system

Abstract

Provide a system. A means for receiving a story title as input from a user; A means for analyzing the content of a story based on the title of the story and extracting a number of characters and major events; A means of generating stories from different perspectives based on the extracted information; a means for presenting the user with story options from different generated perspectives; means for displaying the generated story from a particular perspective based on a user selection; A system including:

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] Many conventional novels and stories are written from the perspective of the main character, who is the main point of view. As a result, readers are unable to gain a deep understanding of the perspectives and backgrounds of other characters in the story, and their perspective tends to be narrow. This problem can hinder a deeper understanding of the story and the ability to enjoy it from multiple angles. Furthermore, in order to gain individual perspectives on the story, readers must use their own imagination, which is often not easy. There is a need to provide a system that solves these issues and helps users enjoy stories from multiple angles. [Means for solving the problem]

[0005] The present invention includes a means for receiving a story title from a user as input, analyzing the content of the story based on the title, and extracting multiple characters and major events. It also includes a means for generating stories from different perspectives based on the extracted information, and a means for presenting the user with options for the generated stories from different perspectives. If the user selects a particular perspective, it also includes a means for displaying the story generated from that perspective. The present invention also includes a means for allowing the user to input feedback on the generated story, storing the feedback in a database, and using it to improve the system. It also includes a means for using generative artificial intelligence to analyze the content of the story and generate stories from different perspectives. This allows the user to enjoy the story from multiple perspectives and gain a deeper understanding.

[0006] "User" refers to an individual or individuals who utilize the system to experience a narrative perspective.

[0007] "Narrative" refers to a story written in a novel, fairy tale, fable, or similar written form.

[0008] "Title" refers to the name or title of a story, and is used by the user to indicate a particular story.

[0009] "Analysis" refers to the analytical process used to understand the story and extract key characters and events.

[0010] "Characters" refers to the characters and people depicted in the story.

[0011] A "major event" is an event or action that plays a significant role in the progression of the story.

[0012] "Point of view" refers to the position or perspective of a particular character when depicting a story, and means reconstructing the story from that character's perspective.

[0013] "Choices" refer to options that a user can choose from multiple perspectives.

[0014] "Feedback" refers to the opinions, comments, or reactions that users give to the generated story.

[0015] "Generative AI" refers to AI techniques used to analyze story content and generate stories from different perspectives. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] An embodiment of the present invention provides a system that allows a user to enjoy a story from different perspectives. This system extracts detailed information about a story based on the title of the story entered by the user, and generates and presents the story from different perspectives. Specific embodiments of the present invention will be described below.

[0038] User Input

[0039] Terminal

[0040] The user inputs the title of the story he or she is interested in through the terminal interface, for example, "Urashima Taro." This title is then sent to the system.

[0041] Server Processing: A Narrative Analysis

[0042] server

[0043] The server receives the title sent by the user and analyzes the story's content based on the title. This analysis uses generative artificial intelligence to automatically extract the story's main characters and events. For example, for "Urashima Taro," information such as Urashima Taro, Princess Otohime, and the Dragon Palace in the sea is extracted.

[0044] Server processing: View generation

[0045] server

[0046] Based on the extracted information, the server generates a story from multiple different perspectives. It uses generative artificial intelligence to reconstruct the story from each character's point of view. For example, in the case of the story of Urashima Taro, the perspectives of Urashima Taro, Princess Otohime, and the turtle could all be considered. Each perspective would depict a different aspect of the story.

[0047] Server processing: Presenting story options

[0048] Terminal

[0049] The server compiles the generated stories from multiple perspectives and presents them to the user. This allows the user to choose from which perspective they would like to read the story. For example, options such as "Read from Urashima Taro's perspective," "Read from Otohime's perspective," or "Read from the turtle's perspective" are presented.

[0050] User Selection

[0051] User

[0052] The user operates the device and clicks on the viewpoint they are interested in from the displayed options. For example, they select "Otohime's viewpoint."

[0053] Server processing: Narrative generation and presentation

[0054] server

[0055] The server retrieves the story generated based on the viewpoint selected by the user and sends it to the device. This allows the user to enjoy the story reconstructed from a specific viewpoint. For example, the story of Urashima Taro reconstructed from Otohime's viewpoint is displayed as text.

[0056] User Feedback

[0057] User

[0058] After reading the generated story, users can use the feedback form to enter their impressions and comments, which will be used to improve the system.

[0059] Server processing: feedback storage and analysis

[0060] server

[0061] The server receives feedback from users, stores it in a database, and analyzes the collected feedback to help improve the system in the future.

[0062] In this way, the present invention provides users with a variety of ways to enjoy stories, promoting a deeper understanding of the story. As a specific example, by enjoying the story of "Urashima Taro" from Otohime's perspective, users can understand the background of her feelings and actions, and gain a new perspective on the story as a whole.

[0063] The processing flow will be explained below.

[0064] Step 1:

[0065] User:

[0066] The user inputs the title of the story he or she is interested in through the terminal interface, for example, "Cinderella."

[0067] Step 2:

[0068] Device:

[0069] It takes the title entered by the user, parses it into JSON format, and creates an HTTP POST request containing the parsed data and sends it to the server.

[0070] Step 3:

[0071] server:

[0072] Receives an HTTP request, retrieves the story title entered by the user, and retrieves the story content from an external database or API based on this title.

[0073] Step 4:

[0074] server:

[0075] The acquired story content is passed to the generative AI, which then begins analyzing the story. The generative AI analyzes the story and extracts the main characters (e.g., Cinderella, the stepmother, the prince) and key events (the ball, the glass slippers, etc.).

[0076] Step 5:

[0077] server:

[0078] Based on the extracted results, a story is generated from multiple different perspectives. For example, Cinderella's perspective, the stepmother's perspective, and the prince's perspective are generated using generative artificial intelligence.

[0079] Step 6:

[0080] server:

[0081] The generated stories from different perspectives are compiled into a list, and data to be presented to the user is generated. An HTTP response including this data is generated and sent to the terminal.

[0082] Step 7:

[0083] Device:

[0084] Parse the response received from the server and present the user with a choice of different perspectives on the story, for example, "Read from Cinderella's point of view," "Read from the Stepmother's point of view," or "Read from the Prince's point of view."

[0085] Step 8:

[0086] User:

[0087] Choose the perspective you're interested in (e.g., "The Prince's Perspective") and click on the option.

[0088] Step 9:

[0089] Device:

[0090] It receives the user's selection, parses the data containing the selected viewpoint into JSON format, and creates an HTTP POST request containing the parsed data and sends it to the server.

[0091] Step 10:

[0092] server:

[0093] The system receives the user's selection, obtains a story based on the selected perspective (e.g., "the prince's perspective"), generates an HTTP response containing the story data, and sends it to the terminal.

[0094] Step 11:

[0095] Device:

[0096] It parses the story data returned by the server and displays to the user a reconstructed version of the story from a particular point of view, for example, displaying the text of the Cinderella story reconstructed from the prince's point of view.

[0097] Step 12:

[0098] User:

[0099] After reading the generated story, users enter their impressions and comments into the input form and submit it as feedback.

[0100] Step 13:

[0101] Device:

[0102] Receives user feedback, parses it into JSON format, creates an HTTP POST request with the feedback data, and sends it to the server.

[0103] Step 14:

[0104] server:

[0105] Receive feedback data and store it in a database. Analyze the collected feedback and use it to improve the system in the future.

[0106] Through the above specific processing flow, this system can provide users with a multifaceted story experience.

[0107] Example 1

[0108] 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."

[0109] Conventional story generation systems typically provide users with a single perspective, preventing them from enjoying a variety of perspectives. Furthermore, they do not effectively utilize feedback, making it difficult to improve the system. Furthermore, they sometimes produce inaccurate results in story content analysis and story generation from different perspectives.

[0110] 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.

[0111] In this invention, the server includes means for receiving a story title from a user as input, means for analyzing the content of the story based on the story title and extracting multiple characters and major events, means for generating stories from different perspectives based on the extracted information, means for presenting options for the generated stories from different perspectives to the user, means for displaying the generated story from a specific perspective based on the user's selection, means for inputting and saving user feedback on the generated story and using it to improve the system, and means for using prompt sentences to analyze the story and generate stories from different perspectives using a generative AI model. This allows users to enjoy stories from different perspectives, improves the accuracy of the system, and makes it possible to effectively utilize user feedback to improve the system.

[0112] A "user" is someone who uses the system to input the title of a story and select and enjoy stories from different perspectives.

[0113] "Story Title" is the name of a particular piece of story that the user enters into the system.

[0114] "Story content" is text or data containing characters, major events, and other information relevant to the story.

[0115] A "character" is a character or person who plays a specific role in a story.

[0116] A "major event" is an event or occurrence that plays a significant role in the progression of the story.

[0117] A "point of view" is a standpoint or perspective from which a story is portrayed from different characters or points of view.

[0118] "Choices" are multiple perspectives or options presented to the user.

[0119] "Feedback" refers to thoughts and comments that users input about the generated story.

[0120] The "server" is the central computer of the system, and is the device that processes input from users, analyzes the content of the story, and generates and transmits stories from different perspectives.

[0121] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to analyze the content of a story and generate a story from different perspectives.

[0122] A "prompt" is a text sentence used to give specific instructions to a generative AI model.

[0123] "Database" means an electronic storage system that stores collected data and feedback so that it can be searched and analyzed as needed.

[0124] An embodiment of the present invention is a system for allowing a user to enjoy different perspectives on a story. Based on the title of a story entered by a user, the system extracts detailed information about the story and generates and presents the story from different perspectives.

[0125] User Input

[0126] Terminal

[0127] The user inputs the title of the story using the terminal interface. For example, the user inputs a title such as "Story A" into an input field on the terminal. This information is sent to the server.

[0128] Server Processing: A Narrative Analysis

[0129] server

[0130] The server receives the story title sent by the user and analyzes its content using a generative AI model (e.g., GPT-3 (registered trademark)). The server sends the following prompt to the generative AI model:

[0131] List the characters and major events in "Story A."

[0132] The generative AI model extracts the content of the story (characters and major events) based on the prompt sent. For example, for "Story A," information such as characters X, Y, and Z and major events 1, 2, and 3 can be obtained.

[0133] Server processing: View generation

[0134] server

[0135] The server uses a generative AI model to generate stories from multiple different perspectives based on the extracted list of characters and events. For each perspective, it generates a prompt and sends it to the model. For example:

[0136] Tell us "Story A" from the perspective of Character X.

[0137] The generative AI model responds with the story from the perspective of character X. It does the same for other perspectives (characters Y, Z, etc.).

[0138] Server processing: Presenting story options

[0139] server

[0140] The server compiles the generated stories from multiple perspectives and sends them to the device in the form of a choice, which the device presents to the user (e.g., "Read from X's perspective," "Read from Y's perspective," "Read from Z's perspective").

[0141] User Selection

[0142] User

[0143] The user operates the device interface and selects the perspective they are interested in from the options presented, for example, "Read from Y's perspective."

[0144] Server processing: Narrative generation and presentation

[0145] server

[0146] The server retrieves a story already created based on the user's selected viewpoint and sends it to the device, which then displays the story text on the screen, allowing the user to enjoy the story reconstructed from a specific viewpoint.

[0147] User Feedback

[0148] User

[0149] After reading the story, the user enters their impressions and comments in the feedback form, and the user's feedback is sent to the server.

[0150] Server processing: feedback storage and analysis

[0151] server

[0152] The server receives feedback from users, stores it in a database (e.g., MySQL (registered trademark) or MongoDB), and analyzes the collected feedback to help improve the system in the future.

[0153] In this way, the present invention is a system that provides users with multiple ways to enjoy stories and promotes a deeper understanding of the story. As a specific example, by enjoying "Story A" from the perspective of character Y, users can understand the background of Y's feelings and actions, and gain a new perspective on the story as a whole.

[0154] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0155] Step 1:

[0156] Terminal

[0157] The user inputs the title of the story through the terminal interface. For example, they input "Story A." This input data is temporarily saved on the terminal and sent to the server when the send button is pressed.

[0158] input:

[0159] Story title entered by the user

[0160] output:

[0161] Subject data sent to the server

[0162] Specific behavior:

[0163] The user enters "Story A" in the title input field and clicks the submit button.

[0164] Step 2:

[0165] server

[0166] The server receives the story title submitted by the user and analyzes the story content by sending the following prompt to the generative AI model:

[0167] List the characters and major events in "Story A."

[0168] Based on this prompt, the generative AI model analyzes the story's content and lists the characters and key events.

[0169] input:

[0170] Story title received from user

[0171] Prompt statement

[0172] output:

[0173] List of characters and major events

[0174] Specific behavior:

[0175] The server sends a prompt to the generative AI model to retrieve characters and key events. For "Story A," characters X, Y, and Z and key events 1, 2, and 3 are extracted.

[0176] Step 3:

[0177] server

[0178] The server uses a generative AI model to generate stories from multiple different perspectives based on the extracted list of characters and events. For each perspective, it generates a prompt and sends it to the model. For example:

[0179] Tell us "Story A" from the perspective of Character X.

[0180] The model generates a story from each perspective.

[0181] input:

[0182] List of characters and major events

[0183] Prompt statement

[0184] output:

[0185] A story from a different perspective

[0186] Specific behavior:

[0187] The server generates a prompt sentence and obtains a story from the perspective of characters X, Y, and Z. For example, a story from X's perspective, a story from Y's perspective, and a story from Z's perspective are generated respectively.

[0188] Step 4:

[0189] server

[0190] The server compiles the stories from different perspectives and sends them to the device in the form of a selection, for example:

[0191] {

[0192] "views": [

[0193] "Read from X's point of view",

[0194] "Read from Y's perspective",

[0195] "Reading from Z's Perspective"

[0196] ]

[0197] }

[0198] The terminal presents this to the user.

[0199] input:

[0200] A story from a different perspective

[0201] output:

[0202] The options to present to the user

[0203] Specific behavior:

[0204] The server converts the data into a choice format and sends it to the terminal, which then displays the choices to the user.

[0205] Step 5:

[0206] User

[0207] The user operates the device interface and selects the perspective they are interested in from the options presented, for example, "Read from Y's perspective."

[0208] input:

[0209] The viewpoint selected by the user

[0210] output:

[0211] Selected viewpoint data

[0212] Specific behavior:

[0213] The user selects "Read from Y's perspective" and clicks the Select button.

[0214] Step 6:

[0215] server

[0216] The server retrieves the already generated story based on the viewpoint selected by the user and sends it to the terminal in the form of a text version of the story.

[0217] input:

[0218] Selected viewpoint data

[0219] output:

[0220] Narrative text from selected perspectives

[0221] Specific behavior:

[0222] The server retrieves the story from the saved viewpoint and sends it to the device.

[0223] Step 7:

[0224] Terminal

[0225] The terminal displays the story text received from the server to the user.

[0226] input:

[0227] Story text received from the server

[0228] output:

[0229] Displaying narrative text

[0230] Specific behavior:

[0231] The device displays the story text on the screen.

[0232] Step 8:

[0233] User

[0234] After reading the generated story, the user enters their impressions and comments in a feedback form, which is then sent from the device to the server.

[0235] input:

[0236] User-entered feedback

[0237] output:

[0238] Feedback data sent to the server

[0239] Specific behavior:

[0240] The user enters their thoughts and comments into the feedback form and clicks the submit button.

[0241] Step 9:

[0242] server

[0243] The server stores user feedback in a database and analyzes it to help improve the system.

[0244] input:

[0245] Feedback data received from users

[0246] output:

[0247] Stored Feedback Data

[0248] Analysis results

[0249] Specific behavior:

[0250] The server stores the feedback data in a database and performs analysis to use it to improve the system.

[0251] (Application example 1)

[0252] 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."

[0253] With conventional content distribution services, viewing of movies and dramas is limited to a set viewpoint or edited content, preventing users from freely enjoying the story from different perspectives. While systems exist for reconstructing a story from different viewpoints, they are primarily text-based and difficult to apply to video content. Another issue is the lack of in-depth analysis based on the viewpoint of the story or interactive feedback functions for the psychological portrayal of characters.

[0254] 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.

[0255] In this invention, the server includes means for receiving a story title as input from a user, means for analyzing the content of the story based on the story title and extracting a plurality of characters and major events, means for generating stories from different perspectives based on the extracted information, means for presenting to the user options for the stories from the generated different perspectives, means for displaying a story generated from a specific perspective based on the user's selection, means for selecting a specific perspective from the option options presented to the user, and means for providing the user with a story generated based on a specific perspective. This allows the user to freely select different perspectives when watching a movie or drama and enjoy the story from each perspective.

[0256] A "user" is an individual or group that uses the system, inputs the title of a story, and enjoys the story from a particular perspective.

[0257] "Story title" is the name of the story to be analyzed, entered by the user.

[0258] "Story content" refers to information such as the story, events, and characters that are analyzed based on the story title.

[0259] A "character" is someone who has a role in the story.

[0260] An "incident" is a major event or action that occurs in a story.

[0261] "Point of view" is the perspective of a story from the perspective of a particular character or role in the story.

[0262] "Feedback" refers to opinions, impressions, and information for improvement that users input into the system.

[0263] "Generative AI" is an AI technology that automatically generates new stories and information based on input data.

[0264] "Deep story analysis" is the process of analyzing the content of a story in detail to reveal the psychological state and background information of the characters.

[0265] "Additional information" is supplemental information provided as the story progresses based on the perspective selected by the user.

[0266] In order to put the present invention into practice, it is necessary to build a system that allows a user to input the title of a story and enjoy the story from different perspectives. This system is configured as follows.

[0267] User Input

[0268] Through the terminal interface, the user inputs the title of the story they are interested in. This title is then sent to the system.

[0269] Server Processing: A Narrative Analysis

[0270] The server receives the title sent by the user and analyzes the content of the story based on that title. This analysis uses generative artificial intelligence (AI) to automatically extract the story's main characters and events. An example of the AI ​​model used is OpenAI's (registered trademark) GPT-3. For example, if the story "Urashima Taro" is input, information such as Urashima Taro, Princess Otohime, and the Dragon Palace in the sea will be extracted.

[0271] Server processing: View generation

[0272] The server generates a story from multiple different perspectives based on the extracted information. It uses a generative AI model to reconstruct the story from each character's perspective. For example, for the "Tale of Urashima Taro," the perspectives of Urashima Taro, Princess Otohime, and the turtle could all be considered.

[0273] Server processing: Presenting story options

[0274] The server compiles the generated stories from multiple perspectives and presents them to the user. This allows the user to choose from which perspective they would like to read the story. For example, options such as "Read from Urashima Taro's perspective," "Read from Otohime's perspective," or "Read from the turtle's perspective" are presented.

[0275] User Selection

[0276] The user operates the device and clicks on the viewpoint they are interested in from the displayed options. For example, they select "Otohime's viewpoint."

[0277] Server processing: Narrative generation and presentation

[0278] The server retrieves the story generated based on the viewpoint selected by the user and sends it to the device. The user can enjoy the story reconstructed from this specific viewpoint. For example, the story of Urashima Taro reconstructed from Otohime's viewpoint is displayed as text.

[0279] User Feedback

[0280] After reading the generated story, users can use the feedback form to enter their impressions and comments, such as additional information they would like to know or suggestions for improving the story.

[0281] Server processing: feedback storage and analysis

[0282] The server receives user feedback, stores it in a database, and analyzes it to perform in-depth analysis of the story, improving the system to provide a richer story experience.

[0283] Specific examples

[0284] For example, to allow a user to experience the story of Urashima Taro from Otohime's perspective, the following prompt sentence is input to the generative AI model:

[0285] Title: Reconstruct the story of "Urashima Taro" from Otohime's perspective.

[0286] This prompt sentence generates a story reconstructed from Otohime's perspective and presents it to the user.

[0287] Unlike traditional movie or TV drama viewing experiences, the system of the present invention allows users to freely enjoy a story from various perspectives. Furthermore, by conducting in-depth analysis of the story content and each perspective based on user feedback, a more fulfilling story experience can be provided.

[0288] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0289] Step 1:

[0290] The user uses the terminal interface to input the title of the story they are interested in and send it to the system. Input data: Story title. Output data: Story title sent to the system.

[0291] Step 2:

[0292] The server receives the story title sent by the user and analyzes the content of the story based on the title. It sends prompt sentences to the generative AI model to extract the main characters and events. Input data: Story title. Output data: Main characters and events.

[0293] Step 3:

[0294] The server generates stories from different perspectives based on the extracted characters and events. Using a generative AI model, it reconstructs the story based on each perspective. Input data: extracted characters and events. Output data: stories from different perspectives.

[0295] Step 4:

[0296] The server presents the generated story options from different viewpoints to the user. Multiple viewpoint options are displayed on the terminal. Input data: Stories from different viewpoints. Output data: Display of viewpoint options.

[0297] Step 5:

[0298] The user operates the terminal and selects the viewpoint of interest from the presented viewpoint options. Input data: viewpoint options. Output data: selected viewpoint.

[0299] Step 6:

[0300] The server sends the generated story based on the viewpoint selected by the user to the terminal. The terminal displays the story reconstructed from that particular viewpoint to the user. Input data: Selected viewpoint. Output data: Reconstructed story.

[0301] Step 7:

[0302] After reading the generated story, the user submits their impressions and comments to the system through a feedback form. Input data: impressions and comments. Output data: feedback form submission.

