System

Abstract

A system is provided.SOLUTION: A system, comprising: means for downloading a basic story to a user device; means for transmitting a generated ending to the user device; means for generating a different ending each time according to a generation AI; means for collecting feedback from a user; and means for storing the collected feedback and reflecting the collected feedback on generation of a next ending.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] While children want the same picture books to be read to them over and over again, parents often tire of the repetition. Furthermore, because traditional picture books have a fixed story and ending, parent-child interactions tend to be one-off. Furthermore, repeated reading can lead to boredom of the story, making it difficult to maintain a child's interest. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for downloading a basic story to a user terminal, a means for transmitting generated endings to the user terminal, a means for generating a different ending each time using a generation AI, a means for collecting feedback from users, and a means for saving the collected feedback and reflecting it in the generation of the next ending. Furthermore, by including a filtering means for maintaining consistency between the basic story and the generated endings and a means for personalizing the content of the generated endings based on the user's interests and age, parents and children can enjoy a new ending every night, thereby continuously maintaining the child's interest and curiosity.

[0006] The "basic story" is a fixed storyline that is consistently provided in a picture book app.

[0007] A "user device" is an electronic device, such as a tablet or smartphone, that a user uses to access the picture book app.

[0008] A "generated ending" is the conclusion of a story that is newly generated each time by the generation AI.

[0009] "Generative AI" is an artificial intelligence system that generates new endings based on the context of the story.

[0010] "Feedback" refers to data such as impressions and opinions provided by users after reading a picture book.

[0011] The "filtering method" is a function that checks and adjusts whether the generated ending is consistent with the basic story and whether it is suitable for the user's age and interests.

[0012] "Personalization means" is a function that adjusts the content of the generated ending based on the user's interests and age.

[0013] A "system" is a set of components that provide a basic story, generate endings, collect and incorporate feedback, and so on. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] The present invention is a system that downloads a basic story to a user's device, generates a different ending each time using a generation AI, and sends the generated ending to the user's device. The system also includes a means for collecting feedback from users and reflecting that feedback in generating the next ending.

[0036] System configuration

[0037] 1. Providing a basic story

[0038] The server stores the basic storyline for a particular picture book application and provides the basic story upon request from the user.

[0039] The terminal requests the basic story of the picture book selected by the user from the server and displays the downloaded basic story to the user.

[0040] 2. Generating the ending

[0041] After reading the basic story, the device sends a request to the server to generate a new ending when it approaches the ending.

[0042] The server's generation AI analyzes the request and the contextual information of the story, and generates a new ending based on that.

[0043] 3. Sending and displaying the ending

[0044] The server filters the generated endings to check whether they are consistent with the basic story and appropriate for the user's age and interests. Endings that pass the filter are sent to the device.

[0045] The terminal displays the received ending to the user as a continuation of the story.

[0046] 4. Gather and incorporate feedback

[0047] After the user has finished reading the picture book, the device displays a feedback screen where the user can enter their thoughts and opinions.

[0048] The terminal sends this collected feedback to the server, which then reflects this feedback in generating subsequent endings.

[0049] Specific examples

[0050] Scenario: "Forest of Adventure"

[0051] 1. User Access

[0052] A parent and child launch the app on a tablet and select a picture book titled "Adventure Forest." The device then notifies the server of the selection.

[0053] 2. Loading the Basic Story

[0054] The server sends the basic story of "Adventure Forest" to the device, such as a story about children getting lost and meeting various characters.

[0055] The device displays the downloaded basic story to the parent and child.

[0056] 3. Ending Generation Request

[0057] When the forest adventure reaches its climax, the device sends a request to the server to generate a new ending.

[0058] 4. Processing and sending the generated AI

[0059] The server's generation AI analyzes the context information and generates a new ending, such as "The children find a magical lake deep in the forest and are saved by a lake fairy."

[0060] This ending is filtered and then sent to the terminal.

[0061] The device will display this new ending to the parent and child.

[0062] 5. Gathering Feedback

[0063] After finishing reading the picture book, the device displays a feedback screen where parents and children can enter their impressions and opinions.

[0064] The device sends the collected feedback to the server, which then reflects it in the next ending generation.

[0065] With this type of structure and operation, a system allows parents and children to enjoy a different ending every night, continuously stimulating children's interest and curiosity.

[0066] The processing flow will be explained below.

[0067] Step 1:

[0068] The user launches the picture book app on their device, and the app interface is displayed on the device.

[0069] Step 2:

[0070] The user selects the picture book they want to read from the list of picture books in the app. After selection, the device requests the basic story of the selected picture book from the server.

[0071] Step 3:

[0072] The server receives the request for the selected picture book and sends the corresponding basic story data to the device. The data sent is in JSON format.

[0073] Step 4:

[0074] The device parses the received basic story and displays it to the user in an easy-to-read format, for example, by displaying the story page by page.

[0075] Step 5:

[0076] As the user reads through the basic story and approaches the ending, the device sends a request to the server to generate a new ending.

[0077] Step 6:

[0078] The server receives a request to generate an ending and analyzes the story's context information (basic story content).

[0079] Step 7:

[0080] The server-based AI generates a new ending based on the analyzed context information, taking into account past feedback data.

[0081] Step 8:

[0082] The generated endings go through a filtering process where the server checks whether the endings are consistent with the underlying storyline and appropriate for the user's age and interests.

[0083] Step 9:

[0084] The filtered ending is sent from the server to the device, and the data sent is properly formatted.

[0085] Step 10:

[0086] The device displays the ending it has received to the user. The ending is displayed as a continuation of the basic story, so it is positioned so that it does not feel out of place.

[0087] Step 11:

[0088] After the user finishes reading the picture book, the device displays a feedback screen where the user can enter their impressions and opinions.

[0089] Step 12:

[0090] When the user inputs feedback and presses the send button, the terminal transmits the feedback data to the server.

[0091] Step 13:

[0092] The server stores the received feedback data and reflects it in the ending generation process from the next time onwards. The feedback may be incorporated into the generation AI model as a re-learning process.

[0093] Example 1

[0094] 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."

[0095] Conventional story delivery systems often repeat the same ending, making it difficult to sustain user interest. Furthermore, they lack the ability to reflect user feedback, making it difficult to provide endings that are appropriate for each individual user. Furthermore, the consistency and personalization of the generated endings remain issues.

[0096] 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.

[0097] In this invention, the server includes a means for downloading the basic story to the user terminal, a means for transmitting the generated ending to the user terminal, and a means for generating a different ending each time using a generation AI. This makes it possible to provide a different ending for each user and maintain the user's interest. The server also includes a means for collecting feedback from the user and reflecting this in the next ending generation, a means for filtering the generated ending to ensure consistency with the basic story, a means for personalizing the content of the generated ending based on the user's interests and age, a means in the user terminal for transmitting an ending generation request to the server, and a means for inputting a prompt sentence into the generation AI model. This makes it possible to provide a high-quality, personalized ending that reflects the feedback.

[0098] The "basic story" refers to the main parts of the original story provided to the user, such as the prologue and middle chapters, and includes the story parts excluding the ending.

[0099] "User terminal" refers to a computing device used by a user, and specifically includes tablets, smartphones, personal computers, etc.

[0100] "Generated ending" refers to one of several different endings generated by the generation AI as the conclusion of the basic story.

[0101] "Generative AI" refers to algorithms or programs that use artificial intelligence techniques to generate new sentences or story structures based on input data.

[0102] "Feedback" refers to opinions and impressions provided by users after use, and specifically includes written comments and evaluations.

[0103] "Filtering" refers to the process of reviewing the content of the generated endings and determining whether they are appropriate according to certain criteria.

[0104] "Personalization" refers to the process of tailoring content to a user based on individual information such as the user's interests or age.

[0105] An "ending generation request" refers to a message sent from a user terminal to a server requesting the generation of a new ending.

[0106] "Generative AI model" refers to a model trained to perform a specific task using artificial intelligence algorithms, and specifically includes natural language generation models.

[0107] A "prompt sentence" is a portion of text that is input to a generative AI model and contains the information that forms the basis of the generated output.

[0108] The system of the present invention downloads a basic story to a user's device, generates a different ending each time using a generation AI, and sends the generated ending to the user's device. This system also includes a function to collect feedback from users and reflect it in the generation of the next ending.

