of novels, making it difficult to provide personalized recommendations that take the user's emotional state into account. Furthermore, they lack the means to appropriately utilize user feedback and improve the overall evaluation accuracy of the system. Therefore, a new system is needed that can effectively achieve high-quality novel evaluations and personalized recommendations that reflect the user's emotional state.

[1767] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1768] In this invention, the server includes means for receiving and saving novel data, means for passing the saved novel data to a text analysis module to analyze the story structure, character descriptions, writing style, plot progression, etc., means for inputting the analysis results into multiple generative AI models and evaluating the novel based on their respective evaluation criteria, means for integrating the evaluation results of each generative AI model to calculate an overall evaluation score, means for providing the overall evaluation score and evaluation details, means for analyzing feedback provided by the user with an emotion engine and personalizing the novel evaluation results based on the emotion data, and means for accumulating the user's emotion history and adjusting the novel recommendation algorithm based on past emotion patterns. This enables high-quality novel evaluations and personalized recommendations according to the user's emotional state.

[1769] "Novel data" is digital data that includes the text of the novel, author information, genre, plot summary, etc.

[1770] The "text analysis module" is a software module that analyzes novel data to evaluate the story structure, character descriptions, writing style, plot progression, etc.

[1771] A "generative AI model" is an artificial intelligence model used to evaluate novels based on analysis results. Specifically, it refers to a model that utilizes natural language processing technology.

[1772] The "evaluation criteria" are items that serve as indicators for evaluating a novel, such as the consistency of the story, the depth of the characters, and the clarity of the writing style.

[1773] The "overall evaluation score" is a number that indicates the overall evaluation of a novel, calculated by combining the evaluation results obtained from multiple generative AI models.

[1774] The "emotion engine" is a software engine that analyzes emotions based on user-provided feedback and real-time operational data.

[1775] "Personalization" refers to providing an optimized experience for a user by adjusting the system's behavior and recommendations based on the user's individual attributes and emotional state.

[1776] "Emotion history" is data that records and accumulates a user's past emotional data. This data will improve the accuracy of the recommendation algorithm from the next time onwards.

[1777] "Interface" refers to the means of providing a screen and a set of functions for users to operate a system.

[1778] "Feedback" refers to the user's impressions and evaluations of the novels they have read. It is used to improve the accuracy of the system's evaluations.

[1779] The present invention relates to a system for receiving and storing novel data, a system for analyzing and rating novel data, and a method for improving the accuracy and personalization of novel ratings by combining an emotion engine for analyzing user emotions.

[1780] server

[1781] The server receives novel data sent over the internet from authors or publishers. This data includes the novel's text, author information, genre, and synopsis. The received data is immediately stored in a database. The server uses libraries such as NLTK (Natural Language Toolkit) and SpaCy, which use the Python language, to send the novel data to a text analysis module for analysis. This analyzes the story structure, character descriptions, writing style, and plot progression. The text analysis results are input into multiple generative AI models, which evaluate the story's coherence and character depth. This is done using prompts such as, "Please rate the story coherence and character depth of this newly released novel." The evaluation results from each generative AI model are combined to calculate an overall evaluation score. The calculated overall evaluation score and detailed evaluation results are then notified to the author or publisher. Automatically generated taglines, introductions, and obi text are also provided.

[1782] Terminal

[1783] The terminal provides an interface for users to access and operate the system. This includes uploading novel data, viewing evaluation results, and submitting feedback through a web browser or dedicated application. The evaluation results sent from the server are visually displayed to the user via the terminal. As the user reads the novel, their emotions are analyzed in real time and sent to the emotion engine. This allows emotions to be recognized using the user's operation patterns and facial recognition technology when using a smartphone or tablet. Feedback and impressions provided by the user are also sent from the terminal to the server.

[1784] Emotion Engine

[1785] The emotion engine performs sentiment analysis on feedback provided by users and categorizes them as positive, negative, or neutral. It uses sentiment analysis APIs such as Microsoft Azure's Text Analytics API. It analyzes the user's emotional state in real time and personalizes the novel evaluation results based on this. For example, if a user has a lot of positive comments, it will recommend novels based on those emotions. Emotion data is stored on the server, and the novel recommendation algorithm is adjusted based on past emotional patterns.