[0303] Step 8:

[0304] The server receives feedback from users and stores it in a database. It analyzes the feedback and uses it to improve the system. Input data: User feedback. Output data: Stored feedback and analysis results.

[0305] 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.

[0306] An embodiment of the present invention provides a system that allows users to enjoy different perspectives on a story through an interactive system that combines generative artificial intelligence and an emotion engine. This system not only acquires information about the story from the user and generates and displays the content of the story based on that information, but also recognizes and analyzes the user's emotions to provide a more personalized experience. Specific embodiments of the present invention are described below.

[0307] User Input and Emotion Recognition

[0308] Terminal

[0309] The user inputs the title of a story they are interested in through the device interface. An emotion engine then operates to recognize the user's emotions in real time based on their input and dialogue behavior. For example, when the user inputs the title "Cinderella," the emotion engine analyzes the user's facial expression and tone of voice to determine their emotional state (e.g., excitement, curiosity, sadness, etc.).

[0310] Server Processing: Narrative Analysis and Sentiment Analysis

[0311] server

[0312] The server receives the title submitted by the user and the emotional data analyzed by the emotion engine. It then analyzes the story content based on the title and extracts the main characters and events. This process is carried out using generative artificial intelligence. For example, in the case of "Cinderella," Cinderella, the stepmother, the prince, the ball, the glass slippers, etc. are extracted.

[0313] Server processing: Emotion-based viewpoint generation

[0314] server

[0315] The server combines the extracted story information with the user's emotional data to generate a story from the most appropriate perspective. Generative AI is used to reconstruct the story based on the user's emotional state. For example, if the user expresses curiosity, the server generates a perspective that focuses on more detailed background information or hidden truths.

[0316] Server Processing: Presenting Narrative Options and Reevaluating Emotions

[0317] Terminal

[0318] The server presents the generated story from multiple perspectives to the user and re-presents the most suitable option to the user. This re-presentation re-evaluates the user's emotional state at the time of their initial selection and adjusts the options as necessary. For example, the server presents multiple options such as "Read from Cinderella's perspective," "Read from the stepmother's perspective," and "Read from the prince's perspective," and emphasizes the recommended perspective based on the user's emotions.

[0319] User selection and story display

[0320] User

[0321] The user selects the perspective they are interested in from the displayed options. For example, they select "The Prince's Perspective." The story based on the selected perspective is then displayed on the device. This allows the user to read the story reconstructed from a specific perspective.

[0322] User feedback and sentiment analysis

[0323] Terminal Server

[0324] After reading the generated story, the user enters their thoughts and comments in a feedback form. The emotion engine analyzes the user's emotions at the time of the feedback to gain a more detailed understanding of the feedback content. The server receives this feedback data, stores it in a database, and uses it to improve the system.

[0325] Through this specific processing flow, the system provides users with a multifaceted and personalized story experience, helping them gain a deeper understanding of the story and new perspectives. For example, by enjoying the story of "Cinderella" from the prince's perspective, users can understand the prince's psychological state and the hidden meaning behind his actions, gaining new insights into the story as a whole. Furthermore, feedback based on the user's emotions allows the system to further optimize future story generation and perspective presentation methods.

[0326] The processing flow will be explained below.

[0327] Step 1:

[0328] User:

[0329] The user inputs the title of the story through the device interface, for example, "Cinderella." At this time, the emotion engine recognizes the user's facial expressions and tone of voice and collects emotional data.

[0330] Step 2:

[0331] Device:

[0332] The title entered by the user is parsed into JSON format. At the same time, the emotion data recognized by the emotion engine is also parsed. An HTTP POST request containing this data is generated and sent to the server.

[0333] Step 3:

[0334] server:

[0335] Receives an HTTP request, retrieves the story title and emotion data entered by the user, and retrieves the story content from an external database or API based on the title.

[0336] Step 4:

[0337] server:

[0338] The acquired story content is passed to the generative AI to begin analysis. The generative AI analyzes the story and extracts the main characters (Cinderella, the stepmother, the prince, etc.) and key events (the ball, the glass slippers, etc.).

[0339] Step 5:

[0340] server:

[0341] Based on the extracted information and emotional data, the system generates stories from multiple different perspectives. The generative AI identifies the perspective that best matches the user's emotional state and reconstructs the story from that perspective. For example, if the user is excited, it generates a story from a perspective filled with action and dramatic elements.

[0342] Step 6:

[0343] server:

[0344] The generated stories from multiple perspectives are compiled into a list, and data to be presented to the user is generated. An HTTP response including this data is generated and sent to the terminal.

[0345] Step 7:

[0346] Device:

[0347] The response received from the server is parsed and the user is presented with a choice of different perspectives for the story. For example, options such as "Read from Cinderella's point of view," "Read from the stepmother's point of view," or "Read from the prince's point of view" are displayed. At this time, the emotion engine again recognizes the user's emotions and highlights the most recommended options.

[0348] Step 8:

[0349] User:

[0350] Choose the perspective that interests you (for example, "The Prince's Perspective") and click on that option.

[0351] Step 9:

[0352] Device:

[0353] It receives the user's selection, generates an HTTP POST request in JSON format containing the selected viewpoint and emotion data, and sends it to the server.

[0354] Step 10:

[0355] server:

[0356] Receives the user's selection, retrieves from the database a story generated based on the selected viewpoint, generates an HTTP response containing the story data, and sends it to the device.

[0357] Step 11:

[0358] Device:

[0359] It parses the story data returned by the server and displays to the user a reconstructed version of the story from a particular point of view, for example, displaying the text of the Cinderella story reconstructed from the prince's point of view.

[0360] Step 12:

[0361] User:

[0362] After reading the generated story, users can enter their impressions and comments in a feedback form. At this time, the emotion engine will recognize the user's emotions again and include them in the feedback.

[0363] Step 13:

[0364] Device:

[0365] Parse the user-entered feedback and emotion data into JSON format, generate an HTTP POST request, and send it to the server.

[0366] Step 14:

[0367] server:

[0368] Feedback and emotional data are received and stored in a database, and the emotional data is analyzed and used to improve the system and optimize story generation.

[0369] Through the specific processing flow described above, the present system can provide users with a multifaceted and personalized story experience.

[0370] Example 2

[0371] 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."

[0372] Existing story generation systems simply generate and display stories, making it difficult to provide a personalized experience based on the user's emotions and interests. Furthermore, they lack the technology to analyze user emotions and dynamically reconstruct stories based on those emotions, making it impossible to provide optimal content for each individual user. This results in a decline in user engagement and satisfaction.

[0373] 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.

[0374] In this invention, the server includes means for receiving a story title as input from a user, means for analyzing the content of the story based on the story title and extracting multiple characters and major events, means for generating stories from different perspectives based on the extracted information, means for presenting to the user options for the generated stories from the different perspectives, means for displaying the story generated from a specific perspective based on the user's selection, means for recognizing and analyzing user emotions in real time from the user's input and dialogue behavior, and means for reconstructing the story based on the user's emotion data, thereby making it possible to provide a personalized story experience based on the emotions and interests of each individual user.

[0375] "Story Title" is a name entered by the user to indicate the story in which they are interested.

[0376] A "terminal" is a device used by a user for input and interaction, and includes smartphones, tablets, PCs, etc.

[0377] An "emotion engine" is a technology that analyzes a user's facial expressions and tone of voice to recognize their emotional state.

[0378] "Emotion data" is information that indicates the user's emotional state analyzed by the emotion engine.

[0379] "Generative AI" refers to AI techniques for generating content based on given input, with the ability to create text based on specific prompts.

[0380] A "prompt" is text that contains specific instructions or questions to be given to a generative artificial intelligence.

[0381] "Extract" refers to extracting specific data from the analyzed information.

[0382] "A story from another perspective" refers to a story that has been reconstructed from different characters or perspectives within the same story.

[0383] "Presenting" refers to displaying options or information to the user.

[0384] "Feedback" refers to the opinions and thoughts that users provide about the generated story.

[0385] A "database" is a system for systematically storing and managing information.

[0386] A "personalized experience" is the provision of specific content and services based on an individual user's interests and emotions.

[0387] "Engagement" refers to the degree of involvement a user has with a service or content.

[0388] "Analysis" is the act of examining data in detail to reveal its meaning and structure.

[0389] "Reconstructing" refers to reassembling content from the original data based on a new perspective or structure.

[0390] This invention combines generative artificial intelligence and an emotion engine to provide an interactive system for users, allowing them to enjoy different perspectives on a story. This system not only acquires information about the story from the user and generates and displays the content of the story based on that information, but also recognizes and analyzes the user's emotions to provide a more personalized experience.

[0391] User Input and Emotion Recognition

[0392] First, the user inputs the title of a story they are interested in through the device interface. For example, they input "Cinderella." At this time, the device's built-in emotion engine (e.g., emotion analysis API) analyzes the user's facial expressions and tone of voice to recognize the user's emotional state (e.g., excitement, curiosity, sadness, etc.) in real time.

[0393] Narrative and sentiment analysis

[0394] Next, the server receives the story title and emotion data sent by the user. Using generative artificial intelligence (e.g., GPT-4 (registered trademark)), the server analyzes the content of the story and extracts the main characters and events. For example, in the case of "Cinderella," it extracts Cinderella, the stepmother, the prince, the ball, the glass slippers, etc.

[0395] Emotion-based perspective generation

[0396] The server combines the extracted story information with the user's emotional data to generate a story from the most appropriate perspective. The generative AI reconstructs the story according to the user's emotional state. For example, if the user expresses curiosity, it generates a story that focuses on detailed background information or hidden truths. This operation is performed using prompt sentences. Examples of specific prompt sentences include, "Please reconstruct the story of Cinderella from the stepmother's perspective" and "The user is curious, so please generate a story that focuses on Cinderella's hidden truth."

[0397] Presenting narrative options and reassessing emotions

[0398] The generated stories from multiple perspectives are sent from the server to the device and presented to the user. At this time, the emotional state of the user at the time of their initial selection is reevaluated, and the optimal choice is adjusted. For example, multiple options such as "Read from Cinderella's perspective," "Read from the stepmother's perspective," and "Read from the prince's perspective" are presented, and the most recommended perspective is highlighted.

[0399] User selection and story display

[0400] The user selects the perspective they are interested in from the displayed options. For example, they select "The Prince's Perspective." The story based on the selected perspective is then displayed on the device. This allows the user to read the story reconstructed from a specific perspective.

[0401] User feedback and sentiment analysis

[0402] After reading the story, the user enters their thoughts and comments about the generated story into a feedback form. The device's built-in emotion engine also analyzes the user's emotions at the time of this feedback. The server receives the feedback data and emotion data and stores them in a database. This feedback data is used to improve the system.

[0403] This specific processing flow allows users to enjoy a multifaceted and personalized storytelling experience. For example, by experiencing the story of Cinderella from the prince's perspective, users can gain new insights and the system can further improve itself based on that feedback.

[0404] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0405] System program processing flow

[0406] Step 1: User enters story title

[0407] User: The user uses the terminal interface to input the title of a story that interests them.

[0408] Input: The title of the story (e.g., "Cinderella").

[0409] Output: The input title data.

[0410] Specific actions: Enter a title in the text input form displayed on the device screen and press the send button.

[0411] Step 2: The emotion engine analyzes the emotion

[0412] Device: The device's built-in emotion engine analyzes the user's facial expressions and tone of voice in real time.

[0413] Input: User's facial image and voice data.

[0414] Output: The user's emotional state (e.g., excitement, curiosity, sadness, etc.).

[0415] What it does: It uses a camera and microphone to capture facial expressions and tone of voice as data and then applies emotion analysis algorithms.

[0416] Step 3: The server receives the data

[0417] Server: The server receives the story title and emotion data sent from the device.

[0418] Input: Story title data, emotion data.

[0419] Output: Raw data stored in the server database.

[0420] Specific operation: Receives HTTP requests and saves data to a database.

[0421] Step 4: Story Analysis

[0422] Server: The server uses generative artificial intelligence to extract key characters and events from the story based on the title it receives.

[0423] Input: Story title data.

[0424] Output: Extracted characters and events (e.g., "Cinderella," "Stepmother," "Prince," "Ball," "Glass Slippers").

[0425] Specific operations: The title of the story is input as a prompt into the generative AI, which then performs an analysis to extract characters and key events.

[0426] Step 5: Combining emotion data with narrative information

[0427] Server: The server combines the emotion data with the extracted story information and generates a story from the most appropriate perspective.

[0428] Input: Emotion data, character and event data.

[0429] Output: A reconstructed story based on the user's emotions.

[0430] Specific operation: Based on the emotion data, a prompt is input to the generative AI to generate a story that focuses on detailed background information and hidden truths. For example, the prompt is input as follows: "The user is curious, so please generate a story that focuses on the hidden truth of Cinderella."

[0431] Step 6: Generate narrative options

[0432] Server: Generates stories from multiple perspectives and presents them to the user.

[0433] Input: Reconstructed narrative data.

[0434] Output: Story options (e.g., "Read from Cinderella's point of view," "Read from the stepmother's point of view," "Read from the prince's point of view").

[0435] What it does: Generate a story from multiple perspectives and prepare each option in list form.

[0436] Step 7: Present and reassess options

[0437] Terminal: The terminal displays the generated options to the user and highlights the recommended viewpoint based on the emotional data.

[0438] Input: Narrative choices, emotion data.

[0439] Output: Story options displayed on the user interface.

[0440] Specific operation: Display options for each viewpoint on the screen and label them to reflect the user's excitement and curiosity.

[0441] Step 8: Selecting Users

[0442] User: The user selects the viewpoint of interest from the displayed options.

[0443] Input: Select the perspective of the story (e.g., "The Prince's perspective").

[0444] Output: Selected viewpoint information.

[0445] Specific actions: Click the desired viewpoint from the displayed options.

[0446] Step 9: Presenting a narrative based on point of view

[0447] Terminal: The terminal displays the story based on the selected point of view.

[0448] Input: Selected viewpoint information, reconstructed narrative.

[0449] Output: The displayed narrative text.

[0450] What it does: The story from the selected point of view is displayed on the screen.

[0451] Step 10: User feedback and sentiment analysis

[0452] User: The user enters their thoughts and comments about the generated story in a feedback form.

[0453] Input: Feedback text.

[0454] Output: The input feedback data.

[0455] Specific actions: Enter your opinions and thoughts in text into the form and press the submit button.

[0456] Step 11: Sentiment Analysis

[0457] Device: The emotion engine installed in the device analyzes the user's emotions during feedback.

[0458] Input: Facial image and voice data at the time of feedback.

[0459] Output: Emotion data at the time of feedback.

[0460] Specific operation: Analyze facial expressions and voice during feedback to generate emotional data.

[0461] Step 12: Save your feedback data

[0462] Server: The server receives the feedback data including the analysis results and stores them in a database.

[0463] Input: Feedback data, emotion data.

[0464] Output: Feedback information stored in a database.

[0465] What it does: Runs SQL queries to add feedback and sentiment data to the database.

[0466] This allows users to enjoy a multifaceted and personalized storytelling experience, while the system is further improved based on their feedback.

[0467] (Application example 2)

[0468] 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."

[0469] Conventional storytelling systems lacked sufficient personalization for users, making it difficult to provide an experience that reflected each individual user's emotions. Furthermore, the ability to change the perspective of the story was limited, leaving users with few options for deeper enjoyment. As a result, the story experience tended to be uniform, resulting in lower user satisfaction.

[0470] 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 a story title from a user as input, means for analyzing the content of the story based on the story title and extracting multiple characters and major events, means for generating stories from different perspectives based on the extracted information, means for presenting options for the generated stories from the different perspectives to the user, means for recognizing emotions from the user's facial expressions and voice in real time, means for optimizing the content of the story based on the recognized emotions, and means for displaying the story generated from a specific perspective based on the user's selection. This makes it possible to provide a personalized story experience based on the user's emotions.

[0471] A "user" is an individual who uses the story experience system.

[0472] "Story Title" is the title of the story entered by the user.

[0473] "Multiple characters and major events" refers to the main characters and important events that make up the content of the story.

[0474] "Different perspectives" refers to a story being reconstructed from several different angles.

[0475] "Generated narrative options from different perspectives" are narrative options seen from multiple perspectives generated by the system.

[0476] "Means for recognizing emotions in real time from facial expressions and voice" refers to technology that recognizes emotions by analyzing a user's facial expressions and tone of voice.

[0477] "Recognized emotions" are information obtained by the system analyzing the user's real-time emotions.

[0478] "Means for optimizing story content" refers to techniques that adjust and personalize story content based on the user's emotional state.

[0479] "Generative AI" is a type of AI used to generate stories, using specific algorithms and prompts to generate stories.

[0480] A "prompt sentence" is the input text that serves as the basis for a generative artificial intelligence to generate a story.

[0481] "Feedback" is information provided by a user as impressions or comments on a generated story.

[0482] A "database" is an information storage system that stores feedback and other data for later analysis and system improvement.

[0483] An embodiment of the present invention is based on an interactive system that combines generative artificial intelligence and a sentiment analysis engine to provide a personalized story experience using a story title and user-entered sentiment data.

[0484] 1. System Configuration

[0485] Hardware

[0486] Terminals: Input and display devices such as smartphones, smart glasses, and head-mounted displays

[0487] Server: High-performance computer server, cloud computing service

[0488] Input devices: Webcam, microphone

[0489] software

[0490] Generative artificial intelligence: OpenAI GPT-3 API

[0491] Emotion Recognition Engine: EmotionRecognizer Library

[0492] Others: OpenCV library, librosa library

[0493] 2. Processing flow

[0494] User Input

[0495] The user inputs the title of the story he or she is interested in through the terminal interface, for example, "Cinderella."

[0496] emotion recognition

[0497] The server uses a camera and microphone to analyze the user's facial expression and voice. It uses the EmotionRecognizer library, OpenCV, and librosa to recognize the user's emotions in real time. For example, if the server recognizes "excited" from the user's facial expression and "excited" from their voice, it determines the user's emotional state as "excited."

[0498] Narrative analysis and perspective generation

[0499] Based on the story title and the recognized emotion data, a generative artificial intelligence (GPT-3) generates a new story. Here, a prompt is used to indicate the content and perspective of the story. For example, the following prompt is used:

[0500] When the user's emotion is "excited," reframe the Cinderella story from a different perspective.

[0501] Presenting options

[0502] The generated stories from multiple perspectives are presented to the user, who can select the perspective they are interested in. Among the presented perspectives, particularly recommended ones are highlighted.

[0503] Emotion-based storytelling

[0504] The reconstructed story is displayed based on the viewpoint selected by the user, allowing the user to enjoy a personalized story from a specific perspective.

[0505] Feedback and Reassessment

[0506] After reading the story, the user provides feedback such as their impressions and comments. The EmotionRecognizer library is used to recognize emotions again and to understand the feedback in more detail. This feedback data is stored in a database and used to improve the system.

[0507] This embodiment allows users to enjoy a multifaceted and personalized story experience that is completely tailored to their individual emotions, unlike conventional story experiences.

[0508] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0509] Step 1:

[0510] The user inputs the title of the story he or she is interested in through the terminal interface, and the input story title is sent to the server.

[0511] Input: Story title

[0512] Output: The story title sent to the server

[0513] Step 2:

[0514] The server receives the story title and analyzes the story content based on it. It uses generative artificial intelligence to extract multiple characters and key events. For example, if the title "Cinderella" is input, it will extract characters and events such as Cinderella, the stepmother, the prince, the ball, and the glass slippers.

[0515] Input: The story title sent to the server

[0516] Output: Extracted characters and events

[0517] Step 3:

[0518] The device's camera and microphone are used to capture the user's facial expressions and voice in real time. The EmotionRecognizer library, OpenCV, and librosa are used to recognize the user's emotions and send the emotion data to the server.

[0519] Input: User's facial and voice data

[0520] Output: Recognized emotion data

[0521] Step 4:

[0522] The server receives the title and emotion data and uses a generative artificial intelligence (GPT-3) to recreate the story, using the following prompt:

[0523] When the user's emotion is "excited," reframe the Cinderella story from a different perspective.

[0524] The generated story content is output as seen from multiple perspectives.

[0525] Input: Title and sentiment data

[0526] Output: Reproduced story (from multiple points of view)

[0527] Step 5:

[0528] The server sends the generated story options from different viewpoints to the device, which displays them to the user, highlighting the recommended viewpoints so that the user can select the viewpoint that interests them.

[0529] Input: Generated stories (from multiple perspectives)

[0530] Output: Viewpoint choices displayed to the user

[0531] Step 6:

[0532] The user selects the viewpoint he or she is interested in from the options, and the selected viewpoint information is sent to the server.

[0533] Input: User selected viewpoint

[0534] Output: Selections sent to the server

[0535] Step 7:

[0536] The server sends a story based on the viewpoint selected by the user to the terminal, which then displays it.

[0537] Input: Selections sent to the server

[0538] Output: A narrative based on the selected viewpoint displayed

[0539] Step 8:

[0540] After reading the story, the user enters their thoughts and comments through the feedback form on the device. At this time, the user's emotions are captured again by the camera and microphone and analyzed by the EmotionRecognizer library. The feedback content and emotional data are sent to the server and stored in a database.

[0541] Input: User feedback and sentiment data

[0542] Output: Feedback and emotion data stored in a database

[0543] Step 9:

[0544] The server analyzes the stored feedback and sentiment data and uses it to improve the personalization of the system.