[0109] System Configuration

[0110] server:

[0111] The server stores the basic story and provides it in response to user requests. The server is equipped with a generative AI that generates new endings based on ending generation requests. It also stores collected feedback and reflects it in the next ending generation. Specific generative AI models that can be used include OpenAI's ChatGPT.

[0112] User device:

[0113] A user terminal is a computing device such as a tablet or smartphone. The user terminal requests the basic story of a picture book selected by the user from the server and displays the downloaded basic story to the user. When the story reaches its ending, the user terminal also sends a request to the server to generate an ending, receives the generated ending, and displays it to the user. The user terminal is also used to collect feedback.

[0114] Hardware and software used

[0115] Server: A high performance computing device or cloud server

[0116] Generative AI models: such as OpenAI's ChatGPT

[0117] User devices: tablets, smartphones, computers

[0118] Data processing and calculation

[0119] The server retrieves the basic story from the database and sends it to the user's device. The generative AI model generates a new ending based on the input prompt. This generation process uses a natural language generation algorithm to output an appropriate ending based on context information.

[0120] The user terminal displays the received basic story and the generated ending to the user, and transmits the user's feedback to the server.

[0121] Specific examples

[0122] Scenario: "Forest of Adventure"

[0123] 1. User Access:

[0124] A parent and child launch the app on a tablet and select a picture book titled "Adventure Forest." The device then notifies the server of the selection.

[0125] 2. Load the basic story:

[0126] The server sends the basic story of "Adventure Forest" to the device, such as a story about children getting lost and meeting various characters.

[0127] The device displays the downloaded basic story to the parent and child.

[0128] 3. Ending Generation Request:

[0129] When the forest adventure reaches its climax, the device sends a request to the server to generate a new ending.

[0130] 4. Processing and sending the generated AI:

[0131] The server's generation AI analyzes the context information and generates a new ending, such as "The children find a magical lake deep in the forest and are saved by a lake fairy."

[0132] This ending is filtered and then sent to the terminal.

[0133] The device will display this new ending to the parent and child.

[0134] 5. Gathering Feedback:

[0135] After finishing reading the picture book, the device displays a feedback screen where parents and children can enter their impressions and opinions.

[0136] The device sends the collected feedback to the server, which then reflects it in the next ending generation.

[0137] Prompt Sentence Examples

[0138] An example of a prompt used to generate an ending is the text, "In the basic story, the children get lost deep in the forest. What happens next?" Based on this prompt, the generative AI model generates a new ending.

[0139] The above is an embodiment of the present invention. This system allows the user to enjoy a new ending every time, and can maintain the user's interest and curiosity.

[0140] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0141] Step 1:

[0142] User selection of picture book and request submission

[0143] The user launches a dedicated picture book app using a tablet or smartphone and selects the title of the picture book they want to read. The device sends this selection information to the server as a request. This request includes the picture book title and user ID. The input is the user's selection information, and the output is a request including the picture book title and user ID. Specifically, it sends an HTTP request to the server's API endpoint.

[0144] Step 2:

[0145] Get and send basic stories

[0146] The server receives the request and retrieves the basic story of the specified picture book from the database. It then sends the retrieved basic story to the device. The input is the request received in step 1, and the output is the basic story. Specifically, it executes a database query and returns the retrieved data to the device.

[0147] Step 3:

[0148] Viewing the Basic Story

[0149] The terminal displays the basic story received from the server to the user. The input is the basic story received from the server, and the output is the story displayed to the user. Specifically, the terminal renders the text and images of the basic story on the user interface.

[0150] Step 4:

[0151] Sending an ending generation request

[0152] As the user reads the basic story and approaches the ending, the device sends a request to the server to generate a new ending. The request includes the user's input data and story context information. The input is the context information of the story the user has read, and the output is a request to generate an ending. Specifically, the HTTP request is sent when an event is triggered by user operation.

[0153] Step 5:

[0154] Generating the ending

[0155] The server's generation AI analyzes the received request information and context information and inputs the prompt text into the generation AI model. The generation AI model (e.g., OpenAI's ChatGPT) generates a new ending based on this prompt text. The input is the prompt text, and the output is the generated ending. Specifically, the prompt text is sent to the API endpoint of the generation AI model, and the generated ending is obtained.

[0156] Step 6:

[0157] Filtering and sending endings

[0158] The server filters the generated endings to check whether they are consistent with the basic story and appropriate for the user's age and interests. The filtered endings are then sent to the device. The input is the generated ending, and the output is the filtered ending. Specifically, the server applies a rule-based filtering algorithm to check whether the ending matches the filter criteria.

[0159] Step 7:

[0160] Displaying the ending

[0161] The device displays the received ending to the user as a continuation of the story. The input is the filtered ending, and the output is the ending displayed to the user. Specifically, it renders the ending text and images on the user interface.

[0162] Step 8:

[0163] Gathering feedback

[0164] After finishing reading the picture book, the device displays a feedback screen for users to enter their thoughts and opinions. The user enters their feedback, and the device sends it to the server. The input is the user's feedback, and the output is the feedback sent to the server. Specifically, the device displays an input form on the user interface and sends the user's input to the server's API endpoint.

[0165] Step 9:

[0166] Reflecting feedback

[0167] The server reflects the received feedback in the next ending generation. The input is the user's feedback, and the output is the ending generation process that reflects the feedback. Specific operations include adding the feedback information to the training data of the generative AI model and adjusting the generation rules.

[0168] (Application example 1)

[0169] 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."

[0170] Conventional story delivery systems have the problem that once a user finishes reading a story, the story loses its freshness. Stories that have been read once are rarely read again, making it difficult to sustain the user's interest and curiosity. In addition, there is a lack of a mechanism for utilizing user feedback to evolve the story, and personalization for each individual user is not adequately implemented.

[0171] 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.

[0172] In this invention, the server includes means for downloading the basic story to the user terminal, means for transmitting the generated ending to the user terminal, means for generating a different ending each time using a generation AI, means for collecting feedback from the user, means for saving the collected feedback and reflecting it in the next ending generation, means for transmitting the generated ending to the user terminal after passing through the server's filtering, means for transmitting context information for ending generation from the user terminal to the server, and means for personalizing the ending based on the user's interests and age. This allows the user to enjoy a fresh and interesting story each time, and makes it possible to personalize the ending based on the user's feedback.

[0173] The "base story" refers to the main plot or storyline that forms the basis of the story, and is the initial introduction that gets users started reading the story.

[0174] A "user terminal" is an electronic device used by a user to read a story, including a smartphone, tablet, or PC.

[0175] A "generated ending" is a different story ending each time created using generative AI, providing users with new surprises.

[0176] The term "means" refers to a method or apparatus for achieving a specific purpose, and is a component for realizing each function in this invention.

[0177] "Generative AI" is a system that uses artificial intelligence technology to generate text and story content, and is used to generate endings.

[0178] "Feedback" refers to opinions and impressions collected from users, and is information that can be used to generate the next ending.

[0179] A "server" is a computer system that provides data over a network and returns responses in response to user requests.

[0180] "Filtering" is a process to ensure that the generated ending is consistent with the basic story and appropriate for the user's interests and age.

[0181] "Contextual information" refers to information such as the story's progress, setting, and character background, and is an element necessary for generating an ending.

[0182] "Personalization" is the process of customizing an ending based on a particular user's interests and age.

[0183] This invention is a story provision system that provides a new ending to the user each time, and is realized using a server, terminals, and generation AI. The main components include providing the basic story, generating and displaying endings, and collecting and incorporating feedback.

[0184] Providing the basic story

[0185] The server stores the basic story and sends it to the device in response to a user request. The specific software used is a RESTful API, and the basic story is sent in JSON format via an HTTP request.

[0186] Ending generation and display

[0187] After reading the basic story, when the device approaches the ending, it sends a request to the server to generate a new ending. Specifically, the request, including contextual information, is sent to the server via a RESTful API. On the server, a generative AI model analyzes this request and generates a new ending.

[0188] The generated endings are filtered on the server to ensure consistency with the basic story and suitability for the user's interests and age. This filtering uses natural language processing technology and rule-based algorithms. Endings that pass the filtering are sent to the device and displayed to the user.