[1786] Specific examples

[1787] For example, a user purchases a newly released novel through a device and begins reading it. This novel data is uploaded and stored on a server by the author or publisher. The server then sends the novel data to a text analysis module, which evaluates the story's coherence, character depth, and writing style. The analysis results are input into multiple generative AI models, which then perform an evaluation. The evaluation results are integrated to calculate an overall evaluation score. This score and detailed evaluation results are provided to the user through the device. Furthermore, emotions are analyzed in real time as the user reads the novel, and the user's emotional state is recorded. The emotion engine then personalizes the evaluation results based on this real-time data and makes optimal recommendations to the user. After reading, feedback provided by the user is also analyzed by the emotion engine and sent to the server. Through this series of processes, the present invention can achieve high-quality novel evaluations and personalized recommendations based on the user's emotional state.

[1788] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1789] Step 1:

[1790] The server receives novel data sent from an author or a publisher via the Internet.

[1791] Input: Digital data including the text of the novel, author information, genre, plot summary, etc.

[1792] Data processing: Decodes the received data and converts it into the appropriate format.

[1793] Output: Decoded novel data.

[1794] Specific operation: The server receives data through a specific API endpoint and stores it in a database.

[1795] Step 2:

[1796] The server transmits the stored novel data to a text analysis module.

[1797] Input: Novel data stored in the database.

[1798] Data Computing: Perform natural language analysis using libraries such as Python's NLTK and SpaCy.

[1799] Output: Analysis of narrative structure, characterization, writing style, and plot progression.

[1800] Specific operation: The server passes the data to the analysis module, which analyzes the structure, character, and style of the text.

[1801] Step 3:

[1802] The server inputs the results of the text analysis into multiple generative AI models, which then evaluate the novel based on their respective evaluation criteria.

[1803] Input: Analysis results output from the text analysis module.

[1804] Data calculation: The analysis results are input into each generative AI model and evaluated using prompt statements.

[1805] Output: Evaluation results from each generative AI model.

[1806] Specific behavior: The server generates a prompt statement such as "Please rate the story coherence and character depth of a newly released novel" and gives it to each AI model.

[1807] Step 4:

[1808] The server integrates the evaluation results obtained from each generative AI model and calculates an overall evaluation score.

[1809] Input: Evaluation scores for each generative AI model.

[1810] Data calculation: The evaluation scores are averaged and combined.

[1811] Output: Overall evaluation score.

[1812] Specific operation: The server aggregates the evaluation scores of each AI model, calculates the average value, and derives the overall evaluation score.

[1813] Step 5:

[1814] The server notifies the author or publisher of the detailed evaluation results and the overall evaluation score.

[1815] Input: Overall assessment score and detailed assessment results.

[1816] Data processing: converting the results into a format for notification.

[1817] Output: Notification of evaluation results.

[1818] Specific operation: The server notifies the user of the evaluation results via email or dashboard, and also automatically generates and provides a catchy slogan, introduction, and obi text.

[1819] Step 6:

[1820] The terminal provides an interface for the user to access and operate.

[1821] Input: User operation request.

[1822] Data processing: Generate and display the user interface.

[1823] Output: The interface that is displayed to the user.

[1824] Specific operation: The device provides a UI for uploading, viewing evaluation results, and submitting feedback via a web browser or dedicated app.

[1825] Step 7:

[1826] The terminal visually displays the evaluation results sent from the server to the user.

[1827] Input: The evaluation result sent from the server.

[1828] Data processing: Convert the evaluation results into a visually easy-to-read format.

[1829] Output: The evaluation results that are displayed to the user.

[1830] Specific operation: The device displays the evaluation results in graphs and text, making it easy for the user to understand.

[1831] Step 8:

[1832] The terminal collects feedback from the user and sends it to the server.

[1833] Input: User feedback.

[1834] Data Processing: Collect feedback and convert it into a format that can be sent to the server.

[1835] Output: Feedback data to the server.

[1836] Specific operation: The device accepts feedback via an input form and sends it to the server's feedback API.

[1837] Step 9:

[1838] The server uses an emotion engine to perform emotion analysis of the feedback provided by the user.

[1839] Input: User feedback data.

[1840] Data Computation: Perform sentiment analysis using the sentiment engine.

[1841] Output: Positive, negative, or neutral sentiment classification results.

[1842] Specific operation: The server uses a sentiment analysis API (e.g., Microsoft Azure's Text Analytics API) to perform sentiment classification.

[1843] Step 10:

[1844] The device analyzes the user's emotional state in real time and transmits it to the emotion engine.

[1845] Input: Real-time user operation data.