[0545] Input: Feedback and emotion data stored in a database

[0546] Output: Improved system personalization

[0547] 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.

[0548] 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.

[0549] 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.

[0550] [Second embodiment]

[0551] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0552] 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.

[0553] 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).

[0554] 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.

[0555] 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.

[0556] 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).

[0557] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for 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.

[0558] 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.

[0559] 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.

[0560] 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.

[0561] In the smart glasses 214, the 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.

[0562] 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."

[0563] An embodiment of the present invention provides a system that allows a user to enjoy a story from different perspectives. This system extracts detailed information about a story based on the title of the story entered by the user, and generates and presents the story from different perspectives. Specific embodiments of the present invention will be described below.

[0564] User Input

[0565] Terminal

[0566] The user inputs the title of the story he or she is interested in through the terminal interface, for example, "Urashima Taro." This title is then sent to the system.

[0567] Server Processing: A Narrative Analysis

[0568] server

[0569] The server receives the title sent by the user and analyzes the story's content based on the title. This analysis uses generative artificial intelligence to automatically extract the story's main characters and events. For example, for "Urashima Taro," information such as Urashima Taro, Princess Otohime, and the Dragon Palace in the sea is extracted.

[0570] Server processing: View generation

[0571] server

[0572] Based on the extracted information, the server generates a story from multiple different perspectives. It uses generative artificial intelligence to reconstruct the story from each character's point of view. For example, in the case of the story of Urashima Taro, the perspectives of Urashima Taro, Princess Otohime, and the turtle could all be considered. Each perspective would depict a different aspect of the story.

[0573] Server processing: Presenting story options

[0574] Terminal

[0575] The server compiles the generated stories from multiple perspectives and presents them to the user. This allows the user to choose from which perspective they would like to read the story. For example, options such as "Read from Urashima Taro's perspective," "Read from Otohime's perspective," or "Read from the turtle's perspective" are presented.

[0576] User Selection

[0577] User

[0578] The user operates the device and clicks on the viewpoint they are interested in from the displayed options. For example, they select "Otohime's viewpoint."

[0579] Server processing: Narrative generation and presentation

[0580] server

[0581] The server retrieves the story generated based on the viewpoint selected by the user and sends it to the device. This allows the user to enjoy the story reconstructed from a specific viewpoint. For example, the story of Urashima Taro reconstructed from Otohime's viewpoint is displayed as text.

[0582] User Feedback

[0583] User

[0584] After reading the generated story, users can use the feedback form to enter their impressions and comments, which will be used to improve the system.

[0585] Server processing: feedback storage and analysis

[0586] server

[0587] The server receives feedback from users, stores it in a database, and analyzes the collected feedback to help improve the system in the future.

[0588] In this way, the present invention provides users with a variety of ways to enjoy stories, promoting a deeper understanding of the story. As a specific example, by enjoying the story of "Urashima Taro" from Otohime's perspective, users can understand the background of her feelings and actions, and gain a new perspective on the story as a whole.

[0589] The processing flow will be explained below.

[0590] Step 1:

[0591] User:

[0592] The user inputs the title of the story he or she is interested in through the terminal interface, for example, "Cinderella."

[0593] Step 2:

[0594] Device:

[0595] It takes the title entered by the user, parses it into JSON format, and creates an HTTP POST request containing the parsed data and sends it to the server.

[0596] Step 3:

[0597] server:

[0598] Receives an HTTP request, retrieves the story title entered by the user, and retrieves the story content from an external database or API based on this title.

[0599] Step 4:

[0600] server:

[0601] The acquired story content is passed to the generative AI, which then begins analyzing the story. The generative AI analyzes the story and extracts the main characters (e.g., Cinderella, the stepmother, the prince) and key events (the ball, the glass slippers, etc.).

[0602] Step 5:

[0603] server:

[0604] Based on the extracted results, a story is generated from multiple different perspectives. For example, Cinderella's perspective, the stepmother's perspective, and the prince's perspective are generated using generative artificial intelligence.

[0605] Step 6:

[0606] server:

[0607] The generated stories from different perspectives are compiled into a list, and data to be presented to the user is generated. An HTTP response including this data is generated and sent to the terminal.

[0608] Step 7:

[0609] Device:

[0610] Parse the response received from the server and present the user with a choice of different perspectives on the story, for example, "Read from Cinderella's point of view," "Read from the Stepmother's point of view," or "Read from the Prince's point of view."

[0611] Step 8:

[0612] User:

[0613] Choose the perspective you're interested in (e.g., "The Prince's Perspective") and click on the option.

[0614] Step 9:

[0615] Device:

[0616] It receives the user's selection, parses the data containing the selected viewpoint into JSON format, and creates an HTTP POST request containing the parsed data and sends it to the server.

[0617] Step 10:

[0618] server:

[0619] The system receives the user's selection, obtains a story based on the selected perspective (e.g., "the prince's perspective"), generates an HTTP response containing the story data, and sends it to the terminal.

[0620] Step 11:

[0621] Device:

[0622] It parses the story data returned by the server and displays to the user a reconstructed version of the story from a particular point of view, for example, displaying the text of the Cinderella story reconstructed from the prince's point of view.

[0623] Step 12:

[0624] User:

[0625] After reading the generated story, users enter their impressions and comments into the input form and submit it as feedback.

[0626] Step 13:

[0627] Device:

[0628] Receives user feedback, parses it into JSON format, creates an HTTP POST request with the feedback data, and sends it to the server.

[0629] Step 14:

[0630] server:

[0631] Receive feedback data and store it in a database. Analyze the collected feedback and use it to improve the system in the future.

[0632] Through the above specific processing flow, this system can provide users with a multifaceted story experience.

[0633] Example 1

[0634] 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."

[0635] Conventional story generation systems typically provide users with a single perspective, preventing them from enjoying a variety of perspectives. Furthermore, they do not effectively utilize feedback, making it difficult to improve the system. Furthermore, they sometimes produce inaccurate results in story content analysis and story generation from different perspectives.

[0636] 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.

[0637] In this invention, the server includes means for receiving a story title from a user as input, means for analyzing the content of the story based on the story title and extracting multiple characters and major events, means for generating stories from different perspectives based on the extracted information, means for presenting options for the generated stories from different perspectives to the user, means for displaying the generated story from a specific perspective based on the user's selection, means for inputting and saving user feedback on the generated story and using it to improve the system, and means for using prompt sentences to analyze the story and generate stories from different perspectives using a generative AI model. This allows users to enjoy stories from different perspectives, improves the accuracy of the system, and makes it possible to effectively utilize user feedback to improve the system.

[0638] A "user" is someone who uses the system to input the title of a story and select and enjoy stories from different perspectives.

[0639] "Story Title" is the name of a particular piece of story that the user enters into the system.

[0640] "Story content" is text or data containing characters, major events, and other information relevant to the story.

[0641] A "character" is a character or person who plays a specific role in a story.

[0642] A "major event" is an event or occurrence that plays a significant role in the progression of the story.

[0643] A "point of view" is a standpoint or perspective from which a story is portrayed from different characters or points of view.

[0644] "Choices" are multiple perspectives or options presented to the user.

[0645] "Feedback" refers to thoughts and comments that users input about the generated story.

[0646] The "server" is the central computer of the system, and is the device that processes input from users, analyzes the content of the story, and generates and transmits stories from different perspectives.

[0647] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to analyze the content of a story and generate a story from different perspectives.

[0648] A "prompt" is a text sentence used to give specific instructions to a generative AI model.

[0649] "Database" means an electronic storage system that stores collected data and feedback so that it can be searched and analyzed as needed.

[0650] An embodiment of the present invention is a system for allowing a user to enjoy different perspectives on a story. Based on the title of a story entered by a user, the system extracts detailed information about the story and generates and presents the story from different perspectives.

[0651] User Input

[0652] Terminal

[0653] The user inputs the title of the story using the terminal interface. For example, the user inputs a title such as "Story A" into an input field on the terminal. This information is sent to the server.

[0654] Server Processing: A Narrative Analysis

[0655] server

[0656] The server receives the story title sent by the user and analyzes its content. This analysis is performed using a generative AI model (e.g., GPT-3). The server sends the following prompt to the generative AI model:

[0657] List the characters and major events in "Story A."

[0658] The generative AI model extracts the content of the story (characters and major events) based on the prompt sent. For example, for "Story A," information such as characters X, Y, and Z and major events 1, 2, and 3 can be obtained.

[0659] Server processing: View generation

[0660] server

[0661] The server uses a generative AI model to generate stories from multiple different perspectives based on the extracted list of characters and events. For each perspective, it generates a prompt and sends it to the model. For example:

[0662] Tell us "Story A" from the perspective of Character X.

[0663] The generative AI model responds with the story from the perspective of character X. It does the same for other perspectives (characters Y, Z, etc.).

[0664] Server processing: Presenting story options

[0665] server

[0666] The server compiles the generated stories from multiple perspectives and sends them to the device in the form of a choice, which the device presents to the user (e.g., "Read from X's perspective," "Read from Y's perspective," "Read from Z's perspective").

[0667] User Selection

[0668] User

[0669] The user operates the device interface and selects the perspective they are interested in from the options presented, for example, "Read from Y's perspective."

[0670] Server processing: Narrative generation and presentation

[0671] server

[0672] The server retrieves a story already created based on the user's selected viewpoint and sends it to the device, which then displays the story text on the screen, allowing the user to enjoy the story reconstructed from a specific viewpoint.

[0673] User Feedback

[0674] User

[0675] After reading the story, the user enters their impressions and comments in the feedback form, and the user's feedback is sent to the server.

[0676] Server processing: feedback storage and analysis

[0677] server

[0678] The server receives user feedback, stores it in a database (e.g., MySQL or MongoDB), and analyzes the collected feedback to help improve the system in the future.

[0679] In this way, the present invention is a system that provides users with multiple ways to enjoy stories and promotes a deeper understanding of the story. As a specific example, by enjoying "Story A" from the perspective of character Y, users can understand the background of Y's feelings and actions, and gain a new perspective on the story as a whole.

[0680] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0681] Step 1:

[0682] Terminal

[0683] The user inputs the title of the story through the terminal interface. For example, they input "Story A." This input data is temporarily saved on the terminal and sent to the server when the send button is pressed.

[0684] input:

[0685] Story title entered by the user

[0686] output:

[0687] Subject data sent to the server

[0688] Specific behavior:

[0689] The user enters "Story A" in the title input field and clicks the submit button.

[0690] Step 2:

[0691] server

[0692] The server receives the story title submitted by the user and analyzes the story content by sending the following prompt to the generative AI model:

[0693] List the characters and major events in "Story A."

[0694] Based on this prompt, the generative AI model analyzes the story's content and lists the characters and key events.

[0695] input:

[0696] Story title received from user

[0697] Prompt statement

[0698] output:

[0699] List of characters and major events

[0700] Specific behavior:

[0701] The server sends a prompt to the generative AI model to retrieve characters and key events. For "Story A," characters X, Y, and Z and key events 1, 2, and 3 are extracted.

[0702] Step 3:

[0703] server

[0704] The server uses a generative AI model to generate stories from multiple different perspectives based on the extracted list of characters and events. For each perspective, it generates a prompt and sends it to the model. For example:

[0705] Tell us "Story A" from the perspective of Character X.

[0706] The model generates a story from each perspective.

[0707] input:

[0708] List of characters and major events

[0709] Prompt statement

[0710] output:

[0711] A story from a different perspective

[0712] Specific behavior:

[0713] The server generates a prompt sentence and obtains a story from the perspective of characters X, Y, and Z. For example, a story from X's perspective, a story from Y's perspective, and a story from Z's perspective are generated respectively.

[0714] Step 4:

[0715] server

[0716] The server compiles the stories from different perspectives and sends them to the device in the form of a selection, for example:

[0717] {

[0718] "views": [

[0719] "Read from X's point of view",

[0720] "Read from Y's perspective",

[0721] "Reading from Z's Perspective"

[0722] ]

[0723] }

[0724] The terminal presents this to the user.

[0725] input:

[0726] A story from a different perspective

[0727] output:

[0728] The options to present to the user

[0729] Specific behavior:

[0730] The server converts the data into a choice format and sends it to the terminal, which then displays the choices to the user.

[0731] Step 5:

[0732] User

[0733] The user operates the device interface and selects the perspective they are interested in from the options presented, for example, "Read from Y's perspective."

[0734] input:

[0735] The viewpoint selected by the user

[0736] output:

[0737] Selected viewpoint data

[0738] Specific behavior:

[0739] The user selects "Read from Y's perspective" and clicks the Select button.

[0740] Step 6:

[0741] server

[0742] The server retrieves the already generated story based on the viewpoint selected by the user and sends it to the terminal in the form of a text version of the story.

[0743] input:

[0744] Selected viewpoint data

[0745] output:

[0746] Narrative text from selected perspectives

[0747] Specific behavior:

[0748] The server retrieves the story from the saved viewpoint and sends it to the device.

[0749] Step 7:

[0750] Terminal

[0751] The terminal displays the story text received from the server to the user.

[0752] input:

[0753] Story text received from the server

[0754] output:

[0755] Displaying narrative text

[0756] Specific behavior:

[0757] The device displays the story text on the screen.

[0758] Step 8:

[0759] User

[0760] After reading the generated story, the user enters their impressions and comments in a feedback form, which is then sent from the device to the server.

[0761] input:

[0762] User-entered feedback

[0763] output:

[0764] Feedback data sent to the server

[0765] Specific behavior:

[0766] The user enters their thoughts and comments into the feedback form and clicks the submit button.

[0767] Step 9:

[0768] server

[0769] The server stores user feedback in a database and analyzes it to help improve the system.

[0770] input:

[0771] Feedback data received from users

[0772] output:

[0773] Stored Feedback Data

[0774] Analysis results

[0775] Specific behavior:

[0776] The server stores the feedback data in a database and performs analysis to use it to improve the system.

[0777] (Application example 1)

[0778] 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."

[0779] With conventional content distribution services, viewing of movies and dramas is limited to a set viewpoint or edited content, preventing users from freely enjoying the story from different perspectives. While systems exist for reconstructing a story from different viewpoints, they are primarily text-based and difficult to apply to video content. Another issue is the lack of in-depth analysis based on the viewpoint of the story or interactive feedback functions for the psychological portrayal of characters.

[0780] 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.

[0781] In this invention, the server includes means for receiving a story title as input from a user, means for analyzing the content of the story based on the story title and extracting a plurality of characters and major events, means for generating stories from different perspectives based on the extracted information, means for presenting to the user options for the stories from the generated different perspectives, means for displaying a story generated from a specific perspective based on the user's selection, means for selecting a specific perspective from the option options presented to the user, and means for providing the user with a story generated based on a specific perspective. This allows the user to freely select different perspectives when watching a movie or drama and enjoy the story from each perspective.

[0782] A "user" is an individual or group that uses the system, inputs the title of a story, and enjoys the story from a particular perspective.

[0783] "Story title" is the name of the story to be analyzed, entered by the user.

[0784] "Story content" refers to information such as the story, events, and characters that are analyzed based on the story title.

[0785] A "character" is someone who has a role in the story.

[0786] An "incident" is a major event or action that occurs in a story.

[0787] "Point of view" is the perspective of a story from the perspective of a particular character or role in the story.

[0788] "Feedback" refers to opinions, impressions, and information for improvement that users input into the system.

[0789] "Generative AI" is an AI technology that automatically generates new stories and information based on input data.

[0790] "Deep story analysis" is the process of analyzing the content of a story in detail to reveal the psychological state and background information of the characters.

[0791] "Additional information" is supplemental information provided as the story progresses based on the perspective selected by the user.

[0792] In order to put the present invention into practice, it is necessary to build a system that allows a user to input the title of a story and enjoy the story from different perspectives. This system is configured as follows.

[0793] User Input

[0794] Through the terminal interface, the user inputs the title of the story they are interested in. This title is then sent to the system.

[0795] Server Processing: A Narrative Analysis

[0796] The server receives the title sent by the user and analyzes the content of the story based on that title. This analysis uses generative artificial intelligence (AI) to automatically extract the main characters and events of the story. An example of the AI ​​model used is OpenAI's GPT-3. For example, if the story "Urashima Taro" is input, information such as Urashima Taro, Princess Otohime, and the Dragon Palace in the sea will be extracted.

[0797] Server processing: View generation

[0798] The server generates a story from multiple different perspectives based on the extracted information. It uses a generative AI model to reconstruct the story from each character's perspective. For example, for the "Tale of Urashima Taro," the perspectives of Urashima Taro, Princess Otohime, and the turtle could all be considered.

[0799] Server processing: Presenting story options

[0800] The server compiles the generated stories from multiple perspectives and presents them to the user. This allows the user to choose from which perspective they would like to read the story. For example, options such as "Read from Urashima Taro's perspective," "Read from Otohime's perspective," or "Read from the turtle's perspective" are presented.

[0801] User Selection

[0802] The user operates the device and clicks on the viewpoint they are interested in from the displayed options. For example, they select "Otohime's viewpoint."

[0803] Server processing: Narrative generation and presentation

[0804] The server retrieves the story generated based on the viewpoint selected by the user and sends it to the device. The user can enjoy the story reconstructed from this specific viewpoint. For example, the story of Urashima Taro reconstructed from Otohime's viewpoint is displayed as text.

[0805] User Feedback

[0806] After reading the generated story, users can use the feedback form to enter their impressions and comments, such as additional information they would like to know or suggestions for improving the story.

[0807] Server processing: feedback storage and analysis

[0808] The server receives user feedback, stores it in a database, and analyzes it to perform in-depth analysis of the story, improving the system to provide a richer story experience.

[0809] Specific examples

[0810] For example, to allow a user to experience the story of Urashima Taro from Otohime's perspective, the following prompt sentence is input to the generative AI model:

[0811] Title: Reconstruct the story of "Urashima Taro" from Otohime's perspective.

[0812] This prompt sentence generates a story reconstructed from Otohime's perspective and presents it to the user.

[0813] Unlike traditional movie or TV drama viewing experiences, the system of the present invention allows users to freely enjoy a story from various perspectives. Furthermore, by conducting in-depth analysis of the story content and each perspective based on user feedback, a more fulfilling story experience can be provided.

[0814] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0815] Step 1:

[0816] The user uses the terminal interface to input the title of the story they are interested in and send it to the system. Input data: Story title. Output data: Story title sent to the system.

[0817] Step 2:

[0818] The server receives the story title sent by the user and analyzes the content of the story based on the title. It sends prompt sentences to the generative AI model to extract the main characters and events. Input data: Story title. Output data: Main characters and events.

[0819] Step 3:

[0820] The server generates stories from different perspectives based on the extracted characters and events. Using a generative AI model, it reconstructs the story based on each perspective. Input data: extracted characters and events. Output data: stories from different perspectives.

[0821] Step 4:

[0822] The server presents the generated story options from different viewpoints to the user. Multiple viewpoint options are displayed on the terminal. Input data: Stories from different viewpoints. Output data: Display of viewpoint options.

[0823] Step 5:

[0824] The user operates the terminal and selects the viewpoint of interest from the presented viewpoint options. Input data: viewpoint options. Output data: selected viewpoint.

[0825] Step 6:

[0826] The server sends the generated story based on the viewpoint selected by the user to the terminal. The terminal displays the story reconstructed from that particular viewpoint to the user. Input data: Selected viewpoint. Output data: Reconstructed story.

[0827] Step 7:

[0828] After reading the generated story, the user submits their impressions and comments to the system through a feedback form. Input data: impressions and comments. Output data: feedback form submission.

[0829] Step 8:

[0830] The server receives feedback from users and stores it in a database. It analyzes the feedback and uses it to improve the system. Input data: User feedback. Output data: Stored feedback and analysis results.

[0831] 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.

[0832] An embodiment of the present invention provides a system that allows users to enjoy different perspectives on a story through an interactive system that combines generative artificial intelligence and an emotion engine. This system not only acquires information about the story from the user and generates and displays the content of the story based on that information, but also recognizes and analyzes the user's emotions to provide a more personalized experience. Specific embodiments of the present invention are described below.

[0833] User Input and Emotion Recognition

[0834] Terminal

[0835] The user inputs the title of a story they are interested in through the device interface. An emotion engine then operates to recognize the user's emotions in real time based on their input and dialogue behavior. For example, when the user inputs the title "Cinderella," the emotion engine analyzes the user's facial expression and tone of voice to determine their emotional state (e.g., excitement, curiosity, sadness, etc.).

[0836] Server Processing: Narrative Analysis and Sentiment Analysis

[0837] server

[0838] The server receives the title submitted by the user and the emotional data analyzed by the emotion engine. It then analyzes the story content based on the title and extracts the main characters and events. This process is carried out using generative artificial intelligence. For example, in the case of "Cinderella," Cinderella, the stepmother, the prince, the ball, the glass slippers, etc. are extracted.

[0839] Server processing: Emotion-based viewpoint generation

[0840] server

[0841] The server combines the extracted story information with the user's emotional data to generate a story from the most appropriate perspective. Generative AI is used to reconstruct the story based on the user's emotional state. For example, if the user expresses curiosity, the server generates a perspective that focuses on more detailed background information or hidden truths.

[0842] Server Processing: Presenting Narrative Options and Reevaluating Emotions

[0843] Terminal

[0844] The server presents the generated story from multiple perspectives to the user and re-presents the most suitable option to the user. This re-presentation re-evaluates the user's emotional state at the time of their initial selection and adjusts the options as necessary. For example, the server presents multiple options such as "Read from Cinderella's perspective," "Read from the stepmother's perspective," and "Read from the prince's perspective," and emphasizes the recommended perspective based on the user's emotions.