[0189] Gathering and implementing feedback

[0190] After the user finishes reading the story, the device provides a feedback screen to collect the user's impressions and opinions. The collected feedback is sent back to the server and reflected in the next ending generation. For this purpose, the feedback data is stored in a database and used as training data for the generation AI model.

[0191] Specific examples

[0192] For example, if a user selects the basic story "Adventure Library" and reads it, a new ending will be generated at the climax. One example of a generated ending is a story in which the protagonists interact with an ancient book and discover hidden knowledge.

[0193] Prompt Sentence Examples

[0194] Use this example prompt to have a generative AI model generate a new ending.

[0195] "Our heroes arrive at an old library and find an ancient book. They open it in search of ancient knowledge."

[0196] User Interests: Adventure, Fantasy

[0197] This system allows users to experience a new ending every time, allowing for a more personalized narrative experience that incorporates feedback.

[0198] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0199] Step 1:

[0200] The server stores basic stories and receives requests from user devices. The device sends a request for a basic story to the server along with a specific story ID. This request is made via a RESTful API, and the data format is JSON. After receiving the request, the server retrieves the corresponding basic story from the database and responds to the device in JSON format. The device then retrieves the basic story and displays it to the user.

[0201] Step 2:

[0202] The device displays the basic story to the user, and when the story reaches its climax, it sends a request to the server to generate a new ending. This request includes current context information (such as the progress of the basic story and character backgrounds). The request data from the device is again in JSON format.

[0203] Step 3:

[0204] The server analyzes the contextual information received from the device and inputs it into a generative AI model. The generative AI model uses natural language processing technology to generate a new ending. This process takes into account the contextual information and data such as the user's interests and age. The generative AI model generates an ending based on the contextual information and returns the generated result to the server in JSON format.

[0205] Step 4:

[0206] The server then filters the generated endings to ensure they maintain consistency with the basic story and are appropriate for the user's interests and age. Endings that pass the filtering process are then sent back to the device in JSON format. Rule-based algorithms and natural language processing techniques are used for filtering.

[0207] Step 5:

[0208] The terminal receives the generated ending sent from the server and displays it to the user, allowing the user to enjoy the newly generated ending.

[0209] Step 6:

[0210] After the user finishes reading the story, the device displays a feedback screen to collect the user's thoughts and opinions, which are then sent to the server in JSON format and stored in a database.

[0211] Step 7:

[0212] The server analyzes the collected feedback data and reflects it in the next ending generation. Specifically, the feedback data is used as training data for the generation AI model. This allows the generated endings to continue evolving based on user preferences.

[0213] This process allows users to enjoy a new ending every time, providing a more personalized narrative experience that reflects their feedback.

[0214] 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.

[0215] The present invention is a system that downloads a basic story to a user's device, generates a different ending each time using a generation AI, and sends the generated ending to the user's device. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system also incorporates the user's emotional data into the ending generation. The system also includes a means for collecting feedback from the user and reflecting that feedback in the next ending generation.

[0216] System configuration

[0217] 1. Providing a basic story

[0218] The server stores the basic storyline for a particular picture book application and provides the basic story upon request from the user.

[0219] The terminal requests the basic story of the picture book selected by the user from the server and displays the downloaded basic story to the user.

[0220] 2. Generating the ending

[0221] After reading the basic story, the device sends a request to the server to generate a new ending when it approaches the ending.

[0222] The server's generation AI analyzes the request, contextual information about the story, and past feedback data, and generates a new ending based on that.

[0223] 3. Emotion Recognition by Emotion Engine

[0224] The device collects emotion data from the user's facial expressions and voice and sends it to the emotion engine.

[0225] The emotion engine analyzes the collected emotional data and reflects the results in the ending generation process.

[0226] 4. Sending and displaying the ending

[0227] The server filters the generated endings to check whether they are consistent with the basic story and appropriate for the user's age and interests. Endings that pass the filter are sent to the device.

[0228] The terminal displays the received ending to the user as a continuation of the story.

[0229] 5. Gather and incorporate feedback

[0230] After the user has finished reading the picture book, the terminal displays a feedback screen on which the user can input their impressions and opinions.

[0231] The device sends the collected feedback to the server, which then reflects it in generating the next and subsequent endings.

[0232] Specific examples

[0233] Scenario: "Forest of Adventure"

[0234] 1. User Access

[0235] A parent and child launch the app on a tablet and select a picture book titled "Adventure Forest." The device then notifies the server of the selection.

[0236] 2. Loading the Basic Story

[0237] The server sends the basic story of "Adventure Forest" to the device, such as a story about children getting lost and meeting various characters.

[0238] The device displays the downloaded basic story to the parent and child.

[0239] 3. Ending Generation Request

[0240] When the forest adventure reaches its climax, the device sends a request to the server to generate a new ending.

[0241] 4. Processing and sending the generated AI

[0242] The server's generation AI analyzes the context information and generates a new ending, such as "The children find a magical lake deep in the forest and are saved by a lake fairy."

[0243] This ending is filtered and then sent to the terminal.

[0244] The device will display this new ending to the parent and child.

[0245] 5. Emotion Recognition by Emotion Engine

[0246] The device collects emotional data from the parent and child's facial expressions and voices, for example, using a camera or microphone.

[0247] The emotion engine analyzes this emotional data and obtains information such as "the child is having fun" or "the parent is excited." This information is reflected in the generation of the next ending.

[0248] 6. Gathering Feedback

[0249] After finishing reading the picture book, the device displays a feedback screen where parents and children can enter their thoughts and opinions.

[0250] The terminal sends the collected feedback to the server, which stores it and uses it to generate the next ending.

[0251] This system allows the user's emotional data and feedback to be reflected in the ending generation, enabling more personalized and engaging storytelling for the user.

[0252] The processing flow will be explained below.

[0253] Specific processing steps of the system based on the embodiment for implementing the invention

[0254] Step 1:

[0255] The user launches the picture book app on their device, and the app interface appears on the device screen.

[0256] Step 2:

[0257] The user selects the picture book they want to read from the list of picture books in the app. After selection, the device requests the basic story of the selected picture book from the server.

[0258] Step 3:

[0259] The server receives a request for the selected picture book and sends the corresponding basic story data in JSON format to the terminal.

[0260] Step 4:

[0261] The device analyzes the basic story it receives and displays it to the user in an easy-to-read format, page by page.

[0262] Step 5:

[0263] As the user reads the basic story, the device collects the user's facial expressions and voice and sends this data to the emotion engine.

[0264] Step 6:

[0265] The emotion engine analyzes the user's facial expression data and voice data sent from the device and determines the user's emotional state (e.g., happy, excited, surprised, etc.).

[0266] Step 7:

[0267] When the user reaches the end of the basic story, the device sends a request to the server to generate a new ending, and at the same time, emotion data from the emotion engine is also sent to the server.

[0268] Step 8:

[0269] The server's generation AI analyzes the basic story's contextual information, past feedback data, and emotional data, and generates a new ending based on that.

[0270] Step 9:

[0271] The generated endings go through a filtering process where the server checks whether the endings are consistent with the underlying storyline and appropriate for the user's age and interests.

[0272] Step 10:

[0273] The filtered ending is sent from the server to the device, and the data sent is properly formatted.

[0274] Step 11:

[0275] The device displays the ending it has received to the user. The ending is displayed as a continuation of the basic story, so it is positioned so that it does not feel out of place.

[0276] Step 12:

[0277] After the user has finished reading the picture book, the device displays a feedback screen for the user to enter their impressions and opinions.

[0278] Step 13:

[0279] When the user inputs feedback and presses the send button, the terminal transmits the feedback data to the server.

[0280] Step 14:

[0281] The server stores the received feedback data and reflects it in the ending generation process from the next time onwards. The feedback may be incorporated into the generation AI model as a re-learning process.

[0282] Specific examples

[0283] Scenario: "Forest of Adventure"

[0284] Step 1:

[0285] A parent and child launch the app on a tablet and select a picture book titled "Adventure Forest." The device then notifies the server of the selection.

[0286] Step 2:

[0287] The server sends the basic story of "Adventure Forest" to the device, which then displays the downloaded basic story to the parent and child.

[0288] Step 3:

[0289] As the parent and child read, the device uses a camera and microphone to collect the user's facial expressions and voice.