[1846] Data calculation: Analyzes operational data and recognizes real-time emotional states.

[1847] Output: Emotion state data to the emotion engine.

[1848] Specific operation: The device estimates the user's emotional state using facial recognition and operation patterns, and transmits the information to the server in real time.

[1849] Step 11:

[1850] The server personalizes the evaluation results of the novel based on the emotional data obtained from the emotion engine.

[1851] Input: Emotion data from the emotion engine.

[1852] Data calculation: Emotional data is used to individually optimize evaluation results.

[1853] Output: Personalized assessment results.

[1854] Specific operation: The server analyzes the emotion data and adjusts the evaluation results based on the user's emotion patterns.

[1855] Step 12:

[1856] The server accumulates the user's emotional history data and adjusts the novel recommendation algorithm based on past emotional patterns.

[1857] Input: Emotion history data.

[1858] Data calculation: Emotional data is accumulated and used to adjust algorithms.

[1859] Output: The adjusted recommendation algorithm.

[1860] Specific operation: The server stores the emotion history data in a database and optimizes the next recommendation based on past patterns.

[1861] (Application example 2)

[1862] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1863] Conventional novel rating systems rely on fixed evaluation criteria and have the problem of not being able to fully reflect the individual feelings and preferences of users. This makes it difficult to recommend novels that truly interest users and are personalized. Furthermore, because it is not possible to check feelings in real time and update evaluation results accordingly, users' reading experience is uniform, which can lead to a decrease in satisfaction.

[1864] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: [means for receiving and saving novel data;] [means for passing the saved novel data to a text analysis module and analyzing the story structure, character descriptions, writing style, plot progression, etc.;] [means for inputting the analysis results into multiple generative AI models and evaluating the novel based on their respective evaluation criteria;] [means for integrating the evaluation results of each generative AI model and calculating an overall evaluation score;] [means for providing the overall evaluation score and evaluation content;] [means for analyzing the user's emotions in real time and personalizing the evaluation results based on the emotional state; and] [means for accumulating the user's emotional history data and adjusting the evaluation algorithm.] This enables highly accurate personalized evaluation and recommendations based on the user's emotions and preferences.

[1865] "Novel data" refers to data sent by the author or publisher that includes the text of the novel, author information, genre, plot summary, etc.

[1866] The "text analysis module" is a software module for analyzing the narrative structure, character descriptions, writing style, plot progression, etc. of novel data.

[1867] A "generative AI model" is an artificial intelligence model that has multiple different evaluation criteria for evaluating novels based on the results of text analysis.

[1868] "Evaluation results" is a collective term for scores and detailed reviews based on each evaluation criterion applied to the novel data analyzed by the generative AI model.

[1869] The "overall evaluation score" is an overall evaluation score calculated by integrating the evaluation results from multiple generative AI models.

[1870] An "emotion engine" is a software engine that analyzes users' emotions and reflects the results in rating and recommending novels.

[1871] "Personalized ratings" refer to ratings or recommendations that are tailored based on a user's emotional state and preferences.

[1872] "Emotion history data" is data about a user's past emotional patterns, information that is used to adjust future rating algorithms.

[1873] An "interface" is an operation screen or operation means that allows users to upload novel data, view evaluation results, submit feedback, and so on.

[1874] The present invention relates to a system for receiving and storing novel data, a system for analyzing and evaluating novel data, and a method for combining an emotion engine that analyzes user emotions to improve the accuracy and personalization of evaluations.

[1875] Server Roles

[1876] The server has the following functions:

[1877] Data reception and storage

[1878] The server receives novel data sent from authors or publishers via the Internet. This data includes the novel's text, author inf...

Claims

1. A means for receiving and storing novel data; A method for passing saved novel data to a text analysis module to analyze the story structure, character descriptions, writing style, plot progression, etc. A means of inputting the analysis results into multiple generative AI models and having them evaluate the novel based on their respective evaluation criteria; A means for integrating the evaluation results of each generative AI model and calculating an overall evaluation score; A system including a means for providing an overall assessment score and assessment content.

2. A means for providing an interface for accepting uploads of novel data and transmitting the data to a server; means for visually displaying the evaluation results to the user; 10. The system of claim 1, further comprising means for collecting feedback from users and transmitting it to the server.

3. 2. The system according to claim 1, further comprising means for automatically generating new catch phrases, introductions, and jacket text based on the novel evaluation results.

Images