[0845] User selection and story display

[0846] User

[0847] The user selects the perspective they are interested in from the displayed options. For example, they select "The Prince's Perspective." The story based on the selected perspective is then displayed on the device. This allows the user to read the story reconstructed from a specific perspective.

[0848] User feedback and sentiment analysis

[0849] Terminal Server

[0850] After reading the generated story, the user enters their thoughts and comments in a feedback form. The emotion engine analyzes the user's emotions at the time of the feedback to gain a more detailed understanding of the feedback content. The server receives this feedback data, stores it in a database, and uses it to improve the system.

[0851] Through this specific processing flow, the system provides users with a multifaceted and personalized story experience, helping them gain a deeper understanding of the story and new perspectives. For example, by enjoying the story of "Cinderella" from the prince's perspective, users can understand the prince's psychological state and the hidden meaning behind his actions, gaining new insights into the story as a whole. Furthermore, feedback based on the user's emotions allows the system to further optimize future story generation and perspective presentation methods.

[0852] The processing flow will be explained below.

[0853] Step 1:

[0854] User:

[0855] The user inputs the title of the story through the device interface, for example, "Cinderella." At this time, the emotion engine recognizes the user's facial expressions and tone of voice and collects emotional data.

[0856] Step 2:

[0857] Device:

[0858] The title entered by the user is parsed into JSON format. At the same time, the emotion data recognized by the emotion engine is also parsed. An HTTP POST request containing this data is generated and sent to the server.

[0859] Step 3:

[0860] server:

[0861] Receives an HTTP request, retrieves the story title and emotion data entered by the user, and retrieves the story content from an external database or API based on the title.

[0862] Step 4:

[0863] server:

[0864] The acquired story content is passed to the generative AI to begin analysis. The generative AI analyzes the story and extracts the main characters (Cinderella, the stepmother, the prince, etc.) and key events (the ball, the glass slippers, etc.).

[0865] Step 5:

[0866] server:

[0867] Based on the extracted information and emotional data, the system generates stories from multiple different perspectives. The generative AI identifies the perspective that best matches the user's emotional state and reconstructs the story from that perspective. For example, if the user is excited, it generates a story from a perspective filled with action and dramatic elements.

[0868] Step 6:

[0869] server:

[0870] The generated stories from multiple perspectives are compiled into a list, and data to be presented to the user is generated. An HTTP response including this data is generated and sent to the terminal.

[0871] Step 7:

[0872] Device:

[0873] The response received from the server is parsed and the user is presented with a choice of different perspectives for the story. For example, options such as "Read from Cinderella's point of view," "Read from the stepmother's point of view," or "Read from the prince's point of view" are displayed. At this time, the emotion engine again recognizes the user's emotions and highlights the most recommended options.

[0874] Step 8:

[0875] User:

[0876] Choose the perspective that interests you (for example, "The Prince's Perspective") and click on that option.

[0877] Step 9:

[0878] Device:

[0879] It receives the user's selection, generates an HTTP POST request in JSON format containing the selected viewpoint and emotion data, and sends it to the server.

[0880] Step 10:

[0881] server:

[0882] Receives the user's selection, retrieves from the database a story generated based on the selected viewpoint, generates an HTTP response containing the story data, and sends it to the device.

[0883] Step 11:

[0884] Device:

[0885] It parses the story data returned by the server and displays to the user a reconstructed version of the story from a particular point of view, for example, displaying the text of the Cinderella story reconstructed from the prince's point of view.

[0886] Step 12:

[0887] User:

[0888] After reading the generated story, users can enter their impressions and comments in a feedback form. At this time, the emotion engine will recognize the user's emotions again and include them in the feedback.

[0889] Step 13:

[0890] Device:

[0891] Parse the user-entered feedback and emotion data into JSON format, generate an HTTP POST request, and send it to the server.

[0892] Step 14:

[0893] server:

[0894] Feedback and emotional data are received and stored in a database, and the emotional data is analyzed and used to improve the system and optimize story generation.

[0895] Through the specific processing flow described above, the present system can provide users with a multifaceted and personalized story experience.

[0896] Example 2

[0897] 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."

[0898] Existing story generation systems simply generate and display stories, making it difficult to provide a personalized experience based on the user's emotions and interests. Furthermore, they lack the technology to analyze user emotions and dynamically reconstruct stories based on those emotions, making it impossible to provide optimal content for each individual user. This results in a decline in user engagement and satisfaction.

[0899] 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.

[0900] In this invention, the server includes means for receiving a story title as input from a user, means for analyzing the content of the story based on the story title and extracting multiple characters and major events, means for generating stories from different perspectives based on the extracted information, means for presenting to the user options for the generated stories from the different perspectives, means for displaying the story generated from a specific perspective based on the user's selection, means for recognizing and analyzing user emotions in real time from the user's input and dialogue behavior, and means for reconstructing the story based on the user's emotion data, thereby making it possible to provide a personalized story experience based on the emotions and interests of each individual user.

[0901] "Story Title" is a name entered by the user to indicate the story in which they are interested.

[0902] A "terminal" is a device used by a user for input and interaction, and includes smartphones, tablets, PCs, etc.

[0903] An "emotion engine" is a technology that analyzes a user's facial expressions and tone of voice to recognize their emotional state.

[0904] "Emotion data" is information that indicates the user's emotional state analyzed by the emotion engine.

[0905] "Generative AI" refers to AI techniques for generating content based on given input, with the ability to create text based on specific prompts.

[0906] A "prompt" is text that contains specific instructions or questions to be given to a generative artificial intelligence.

[0907] "Extract" refers to extracting specific data from the analyzed information.

[0908] "A story from another perspective" refers to a story that has been reconstructed from different characters or perspectives within the same story.

[0909] "Presenting" refers to displaying options or information to the user.

[0910] "Feedback" refers to the opinions and thoughts that users provide about the generated story.

[0911] A "database" is a system for systematically storing and managing information.

[0912] A "personalized experience" is the provision of specific content and services based on an individual user's interests and emotions.

[0913] "Engagement" refers to the degree of involvement a user has with a service or content.

[0914] "Analysis" is the act of examining data in detail to reveal its meaning and structure.

[0915] "Reconstructing" refers to reassembling content from the original data based on a new perspective or structure.

[0916] This invention combines generative artificial intelligence and an emotion engine to provide an interactive system for users, allowing them to enjoy different perspectives on a story. This system not only acquires information about the story from the user and generates and displays the content of the story based on that information, but also recognizes and analyzes the user's emotions to provide a more personalized experience.

[0917] User Input and Emotion Recognition

[0918] First, the user inputs the title of a story they are interested in through the device interface. For example, they input "Cinderella." At this time, the device's built-in emotion engine (e.g., emotion analysis API) analyzes the user's facial expressions and tone of voice to recognize the user's emotional state (e.g., excitement, curiosity, sadness, etc.) in real time.

[0919] Narrative and sentiment analysis

[0920] Next, the server receives the story title and emotion data sent by the user. Using generative AI (e.g., GPT-4), the server analyzes the story and extracts key characters and events. For example, in the case of "Cinderella," it extracts Cinderella, the stepmother, the prince, the ball, the glass slippers, etc.

[0921] Emotion-based perspective generation

[0922] The server combines the extracted story information with the user's emotional data to generate a story from the most appropriate perspective. The generative AI reconstructs the story according to the user's emotional state. For example, if the user expresses curiosity, it generates a story that focuses on detailed background information or hidden truths. This operation is performed using prompt sentences. Examples of specific prompt sentences include, "Please reconstruct the story of Cinderella from the stepmother's perspective" and "The user is curious, so please generate a story that focuses on Cinderella's hidden truth."

[0923] Presenting narrative options and reassessing emotions

[0924] The generated stories from multiple perspectives are sent from the server to the device and presented to the user. At this time, the emotional state of the user at the time of their initial selection is reevaluated, and the optimal choice is adjusted. For example, multiple options such as "Read from Cinderella's perspective," "Read from the stepmother's perspective," and "Read from the prince's perspective" are presented, and the most recommended perspective is highlighted.

[0925] User selection and story display

[0926] The user selects the perspective they are interested in from the displayed options. For example, they select "The Prince's Perspective." The story based on the selected perspective is then displayed on the device. This allows the user to read the story reconstructed from a specific perspective.

[0927] User feedback and sentiment analysis

[0928] After reading the story, the user enters their thoughts and comments about the generated story into a feedback form. The device's built-in emotion engine also analyzes the user's emotions at the time of this feedback. The server receives the feedback data and emotion data and stores them in a database. This feedback data is used to improve the system.

[0929] This specific processing flow allows users to enjoy a multifaceted and personalized storytelling experience. For example, by experiencing the story of Cinderella from the prince's perspective, users can gain new insights and the system can further improve itself based on that feedback.

[0930] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0931] System program processing flow

[0932] Step 1: User enters story title

[0933] User: The user uses the terminal interface to input the title of a story that interests them.

[0934] Input: The title of the story (e.g., "Cinderella").

[0935] Output: The input title data.

[0936] Specific actions: Enter a title in the text input form displayed on the device screen and press the send button.

[0937] Step 2: The emotion engine analyzes the emotion

[0938] Device: The device's built-in emotion engine analyzes the user's facial expressions and tone of voice in real time.

[0939] Input: User's facial image and voice data.

[0940] Output: The user's emotional state (e.g., excitement, curiosity, sadness, etc.).

[0941] What it does: It uses a camera and microphone to capture facial expressions and tone of voice as data and then applies emotion analysis algorithms.

[0942] Step 3: The server receives the data

[0943] Server: The server receives the story title and emotion data sent from the device.

[0944] Input: Story title data, emotion data.

[0945] Output: Raw data stored in the server database.

[0946] Specific operation: Receives HTTP requests and saves data to a database.

[0947] Step 4: Story Analysis

[0948] Server: The server uses generative artificial intelligence to extract key characters and events from the story based on the title it receives.

[0949] Input: Story title data.

[0950] Output: Extracted characters and events (e.g., "Cinderella," "Stepmother," "Prince," "Ball," "Glass Slippers").

[0951] Specific operations: The title of the story is input as a prompt into the generative AI, which then performs an analysis to extract characters and key events.

[0952] Step 5: Combining emotion data with narrative information

[0953] Server: The server combines the emotion data with the extracted story information and generates a story from the most appropriate perspective.

[0954] Input: Emotion data, character and event data.

[0955] Output: A reconstructed story based on the user's emotions.

[0956] Specific operation: Based on the emotion data, a prompt is input to the generative AI to generate a story that focuses on detailed background information and hidden truths. For example, the prompt is input as follows: "The user is curious, so please generate a story that focuses on the hidden truth of Cinderella."

[0957] Step 6: Generate narrative options

[0958] Server: Generates stories from multiple perspectives and presents them to the user.

[0959] Input: Reconstructed narrative data.

[0960] Output: Story options (e.g., "Read from Cinderella's point of view," "Read from the stepmother's point of view," "Read from the prince's point of view").

[0961] What it does: Generate a story from multiple perspectives and prepare each option in list form.

[0962] Step 7: Present and reassess options

[0963] Terminal: The terminal displays the generated options to the user and highlights the recommended viewpoint based on the emotional data.

[0964] Input: Narrative choices, emotion data.

[0965] Output: Story options displayed on the user interface.

[0966] Specific operation: Display options for each viewpoint on the screen and label them to reflect the user's excitement and curiosity.

[0967] Step 8: Selecting Users

[0968] User: The user selects the viewpoint of interest from the displayed options.

[0969] Input: Select the perspective of the story (e.g., "The Prince's perspective").

[0970] Output: Selected viewpoint information.

[0971] Specific actions: Click the desired viewpoint from the displayed options.

[0972] Step 9: Presenting a narrative based on point of view

[0973] Terminal: The terminal displays the story based on the selected point of view.

[0974] Input: Selected viewpoint information, reconstructed narrative.

[0975] Output: The displayed narrative text.

[0976] What it does: The story from the selected point of view is displayed on the screen.

[0977] Step 10: User feedback and sentiment analysis

[0978] User: The user enters their thoughts and comments about the generated story in a feedback form.

[0979] Input: Feedback text.

[0980] Output: The input feedback data.

[0981] Specific actions: Enter your opinions and thoughts in text into the form and press the submit button.

[0982] Step 11: Sentiment Analysis

[0983] Device: The emotion engine installed in the device analyzes the user's emotions during feedback.

[0984] Input: Facial image and voice data at the time of feedback.

[0985] Output: Emotion data at the time of feedback.

[0986] Specific operation: Analyze facial expressions and voice during feedback to generate emotional data.

[0987] Step 12: Save your feedback data

[0988] Server: The server receives the feedback data including the analysis results and stores them in a database.

[0989] Input: Feedback data, emotion data.

[0990] Output: Feedback information stored in a database.

[0991] What it does: Runs SQL queries to add feedback and sentiment data to the database.

[0992] This allows users to enjoy a multifaceted and personalized storytelling experience, while the system is further improved based on their feedback.

[0993] (Application example 2)

[0994] 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."

[0995] Conventional storytelling systems lacked sufficient personalization for users, making it difficult to provide an experience that reflected each individual user's emotions. Furthermore, the ability to change the perspective of the story was limited, leaving users with few options for deeper enjoyment. As a result, the story experience tended to be uniform, resulting in lower user satisfaction.

[0996] 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 a story title from a user as input, means for analyzing the content of the story based on the story title and extracting multiple characters and major events, means for generating stories from different perspectives based on the extracted information, means for presenting options for the generated stories from the different perspectives to the user, means for recognizing emotions from the user's facial expressions and voice in real time, means for optimizing the content of the story based on the recognized emotions, and means for displaying the story generated from a specific perspective based on the user's selection. This makes it possible to provide a personalized story experience based on the user's emotions.

[0997] A "user" is an individual who uses the story experience system.

[0998] "Story Title" is the title of the story entered by the user.

[0999] "Multiple characters and major events" refers to the main characters and important events that make up the content of the story.

[1000] "Different perspectives" refers to a story being reconstructed from several different angles.

[1001] "Generated narrative options from different perspectives" are narrative options seen from multiple perspectives generated by the system.

[1002] "Means for recognizing emotions in real time from facial expressions and voice" refers to technology that recognizes emotions by analyzing a user's facial expressions and tone of voice.

[1003] "Recognized emotions" are information obtained by the system analyzing the user's real-time emotions.

[1004] "Means for optimizing story content" refers to techniques that adjust and personalize story content based on the user's emotional state.

[1005] "Generative AI" is a type of AI used to generate stories, using specific algorithms and prompts to generate stories.

[1006] A "prompt sentence" is the input text that serves as the basis for a generative artificial intelligence to generate a story.

[1007] "Feedback" is information provided by a user as impressions or comments on a generated story.

[1008] A "database" is an information storage system that stores feedback and other data for later analysis and system improvement.

[1009] An embodiment of the present invention is based on an interactive system that combines generative artificial intelligence and a sentiment analysis engine to provide a personalized story experience using a story title and user-entered sentiment data.

[1010] 1. System Configuration

[1011] Hardware

[1012] Terminals: Input and display devices such as smartphones, smart glasses, and head-mounted displays

[1013] Server: High-performance computer server, cloud computing service

[1014] Input devices: Webcam, microphone

[1015] software

[1016] Generative artificial intelligence: OpenAI GPT-3 API

[1017] Emotion Recognition Engine: EmotionRecognizer Library

[1018] Others: OpenCV library, librosa library

[1019] 2. Processing flow

[1020] User Input

[1021] The user inputs the title of the story he or she is interested in through the terminal interface, for example, "Cinderella."

[1022] emotion recognition

[1023] The server uses a camera and microphone to analyze the user's facial expression and voice. It uses the EmotionRecognizer library, OpenCV, and librosa to recognize the user's emotions in real time. For example, if the server recognizes "excited" from the user's facial expression and "excited" from their voice, it determines the user's emotional state as "excited."

[1024] Narrative analysis and perspective generation

[1025] Based on the story title and the recognized emotion data, a generative artificial intelligence (GPT-3) generates a new story. Here, a prompt is used to indicate the content and perspective of the story. For example, the following prompt is used:

[1026] When the user's emotion is "excited," reframe the Cinderella story from a different perspective.

[1027] Presenting options

[1028] The generated stories from multiple perspectives are presented to the user, who can select the perspective they are interested in. Among the presented perspectives, particularly recommended ones are highlighted.

[1029] Emotion-based storytelling

[1030] The reconstructed story is displayed based on the viewpoint selected by the user, allowing the user to enjoy a personalized story from a specific perspective.

[1031] Feedback and Reassessment

[1032] After reading the story, the user provides feedback such as their impressions and comments. The EmotionRecognizer library is used to recognize emotions again and to understand the feedback in more detail. This feedback data is stored in a database and used to improve the system.

[1033] This embodiment allows users to enjoy a multifaceted and personalized story experience that is completely tailored to their individual emotions, unlike conventional story experiences.

[1034] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1035] Step 1:

[1036] The user inputs the title of the story he or she is interested in through the terminal interface, and the input story title is sent to the server.

[1037] Input: Story title

[1038] Output: The story title sent to the server

[1039] Step 2:

[1040] The server receives the story title and analyzes the story content based on it. It uses generative artificial intelligence to extract multiple characters and key events. For example, if the title "Cinderella" is input, it will extract characters and events such as Cinderella, the stepmother, the prince, the ball, and the glass slippers.

[1041] Input: The story title sent to the server

[1042] Output: Extracted characters and events

[1043] Step 3:

[1044] The device's camera and microphone are used to capture the user's facial expressions and voice in real time. The EmotionRecognizer library, OpenCV, and librosa are used to recognize the user's emotions and send the emotion data to the server.

[1045] Input: User's facial and voice data

[1046] Output: Recognized emotion data

[1047] Step 4:

[1048] The server receives the title and emotion data and uses a generative artificial intelligence (GPT-3) to recreate the story, using the following prompt:

[1049] When the user's emotion is "excited," reframe the Cinderella story from a different perspective.

[1050] The generated story content is output as seen from multiple perspectives.

[1051] Input: Title and sentiment data

[1052] Output: Reproduced story (from multiple points of view)

[1053] Step 5:

[1054] The server sends the generated story options from different viewpoints to the device, which displays them to the user, highlighting the recommended viewpoints so that the user can select the viewpoint that interests them.

[1055] Input: Generated stories (from multiple perspectives)

[1056] Output: Viewpoint choices displayed to the user

[1057] Step 6:

[1058] The user selects the viewpoint he or she is interested in from the options, and the selected viewpoint information is sent to the server.

[1059] Input: User selected viewpoint

[1060] Output: Selections sent to the server

[1061] Step 7:

[1062] The server sends a story based on the viewpoint selected by the user to the terminal, which then displays it.

[1063] Input: Selections sent to the server

[1064] Output: A narrative based on the selected viewpoint displayed

[1065] Step 8:

[1066] After reading the story, the user enters their thoughts and comments through the feedback form on the device. At this time, the user's emotions are captured again by the camera and microphone and analyzed by the EmotionRecognizer library. The feedback content and emotional data are sent to the server and stored in a database.

[1067] Input: User feedback and sentiment data

[1068] Output: Feedback and emotion data stored in a database

[1069] Step 9:

[1070] The server analyzes the stored feedback and sentiment data and uses it to improve the personalization of the system.

[1071] Input: Feedback and emotion data stored in a database

[1072] Output: Improved system personalization

[1073] 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.

[1074] 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.

[1075] 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.

[1076] [Third embodiment]

[1077] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1078] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1079] 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).

[1080] 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.

[1081] 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.

[1082] 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).

[1083] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for 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.

[1084] 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.

[1085] 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.

[1086] 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.

[1087] 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.

[1088] 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."

[1089] An embodiment of the present invention provides a system that allows a user to enjoy a story from different perspectives. This system extracts detailed information about a story based on the title of the story entered by the user, and generates and presents the story from different perspectives. Specific embodiments of the present invention will be described below.

[1090] User Input

[1091] Terminal

[1092] The user inputs the title of the story he or she is interested in through the terminal interface, for example, "Urashima Taro." This title is then sent to the system.

[1093] Server Processing: A Narrative Analysis

[1094] server

[1095] The server receives the title sent by the user and analyzes the story's content based on the title. This analysis uses generative artificial intelligence to automatically extract the story's main characters and events. For example, for "Urashima Taro," information such as Urashima Taro, Princess Otohime, and the Dragon Palace in the sea is extracted.

[1096] Server processing: View generation

[1097] server

[1098] Based on the extracted information, the server generates a story from multiple different perspectives. It uses generative artificial intelligence to reconstruct the story from each character's point of view. For example, in the case of the story of Urashima Taro, the perspectives of Urashima Taro, Princess Otohime, and the turtle could all be considered. Each perspective would depict a different aspect of the story.

[1099] Server processing: Presenting story options

[1100] Terminal

[1101] The server compiles the generated stories from multiple perspectives and presents them to the user. This allows the user to choose from which perspective they would like to read the story. For example, options such as "Read from Urashima Taro's perspective," "Read from Otohime's perspective," or "Read from the turtle's perspective" are presented.

[1102] User Selection

[1103] User

[1104] The user operates the device and clicks on the viewpoint they are interested in from the displayed options. For example, they select "Otohime's viewpoint."