[0290] Step 4:

[0291] The emotion engine analyzes the collected data and determines the user's emotional state, for example, determining "fun" based on smiles and tone of voice.

[0292] Step 5:

[0293] Just before the end of the basic story, the device sends a request to the server to generate a new ending. At the same time, emotion data from the emotion engine is also sent to the server.

[0294] Step 6:

[0295] The server's generation AI generates new endings based on the basic story content, past feedback, and emotional data.

[0296] Step 7:

[0297] The generated endings go through a filtering process to ensure consistency and appropriateness with the basic story.

[0298] Step 8:

[0299] The filtered ending is sent from the server to the terminal.

[0300] Step 9:

[0301] The device will then display the new ending to the parent and child, for example, "The children find a magical lake deep in the forest and are rescued by the lake fairy."

[0302] Step 10:

[0303] After the parent and child finish reading the picture book, the device displays a feedback screen where the parent and child can enter their thoughts and opinions.

[0304] Step 11:

[0305] The device sends the collected feedback to the server, which stores it and uses it to generate the next ending.

[0306] In this way, the user's emotional data and feedback are reflected in the ending generation, resulting in more personalized and engaging storytelling for the user.

[0307] Example 2

[0308] 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."

[0309] Conventional storytelling systems have had difficulty generating endings that reflect the user's needs and emotions. This has resulted in inconsistent or uninteresting endings that fail to increase user satisfaction. Furthermore, mechanisms for evolving the story by regenerating it based on effective use of user feedback have been inadequate, making it difficult to personalize the story to meet individual user needs.

[0310] 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.

[0311] In this invention, the server includes means for downloading the basic story to the user terminal, means for transmitting the generated ending to the user terminal, means for generating a different ending each time using a generation AI, means for collecting and analyzing emotional data from the user's facial expressions and voice, means for reflecting the collected emotional data in generating the next ending, means for collecting feedback from the user, and means for saving the collected feedback and reflecting it in generating the next ending. This makes it possible to provide a consistent, personalized ending that reflects the user's emotions and feedback.

[0312] "Base story" refers to the main plot or content of the story selected by the user.

[0313] A "user terminal" is an electronic device used by a user, and includes, for example, a tablet or smartphone.

[0314] "Generated ending" refers to the conclusion of a story generated by the generation AI based on the basic story.

[0315] "Generative AI" refers to technology that uses artificial intelligence to generate text or story endings.

[0316] "Emotion data" refers to information about emotions acquired from the user's facial expressions, voice, etc.

[0317] An "emotion engine" refers to a technology that analyzes emotional data and reflects the results in specific processing.

[0318] "Feedback" refers to the thoughts and opinions that users provide after reading a story.

[0319] "Filtering means" refers to a method for evaluating the consistency and suitability of the generated endings and eliminating inappropriate content.

[0320] "Personalization" refers to the individual adjustment of content based on the user's interests and age.

[0321] This invention is a system that provides users with personalized endings. This system is based on a server and a user terminal, and by incorporating a generative AI and an emotion engine, it provides a more advanced user experience.

[0322] This system is configured as follows:

[0323] First, the server has a means for downloading basic stories to user terminals. The server transmits pre-stored basic storylines in response to requests from each user terminal. The user terminal receives the basic storylines and displays them to the user. For example, the story "Forest of Adventure" includes a basic story in which children get lost and meet various characters.

[0324] As the user reads the story and reaches the climax, the user device sends a request to the server to generate a new ending. The server receives this request and uses a generative AI model to generate a new ending. The generative AI model generates an ending based on the story's context information and past feedback data. For example, the following prompt might be used: "In the Adventure Forest, the children get lost. We've now reached the climax. What happens next?" Based on this prompt, the generative AI generates an ending in which "the children find a magical lake deep in the forest and are saved by the lake fairy."

[0325] Furthermore, the user device uses a camera and microphone to collect emotional data from the user's facial expressions and voice. The emotional data is sent to the emotion engine and analyzed. For example, information such as "the user is having fun" or "the parent is excited" can be obtained. This emotional data is reflected in the generation of the next ending.

[0326] The server filters the generated endings to check for consistency and suitability for the user's age and interests. The server then sends the endings that pass the filter to the user's device. The user's device displays the received ending to the user, allowing them to enjoy the continuation of the story.

[0327] After reading the story, the user's device displays a feedback screen, allowing the user to input their thoughts and opinions. The device sends the collected feedback to the server, which stores it and reflects it in the creation of the next ending. For example, a comment like "The ending was really interesting!" will influence the creation of future stories.

[0328] A system configured in this way allows users' emotional data and feedback to be reflected in the ending generation, making it possible to provide consistent and personalized endings.

[0329] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0330] Step 1:

[0331] The user selects a picture book. The user launches the picture book app and selects a title, for example, "Adventure Forest." The user's device notifies the server of this selection as input and waits for a response from the server.

[0332] Step 2:

[0333] The server provides the basic story. The server receives a request from the user's device and searches for the basic storyline of the relevant picture book. It processes this storyline and sends it to the user's device. The user's device displays the downloaded basic story as output to the user. For example, it may display a story about children who get lost and meet various characters.

[0334] Step 3:

[0335] The user reads the basic story. The user reads the story on a tablet or smartphone and reaches the climax.

[0336] Step 4:

[0337] The device sends a request to generate an ending. When the device recognizes that the user has reached the climax of the story, it sends a request to the server to generate a new ending.

[0338] Step 5:

[0339] The server generates the ending. The server receives the request and launches the generative AI model. Using the story's context information and past feedback data as input, it provides a prompt to the generative AI. For example, the prompt "In the Forest of Adventure, the children are lost. We're now reaching the climax. What happens next?" is input to the generative AI. The generative AI performs data calculations based on the input prompt, generates a new ending, and outputs it to the server. For example, the ending output is "The children find a magical lake deep in the forest and are saved by the lake fairy."

[0340] Step 6:

[0341] The device collects the user's emotional data. The device uses a camera and microphone to obtain emotional data from the user's facial expressions and voice. Specifically, the camera captures the user's facial expressions and the microphone records their voice tone. These data are sent as input to the emotion engine.

[0342] Step 7:

[0343] The emotion engine analyzes the emotion data. The emotion engine analyzes the input emotion data and outputs information such as "The user is having fun" or "The parent is excited." This output data is used to generate the next ending.

[0344] Step 8:

[0345] The server filters the endings. The server filters the generated endings to evaluate their consistency and suitability for the user's age and interests. The endings that pass this filtering are sent to the user's device as the final output.

[0346] Step 9:

[0347] The device displays the ending. The user device displays the received ending to the user as a continuation of the story. For example, the tablet screen may show an ending in which the children find a magical lake deep in the forest and are saved by a lake fairy.

[0348] Step 10:

[0349] The device collects feedback. After reading the story, the user's device displays a feedback screen, allowing the user to enter their thoughts and opinions.

[0350] Step 11:

[0351] The server saves the feedback and reflects it in the next ending. The device sends the collected feedback to the server, which saves it. This allows the user's feedback to be reflected in the next ending generation.

[0352] (Application example 2)

[0353] 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."

[0354] In conventional storytelling systems, the ending is fixed, making it difficult to provide a new experience when revisiting the same story. Furthermore, because the ending is generated without taking into account the user's emotions or feedback, it is limited in providing individually personalized stories. This leads to user boredom and reduces the value of replaying the story.

[0355] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0356] In this invention, the server includes means for downloading the basic story to the user terminal, means for transmitting the generated ending to the user terminal, means for generating a different ending each time using a generation AI, means for collecting feedback from the user, means for saving the collected feedback and reflecting it in generating the next ending, means for collecting the user's facial expressions and voice to recognize the user's emotions, and means for analyzing the collected emotional data and reflecting it in generating the ending. This makes it possible to generate a different, personalized ending each time based on the user's emotions and feedback, providing a new reading experience.

[0357] The "basic story" is the main flow and structure of the story, and is the content that the user views first.

[0358] A "user terminal" is an electronic device that a user operates to view information.

[0359] A "generated ending" is the conclusion of a story created by a generative AI.

[0360] "Generative AI" is a system that generates text and data using artificial intelligence technology.

[0361] "Feedback" refers to information such as impressions, evaluations, and opinions collected from users.