[1105] Server processing: Narrative generation and presentation

[1106] server

[1107] The server retrieves the story generated based on the viewpoint selected by the user and sends it to the device. This allows the user to enjoy the story reconstructed from a specific viewpoint. For example, the story of Urashima Taro reconstructed from Otohime's viewpoint is displayed as text.

[1108] User Feedback

[1109] User

[1110] After reading the generated story, users can use the feedback form to enter their impressions and comments, which will be used to improve the system.

[1111] Server processing: feedback storage and analysis

[1112] server

[1113] The server receives feedback from users, stores it in a database, and analyzes the collected feedback to help improve the system in the future.

[1114] In this way, the present invention provides users with a variety of ways to enjoy stories, promoting a deeper understanding of the story. As a specific example, by enjoying the story of "Urashima Taro" from Otohime's perspective, users can understand the background of her feelings and actions, and gain a new perspective on the story as a whole.

[1115] The processing flow will be explained below.

[1116] Step 1:

[1117] User:

[1118] The user inputs the title of the story he or she is interested in through the terminal interface, for example, "Cinderella."

[1119] Step 2:

[1120] Device:

[1121] It takes the title entered by the user, parses it into JSON format, and creates an HTTP POST request containing the parsed data and sends it to the server.

[1122] Step 3:

[1123] server:

[1124] Receives an HTTP request, retrieves the story title entered by the user, and retrieves the story content from an external database or API based on this title.

[1125] Step 4:

[1126] server:

[1127] The acquired story content is passed to the generative AI, which then begins analyzing the story. The generative AI analyzes the story and extracts the main characters (e.g., Cinderella, the stepmother, the prince) and key events (the ball, the glass slippers, etc.).

[1128] Step 5:

[1129] server:

[1130] Based on the extracted results, a story is generated from multiple different perspectives. For example, Cinderella's perspective, the stepmother's perspective, and the prince's perspective are generated using generative artificial intelligence.

[1131] Step 6:

[1132] server:

[1133] The generated stories from different perspectives are compiled into a list, and data to be presented to the user is generated. An HTTP response including this data is generated and sent to the terminal.

[1134] Step 7:

[1135] Device:

[1136] Parse the response received from the server and present the user with a choice of different perspectives on the story, for example, "Read from Cinderella's point of view," "Read from the Stepmother's point of view," or "Read from the Prince's point of view."

[1137] Step 8:

[1138] User:

[1139] Choose the perspective you're interested in (e.g., "The Prince's Perspective") and click on the option.

[1140] Step 9:

[1141] Device:

[1142] It receives the user's selection, parses the data containing the selected viewpoint into JSON format, and creates an HTTP POST request containing the parsed data and sends it to the server.

[1143] Step 10:

[1144] server:

[1145] The system receives the user's selection, obtains a story based on the selected perspective (e.g., "the prince's perspective"), generates an HTTP response containing the story data, and sends it to the terminal.

[1146] Step 11:

[1147] Device:

[1148] It parses the story data returned by the server and displays to the user a reconstructed version of the story from a particular point of view, for example, displaying the text of the Cinderella story reconstructed from the prince's point of view.

[1149] Step 12:

[1150] User:

[1151] After reading the generated story, users enter their impressions and comments into the input form and submit it as feedback.

[1152] Step 13:

[1153] Device:

[1154] Receives user feedback, parses it into JSON format, creates an HTTP POST request with the feedback data, and sends it to the server.

[1155] Step 14:

[1156] server:

[1157] Receive feedback data and store it in a database. Analyze the collected feedback and use it to improve the system in the future.

[1158] Through the above specific processing flow, this system can provide users with a multifaceted story experience.

[1159] Example 1

[1160] 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."

[1161] Conventional story generation systems typically provide users with a single perspective, preventing them from enjoying a variety of perspectives. Furthermore, they do not effectively utilize feedback, making it difficult to improve the system. Furthermore, they sometimes produce inaccurate results in story content analysis and story generation from different perspectives.

[1162] 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.

[1163] In this invention, the server includes means for receiving a story title from a user as input, means for analyzing the content of the story based on the story title and extracting multiple characters and major events, means for generating stories from different perspectives based on the extracted information, means for presenting options for the generated stories from different perspectives to the user, means for displaying the generated story from a specific perspective based on the user's selection, means for inputting and saving user feedback on the generated story and using it to improve the system, and means for using prompt sentences to analyze the story and generate stories from different perspectives using a generative AI model. This allows users to enjoy stories from different perspectives, improves the accuracy of the system, and makes it possible to effectively utilize user feedback to improve the system.

[1164] A "user" is someone who uses the system to input the title of a story and select and enjoy stories from different perspectives.

[1165] "Story Title" is the name of a particular piece of story that the user enters into the system.

[1166] "Story content" is text or data containing characters, major events, and other information relevant to the story.

[1167] A "character" is a character or person who plays a specific role in a story.

[1168] A "major event" is an event or occurrence that plays a significant role in the progression of the story.

[1169] A "point of view" is a standpoint or perspective from which a story is portrayed from different characters or points of view.

[1170] "Choices" are multiple perspectives or options presented to the user.

[1171] "Feedback" refers to thoughts and comments that users input about the generated story.

[1172] The "server" is the central computer of the system, and is the device that processes input from users, analyzes the content of the story, and generates and transmits stories from different perspectives.

[1173] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to analyze the content of a story and generate a story from different perspectives.

[1174] A "prompt" is a text sentence used to give specific instructions to a generative AI model.

[1175] "Database" means an electronic storage system that stores collected data and feedback so that it can be searched and analyzed as needed.

[1176] An embodiment of the present invention is a system for allowing a user to enjoy different perspectives on a story. Based on the title of a story entered by a user, the system extracts detailed information about the story and generates and presents the story from different perspectives.

[1177] User Input

[1178] Terminal

[1179] The user inputs the title of the story using the terminal interface. For example, the user inputs a title such as "Story A" into an input field on the terminal. This information is sent to the server.

[1180] Server Processing: A Narrative Analysis

[1181] server

[1182] The server receives the story title sent by the user and analyzes its content. This analysis is performed using a generative AI model (e.g., GPT-3). The server sends the following prompt to the generative AI model:

[1183] List the characters and major events in "Story A."

[1184] The generative AI model extracts the content of the story (characters and major events) based on the prompt sent. For example, for "Story A," information such as characters X, Y, and Z and major events 1, 2, and 3 can be obtained.

[1185] Server processing: View generation

[1186] server

[1187] The server uses a generative AI model to generate stories from multiple different perspectives based on the extracted list of characters and events. For each perspective, it generates a prompt and sends it to the model. For example:

[1188] Tell us "Story A" from the perspective of Character X.

[1189] The generative AI model responds with the story from the perspective of character X. It does the same for other perspectives (characters Y, Z, etc.).

[1190] Server processing: Presenting story options

[1191] server

[1192] The server compiles the generated stories from multiple perspectives and sends them to the device in the form of a choice, which the device presents to the user (e.g., "Read from X's perspective," "Read from Y's perspective," "Read from Z's perspective").

[1193] User Selection

[1194] User

[1195] The user operates the device interface and selects the perspective they are interested in from the options presented, for example, "Read from Y's perspective."

[1196] Server processing: Narrative generation and presentation

[1197] server

[1198] The server retrieves a story already created based on the user's selected viewpoint and sends it to the device, which then displays the story text on the screen, allowing the user to enjoy the story reconstructed from a specific viewpoint.

[1199] User Feedback

[1200] User

[1201] After reading the story, the user enters their impressions and comments in the feedback form, and the user's feedback is sent to the server.

[1202] Server processing: feedback storage and analysis

[1203] server

[1204] The server receives user feedback, stores it in a database (e.g., MySQL or MongoDB), and analyzes the collected feedback to help improve the system in the future.

[1205] In this way, the present invention is a system that provides users with multiple ways to enjoy stories and promotes a deeper understanding of the story. As a specific example, by enjoying "Story A" from the perspective of character Y, users can understand the background of Y's feelings and actions, and gain a new perspective on the story as a whole.

[1206] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1207] Step 1:

[1208] Terminal

[1209] The user inputs the title of the story through the terminal interface. For example, they input "Story A." This input data is temporarily saved on the terminal and sent to the server when the send button is pressed.

[1210] input:

[1211] Story title entered by the user

[1212] output:

[1213] Subject data sent to the server

[1214] Specific behavior:

[1215] The user enters "Story A" in the title input field and clicks the submit button.

[1216] Step 2:

[1217] server

[1218] The server receives the story title submitted by the user and analyzes the story content by sending the following prompt to the generative AI model:

[1219] List the characters and major events in "Story A."

[1220] Based on this prompt, the generative AI model analyzes the story's content and lists the characters and key events.

[1221] input:

[1222] Story title received from user

[1223] Prompt statement

[1224] output:

[1225] List of characters and major events

[1226] Specific behavior:

[1227] The server sends a prompt to the generative AI model to retrieve characters and key events. For "Story A," characters X, Y, and Z and key events 1, 2, and 3 are extracted.

[1228] Step 3:

[1229] server

[1230] The server uses a generative AI model to generate stories from multiple different perspectives based on the extracted list of characters and events. For each perspective, it generates a prompt and sends it to the model. For example:

[1231] Tell us "Story A" from the perspective of Character X.

[1232] The model generates a story from each perspective.

[1233] input:

[1234] List of characters and major events

[1235] Prompt statement

[1236] output:

[1237] A story from a different perspective

[1238] Specific behavior:

[1239] The server generates a prompt sentence and obtains a story from the perspective of characters X, Y, and Z. For example, a story from X's perspective, a story from Y's perspective, and a story from Z's perspective are generated respectively.

[1240] Step 4:

[1241] server

[1242] The server compiles the stories from different perspectives and sends them to the device in the form of a selection, for example:

[1243] {

[1244] "views": [

[1245] "Read from X's point of view",

[1246] "Read from Y's perspective",

[1247] "Reading from Z's Perspective"

[1248] ]

[1249] }

[1250] The terminal presents this to the user.

[1251] input:

[1252] A story from a different perspective

[1253] output:

[1254] The options to present to the user

[1255] Specific behavior:

[1256] The server converts the data into a choice format and sends it to the terminal, which then displays the choices to the user.

[1257] Step 5:

[1258] User

[1259] The user operates the device interface and selects the perspective they are interested in from the options presented, for example, "Read from Y's perspective."

[1260] input:

[1261] The viewpoint selected by the user

[1262] output:

[1263] Selected viewpoint data

[1264] Specific behavior:

[1265] The user selects "Read from Y's perspective" and clicks the Select button.

[1266] Step 6:

[1267] server

[1268] The server retrieves the already generated story based on the viewpoint selected by the user and sends it to the terminal in the form of a text version of the story.

[1269] input:

[1270] Selected viewpoint data

[1271] output:

[1272] Narrative text from selected perspectives

[1273] Specific behavior:

[1274] The server retrieves the story from the saved viewpoint and sends it to the device.

[1275] Step 7:

[1276] Terminal

[1277] The terminal displays the story text received from the server to the user.

[1278] input:

[1279] Story text received from the server

[1280] output:

[1281] Displaying narrative text

[1282] Specific behavior:

[1283] The device displays the story text on the screen.

[1284] Step 8:

[1285] User

[1286] After reading the generated story, the user enters their impressions and comments in a feedback form, which is then sent from the device to the server.

[1287] input:

[1288] User-entered feedback

[1289] output:

[1290] Feedback data sent to the server

[1291] Specific behavior:

[1292] The user enters their thoughts and comments into the feedback form and clicks the submit button.

[1293] Step 9:

[1294] server

[1295] The server stores user feedback in a database and analyzes it to help improve the system.

[1296] input:

[1297] Feedback data received from users

[1298] output:

[1299] Stored Feedback Data

[1300] Analysis results

[1301] Specific behavior:

[1302] The server stores the feedback data in a database and performs analysis to use it to improve the system.

[1303] (Application example 1)

[1304] 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."

[1305] With conventional content distribution services, viewing of movies and dramas is limited to a set viewpoint or edited content, preventing users from freely enjoying the story from different perspectives. While systems exist for reconstructing a story from different viewpoints, they are primarily text-based and difficult to apply to video content. Another issue is the lack of in-depth analysis based on the viewpoint of the story or interactive feedback functions for the psychological portrayal of characters.

[1306] 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.

[1307] In this invention, the server includes means for receiving a story title as input from a user, means for analyzing the content of the story based on the story title and extracting a plurality of characters and major events, means for generating stories from different perspectives based on the extracted information, means for presenting to the user options for the stories from the generated different perspectives, means for displaying a story generated from a specific perspective based on the user's selection, means for selecting a specific perspective from the option options presented to the user, and means for providing the user with a story generated based on a specific perspective. This allows the user to freely select different perspectives when watching a movie or drama and enjoy the story from each perspective.

[1308] A "user" is an individual or group that uses the system, inputs the title of a story, and enjoys the story from a particular perspective.

[1309] "Story title" is the name of the story to be analyzed, entered by the user.

[1310] "Story content" refers to information such as the story, events, and characters that are analyzed based on the story title.

[1311] A "character" is someone who has a role in the story.

[1312] An "incident" is a major event or action that occurs in a story.

[1313] "Point of view" is the perspective of a story from the perspective of a particular character or role in the story.

[1314] "Feedback" refers to opinions, impressions, and information for improvement that users input into the system.

[1315] "Generative AI" is an AI technology that automatically generates new stories and information based on input data.

[1316] "Deep story analysis" is the process of analyzing the content of a story in detail to reveal the psychological state and background information of the characters.

[1317] "Additional information" is supplemental information provided as the story progresses based on the perspective selected by the user.

[1318] In order to put the present invention into practice, it is necessary to build a system that allows a user to input the title of a story and enjoy the story from different perspectives. This system is configured as follows.

[1319] User Input

[1320] Through the terminal interface, the user inputs the title of the story they are interested in. This title is then sent to the system.

[1321] Server Processing: A Narrative Analysis

[1322] The server receives the title sent by the user and analyzes the content of the story based on that title. This analysis uses generative artificial intelligence (AI) to automatically extract the main characters and events of the story. An example of the AI ​​model used is OpenAI's GPT-3. For example, if the story "Urashima Taro" is input, information such as Urashima Taro, Princess Otohime, and the Dragon Palace in the sea will be extracted.

[1323] Server processing: View generation

[1324] The server generates a story from multiple different perspectives based on the extracted information. It uses a generative AI model to reconstruct the story from each character's perspective. For example, for the "Tale of Urashima Taro," the perspectives of Urashima Taro, Princess Otohime, and the turtle could all be considered.

[1325] Server processing: Presenting story options

[1326] The server compiles the generated stories from multiple perspectives and presents them to the user. This allows the user to choose from which perspective they would like to read the story. For example, options such as "Read from Urashima Taro's perspective," "Read from Otohime's perspective," or "Read from the turtle's perspective" are presented.

[1327] User Selection

[1328] The user operates the device and clicks on the viewpoint they are interested in from the displayed options. For example, they select "Otohime's viewpoint."

[1329] Server processing: Narrative generation and presentation

[1330] The server retrieves the story generated based on the viewpoint selected by the user and sends it to the device. The user can enjoy the story reconstructed from this specific viewpoint. For example, the story of Urashima Taro reconstructed from Otohime's viewpoint is displayed as text.

[1331] User Feedback

[1332] After reading the generated story, users can use the feedback form to enter their impressions and comments, such as additional information they would like to know or suggestions for improving the story.

[1333] Server processing: feedback storage and analysis

[1334] The server receives user feedback, stores it in a database, and analyzes it to perform in-depth analysis of the story, improving the system to provide a richer story experience.

[1335] Specific examples

[1336] For example, to allow a user to experience the story of Urashima Taro from Otohime's perspective, the following prompt sentence is input to the generative AI model:

[1337] Title: Reconstruct the story of "Urashima Taro" from Otohime's perspective.

[1338] This prompt sentence generates a story reconstructed from Otohime's perspective and presents it to the user.

[1339] Unlike traditional movie or TV drama viewing experiences, the system of the present invention allows users to freely enjoy a story from various perspectives. Furthermore, by conducting in-depth analysis of the story content and each perspective based on user feedback, a more fulfilling story experience can be provided.

[1340] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1341] Step 1:

[1342] The user uses the terminal interface to input the title of the story they are interested in and send it to the system. Input data: Story title. Output data: Story title sent to the system.

[1343] Step 2:

[1344] The server receives the story title sent by the user and analyzes the content of the story based on the title. It sends prompt sentences to the generative AI model to extract the main characters and events. Input data: Story title. Output data: Main characters and events.

[1345] Step 3:

[1346] The server generates stories from different perspectives based on the extracted characters and events. Using a generative AI model, it reconstructs the story based on each perspective. Input data: extracted characters and events. Output data: stories from different perspectives.

[1347] Step 4:

[1348] The server presents the generated story options from different viewpoints to the user. Multiple viewpoint options are displayed on the terminal. Input data: Stories from different viewpoints. Output data: Display of viewpoint options.

[1349] Step 5:

[1350] The user operates the terminal and selects the viewpoint of interest from the presented viewpoint options. Input data: viewpoint options. Output data: selected viewpoint.

[1351] Step 6:

[1352] The server sends the generated story based on the viewpoint selected by the user to the terminal. The terminal displays the story reconstructed from that particular viewpoint to the user. Input data: Selected viewpoint. Output data: Reconstructed story.

[1353] Step 7:

[1354] After reading the generated story, the user submits their impressions and comments to the system through a feedback form. Input data: impressions and comments. Output data: feedback form submission.

[1355] Step 8:

[1356] The server receives feedback from users and stores it in a database. It analyzes the feedback and uses it to improve the system. Input data: User feedback. Output data: Stored feedback and analysis results.

[1357] 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.

[1358] An embodiment of the present invention provides a system that allows users to enjoy different perspectives on a story through an interactive system that combines generative artificial intelligence and an emotion engine. This system not only acquires information about the story from the user and generates and displays the content of the story based on that information, but also recognizes and analyzes the user's emotions to provide a more personalized experience. Specific embodiments of the present invention are described below.

[1359] User Input and Emotion Recognition

[1360] Terminal

[1361] The user inputs the title of a story they are interested in through the device interface. An emotion engine then operates to recognize the user's emotions in real time based on their input and dialogue behavior. For example, when the user inputs the title "Cinderella," the emotion engine analyzes the user's facial expression and tone of voice to determine their emotional state (e.g., excitement, curiosity, sadness, etc.).

[1362] Server Processing: Narrative Analysis and Sentiment Analysis

[1363] server

[1364] The server receives the title submitted by the user and the emotional data analyzed by the emotion engine. It then analyzes the story content based on the title and extracts the main characters and events. This process is carried out using generative artificial intelligence. For example, in the case of "Cinderella," Cinderella, the stepmother, the prince, the ball, the glass slippers, etc. are extracted.

[1365] Server processing: Emotion-based viewpoint generation

[1366] server

[1367] The server combines the extracted story information with the user's emotional data to generate a story from the most appropriate perspective. Generative AI is used to reconstruct the story based on the user's emotional state. For example, if the user expresses curiosity, the server generates a perspective that focuses on more detailed background information or hidden truths.

[1368] Server Processing: Presenting Narrative Options and Reevaluating Emotions

[1369] Terminal

[1370] The server presents the generated story from multiple perspectives to the user and re-presents the most suitable option to the user. This re-presentation re-evaluates the user's emotional state at the time of their initial selection and adjusts the options as necessary. For example, the server presents multiple options such as "Read from Cinderella's perspective," "Read from the stepmother's perspective," and "Read from the prince's perspective," and emphasizes the recommended perspective based on the user's emotions.

[1371] User selection and story display

[1372] User

[1373] The user selects the perspective they are interested in from the displayed options. For example, they select "The Prince's Perspective." The story based on the selected perspective is then displayed on the device. This allows the user to read the story reconstructed from a specific perspective.

[1374] User feedback and sentiment analysis

[1375] Terminal Server

[1376] After reading the generated story, the user enters their thoughts and comments in a feedback form. The emotion engine analyzes the user's emotions at the time of the feedback to gain a more detailed understanding of the feedback content. The server receives this feedback data, stores it in a database, and uses it to improve the system.

[1377] Through this specific processing flow, the system provides users with a multifaceted and personalized story experience, helping them gain a deeper understanding of the story and new perspectives. For example, by enjoying the story of "Cinderella" from the prince's perspective, users can understand the prince's psychological state and the hidden meaning behind his actions, gaining new insights into the story as a whole. Furthermore, feedback based on the user's emotions allows the system to further optimize future story generation and perspective presentation methods.

[1378] The processing flow will be explained below.

[1379] Step 1:

[1380] User:

[1381] The user inputs the title of the story through the device interface, for example, "Cinderella." At this time, the emotion engine recognizes the user's facial expressions and tone of voice and collects emotional data.

[1382] Step 2:

[1383] Device:

[1384] The title entered by the user is parsed into JSON format. At the same time, the emotion data recognized by the emotion engine is also parsed. An HTTP POST request containing this data is generated and sent to the server.

[1385] Step 3:

[1386] server:

[1387] Receives an HTTP request, retrieves the story title and emotion data entered by the user, and retrieves the story content from an external database or API based on the title.

[1388] Step 4:

[1389] server:

[1390] The acquired story content is passed to the generative AI to begin analysis. The generative AI analyzes the story and extracts the main characters (Cinderella, the stepmother, the prince, etc.) and key events (the ball, the glass slippers, etc.).