[0362] "Emotion data" is emotional information collected from the user's facial expressions and voice.

[0363] "Personalization" means tailoring content to the interests and circumstances of individual users.

[0364] "Filtering" refers to the process of selecting content so that the generated ending remains consistent with the basic story.

[0365] The present invention provides a system that downloads a basic story and generates a different ending each time based on emotional data and feedback, in order to provide a new reading experience to the user. Specific embodiments for carrying out the present invention will be described below.

[0366] 1. Download the basic story

[0367] The server stores basic stories and provides a means for downloading them to user devices. A user selects a basic story through a device such as smart glasses, and the story is downloaded to the device. For example, if a user selects a picture book titled "Adventure Forest," the basic story is downloaded.

[0368] 2. Generating the ending

[0369] As the user reads the basic story, the device sends a request to the server when it's time to generate an ending. The server's AI analyzes this request, the story's context information, and past feedback data to generate a new ending.

[0370] 3. Emotional Data Collection and Analysis

[0371] The user device (such as smart glasses) uses a camera and microphone to collect the user's facial expressions and voice. This emotional data is sent to the emotion engine for analysis. The results of this analysis are reflected in the ending generation process. For example, if the user is enjoying the story, the ending will be more positive.

[0372] 4. Sending and displaying the ending

[0373] The generated ending is sent from the server to the user's device. The device displays the received ending to the user. This ending is filtered to maintain consistency with the basic story. For example, an ending may be generated in which the children find a magical lake deep in the forest and are saved by a lake fairy.

[0374] 5. Gather and incorporate feedback

[0375] After the user finishes reading the story, the device displays a feedback screen to collect the user's thoughts and opinions. The device then sends this feedback to the server, which then reflects it in the generation of the next ending. This allows for a personalized experience for each user.

[0376] Examples and prompts

[0377] For example, in the story "Adventure Forest," children discover a magical lake, but the ending that awaits them is different each time. An example of a prompt sentence in this case would be, "The children enter the adventure forest and encounter one mysterious event after another. They eventually reach the magical lake, but the ending that awaits them is..."

[0378] This invention uses libraries such as OpenCV to perform facial expression analysis, and a Python program to realize data communication and processing between the server and the device. Furthermore, it uses a generative AI model (e.g., GPT-3) to generate text in real time. In this way, it is possible to provide users with a new storytelling experience.

[0379] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0380] Step 1:

[0381] The server stores the basic stories and provides a means for downloading them to user terminals.

[0382] Input: A request for a selected story from the user

[0383] Data processing: The server reads the story and converts it into a data format for sending to the device.

[0384] Output: Reformatted basic story

[0385] Specific operation: The user selects "Adventure Forest" using the smart glasses, and the request is sent to the server. The server prepares the basic story for download and sends it to the user's device.

[0386] Step 2:

[0387] The terminal displays the basic story to the user and allows the user to read through the story.

[0388] Input: Downloaded base story

[0389] Data processing: Converting story data into a format suitable for display on the user screen.

[0390] Output: The basic story shown on the display

[0391] Specific behavior: The device displays the downloaded story and the user reads it. Example: "A story about children who get lost and meet various characters."

[0392] Step 3:

[0393] The terminal sends a request to the server when it is time to generate the ending.

[0394] Input: Current story progress

[0395] Data calculation: Generates data to send an ending generation request to the server based on the progress

[0396] Output: Ending generation request data

[0397] Specific operation: As the story progresses and approaches its climax, the device sends a request to the server to generate an ending.

[0398] Step 4:

[0399] The server generates new endings using a generation AI.

[0400] Input: Ending generation request, story context, past feedback data

[0401] Data computation: Generate new endings using generative AI (e.g., GPT-3)

[0402] Output: The generated ending text

[0403] How it works: The server's generation AI generates a new ending based on the "Forest of Adventure" and past feedback, such as "The children find a magical lake deep in the forest."

[0404] Step 5:

[0405] The device collects the user's facial expressions and voice and sends them to the emotion engine.

[0406] Input: User's facial expressions and voice data

[0407] Data processing: Collect data using the camera and microphone and send it to the emotion engine

[0408] Output: Emotion data for analysis

[0409] Specific operation: The device's camera and microphone collect the user's emotional state and send it to the emotion engine.

[0410] Step 6:

[0411] The emotion engine analyzes the emotion data and sends it to the server.

[0412] Input: User's facial expressions and voice data

[0413] Data Computing: Identifying emotional states using emotion data analysis algorithms

[0414] Output: Parsed emotion information

[0415] Specific operation: The emotion engine analyzes emotional information such as "the user is having fun" or "the user is excited" and sends this to the server.

[0416] Step 7:

[0417] The server fine-tunes the ending based on the analyzed emotional data.

[0418] Input: Analyzed emotion information, generated ending

[0419] Data calculation: Adjusting the ending text based on emotional information

[0420] Output: Emotionally tweaked ending

[0421] Specific operation: The server generates a positive ending that reflects the "enjoying" state based on emotional data.

[0422] Step 8:

[0423] The server transmits the filtered ending to the user terminal.

[0424] Input: Tweaked ending

[0425] Data calculations: checking consistency with the basic story and filtering

[0426] Output: Filtered ending

[0427] Specific operation: The server uses a recognition engine to check the consistency of the ending and sends it to the device.

[0428] Step 9:

[0429] The terminal displays the filtered ending to the user.

[0430] Input: Filtered ending

[0431] Data processing: converting the ending text into a suitable format for display to the user

[0432] Output: The ending displayed on the user's device display

[0433] Specific action: The device displays the ending "The children find a magical lake deep in the forest and are saved by the lake fairy."

[0434] Step 10:

[0435] The terminal collects feedback from the user and transmits it to the server.

[0436] Input: User feedback

[0437] Data processing: Converting user-entered feedback into data format

[0438] Output: Feedback data sent to the server

[0439] Specific operation: The device displays a feedback screen for the user to enter their thoughts and opinions, and the collected feedback data is sent to the server and stored.

[0440] 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.

[0441] 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.

[0442] 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.

[0443] [Second embodiment]

[0444] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0445] 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.

[0446] 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).

[0447] 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.

[0448] 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.

[0449] 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).

[0450] 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.

[0451] 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.

[0452] 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.

[0453] 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.

[0454] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0455] 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."

[0456] The present invention is a system that downloads a basic story to a user's device, generates a different ending each time using a generation AI, and sends the generated ending to the user's device. The system also includes a means for collecting feedback from users and reflecting that feedback in generating the next ending.

[0457] System configuration

[0458] 1. Providing a basic story

[0459] The server stores the basic storyline for a particular picture book application and provides the basic story upon request from the user.

[0460] The terminal requests the basic story of the picture book selected by the user from the server and displays the downloaded basic story to the user.

[0461] 2. Generating the ending

[0462] After reading the basic story, the device sends a request to the server to generate a new ending when it approaches the ending.

[0463] The server's generation AI analyzes the request and the contextual information of the story, and generates a new ending based on that.

[0464] 3. Sending and displaying the ending

[0465] The server filters the generated endings to check whether they are consistent with the basic story and appropriate for the user's age and interests. Endings that pass the filter are sent to the device.

[0466] The terminal displays the received ending to the user as a continuation of the story.

[0467] 4. Gather and incorporate feedback

[0468] After the user has finished reading the picture book, the device displays a feedback screen where the user can enter their thoughts and opinions.

[0469] The terminal sends this collected feedback to the server, which then reflects this feedback in generating subsequent endings.

[0470] Specific examples

[0471] Scenario: "Forest of Adventure"

[0472] 1. User Access

[0473] A parent and child launch the app on a tablet and select a picture book titled "Adventure Forest." The device then notifies the server of the selection.

[0474] 2. Loading the Basic Story

[0475] The server sends the basic story of "Adventure Forest" to the device, such as a story about children getting lost and meeting various characters.

[0476] The device displays the downloaded basic story to the parent and child.

[0477] 3. Ending Generation Request

[0478] When the forest adventure reaches its climax, the device sends a request to the server to generate a new ending.

[0479] 4. Processing and sending the generated AI

[0480] The server's generation AI analyzes the context information and generates a new ending, such as "The children find a magical lake deep in the forest and are saved by a lake fairy."