[1391] Step 5:

[1392] server:

[1393] Based on the extracted information and emotional data, the system generates stories from multiple different perspectives. The generative AI identifies the perspective that best matches the user's emotional state and reconstructs the story from that perspective. For example, if the user is excited, it generates a story from a perspective filled with action and dramatic elements.

[1394] Step 6:

[1395] server:

[1396] The generated stories from multiple perspectives are compiled into a list, and data to be presented to the user is generated. An HTTP response including this data is generated and sent to the terminal.

[1397] Step 7:

[1398] Device:

[1399] The response received from the server is parsed and the user is presented with a choice of different perspectives for the story. For example, options such as "Read from Cinderella's point of view," "Read from the stepmother's point of view," or "Read from the prince's point of view" are displayed. At this time, the emotion engine again recognizes the user's emotions and highlights the most recommended options.

[1400] Step 8:

[1401] User:

[1402] Choose the perspective that interests you (for example, "The Prince's Perspective") and click on that option.

[1403] Step 9:

[1404] Device:

[1405] It receives the user's selection, generates an HTTP POST request in JSON format containing the selected viewpoint and emotion data, and sends it to the server.

[1406] Step 10:

[1407] server:

[1408] Receives the user's selection, retrieves from the database a story generated based on the selected viewpoint, generates an HTTP response containing the story data, and sends it to the device.

[1409] Step 11:

[1410] Device:

[1411] It parses the story data returned by the server and displays to the user a reconstructed version of the story from a particular point of view, for example, displaying the text of the Cinderella story reconstructed from the prince's point of view.

[1412] Step 12:

[1413] User:

[1414] After reading the generated story, users can enter their impressions and comments in a feedback form. At this time, the emotion engine will recognize the user's emotions again and include them in the feedback.

[1415] Step 13:

[1416] Device:

[1417] Parse the user-entered feedback and emotion data into JSON format, generate an HTTP POST request, and send it to the server.

[1418] Step 14:

[1419] server:

[1420] Feedback and emotional data are received and stored in a database, and the emotional data is analyzed and used to improve the system and optimize story generation.

[1421] Through the specific processing flow described above, the present system can provide users with a multifaceted and personalized story experience.

[1422] Example 2

[1423] 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."

[1424] Existing story generation systems simply generate and display stories, making it difficult to provide a personalized experience based on the user's emotions and interests. Furthermore, they lack the technology to analyze user emotions and dynamically reconstruct stories based on those emotions, making it impossible to provide optimal content for each individual user. This results in a decline in user engagement and satisfaction.

[1425] 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.

[1426] In this invention, the server includes means for receiving a story title as input from a user, means for analyzing the content of the story based on the story title and extracting multiple characters and major events, means for generating stories from different perspectives based on the extracted information, means for presenting to the user options for the generated stories from the different perspectives, means for displaying the story generated from a specific perspective based on the user's selection, means for recognizing and analyzing user emotions in real time from the user's input and dialogue behavior, and means for reconstructing the story based on the user's emotion data, thereby making it possible to provide a personalized story experience based on the emotions and interests of each individual user.

[1427] "Story Title" is a name entered by the user to indicate the story in which they are interested.

[1428] A "terminal" is a device used by a user for input and interaction, and includes smartphones, tablets, PCs, etc.

[1429] An "emotion engine" is a technology that analyzes a user's facial expressions and tone of voice to recognize their emotional state.

[1430] "Emotion data" is information that indicates the user's emotional state analyzed by the emotion engine.

[1431] "Generative AI" refers to AI techniques for generating content based on given input, with the ability to create text based on specific prompts.

[1432] A "prompt" is text that contains specific instructions or questions to be given to a generative artificial intelligence.

[1433] "Extract" refers to extracting specific data from the analyzed information.

[1434] "A story from another perspective" refers to a story that has been reconstructed from different characters or perspectives within the same story.

[1435] "Presenting" refers to displaying options or information to the user.

[1436] "Feedback" refers to the opinions and thoughts that users provide about the generated story.

[1437] A "database" is a system for systematically storing and managing information.

[1438] A "personalized experience" is the provision of specific content and services based on an individual user's interests and emotions.

[1439] "Engagement" refers to the degree of involvement a user has with a service or content.

[1440] "Analysis" is the act of examining data in detail to reveal its meaning and structure.

[1441] "Reconstructing" refers to reassembling content from the original data based on a new perspective or structure.

[1442] This invention combines generative artificial intelligence and an emotion engine to provide an interactive system for users, allowing them to enjoy different perspectives on a story. This system not only acquires information about the story from the user and generates and displays the content of the story based on that information, but also recognizes and analyzes the user's emotions to provide a more personalized experience.

[1443] User Input and Emotion Recognition

[1444] First, the user inputs the title of a story they are interested in through the device interface. For example, they input "Cinderella." At this time, the device's built-in emotion engine (e.g., emotion analysis API) analyzes the user's facial expressions and tone of voice to recognize the user's emotional state (e.g., excitement, curiosity, sadness, etc.) in real time.

[1445] Narrative and sentiment analysis

[1446] Next, the server receives the story title and emotion data sent by the user. Using generative AI (e.g., GPT-4), the server analyzes the story and extracts key characters and events. For example, in the case of "Cinderella," it extracts Cinderella, the stepmother, the prince, the ball, the glass slippers, etc.

[1447] Emotion-based perspective generation

[1448] The server combines the extracted story information with the user's emotional data to generate a story from the most appropriate perspective. The generative AI reconstructs the story according to the user's emotional state. For example, if the user expresses curiosity, it generates a story that focuses on detailed background information or hidden truths. This operation is performed using prompt sentences. Examples of specific prompt sentences include, "Please reconstruct the story of Cinderella from the stepmother's perspective" and "The user is curious, so please generate a story that focuses on Cinderella's hidden truth."

[1449] Presenting narrative options and reassessing emotions

[1450] The generated stories from multiple perspectives are sent from the server to the device and presented to the user. At this time, the emotional state of the user at the time of their initial selection is reevaluated, and the optimal choice is adjusted. For example, multiple options such as "Read from Cinderella's perspective," "Read from the stepmother's perspective," and "Read from the prince's perspective" are presented, and the most recommended perspective is highlighted.

[1451] User selection and story display

[1452] The user selects the perspective they are interested in from the displayed options. For example, they select "The Prince's Perspective." The story based on the selected perspective is then displayed on the device. This allows the user to read the story reconstructed from a specific perspective.

[1453] User feedback and sentiment analysis

[1454] After reading the story, the user enters their thoughts and comments about the generated story into a feedback form. The device's built-in emotion engine also analyzes the user's emotions at the time of this feedback. The server receives the feedback data and emotion data and stores them in a database. This feedback data is used to improve the system.

[1455] This specific processing flow allows users to enjoy a multifaceted and personalized storytelling experience. For example, by experiencing the story of Cinderella from the prince's perspective, users can gain new insights and the system can further improve itself based on that feedback.

[1456] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1457] System program processing flow

[1458] Step 1: User enters story title

[1459] User: The user uses the terminal interface to input the title of a story that interests them.

[1460] Input: The title of the story (e.g., "Cinderella").

[1461] Output: The input title data.

[1462] Specific actions: Enter a title in the text input form displayed on the device screen and press the send button.

[1463] Step 2: The emotion engine analyzes the emotion

[1464] Device: The device's built-in emotion engine analyzes the user's facial expressions and tone of voice in real time.

[1465] Input: User's facial image and voice data.

[1466] Output: The user's emotional state (e.g., excitement, curiosity, sadness, etc.).

[1467] What it does: It uses a camera and microphone to capture facial expressions and tone of voice as data and then applies emotion analysis algorithms.

[1468] Step 3: The server receives the data

[1469] Server: The server receives the story title and emotion data sent from the device.

[1470] Input: Story title data, emotion data.

[1471] Output: Raw data stored in the server database.

[1472] Specific operation: Receives HTTP requests and saves data to a database.

[1473] Step 4: Story Analysis

[1474] Server: The server uses generative artificial intelligence to extract key characters and events from the story based on the title it receives.

[1475] Input: Story title data.

[1476] Output: Extracted characters and events (e.g., "Cinderella," "Stepmother," "Prince," "Ball," "Glass Slippers").

[1477] Specific operations: The title of the story is input as a prompt into the generative AI, which then performs an analysis to extract characters and key events.

[1478] Step 5: Combining emotion data with narrative information

[1479] Server: The server combines the emotion data with the extracted story information and generates a story from the most appropriate perspective.

[1480] Input: Emotion data, character and event data.

[1481] Output: A reconstructed story based on the user's emotions.

[1482] Specific operation: Based on the emotion data, a prompt is input to the generative AI to generate a story that focuses on detailed background information and hidden truths. For example, the prompt is input as follows: "The user is curious, so please generate a story that focuses on the hidden truth of Cinderella."

[1483] Step 6: Generate narrative options

[1484] Server: Generates stories from multiple perspectives and presents them to the user.

[1485] Input: Reconstructed narrative data.

[1486] Output: Story options (e.g., "Read from Cinderella's point of view," "Read from the stepmother's point of view," "Read from the prince's point of view").

[1487] What it does: Generate a story from multiple perspectives and prepare each option in list form.

[1488] Step 7: Present and reassess options

[1489] Terminal: The terminal displays the generated options to the user and highlights the recommended viewpoint based on the emotional data.

[1490] Input: Narrative choices, emotion data.

[1491] Output: Story options displayed on the user interface.

[1492] Specific operation: Display options for each viewpoint on the screen and label them to reflect the user's excitement and curiosity.

[1493] Step 8: Selecting Users

[1494] User: The user selects the viewpoint of interest from the displayed options.

[1495] Input: Select the perspective of the story (e.g., "The Prince's perspective").

[1496] Output: Selected viewpoint information.

[1497] Specific actions: Click the desired viewpoint from the displayed options.

[1498] Step 9: Presenting a narrative based on point of view

[1499] Terminal: The terminal displays the story based on the selected point of view.

[1500] Input: Selected viewpoint information, reconstructed narrative.

[1501] Output: The displayed narrative text.

[1502] What it does: The story from the selected point of view is displayed on the screen.

[1503] Step 10: User feedback and sentiment analysis

[1504] User: The user enters their thoughts and comments about the generated story in a feedback form.

[1505] Input: Feedback text.

[1506] Output: The input feedback data.

[1507] Specific actions: Enter your opinions and thoughts in text into the form and press the submit button.

[1508] Step 11: Sentiment Analysis

[1509] Device: The emotion engine installed in the device analyzes the user's emotions during feedback.

[1510] Input: Facial image and voice data at the time of feedback.

[1511] Output: Emotion data at the time of feedback.

[1512] Specific operation: Analyze facial expressions and voice during feedback to generate emotional data.

[1513] Step 12: Save your feedback data

[1514] Server: The server receives the feedback data including the analysis results and stores them in a database.

[1515] Input: Feedback data, emotion data.

[1516] Output: Feedback information stored in a database.

[1517] What it does: Runs SQL queries to add feedback and sentiment data to the database.

[1518] This allows users to enjoy a multifaceted and personalized storytelling experience, while the system is further improved based on their feedback.

[1519] (Application example 2)

[1520] 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."

[1521] Conventional storytelling systems lacked sufficient personalization for users, making it difficult to provide an experience that reflected each individual user's emotions. Furthermore, the ability to change the perspective of the story was limited, leaving users with few options for deeper enjoyment. As a result, the story experience tended to be uniform, resulting in lower user satisfaction.

[1522] 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 a story title from a user as input, means for analyzing the content of the story based on the story title and extracting multiple characters and major events, means for generating stories from different perspectives based on the extracted information, means for presenting options for the generated stories from the different perspectives to the user, means for recognizing emotions from the user's facial expressions and voice in real time, means for optimizing the content of the story based on the recognized emotions, and means for displaying the story generated from a specific perspective based on the user's selection. This makes it possible to provide a personalized story experience based on the user's emotions.

[1523] A "user" is an individual who uses the story experience system.

[1524] "Story Title" is the title of the story entered by the user.

[1525] "Multiple characters and major events" refers to the main characters and important events that make up the content of the story.

[1526] "Different perspectives" refers to a story being reconstructed from several different angles.

[1527] "Generated narrative options from different perspectives" are narrative options seen from multiple perspectives generated by the system.

[1528] "Means for recognizing emotions in real time from facial expressions and voice" refers to technology that recognizes emotions by analyzing a user's facial expressions and tone of voice.

[1529] "Recognized emotions" are information obtained by the system analyzing the user's real-time emotions.

[1530] "Means for optimizing story content" refers to techniques that adjust and personalize story content based on the user's emotional state.

[1531] "Generative AI" is a type of AI used to generate stories, using specific algorithms and prompts to generate stories.

[1532] A "prompt sentence" is the input text that serves as the basis for a generative artificial intelligence to generate a story.

[1533] "Feedback" is information provided by a user as impressions or comments on a generated story.

[1534] A "database" is an information storage system that stores feedback and other data for later analysis and system improvement.

[1535] An embodiment of the present invention is based on an interactive system that combines generative artificial intelligence and a sentiment analysis engine to provide a personalized story experience using a story title and user-entered sentiment data.

[1536] 1. System Configuration

[1537] Hardware

[1538] Terminals: Input and display devices such as smartphones, smart glasses, and head-mounted displays

[1539] Server: High-performance computer server, cloud computing service

[1540] Input devices: Webcam, microphone

[1541] software

[1542] Generative artificial intelligence: OpenAI GPT-3 API

[1543] Emotion Recognition Engine: EmotionRecognizer Library

[1544] Others: OpenCV library, librosa library

[1545] 2. Processing flow

[1546] User Input

[1547] The user inputs the title of the story he or she is interested in through the terminal interface, for example, "Cinderella."

[1548] emotion recognition

[1549] The server uses a camera and microphone to analyze the user's facial expression and voice. It uses the EmotionRecognizer library, OpenCV, and librosa to recognize the user's emotions in real time. For example, if the server recognizes "excited" from the user's facial expression and "excited" from their voice, it determines the user's emotional state as "excited."

[1550] Narrative analysis and perspective generation

[1551] Based on the story title and the recognized emotion data, a generative artificial intelligence (GPT-3) generates a new story. Here, a prompt is used to indicate the content and perspective of the story. For example, the following prompt is used:

[1552] When the user's emotion is "excited," reframe the Cinderella story from a different perspective.

[1553] Presenting options

[1554] The generated stories from multiple perspectives are presented to the user, who can select the perspective they are interested in. Among the presented perspectives, particularly recommended ones are highlighted.

[1555] Emotion-based storytelling

[1556] The reconstructed story is displayed based on the viewpoint selected by the user, allowing the user to enjoy a personalized story from a specific perspective.

[1557] Feedback and Reassessment

[1558] After reading the story, the user provides feedback such as their impressions and comments. The EmotionRecognizer library is used to recognize emotions again and to understand the feedback in more detail. This feedback data is stored in a database and used to improve the system.

[1559] This embodiment allows users to enjoy a multifaceted and personalized story experience that is completely tailored to their individual emotions, unlike conventional story experiences.

[1560] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1561] Step 1:

[1562] The user inputs the title of the story he or she is interested in through the terminal interface, and the input story title is sent to the server.

[1563] Input: Story title

[1564] Output: The story title sent to the server

[1565] Step 2:

[1566] The server receives the story title and analyzes the story content based on it. It uses generative artificial intelligence to extract multiple characters and key events. For example, if the title "Cinderella" is input, it will extract characters and events such as Cinderella, the stepmother, the prince, the ball, and the glass slippers.

[1567] Input: The story title sent to the server

[1568] Output: Extracted characters and events

[1569] Step 3:

[1570] The device's camera and microphone are used to capture the user's facial expressions and voice in real time. The EmotionRecognizer library, OpenCV, and librosa are used to recognize the user's emotions and send the emotion data to the server.

[1571] Input: User's facial and voice data

[1572] Output: Recognized emotion data

[1573] Step 4:

[1574] The server receives the title and emotion data and uses a generative artificial intelligence (GPT-3) to recreate the story, using the following prompt:

[1575] When the user's emotion is "excited," reframe the Cinderella story from a different perspective.

[1576] The generated story content is output as seen from multiple perspectives.

[1577] Input: Title and sentiment data

[1578] Output: Reproduced story (from multiple points of view)

[1579] Step 5:

[1580] The server sends the generated story options from different viewpoints to the device, which displays them to the user, highlighting the recommended viewpoints so that the user can select the viewpoint that interests them.

[1581] Input: Generated stories (from multiple perspectives)

[1582] Output: Viewpoint choices displayed to the user

[1583] Step 6:

[1584] The user selects the viewpoint he or she is interested in from the options, and the selected viewpoint information is sent to the server.

[1585] Input: User selected viewpoint

[1586] Output: Selections sent to the server

[1587] Step 7:

[1588] The server sends a story based on the viewpoint selected by the user to the terminal, which then displays it.

[1589] Input: Selections sent to the server

[1590] Output: A narrative based on the selected viewpoint displayed

[1591] Step 8:

[1592] After reading the story, the user enters their thoughts and comments through the feedback form on the device. At this time, the user's emotions are captured again by the camera and microphone and analyzed by the EmotionRecognizer library. The feedback content and emotional data are sent to the server and stored in a database.

[1593] Input: User feedback and sentiment data

[1594] Output: Feedback and emotion data stored in a database

[1595] Step 9:

[1596] The server analyzes the stored feedback and sentiment data and uses it to improve the personalization of the system.

[1597] Input: Feedback and emotion data stored in a database

[1598] Output: Improved system personalization

[1599] 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.

[1600] 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.

[1601] 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.

[1602] [Fourth embodiment]

[1603] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1604] 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.

[1605] 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).

[1606] 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.

[1607] 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.

[1608] 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).

[1609] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for 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.

[1610] 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.

[1611] 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.

[1612] 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.

[1613] 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.

[1614] 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.

[1615] 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."

[1616] An embodiment of the present invention provides a system that allows a user to enjoy a story from different perspectives. This system extracts detailed information about a story based on the title of the story entered by the user, and generates and presents the story from different perspectives. Specific embodiments of the present invention will be described below.

[1617] User Input

[1618] Terminal

[1619] The user inputs the title of the story he or she is interested in through the terminal interface, for example, "Urashima Taro." This title is then sent to the system.

[1620] Server Processing: A Narrative Analysis

[1621] server

[1622] The server receives the title sent by the user and analyzes the story's content based on the title. This analysis uses generative artificial intelligence to automatically extract the story's main characters and events. For example, for "Urashima Taro," information such as Urashima Taro, Princess Otohime, and the Dragon Palace in the sea is extracted.

[1623] Server processing: View generation

[1624] server

[1625] Based on the extracted information, the server generates a story from multiple different perspectives. It uses generative artificial intelligence to reconstruct the story from each character's point of view. For example, in the case of the story of Urashima Taro, the perspectives of Urashima Taro, Princess Otohime, and the turtle could all be considered. Each perspective would depict a different aspect of the story.

[1626] Server processing: Presenting story options

[1627] Terminal

[1628] The server compiles the generated stories from multiple perspectives and presents them to the user. This allows the user to choose from which perspective they would like to read the story. For example, options such as "Read from Urashima Taro's perspective," "Read from Otohime's perspective," or "Read from the turtle's perspective" are presented.

[1629] User Selection

[1630] User

[1631] The user operates the device and clicks on the viewpoint they are interested in from the displayed options. For example, they select "Otohime's viewpoint."

[1632] Server processing: Narrative generation and presentation

[1633] server

[1634] The server retrieves the story generated based on the viewpoint selected by the user and sends it to the device. This allows the user to enjoy the story reconstructed from a specific viewpoint. For example, the story of Urashima Taro reconstructed from Otohime's viewpoint is displayed as text.

[1635] User Feedback

[1636] User

[1637] After reading the generated story, users can use the feedback form to enter their impressions and comments, which will be used to improve the system.

[1638] Server processing: feedback storage and analysis

[1639] server

[1640] The server receives feedback from users, stores it in a database, and analyzes the collected feedback to help improve the system in the future.

[1641] In this way, the present invention provides users with a variety of ways to enjoy stories, promoting a deeper understanding of the story. As a specific example, by enjoying the story of "Urashima Taro" from Otohime's perspective, users can understand the background of her feelings and actions, and gain a new perspective on the story as a whole.

[1642] The processing flow will be explained below.

[1643] Step 1:

[1644] User:

[1645] The user inputs the title of the story he or she is interested in through the terminal interface, for example, "Cinderella."

[1646] Step 2:

[1647] Device:

[1648] It takes the title entered by the user, parses it into JSON format, and creates an HTTP POST request containing the parsed data and sends it to the server.

[1649] Step 3:

[1650] server:

[1651] Receives an HTTP request, retrieves the story title entered by the user, and retrieves the story content from an external database or API based on this title.

[1652] Step 4:

[1653] server:

[1654] The acquired story content is passed to the generative AI, which then begins analyzing the story. The generative AI analyzes the story and extracts the main characters (e.g., Cinderella, the stepmother, the prince) and key events (the ball, the glass slippers, etc.).

[1655] Step 5:

[1656] server:

[1657] Based on the extracted results, a story is generated from multiple different perspectives. For example, Cinderella's perspective, the stepmother's perspective, and the prince's perspective are generated using generative artificial intelligence.