[0481] This ending is filtered and then sent to the terminal.

[0482] The device will display this new ending to the parent and child.

[0483] 5. Gathering Feedback

[0484] After finishing reading the picture book, the device displays a feedback screen where parents and children can enter their impressions and opinions.

[0485] The device sends the collected feedback to the server, which then reflects it in the next ending generation.

[0486] With this type of structure and operation, a system allows parents and children to enjoy a different ending every night, continuously stimulating children's interest and curiosity.

[0487] The processing flow will be explained below.

[0488] Step 1:

[0489] The user launches the picture book app on their device, and the app interface is displayed on the device.

[0490] Step 2:

[0491] The user selects the picture book they want to read from the list of picture books in the app. After selection, the device requests the basic story of the selected picture book from the server.

[0492] Step 3:

[0493] The server receives the request for the selected picture book and sends the corresponding basic story data to the device. The data sent is in JSON format.

[0494] Step 4:

[0495] The device parses the received basic story and displays it to the user in an easy-to-read format, for example, by displaying the story page by page.

[0496] Step 5:

[0497] As the user reads through the basic story and approaches the ending, the device sends a request to the server to generate a new ending.

[0498] Step 6:

[0499] The server receives a request to generate an ending and analyzes the story's context information (basic story content).

[0500] Step 7:

[0501] The server-based AI generates a new ending based on the analyzed context information, taking into account past feedback data.

[0502] Step 8:

[0503] The generated endings go through a filtering process where the server checks whether the endings are consistent with the underlying storyline and appropriate for the user's age and interests.

[0504] Step 9:

[0505] The filtered ending is sent from the server to the device, and the data sent is properly formatted.

[0506] Step 10:

[0507] The device displays the ending it has received to the user. The ending is displayed as a continuation of the basic story, so it is positioned so that it does not feel out of place.

[0508] Step 11:

[0509] After the user finishes reading the picture book, the device displays a feedback screen where the user can enter their impressions and opinions.

[0510] Step 12:

[0511] When the user inputs feedback and presses the send button, the terminal transmits the feedback data to the server.

[0512] Step 13:

[0513] The server stores the received feedback data and reflects it in the ending generation process from the next time onwards. The feedback may be incorporated into the generation AI model as a re-learning process.

[0514] Example 1

[0515] 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."

[0516] Conventional story delivery systems often repeat the same ending, making it difficult to sustain user interest. Furthermore, they lack the ability to reflect user feedback, making it difficult to provide endings that are appropriate for each individual user. Furthermore, the consistency and personalization of the generated endings remain issues.

[0517] 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.

[0518] In this invention, the server includes a means for downloading the basic story to the user terminal, a means for transmitting the generated ending to the user terminal, and a means for generating a different ending each time using a generation AI. This makes it possible to provide a different ending for each user and maintain the user's interest. The server also includes a means for collecting feedback from the user and reflecting this in the next ending generation, a means for filtering the generated ending to ensure consistency with the basic story, a means for personalizing the content of the generated ending based on the user's interests and age, a means in the user terminal for transmitting an ending generation request to the server, and a means for inputting a prompt sentence into the generation AI model. This makes it possible to provide a high-quality, personalized ending that reflects the feedback.

[0519] The "basic story" refers to the main parts of the original story provided to the user, such as the prologue and middle chapters, and includes the story parts excluding the ending.

[0520] "User terminal" refers to a computing device used by a user, and specifically includes tablets, smartphones, personal computers, etc.

[0521] "Generated ending" refers to one of several different endings generated by the generation AI as the conclusion of the basic story.

[0522] "Generative AI" refers to algorithms or programs that use artificial intelligence techniques to generate new sentences or story structures based on input data.

[0523] "Feedback" refers to opinions and impressions provided by users after use, and specifically includes written comments and evaluations.

[0524] "Filtering" refers to the process of reviewing the content of the generated endings and determining whether they are appropriate according to certain criteria.

[0525] "Personalization" refers to the process of tailoring content to a user based on individual information such as the user's interests or age.

[0526] An "ending generation request" refers to a message sent from a user terminal to a server requesting the generation of a new ending.

[0527] "Generative AI model" refers to a model trained to perform a specific task using artificial intelligence algorithms, and specifically includes natural language generation models.

[0528] A "prompt sentence" is a portion of text that is input to a generative AI model and contains the information that forms the basis of the generated output.

[0529] The system of the present invention downloads a basic story to a user's device, generates a different ending each time using a generation AI, and sends the generated ending to the user's device. This system also includes a function to collect feedback from users and reflect it in the generation of the next ending.

[0530] System Configuration

[0531] server:

[0532] The server stores the basic story and provides it in response to user requests. The server is equipped with a generative AI that generates new endings based on ending generation requests. It also stores collected feedback and reflects it in the next ending generation. Specific generative AI models that can be used include OpenAI's ChatGPT.

[0533] User device:

[0534] A user terminal is a computing device such as a tablet or smartphone. The user terminal requests the basic story of a picture book selected by the user from the server and displays the downloaded basic story to the user. When the story reaches its ending, the user terminal also sends a request to the server to generate an ending, receives the generated ending, and displays it to the user. The user terminal is also used to collect feedback.

[0535] Hardware and software used

[0536] Server: A high performance computing device or cloud server

[0537] Generative AI models: such as OpenAI's ChatGPT

[0538] User devices: tablets, smartphones, computers

[0539] Data processing and calculation

[0540] The server retrieves the basic story from the database and sends it to the user's device. The generative AI model generates a new ending based on the input prompt. This generation process uses a natural language generation algorithm to output an appropriate ending based on context information.

[0541] The user terminal displays the received basic story and the generated ending to the user, and transmits the user's feedback to the server.

[0542] Specific examples

[0543] Scenario: "Forest of Adventure"

[0544] 1. User Access:

[0545] A parent and child launch the app on a tablet and select a picture book titled "Adventure Forest." The device then notifies the server of the selection.

[0546] 2. Load the basic story:

[0547] The server sends the basic story of "Adventure Forest" to the device, such as a story about children getting lost and meeting various characters.

[0548] The device displays the downloaded basic story to the parent and child.

[0549] 3. Ending Generation Request:

[0550] When the forest adventure reaches its climax, the device sends a request to the server to generate a new ending.

[0551] 4. Processing and sending the generated AI:

[0552] The server's generation AI analyzes the context information and generates a new ending, such as "The children find a magical lake deep in the forest and are saved by a lake fairy."

[0553] This ending is filtered and then sent to the terminal.

[0554] The device will display this new ending to the parent and child.

[0555] 5. Gathering Feedback:

[0556] After finishing reading the picture book, the device displays a feedback screen where parents and children can enter their impressions and opinions.

[0557] The device sends the collected feedback to the server, which then reflects it in the next ending generation.

[0558] Prompt Sentence Examples

[0559] An example of a prompt used to generate an ending is the text, "In the basic story, the children get lost deep in the forest. What happens next?" Based on this prompt, the generative AI model generates a new ending.

[0560] The above is an embodiment of the present invention. This system allows the user to enjoy a new ending every time, and can maintain the user's interest and curiosity.

[0561] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0562] Step 1:

[0563] User selection of picture book and request submission

[0564] The user launches a dedicated picture book app using a tablet or smartphone and selects the title of the picture book they want to read. The device sends this selection information to the server as a request. This request includes the picture book title and user ID. The input is the user's selection information, and the output is a request including the picture book title and user ID. Specifically, it sends an HTTP request to the server's API endpoint.

[0565] Step 2:

[0566] Get and send basic stories

[0567] The server receives the request and retrieves the basic story of the specified picture book from the database. It then sends the retrieved basic story to the device. The input is the request received in step 1, and the output is the basic story. Specifically, it executes a database query and returns the retrieved data to the device.

[0568] Step 3:

[0569] Viewing the Basic Story

[0570] The terminal displays the basic story received from the server to the user. The input is the basic story received from the server, and the output is the story displayed to the user. Specifically, the terminal renders the text and images of the basic story on the user interface.

[0571] Step 4:

[0572] Sending an ending generation request

[0573] As the user reads the basic story and approaches the ending, the device sends a request to the server to generate a new ending. The request includes the user's input data and story context information. The input is the context information of the story the user has read, and the output is a request to generate an ending. Specifically, the HTTP request is sent when an event is triggered by user operation.