[1658] Step 6:

[1659] server:

[1660] The generated stories from different perspectives are compiled into a list, and data to be presented to the user is generated. An HTTP response including this data is generated and sent to the terminal.

[1661] Step 7:

[1662] Device:

[1663] Parse the response received from the server and present the user with a choice of different perspectives on the story, for example, "Read from Cinderella's point of view," "Read from the Stepmother's point of view," or "Read from the Prince's point of view."

[1664] Step 8:

[1665] User:

[1666] Choose the perspective you're interested in (e.g., "The Prince's Perspective") and click on the option.

[1667] Step 9:

[1668] Device:

[1669] It receives the user's selection, parses the data containing the selected viewpoint into JSON format, and creates an HTTP POST request containing the parsed data and sends it to the server.

[1670] Step 10:

[1671] server:

[1672] The system receives the user's selection, obtains a story based on the selected perspective (e.g., "the prince's perspective"), generates an HTTP response containing the story data, and sends it to the terminal.

[1673] Step 11:

[1674] Device:

[1675] It parses the story data returned by the server and displays to the user a reconstructed version of the story from a particular point of view, for example, displaying the text of the Cinderella story reconstructed from the prince's point of view.

[1676] Step 12:

[1677] User:

[1678] After reading the generated story, users enter their impressions and comments into the input form and submit it as feedback.

[1679] Step 13:

[1680] Device:

[1681] Receives user feedback, parses it into JSON format, creates an HTTP POST request with the feedback data, and sends it to the server.

[1682] Step 14:

[1683] server:

[1684] Receive feedback data and store it in a database. Analyze the collected feedback and use it to improve the system in the future.

[1685] Through the above specific processing flow, this system can provide users with a multifaceted story experience.

[1686] Example 1

[1687] 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."

[1688] Conventional story generation systems typically provide users with a single perspective, preventing them from enjoying a variety of perspectives. Furthermore, they do not effectively utilize feedback, making it difficult to improve the system. Furthermore, they sometimes produce inaccurate results in story content analysis and story generation from different perspectives.

[1689] 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.

[1690] In this invention, the server includes means for receiving a story title from a user as input, means for analyzing the content of the story based on the story title and extracting multiple characters and major events, means for generating stories from different perspectives based on the extracted information, means for presenting options for the generated stories from different perspectives to the user, means for displaying the generated story from a specific perspective based on the user's selection, means for inputting and saving user feedback on the generated story and using it to improve the system, and means for using prompt sentences to analyze the story and generate stories from different perspectives using a generative AI model. This allows users to enjoy stories from different perspectives, improves the accuracy of the system, and makes it possible to effectively utilize user feedback to improve the system.

[1691] A "user" is someone who uses the system to input the title of a story and select and enjoy stories from different perspectives.

[1692] "Story Title" is the name of a particular piece of story that the user enters into the system.

[1693] "Story content" is text or data containing characters, major events, and other information relevant to the story.

[1694] A "character" is a character or person who plays a specific role in a story.

[1695] A "major event" is an event or occurrence that plays a significant role in the progression of the story.

[1696] A "point of view" is a standpoint or perspective from which a story is portrayed from different characters or points of view.

[1697] "Choices" are multiple perspectives or options presented to the user.

[1698] "Feedback" refers to thoughts and comments that users input about the generated story.

[1699] The "server" is the central computer of the system, and is the device that processes input from users, analyzes the content of the story, and generates and transmits stories from different perspectives.

[1700] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to analyze the content of a story and generate a story from different perspectives.

[1701] A "prompt" is a text sentence used to give specific instructions to a generative AI model.

[1702] "Database" means an electronic storage system that stores collected data and feedback so that it can be searched and analyzed as needed.

[1703] An embodiment of the present invention is a system for allowing a user to enjoy different perspectives on a story. Based on the title of a story entered by a user, the system extracts detailed information about the story and generates and presents the story from different perspectives.

[1704] User Input

[1705] Terminal

[1706] The user inputs the title of the story using the terminal interface. For example, the user inputs a title such as "Story A" into an input field on the terminal. This information is sent to the server.

[1707] Server Processing: A Narrative Analysis

[1708] server

[1709] The server receives the story title sent by the user and analyzes its content. This analysis is performed using a generative AI model (e.g., GPT-3). The server sends the following prompt to the generative AI model:

[1710] List the characters and major events in "Story A."

[1711] The generative AI model extracts the content of the story (characters and major events) based on the prompt sent. For example, for "Story A," information such as characters X, Y, and Z and major events 1, 2, and 3 can be obtained.

[1712] Server processing: View generation

[1713] server

[1714] The server uses a generative AI model to generate stories from multiple different perspectives based on the extracted list of characters and events. For each perspective, it generates a prompt and sends it to the model. For example:

[1715] Tell us "Story A" from the perspective of Character X.

[1716] The generative AI model responds with the story from the perspective of character X. It does the same for other perspectives (characters Y, Z, etc.).

[1717] Server processing: Presenting story options

[1718] server

[1719] The server compiles the generated stories from multiple perspectives and sends them to the device in the form of a choice, which the device presents to the user (e.g., "Read from X's perspective," "Read from Y's perspective," "Read from Z's perspective").

[1720] User Selection

[1721] User

[1722] The user operates the device interface and selects the perspective they are interested in from the options presented, for example, "Read from Y's perspective."

[1723] Server processing: Narrative generation and presentation

[1724] server

[1725] The server retrieves a story already created based on the user's selected viewpoint and sends it to the device, which then displays the story text on the screen, allowing the user to enjoy the story reconstructed from a specific viewpoint.

[1726] User Feedback

[1727] User

[1728] After reading the story, the user enters their impressions and comments in the feedback form, and the user's feedback is sent to the server.

[1729] Server processing: feedback storage and analysis

[1730] server

[1731] The server receives user feedback, stores it in a database (e.g., MySQL or MongoDB), and analyzes the collected feedback to help improve the system in the future.

[1732] In this way, the present invention is a system that provides users with multiple ways to enjoy stories and promotes a deeper understanding of the story. As a specific example, by enjoying "Story A" from the perspective of character Y, users can understand the background of Y's feelings and actions, and gain a new perspective on the story as a whole.

[1733] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1734] Step 1:

[1735] Terminal

[1736] The user inputs the title of the story through the terminal interface. For example, they input "Story A." This input data is temporarily saved on the terminal and sent to the server when the send button is pressed.

[1737] input:

[1738] Story title entered by the user

[1739] output:

[1740] Subject data sent to the server

[1741] Specific behavior:

[1742] The user enters "Story A" in the title input field and clicks the submit button.

[1743] Step 2:

[1744] server

[1745] The server receives the story title submitted by the user and analyzes the story content by sending the following prompt to the generative AI model:

[1746] List the characters and major events in "Story A."

[1747] Based on this prompt, the generative AI model analyzes the story's content and lists the characters and key events.

[1748] input:

[1749] Story title received from user

[1750] Prompt statement

[1751] output:

[1752] List of characters and major events

[1753] Specific behavior:

[1754] The server sends a prompt to the generative AI model to retrieve characters and key events. For "Story A," characters X, Y, and Z and key events 1, 2, and 3 are extracted.

[1755] Step 3:

[1756] server

[1757] The server uses a generative AI model to generate stories from multiple different perspectives based on the extracted list of characters and events. For each perspective, it generates a prompt and sends it to the model. For example:

[1758] Tell us "Story A" from the perspective of Character X.

[1759] The model generates a story from each perspective.

[1760] input:

[1761] List of characters and major events

[1762] Prompt statement

[1763] output:

[1764] A story from a different perspective

[1765] Specific behavior:

[1766] The server generates a prompt sentence and obtains a story from the perspective of characters X, Y, and Z. For example, a story from X's perspective, a story from Y's perspective, and a story from Z's perspective are generated respectively.

[1767] Step 4:

[1768] server

[1769] The server compiles the stories from different perspectives and sends them to the device in the form of a selection, for example:

[1770] {

[1771] "views": [

[1772] "Read from X's point of view",

[1773] "Read from Y's perspective",

[1774] "Reading from Z's Perspective"

[1775] ]

[1776] }

[1777] The terminal presents this to the user.

[1778] input:

[1779] A story from a different perspective

[1780] output:

[1781] The options to present to the user

[1782] Specific behavior:

[1783] The server converts the data into a choice format and sends it to the terminal, which then displays the choices to the user.

[1784] Step 5:

[1785] User

[1786] The user operates the device interface and selects the perspective they are interested in from the options presented, for example, "Read from Y's perspective."

[1787] input:

[1788] The viewpoint selected by the user

[1789] output:

[1790] Selected viewpoint data

[1791] Specific behavior:

[1792] The user selects "Read from Y's perspective" and clicks the Select button.

[1793] Step 6:

[1794] server

[1795] The server retrieves the already generated story based on the viewpoint selected by the user and sends it to the terminal in the form of a text version of the story.

[1796] input:

[1797] Selected viewpoint data

[1798] output:

[1799] Narrative text from selected perspectives

[1800] Specific behavior:

[1801] The server retrieves the story from the saved viewpoint and sends it to the device.

[1802] Step 7:

[1803] Terminal

[1804] The terminal displays the story text received from the server to the user.

[1805] input:

[1806] Story text received from the server

[1807] output:

[1808] Displaying narrative text

[1809] Specific behavior:

[1810] The device displays the story text on the screen.

[1811] Step 8:

[1812] User

[1813] After reading the generated story, the user enters their impressions and comments in a feedback form, which is then sent from the device to the server.

[1814] input:

[1815] User-entered feedback

[1816] output:

[1817] Feedback data sent to the server

[1818] Specific behavior:

[1819] The user enters their thoughts and comments into the feedback form and clicks the submit button.

[1820] Step 9:

[1821] server

[1822] The server stores user feedback in a database and analyzes it to help improve the system.

[1823] input:

[1824] Feedback data received from users

[1825] output:

[1826] Stored Feedback Data

[1827] Analysis results

[1828] Specific behavior:

[1829] The server stores the feedback data in a database and performs analysis to use it to improve the system.

[1830] (Application example 1)

[1831] 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."

[1832] With conventional content distribution services, viewing of movies and dramas is limited to a set viewpoint or edited content, preventing users from freely enjoying the story from different perspectives. While systems exist for reconstructing a story from different viewpoints, they are primarily text-based and difficult to apply to video content. Another issue is the lack of in-depth analysis based on the viewpoint of the story or interactive feedback functions for the psychological portrayal of characters.

[1833] 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.

[1834] In this invention, the server includes means for receiving a story title as input from a user, means for analyzing the content of the story based on the story title and extracting a plurality of characters and major events, means for generating stories from different perspectives based on the extracted information, means for presenting to the user options for the stories from the generated different perspectives, means for displaying a story generated from a specific perspective based on the user's selection, means for selecting a specific perspective from the option options presented to the user, and means for providing the user with a story generated based on a specific perspective. This allows the user to freely select different perspectives when watching a movie or drama and enjoy the story from each perspective.

[1835] A "user" is an individual or group that uses the system, inputs the title of a story, and enjoys the story from a particular perspective.

[1836] "Story title" is the name of the story to be analyzed, entered by the user.

[1837] "Story content" refers to information such as the story, events, and characters that are analyzed based on the story title.

[1838] A "character" is someone who has a role in the story.

[1839] An "incident" is a major event or action that occurs in a story.

[1840] "Point of view" is the perspective of a story from the perspective of a particular character or role in the story.

[1841] "Feedback" refers to opinions, impressions, and information for improvement that users input into the system.

[1842] "Generative AI" is an AI technology that automatically generates new stories and information based on input data.

[1843] "Deep story analysis" is the process of analyzing the content of a story in detail to reveal the psychological state and background information of the characters.

[1844] "Additional information" is supplemental information provided as the story progresses based on the perspective selected by the user.

[1845] In order to put the present invention into practice, it is necessary to build a system that allows a user to input the title of a story and enjoy the story from different perspectives. This system is configured as follows.

[1846] User Input

[1847] Through the terminal interface, the user inputs the title of the story they are interested in. This title is then sent to the system.

[1848] Server Processing: A Narrative Analysis

[1849] The server receives the title sent by the user and analyzes the content of the story based on that title. This analysis uses generative artificial intelligence (AI) to automatically extract the main characters and events of the story. An example of the AI ​​model used is OpenAI's GPT-3. For example, if the story "Urashima Taro" is input, information such as Urashima Taro, Princess Otohime, and the Dragon Palace in the sea will be extracted.

[1850] Server processing: View generation

[1851] The server generates a story from multiple different perspectives based on the extracted information. It uses a generative AI model to reconstruct the story from each character's perspective. For example, for the "Tale of Urashima Taro," the perspectives of Urashima Taro, Princess Otohime, and the turtle could all be considered.

[1852] Server processing: Presenting story options

[1853] The server compiles the generated stories from multiple perspectives and presents them to the user. This allows the user to choose from which perspective they would like to read the story. For example, options such as "Read from Urashima Taro's perspective," "Read from Otohime's perspective," or "Read from the turtle's perspective" are presented.

[1854] User Selection

[1855] The user operates the device and clicks on the viewpoint they are interested in from the displayed options. For example, they select "Otohime's viewpoint."

[1856] Server processing: Narrative generation and presentation

[1857] The server retrieves the story generated based on the viewpoint selected by the user and sends it to the device. The user can enjoy the story reconstructed from this specific viewpoint. For example, the story of Urashima Taro reconstructed from Otohime's viewpoint is displayed as text.

[1858] User Feedback

[1859] After reading the generated story, users can use the feedback form to enter their impressions and comments, such as additional information they would like to know or suggestions for improving the story.

[1860] Server processing: feedback storage and analysis

[1861] The server receives user feedback, stores it in a database, and analyzes it to perform in-depth analysis of the story, improving the system to provide a richer story experience.

[1862] Specific examples

[1863] For example, to allow a user to experience the story of Urashima Taro from Otohime's perspective, the following prompt sentence is input to the generative AI model:

[1864] Title: Reconstruct the story of "Urashima Taro" from Otohime's perspective.

[1865] This prompt sentence generates a story reconstructed from Otohime's perspective and presents it to the user.

[1866] Unlike traditional movie or TV drama viewing experiences, the system of the present invention allows users to freely enjoy a story from various perspectives. Furthermore, by conducting in-depth analysis of the story content and each perspective based on user feedback, a more fulfilling story experience can be provided.

[1867] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1868] Step 1:

[1869] The user uses the terminal interface to input the title of the story they are interested in and send it to the system. Input data: Story title. Output data: Story title sent to the system.

[1870] Step 2:

[1871] The server receives the story title sent by the user and analyzes the content of the story based on the title. It sends prompt sentences to the generative AI model to extract the main characters and events. Input data: Story title. Output data: Main characters and events.

[1872] Step 3:

[1873] The server generates stories from different perspectives based on the extracted characters and events. Using a generative AI model, it reconstructs the story based on each perspective. Input data: extracted characters and events. Output data: stories from different perspectives.

[1874] Step 4:

[1875] The server presents the generated story options from different viewpoints to the user. Multiple viewpoint options are displayed on the terminal. Input data: Stories from different viewpoints. Output data: Display of viewpoint options.

[1876] Step 5:

[1877] The user operates the terminal and selects the viewpoint of interest from the presented viewpoint options. Input data: viewpoint options. Output data: selected viewpoint.

[1878] Step 6:

[1879] The server sends the generated story based on the viewpoint selected by the user to the terminal. The terminal displays the story reconstructed from that particular viewpoint to the user. Input data: Selected viewpoint. Output data: Reconstructed story.

[1880] Step 7:

[1881] After reading the generated story, the user submits their impressions and comments to the system through a feedback form. Input data: impressions and comments. Output data: feedback form submission.

[1882] Step 8:

[1883] The server receives feedback from users and stores it in a database. It analyzes the feedback and uses it to improve the system. Input data: User feedback. Output data: Stored feedback and analysis results.

[1884] 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.

[1885] An embodiment of the present invention provides a system that allows users to enjoy different perspectives on a story through an interactive system that combines generative artificial intelligence and an emotion engine. This system not only acquires information about the story from the user and generates and displays the content of the story based on that information, but also recognizes and analyzes the user's emotions to provide a more personalized experience. Specific embodiments of the present invention are described below.

[1886] User Input and Emotion Recognition

[1887] Terminal

[1888] The user inputs the title of a story they are interested in through the device interface. An emotion engine then operates to recognize the user's emotions in real time based on their input and dialogue behavior. For example, when the user inputs the title "Cinderella," the emotion engine analyzes the user's facial expression and tone of voice to determine their emotional state (e.g., excitement, curiosity, sadness, etc.).

[1889] Server Processing: Narrative Analysis and Sentiment Analysis

[1890] server

[1891] The server receives the title submitted by the user and the emotional data analyzed by the emotion engine. It then analyzes the story content based on the title and extracts the main characters and events. This process is carried out using generative artificial intelligence. For example, in the case of "Cinderella," Cinderella, the stepmother, the prince, the ball, the glass slippers, etc. are extracted.

[1892] Server processing: Emotion-based viewpoint generation

[1893] server

[1894] The server combines the extracted story information with the user's emotional data to generate a story from the most appropriate perspective. Generative AI is used to reconstruct the story based on the user's emotional state. For example, if the user expresses curiosity, the server generates a perspective that focuses on more detailed background information or hidden truths.

[1895] Server Processing: Presenting Narrative Options and Reevaluating Emotions

[1896] Terminal

[1897] The server presents the generated story from multiple perspectives to the user and re-presents the most suitable option to the user. This re-presentation re-evaluates the user's emotional state at the time of their initial selection and adjusts the options as necessary. For example, the server presents multiple options such as "Read from Cinderella's perspective," "Read from the stepmother's perspective," and "Read from the prince's perspective," and emphasizes the recommended perspective based on the user's emotions.

[1898] User selection and story display

[1899] User

[1900] The user selects the perspective they are interested in from the displayed options. For example, they select "The Prince's Perspective." The story based on the selected perspective is then displayed on the device. This allows the user to read the story reconstructed from a specific perspective.

[1901] User feedback and sentiment analysis

[1902] Terminal Server

[1903] After reading the generated story, the user enters their thoughts and comments in a feedback form. The emotion engine analyzes the user's emotions at the time of the feedback to gain a more detailed understanding of the feedback content. The server receives this feedback data, stores it in a database, and uses it to improve the system.

[1904] Through this specific processing flow, the system provides users with a multifaceted and personalized story experience, helping them gain a deeper understanding of the story and new perspectives. For example, by enjoying the story of "Cinderella" from the prince's perspective, users can understand the prince's psychological state and the hidden meaning behind his actions, gaining new insights into the story as a whole. Furthermore, feedback based on the user's emotions allows the system to further optimize future story generation and perspective presentation methods.

[1905] The processing flow will be explained below.

[1906] Step 1:

[1907] User:

[1908] The user inputs the title of the story through the device interface, for example, "Cinderella." At this time, the emotion engine recognizes the user's facial expressions and tone of voice and collects emotional data.

[1909] Step 2:

[1910] Device:

[1911] The title entered by the user is parsed into JSON format. At the same time, the emotion data recognized by the emotion engine is also parsed. An HTTP POST request containing this data is generated and sent to the server.

[1912] Step 3:

[1913] server:

[1914] Receives an HTTP request, retrieves the story title and emotion data entered by the user, and retrieves the story content from an external database or API based on the title.

[1915] Step 4:

[1916] server:

[1917] The acquired story content is passed to the generative AI to begin analysis. The generative AI analyzes the story and extracts the main characters (Cinderella, the stepmother, the prince, etc.) and key events (the ball, the glass slippers, etc.).

[1918] Step 5:

[1919] server:

[1920] Based on the extracted information and emotional data, the system generates stories from multiple different perspectives. The generative AI identifies the perspective that best matches the user's emotional state and reconstructs the story from that perspective. For example, if the user is excited, it generates a story from a perspective filled with action and dramatic elements.

[1921] Step 6:

[1922] server:

[1923] The generated stories from multiple perspectives are compiled into a list, and data to be presented to the user is generated. An HTTP response including this data is generated and sent to the terminal.

[1924] Step 7:

[1925] Device:

[1926] The response received from the server is parsed and the user is presented with a choice of different perspectives for the story. For example, options such as "Read from Cinderella's point of view," "Read from the stepmother's point of view," or "Read from the prince's point of view" are displayed. At this time, the emotion engine again recognizes the user's emotions and highlights the most recommended options.

[1927] Step 8:

[1928] User:

[1929] Choose the perspective that interests you (for example, "The Prince's Perspective") and click on that option.

[1930] Step 9:

[1931] Device:

[1932] It receives the user's selection, generates an HTTP POST request in JSON format containing the selected viewpoint and emotion data, and sends it to the server.

[1933] Step 10:

[1934] server:

[1935] Receives the user's selection, retrieves from the database a story generated based on the selected viewpoint, generates an HTTP response containing the story data, and sends it to the device.

[1936] Step 11:

[1937] Device:

[1938] It parses the story data returned by the server and displays to the user a reconstructed version of the story from a particular point of view, for example, displaying the text of the Cinderella story reconstructed from the prince's point of view.

[1939] Step 12:

[1940] User:

[1941] After reading the generated story, users can enter their impressions and comments in a feedback form. At this time, the emotion engine will recognize the user's emotions again and include them in the feedback.

[1942] Step 13:

[1943] Device:

[1944] Parse the user-entered feedback and emotion data into JSON format, generate an HTTP POST request, and send it to the server.

[1945] Step 14:

[1946] server:

[1947] Feedback and emotional data are received and stored in a database, and the emotional data is analyzed and used to improve the system and optimize story generation.

[1948] Through the specific processing flow described above, the present system can provide users with a multifaceted and personalized story experience.

[1949] Example 2

[1950] 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."

[1951] Existing story generation systems simply generate and display stories, making it difficult to provide a personalized experience based on the user's emotions and interests. Furthermore, they lack the technology to analyze user emotions and dynamically reconstruct stories based on those emotions, making it impossible to provide optimal content for each individual user. This results in a decline in user engagement and satisfaction.

[1952] 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.

[1953] In this invention, the server includes means for receiving a story title as input from a user, means for analyzing the content of the story based on the story title and extracting multiple characters and major events, means for generating stories from different perspectives based on the extracted information, means for presenting to the user options for the generated stories from the different perspectives, means for displaying the story generated from a specific perspective based on the user's selection, means for recognizing and analyzing user emotions in real time from the user's input and dialogue behavior, and means for reconstructing the story based on the user's emotion data, thereby making it possible to provide a personalized story experience based on the emotions and interests of each individual user.

[1954] "Story Title" is a name entered by the user to indicate the story in which they are interested.

[1955] A "terminal" is a device used by a user for input and interaction, and includes smartphones, tablets, PCs, etc.

[1956] An "emotion engine" is a technology that analyzes a user's facial expressions and tone of voice to recognize their emotional state.

[1957] "Emotion data" is information that indicates the user's emotional state analyzed by the emotion engine.

[1958] "Generative AI" refers to AI techniques for generating content based on given input, with the ability to create text based on specific prompts.

[1959] A "prompt" is text that contains specific instructions or questions to be given to a generative artificial intelligence.

[1960] "Extract" refers to extracting specific data from the analyzed information.

[1961] "A story from another perspective" refers to a story that has been reconstructed from different characters or perspectives within the same story.

[1962] "Presenting" refers to displaying options or information to the user.

[1963] "Feedback" refers to the opinions and thoughts that users provide about the generated story.

[1964] A "database" is a system for systematically storing and managing information.

[1965] A "personalized experience" is the provision of specific content and services based on an individual user's interests and emotions.

[1966] "Engagement" refers to the degree of involvement a user has with a service or content.

[1967] "Analysis" is the act of examining data in detail to reveal its meaning and structure.

[1968] "Reconstructing" refers to reassembling content from the original data based on a new perspective or structure.

[1969] This invention combines generative artificial intelligence and an emotion engine to provide an interactive system for users, allowing them to enjoy different perspectives on a story. This system not only acquires information about the story from the user and generates and displays the content of the story based on that information, but also recognizes and analyzes the user's emotions to provide a more personalized experience.

[1970] User Input and Emotion Recognition

[1971] First, the user inputs the title of a story they are interested in through the device interface. For example, they input "Cinderella." At this time, the device's built-in emotion engine (e.g., emotion analysis API) analyzes the user's facial expressions and tone of voice to recognize the user's emotional state (e.g., excitement, curiosity, sadness, etc.) in real time.

[1972] Narrative and sentiment analysis

[1973] Next, the server receives the story title and emotion data sent by the user. Using generative AI (e.g., GPT-4), the server analyzes the story and extracts key characters and events. For example, in the case of "Cinderella," it extracts Cinderella, the stepmother, the prince, the ball, the glass slippers, etc.

[1974] Emotion-based perspective generation

[1975] The server combines the extracted story information with the user's emotional data to generate a story from the most appropriate perspective. The generative AI reconstructs the story according to the user's emotional state. For example, if the user expresses curiosity, it generates a story that focuses on detailed background information or hidden truths. This operation is performed using prompt sentences. Examples of specific prompt sentences include, "Please reconstruct the story of Cinderella from the stepmother's perspective" and "The user is curious, so please generate a story that focuses on Cinderella's hidden truth."

[1976] Presenting narrative options and reassessing emotions

[1977] The generated stories from multiple perspectives are sent from the server to the device and presented to the user. At this time, the emotional state of the user at the time of their initial selection is reevaluated, and the optimal choice is adjusted. For example, multiple options such as "Read from Cinderella's perspective," "Read from the stepmother's perspective," and "Read from the prince's perspective" are presented, and the most recommended perspective is highlighted.

[1978] User selection and story display

[1979] The user selects the perspective they are interested in from the displayed options. For example, they select "The Prince's Perspective." The story based on the selected perspective is then displayed on the device. This allows the user to read the story reconstructed from a specific perspective.

[1980] User feedback and sentiment analysis

[1981] After reading the story, the user enters their thoughts and comments about the generated story into a feedback form. The device's built-in emotion engine also analyzes the user's emotions at the time of this feedback. The server receives the feedback data and emotion data and stores them in a database. This feedback data is used to improve the system.

[1982] This specific processing flow allows users to enjoy a multifaceted and personalized storytelling experience. For example, by experiencing the story of Cinderella from the prince's perspective, users can gain new insights and the system can further improve itself based on that feedback.

[1983] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1984] System program processing flow

[1985] Step 1: User enters story title

[1986] User: The user uses the terminal interface to input the title of a story that interests them.

[1987] Input: The title of the story (e.g., "Cinderella").

[1988] Output: The input title data.

[1989] Specific actions: Enter a title in the text input form displayed on the device screen and press the send button.

[1990] Step 2: The emotion engine analyzes the emotion

[1991] Device: The device's built-in emotion engine analyzes the user's facial expressions and tone of voice in real time.

[1992] Input: User's facial image and voice data.

[1993] Output: The user's emotional state (e.g., excitement, curiosity, sadness, etc.).

[1994] What it does: It uses a camera and microphone to capture facial expressions and tone of voice as data and then applies emotion analysis algorithms.

[1995] Step 3: The server receives the data

[1996] Server: The server receives the story title and emotion data sent from the device.

[1997] Input: Story title data, emotion data.

[1998] Output: Raw data stored in the server database.

[1999] Specific operation: Receives HTTP requests and saves data to a database.

[2000] Step 4: Story Analysis

[2001] Server: The server uses generative artificial intelligence to extract key characters and events from the story based on the title it receives.

[2002] Input: Story title data.

[2003] Output: Extracted characters and events (e.g., "Cinderella," "Stepmother," "Prince," "Ball," "Glass Slippers").

[2004] Specific operations: The title of the story is input as a prompt into the generative AI, which then performs an analysis to extract characters and key events.

[2005] Step 5: Combining emotion data with narrative information

[2006] Server: The server combines the emotion data with the extracted story information and generates a story from the most appropriate perspective.

[2007] Input: Emotion data, character and event data.

[2008] Output: A reconstructed story based on the user's emotions.

[2009] Specific operation: Based on the emotion data, a prompt is input to the generative AI to generate a story that focuses on detailed background information and hidden truths. For example, the prompt is input as follows: "The user is curious, so please generate a story that focuses on the hidden truth of Cinderella."

[2010] Step 6: Generate narrative options

[2011] Server: Generates stories from multiple perspectives and presents them to the user.

[2012] Input: Reconstructed narrative data.

[2013] Output: Story options (e.g., "Read from Cinderella's point of view," "Read from the stepmother's point of view," "Read from the prince's point of view").

[2014] What it does: Generate a story from multiple perspectives and prepare each option in list form.

[2015] Step 7: Present and reassess options

[2016] Terminal: The terminal displays the generated options to the user and highlights the recommended viewpoint based on the emotional data.

[2017] Input: Narrative choices, emotion data.

[2018] Output: Story options displayed on the user interface.

[2019] Specific operation: Display options for each viewpoint on the screen and label them to reflect the user's excitement and curiosity.

[2020] Step 8: Selecting Users

[2021] User: The user selects the viewpoint of interest from the displayed options.

[2022] Input: Select the perspective of the story (e.g., "The Prince's perspective").

[2023] Output: Selected viewpoint information.

[2024] Specific actions: Click the desired viewpoint from the displayed options.

[2025] Step 9: Presenting a narrative based on point of view

[2026] Terminal: The terminal displays the story based on the selected point of view.

[2027] Input: Selected viewpoint information, reconstructed narrative.

[2028] Output: The displayed narrative text.

[2029] What it does: The story from the selected point of view is displayed on the screen.

[2030] Step 10: User feedback and sentiment analysis

[2031] User: The user enters their thoughts and comments about the generated story in a feedback form.

[2032] Input: Feedback text.

[2033] Output: The input feedback data.

[2034] Specific actions: Enter your opinions and thoughts in text into the form and press the submit button.

[2035] Step 11: Sentiment Analysis

[2036] Device: The emotion engine installed in the device analyzes the user's emotions during feedback.

[2037] Input: Facial image and voice data at the time of feedback.

[2038] Output: Emotion data at the time of feedback.

[2039] Specific operation: Analyze facial expressions and voice during feedback to generate emotional data.

[2040] Step 12: Save your feedback data

[2041] Server: The server receives the feedback data including the analysis results and stores them in a database.

[2042] Input: Feedback data, emotion data.

[2043] Output: Feedback information stored in a database.

[2044] What it does: Runs SQL queries to add feedback and sentiment data to the database.

[2045] This allows users to enjoy a multifaceted and personalized storytelling experience, while the system is further improved based on their feedback.

[2046] (Application example 2)

[2047] 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."

[2048] Conventional storytelling systems lacked sufficient personalization for users, making it difficult to provide an experience that reflected each individual user's emotions. Furthermore, the ability to change the perspective of the story was limited, leaving users with few options for deeper enjoyment. As a result, the story experience tended to be uniform, resulting in lower user satisfaction.

[2049] 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 a story title from a user as input, means for analyzing the content of the story based on the story title and extracting multiple characters and major events, means for generating stories from different perspectives based on the extracted information, means for presenting options for the generated stories from the different perspectives to the user, means for recognizing emotions from the user's facial expressions and voice in real time, means for optimizing the content of the story based on the recognized emotions, and means for displaying the story generated from a specific perspective based on the user's selection. This makes it possible to provide a personalized story experience based on the user's emotions.

[2050] A "user" is an individual who uses the story experience system.

[2051] "Story Title" is the title of the story entered by the user.

[2052] "Multiple characters and major events" refers to the main characters and important events that make up the content of the story.

[2053] "Different perspectives" refers to a story being reconstructed from several different angles.

[2054] "Generated narrative options from different perspectives" are narrative options seen from multiple perspectives generated by the system.

[2055] "Means for recognizing emotions in real time from facial expressions and voice" refers to technology that recognizes emotions by analyzing a user's facial expressions and tone of voice.

[2056] "Recognized emotions" are information obtained by the system analyzing the user's real-time emotions.

[2057] "Means for optimizing story content" refers to techniques that adjust and personalize story content based on the user's emotional state.

[2058] "Generative AI" is a type of AI used to generate stories, using specific algorithms and prompts to generate stories.

[2059] A "prompt sentence" is the input text that serves as the basis for a generative artificial intelligence to generate a story.

[2060] "Feedback" is information provided by a user as impressions or comments on a generated story.

[2061] A "database" is an information storage system that stores feedback and other data for later analysis and system improvement.

[2062] An embodiment of the present invention is based on an interactive system that combines generative artificial intelligence and a sentiment analysis engine to provide a personalized story experience using a story title and user-entered sentiment data.

[2063] 1. System Configuration

[2064] Hardware

[2065] Terminals: Input and display devices such as smartphones, smart glasses, and head-mounted displays

[2066] Server: High-performance computer server, cloud computing service

[2067] Input devices: Webcam, microphone

[2068] software

[2069] Generative artificial intelligence: OpenAI GPT-3 API

[2070] Emotion Recognition Engine: EmotionRecognizer Library

[2071] Others: OpenCV library, librosa library

[2072] 2. Processing flow

[2073] User Input

[2074] The user inputs the title of the story he or she is interested in through the terminal interface, for example, "Cinderella."

[2075] emotion recognition

[2076] The server uses a camera and microphone to analyze the user's facial expression and voice. It uses the EmotionRecognizer library, OpenCV, and librosa to recognize the user's emotions in real time. For example, if the server recognizes "excited" from the user's facial expression and "excited" from their voice, it determines the user's emotional state as "excited."

[2077] Narrative analysis and perspective generation

[2078] Based on the story title and the recognized emotion data, a generative artificial intelligence (GPT-3) generates a new story. Here, a prompt is used to indicate the content and perspective of the story. For example, the following prompt is used:

[2079] When the user's emotion is "excited," reframe the Cinderella story from a different perspective.

[2080] Presenting options

[2081] The generated stories from multiple perspectives are presented to the user, who can select the perspective they are interested in. Among the presented perspectives, particularly recommended ones are highlighted.

[2082] Emotion-based storytelling

[2083] The reconstructed story is displayed based on the viewpoint selected by the user, allowing the user to enjoy a personalized story from a specific perspective.

[2084] Feedback and Reassessment

[2085] After reading the story, the user provides feedback such as their impressions and comments. The EmotionRecognizer library is used to recognize emotions again and to understand the feedback in more detail. This feedback data is stored in a database and used to improve the system.

[2086] This embodiment allows users to enjoy a multifaceted and personalized story experience that is completely tailored to their individual emotions, unlike conventional story experiences.

[2087] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2088] Step 1:

[2089] The user inputs the title of the story he or she is interested in through the terminal interface, and the input story title is sent to the server.

[2090] Input: Story title

[2091] Output: The story title sent to the server

[2092] Step 2:

[2093] The server receives the story title and analyzes the story content based on it. It uses generative artificial intelligence to extract multiple characters and key events. For example, if the title "Cinderella" is input, it will extract characters and events such as Cinderella, the stepmother, the prince, the ball, and the glass slippers.

[2094] Input: The story title sent to the server

[2095] Output: Extracted characters and events

[2096] Step 3:

[2097] The device's camera and microphone are used to capture the user's facial expressions and voice in real time. The EmotionRecognizer library, OpenCV, and librosa are used to recognize the user's emotions and send the emotion data to the server.

[2098] Input: User's facial and voice data

[2099] Output: Recognized emotion data

[2100] Step 4:

[2101] The server receives the title and emotion data and uses a generative artificial intelligence (GPT-3) to recreate the story, using the following prompt:

[2102] When the user's emotion is "excited," reframe the Cinderella story from a different perspective.

[2103] The generated story content is output as seen from multiple perspectives.

[2104] Input: Title and sentiment data

[2105] Output: Reproduced story (from multiple points of view)

[2106] Step 5:

[2107] The server sends the generated story options from different viewpoints to the device, which displays them to the user, highlighting the recommended viewpoints so that the user can select the viewpoint that interests them.

[2108] Input: Generated stories (from multiple perspectives)

[2109] Output: Viewpoint choices displayed to the user

[2110] Step 6:

[2111] The user selects the viewpoint he or she is interested in from the options, and the selected viewpoint information is sent to the server.

[2112] Input: User selected viewpoint

[2113] Output: Selections sent to the server

[2114] Step 7:

[2115] The server sends a story based on the viewpoint selected by the user to the terminal, which then displays it.

[2116] Input: Selections sent to the server

[2117] Output: A narrative based on the selected viewpoint displayed

[2118] Step 8:

[2119] After reading the story, the user enters their thoughts and comments through the feedback form on the device. At this time, the user's emotions are captured again by the camera and microphone and analyzed by the EmotionRecognizer library. The feedback content and emotional data are sent to the server and stored in a database.

[2120] Input: User feedback and sentiment data

[2121] Output: Feedback and emotion data stored in a database

[2122] Step 9:

[2123] The server analyzes the stored feedback and sentiment data and uses it to improve the personalization of the system.

[2124] Input: Feedback and emotion data stored in a database

[2125] Output: Improved system personalization

[2126] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice 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 voice data.

[2127] 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.

[2128] 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 robot 414.

[2129] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2130] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[2131] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[2132] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[2133] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[2134] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[2135] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[2136] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[2137] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[2138] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[2139] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[2140] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[2141] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[2142] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[2143] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[2144] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[2145] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[2146] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[2147] The following is further disclosed regarding the above embodiment.

[2148] (Claim 1)

[2149] means for receiving a story title as input from a user;

[2150] A means for analyzing the content of a story based on the title of the story and extracting a number of characters and major events;

[2151] A means of generating stories from different perspectives based on the extracted information;

[2152] a means for presenting the user with story options from different generated perspectives;

[2153] means for displaying the generated story from a particular perspective based on a user selection;

[2154] A system including:

[2155] (Claim 2)

[2156] means for allowing a user to input feedback on the generated story;

[2157] A means to store the input feedback in a database and use it to improve the system;

[2158] The system of claim 1 further comprising:

[2159] (Claim 3)

[2160] 10. The system of claim 1, including means for using generative artificial intelligence for content analysis of a story and generation of a story from different perspectives.

[2161] "Example 1"

[2162] (Claim 1)

[2163] means for receiving a story title as input from a user;

[2164] A means for analyzing the content of a story based on the title of the story and extracting a plurality of characters and major events;

[2165] A means of generating stories from different perspectives based on the extracted information;

[2166] a means for presenting the user with story options from different generated perspectives;

[2167] means for displaying the generated story from a particular perspective based on a user selection;

[2168] a means for inputting and storing user feedback on the generated stories to be used to improve the system;

[2169] a means for using the prompt sentences to analyze the story and generate stories from different perspectives using a generative AI model;

[2170] A system including:

[2171] (Claim 2)

[2172] a means for inputting feedback on the generated story;

[2173] A means to store the input feedback in a database and use it to improve the system;

[2174] A means of using generative artificial intelligence for story content analysis and story generation from different perspectives;

[2175] The system of claim 1 further comprising:

[2176] (Claim 3)

[2177] 10. The system of claim 1, including means for analyzing the content of a story and generating stories from different perspectives using a generative AI model and prompt sentences.

[2178] "Application Example 1"

[2179] (Claim 1)

[2180] means for receiving a story title as input from a user;

[2181] A means for analyzing the content of a story based on the title of the story and extracting a number of characters and major events;

[2182] A means of generating stories from different perspectives based on the extracted information;

[2183] a means for presenting the user with story options from different generated perspectives;

[2184] means for displaying the generated story from a particular perspective based on a user selection;

[2185] means for selecting a particular viewpoint from a selection of viewpoints presented to a user;

[2186] A means for providing a user with a narrative generated based on a particular point of view;

[2187] A system including:

[2188] (Claim 2)

[2189] means for allowing a user to input feedback on the generated story;

[2190] A means to store the input feedback in a database and use it to improve the system;

[2191] A means for analyzing the story content in depth and the psychological state of the characters;

[2192] a means for providing additional information as the story progresses from the user's selected perspective;

[2193] The system of claim 1 further comprising:

[2194] (Claim 3)

[2195] 10. The system of claim 1, including means for using generative artificial intelligence for content analysis of a story and generation of a story from different perspectives.

[2196] "Example 2: Combining Emotion Engines"

[2197] (Claim 1)

[2198] means for receiving a story title as input from a user;

[2199] A means for analyzing the content of a story based on the title of the story and extracting a number of characters and major events;

[2200] A means of generating stories from different perspectives based on the extracted information;

[2201] a means for presenting the user with story options from different generated perspectives;

[2202] means for displaying the generated story from a particular perspective based on a user selection;

[2203] A means of recognizing and analyzing user emotions in real time from user input and dialogue behavior,

[2204] A means for reconstructing a story based on the user's emotional data;

[2205] A system including:

[2206] (Claim 2)

[2207] means for allowing a user to input feedback on the generated story;

[2208] A means to store the input feedback in a database and use it to improve the system;

[2209] A means of analyzing emotions,

[2210] The system of claim 1 further comprising:

[2211] (Claim 3)

[2212] 10. The system of claim 1, including means for using generative artificial intelligence for content analysis of a story and generation of a story from different perspectives.

[2213] "Application example 2 when combining emotion engines"

[2214] (Claim 1)

[2215] means for receiving a story title as input from a user;

[2216] A means for analyzing the content of a story based on the title of the story and extracting a number of characters and major events;

[2217] A means of generating stories from different perspectives based on the extracted information;

[2218] a means for presenting the user with story options from different generated perspectives;

[2219] means for recognizing emotions from a user's facial expressions and voice in real time;

[2220] A means of optimizing the content of a story based on the perceived emotions; and

[2221] means for displaying the generated story from a particular perspective based on a user selection;

[2222] A system including:

[2223] (Claim 2)

[2224] means for allowing a user to input feedback on the generated story;

[2225] A means to store the input feedback in a database and use it to improve the system;

[2226] A means to re-analyze the emotions during feedback and improve the system's personalization;

[2227] The system of claim 1 further comprising:

[2228] (Claim 3)

[2229] A means of using generative artificial intelligence for story content analysis and story generation from different perspectives;

[2230] 10. The system of claim 1, further comprising means for using prompt sentences in the story generation process. [Explanation of symbols]

[2231] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving a story title as input from a user; A means for analyzing the content of a story based on the title of the story and extracting a number of characters and major events; A means of generating stories from different perspectives based on the extracted information; a means for presenting the user with story options from different generated perspectives; means for displaying the generated story from a particular perspective based on a user selection; A system including:

2. means for allowing a user to input feedback on the generated story; A means to store the input feedback in a database and use it to improve the system; The system of claim 1 further comprising:

3. 10. The system of claim 1, further comprising means for using generative artificial intelligence for content analysis of the story and generation of the story from different perspectives.

Images