[0574] Step 5:

[0575] Generating the ending

[0576] The server's generation AI analyzes the received request information and context information and inputs the prompt text into the generation AI model. The generation AI model (e.g., OpenAI's ChatGPT) generates a new ending based on this prompt text. The input is the prompt text, and the output is the generated ending. Specifically, the prompt text is sent to the API endpoint of the generation AI model, and the generated ending is obtained.

[0577] Step 6:

[0578] Filtering and sending endings

[0579] The server filters the generated endings to check whether they are consistent with the basic story and appropriate for the user's age and interests. The filtered endings are then sent to the device. The input is the generated ending, and the output is the filtered ending. Specifically, the server applies a rule-based filtering algorithm to check whether the ending matches the filter criteria.

[0580] Step 7:

[0581] Displaying the ending

[0582] The device displays the received ending to the user as a continuation of the story. The input is the filtered ending, and the output is the ending displayed to the user. Specifically, it renders the ending text and images on the user interface.

[0583] Step 8:

[0584] Gathering feedback

[0585] After finishing reading the picture book, the device displays a feedback screen for users to enter their thoughts and opinions. The user enters their feedback, and the device sends it to the server. The input is the user's feedback, and the output is the feedback sent to the server. Specifically, the device displays an input form on the user interface and sends the user's input to the server's API endpoint.

[0586] Step 9:

[0587] Reflecting feedback

[0588] The server reflects the received feedback in the next ending generation. The input is the user's feedback, and the output is the ending generation process that reflects the feedback. Specific operations include adding the feedback information to the training data of the generative AI model and adjusting the generation rules.

[0589] (Application example 1)

[0590] 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."

[0591] Conventional story delivery systems have the problem that once a user finishes reading a story, the story loses its freshness. Stories that have been read once are rarely read again, making it difficult to sustain the user's interest and curiosity. In addition, there is a lack of a mechanism for utilizing user feedback to evolve the story, and personalization for each individual user is not adequately implemented.

[0592] 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.

[0593] In this invention, the server includes means for downloading the basic story to the user terminal, means for transmitting the generated ending to the user terminal, means for generating a different ending each time using a generation AI, means for collecting feedback from the user, means for saving the collected feedback and reflecting it in the next ending generation, means for transmitting the generated ending to the user terminal after passing through the server's filtering, means for transmitting context information for ending generation from the user terminal to the server, and means for personalizing the ending based on the user's interests and age. This allows the user to enjoy a fresh and interesting story each time, and makes it possible to personalize the ending based on the user's feedback.

[0594] The "base story" refers to the main plot or storyline that forms the basis of the story, and is the initial introduction that gets users started reading the story.

[0595] A "user terminal" is an electronic device used by a user to read a story, including a smartphone, tablet, or PC.

[0596] A "generated ending" is a different story ending each time created using generative AI, providing users with new surprises.

[0597] The term "means" refers to a method or apparatus for achieving a specific purpose, and is a component for realizing each function in this invention.

[0598] "Generative AI" is a system that uses artificial intelligence technology to generate text and story content, and is used to generate endings.

[0599] "Feedback" refers to opinions and impressions collected from users, and is information that can be used to generate the next ending.

[0600] A "server" is a computer system that provides data over a network and returns responses in response to user requests.

[0601] "Filtering" is a process to ensure that the generated ending is consistent with the basic story and appropriate for the user's interests and age.

[0602] "Contextual information" refers to information such as the story's progress, setting, and character background, and is an element necessary for generating an ending.

[0603] "Personalization" is the process of customizing an ending based on a particular user's interests and age.

[0604] This invention is a story provision system that provides a new ending to the user each time, and is realized using a server, terminals, and generation AI. The main components include providing the basic story, generating and displaying endings, and collecting and incorporating feedback.

[0605] Providing the basic story

[0606] The server stores the basic story and sends it to the device in response to a user request. The specific software used is a RESTful API, and the basic story is sent in JSON format via an HTTP request.

[0607] Ending generation and display

[0608] After reading the basic story, when the device approaches the ending, it sends a request to the server to generate a new ending. Specifically, the request, including contextual information, is sent to the server via a RESTful API. On the server, a generative AI model analyzes this request and generates a new ending.

[0609] The generated endings are filtered on the server to ensure consistency with the basic story and suitability for the user's interests and age. This filtering uses natural language processing technology and rule-based algorithms. Endings that pass the filtering are sent to the device and displayed to the user.

[0610] Gathering and implementing feedback

[0611] After the user finishes reading the story, the device provides a feedback screen to collect the user's impressions and opinions. The collected feedback is sent back to the server and reflected in the next ending generation. For this purpose, the feedback data is stored in a database and used as training data for the generation AI model.

[0612] Specific examples

[0613] For example, if a user selects the basic story "Adventure Library" and reads it, a new ending will be generated at the climax. One example of a generated ending is a story in which the protagonists interact with an ancient book and discover hidden knowledge.

[0614] Prompt Sentence Examples

[0615] Use this example prompt to have a generative AI model generate a new ending.

[0616] "Our heroes arrive at an old library and find an ancient book. They open it in search of ancient knowledge."

[0617] User Interests: Adventure, Fantasy

[0618] This system allows users to experience a new ending every time, allowing for a more personalized narrative experience that incorporates feedback.

[0619] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0620] Step 1:

[0621] The server stores basic stories and receives requests from user devices. The device sends a request for a basic story to the server along with a specific story ID. This request is made via a RESTful API, and the data format is JSON. After receiving the request, the server retrieves the corresponding basic story from the database and responds to the device in JSON format. The device then retrieves the basic story and displays it to the user.

[0622] Step 2:

[0623] The device displays the basic story to the user, and when the story reaches its climax, it sends a request to the server to generate a new ending. This request includes current context information (such as the progress of the basic story and character backgrounds). The request data from the device is again in JSON format.

[0624] Step 3:

[0625] The server analyzes the contextual information received from the device and inputs it into a generative AI model. The generative AI model uses natural language processing technology to generate a new ending. This process takes into account the contextual information and data such as the user's interests and age. The generative AI model generates an ending based on the contextual information and returns the generated result to the server in JSON format.

[0626] Step 4:

[0627] The server then filters the generated endings to ensure they maintain consistency with the basic story and are appropriate for the user's interests and age. Endings that pass the filtering process are then sent back to the device in JSON format. Rule-based algorithms and natural language processing techniques are used for filtering.

[0628] Step 5:

[0629] The terminal receives the generated ending sent from the server and displays it to the user, allowing the user to enjoy the newly generated ending.

[0630] Step 6:

[0631] After the user finishes reading the story, the device displays a feedback screen to collect the user's thoughts and opinions, which are then sent to the server in JSON format and stored in a database.

[0632] Step 7:

[0633] The server analyzes the collected feedback data and reflects it in the next ending generation. Specifically, the feedback data is used as training data for the generation AI model. This allows the generated endings to continue evolving based on user preferences.

[0634] This process allows users to enjoy a new ending every time, providing a more personalized narrative experience that reflects their feedback.

[0635] 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.

[0636] The present invention is a system that downloads a basic story to a user's device, generates a different ending each time using a generation AI, and sends the generated ending to the user's device. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system also incorporates the user's emotional data into the ending generation. The system also includes a means for collecting feedback from the user and reflecting that feedback in the next ending generation.

[0637] System configuration

[0638] 1. Providing a basic story

[0639] The server stores the basic storyline for a particular picture book application and provides the basic story upon request from the user.

[0640] The terminal requests the basic story of the picture book selected by the user from the server and displays the downloaded basic story to the user.

[0641] 2. Generating the ending

[0642] After reading the basic story, the device sends a request to the server to generate a new ending when it approaches the ending.

[0643] The server's generation AI analyzes the request, contextual information about the story, and past feedback data, and generates a new ending based on that.

[0644] 3. Emotion Recognition by Emotion Engine

[0645] The device collects emotion data from the user's facial expressions and voice and sends it to the emotion engine.

[0646] The emotion engine analyzes the collected emotional data and reflects the results in the ending generation process.

[0647] 4. Sending and displaying the ending

[0648] The server filters the generated endings to check whether they are consistent with the basic story and appropriate for the user's age and interests. Endings that pass the filter are sent to the device.

[0649] The terminal displays the received ending to the user as a continuation of the story.

[0650] 5. Gather and incorporate feedback

[0651] After the user has finished reading the picture book, the terminal displays a feedback screen on which the user can input their impressions and opinions.

[0652] The device sends the collected feedback to the server, which then reflects it in generating the next and subsequent endings.

[0653] Specific examples

[0654] Scenario: "Forest of Adventure"

[0655] 1. User Access

[0656] A parent and child launch the app on a tablet and select a picture book titled "Adventure Forest." The device then notifies the server of the selection.

[0657] 2. Loading the Basic Story

[0658] The server sends the basic story of "Adventure Forest" to the device, such as a story about children getting lost and meeting various characters.

[0659] The device displays the downloaded basic story to the parent and child.

[0660] 3. Ending Generation Request

[0661] When the forest adventure reaches its climax, the device sends a request to the server to generate a new ending.

[0662] 4. Processing and sending the generated AI

[0663] The server's generation AI analyzes the context information and generates a new ending, such as "The children find a magical lake deep in the forest and are saved by a lake fairy."

[0664] This ending is filtered and then sent to the terminal.

[0665] The device will display this new ending to the parent and child.

[0666] 5. Emotion Recognition by Emotion Engine

[0667] The device collects emotional data from the parent and child's facial expressions and voices, for example, using a camera or microphone.

[0668] The emotion engine analyzes this emotional data and obtains information such as "the child is having fun" or "the parent is excited." This information is reflected in the generation of the next ending.

[0669] 6. Gathering Feedback

[0670] After finishing reading the picture book, the device displays a feedback screen where parents and children can enter their thoughts and opinions.

[0671] The terminal sends the collected feedback to the server, which stores it and uses it to generate the next ending.

[0672] This system allows the user's emotional data and feedback to be reflected in the ending generation, enabling more personalized and engaging storytelling for the user.

[0673] The processing flow will be explained below.

[0674] Specific processing steps of the system based on the embodiment for implementing the invention

[0675] Step 1:

[0676] The user launches the picture book app on their device, and the app interface appears on the device screen.

[0677] Step 2:

[0678] The user selects the picture book they want to read from the list of picture books in the app. After selection, the device requests the basic story of the selected picture book from the server.

[0679] Step 3:

[0680] The server receives a request for the selected picture book and sends the corresponding basic story data in JSON format to the terminal.

[0681] Step 4:

[0682] The device analyzes the basic story it receives and displays it to the user in an easy-to-read format, page by page.

[0683] Step 5:

[0684] As the user reads the basic story, the device collects the user's facial expressions and voice and sends this data to the emotion engine.

[0685] Step 6:

[0686] The emotion engine analyzes the user's facial expression data and voice data sent from the device and determines the user's emotional state (e.g., happy, excited, surprised, etc.).

[0687] Step 7:

[0688] When the user reaches the end of the basic story, the device sends a request to the server to generate a new ending, and at the same time, emotion data from the emotion engine is also sent to the server.

[0689] Step 8:

[0690] The server's generation AI analyzes the basic story's contextual information, past feedback data, and emotional data, and generates a new ending based on that.

[0691] Step 9:

[0692] The generated endings go through a filtering process where the server checks whether the endings are consistent with the underlying storyline and appropriate for the user's age and interests.

[0693] Step 10:

[0694] The filtered ending is sent from the server to the device, and the data sent is properly formatted.

[0695] Step 11:

[0696] The device displays the ending it has received to the user. The ending is displayed as a continuation of the basic story, so it is positioned so that it does not feel out of place.

[0697] Step 12:

[0698] After the user has finished reading the picture book, the device displays a feedback screen for the user to enter their impressions and opinions.

[0699] Step 13:

[0700] When the user inputs feedback and presses the send button, the terminal transmits the feedback data to the server.

[0701] Step 14:

[0702] The server stores the received feedback data and reflects it in the ending generation process from the next time onwards. The feedback may be incorporated into the generation AI model as a re-learning process.

[0703] Specific examples

[0704] Scenario: "Forest of Adventure"

[0705] Step 1:

[0706] A parent and child launch the app on a tablet and select a picture book titled "Adventure Forest." The device then notifies the server of the selection.

[0707] Step 2:

[0708] The server sends the basic story of "Adventure Forest" to the device, which then displays the downloaded basic story to the parent and child.

[0709] Step 3:

[0710] As the parent and child read, the device uses a camera and microphone to collect the user's facial expressions and voice.

[0711] Step 4:

[0712] The emotion engine analyzes the collected data and determines the user's emotional state, for example, determining "fun" based on smiles and tone of voice.

[0713] Step 5:

[0714] Just before the end of the basic story, the device sends a request to the server to generate a new ending. At the same time, emotion data from the emotion engine is also sent to the server.

[0715] Step 6:

[0716] The server's generation AI generates new endings based on the basic story content, past feedback, and emotional data.

[0717] Step 7:

[0718] The generated endings go through a filtering process to ensure consistency and appropriateness with the basic story.

[0719] Step 8:

[0720] The filtered ending is sent from the server to the terminal.

[0721] Step 9:

[0722] The device will then display the new ending to the parent and child, for example, "The children find a magical lake deep in the forest and are rescued by the lake fairy."

[0723] Step 10:

[0724] After the parent and child finish reading the picture book, the device displays a feedback screen where the parent and child can enter their thoughts and opinions.

[0725] Step 11:

[0726] The device sends the collected feedback to the server, which stores it and uses it to generate the next ending.

[0727] In this way, the user's emotional data and feedback are reflected in the ending generation, resulting in more personalized and engaging storytelling for the user.

[0728] Example 2

[0729] 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."

[0730] Conventional storytelling systems have had difficulty generating endings that reflect the user's needs and emotions. This has resulted in inconsistent or uninteresting endings that fail to increase user satisfaction. Furthermore, mechanisms for evolving the story by regenerating it based on effective use of user feedback have been inadequate, making it difficult to personalize the story to meet individual user needs.

[0731] 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.

[0732] In this invention, the server includes means for downloading the basic story to the user terminal, means for transmitting the generated ending to the user terminal, means for generating a different ending each time using a generation AI, means for collecting and analyzing emotional data from the user's facial expressions and voice, means for reflecting the collected emotional data in generating the next ending, means for collecting feedback from the user, and means for saving the collected feedback and reflecting it in generating the next ending. This makes it possible to provide a consistent, personalized ending that reflects the user's emotions and feedback.

[0733] "Base story" refers to the main plot or content of the story selected by the user.

[0734] A "user terminal" is an electronic device used by a user, and includes, for example, a tablet or smartphone.

[0735] "Generated ending" refers to the conclusion of a story generated by the generation AI based on the basic story.

[0736] "Generative AI" refers to technology that uses artificial intelligence to generate text or story endings.

[0737] "Emotion data" refers to information about emotions acquired from the user's facial expressions, voice, etc.

[0738] An "emotion engine" refers to a technology that analyzes emotional data and reflects the results in specific processing.

[0739] "Feedback" refers to the thoughts and opinions that users provide after reading a story.

[0740] "Filtering means" refers to a method for evaluating the consistency and suitability of the generated endings and eliminating inappropriate content.

[0741] "Personalization" refers to the individual adjustment of content based on the user's interests and age.

[0742] This invention is a system that provides users with personalized endings. This system is based on a server and a user terminal, and by incorporating a generative AI and an emotion engine, it provides a more advanced user experience.

[0743] This system is configured as follows:

[0744] First, the server has a means for downloading basic stories to user terminals. The server transmits pre-stored basic storylines in response to requests from each user terminal. The user terminal receives the basic storylines and displays them to the user. For example, the story "Forest of Adventure" includes a basic story in which children get lost and meet various characters.

[0745] As the user reads the story and reaches the climax, the user device sends a request to the server to generate a new ending. The server receives this request and uses a generative AI model to generate a new ending. The generative AI model generates an ending based on the story's context information and past feedback data. For example, the following prompt might be used: "In the Adventure Forest, the children get lost. We've now reached the climax. What happens next?" Based on this prompt, the generative AI generates an ending in which "the children find a magical lake deep in the forest and are saved by the lake fairy."

[0746] Furthermore, the user device uses a camera and microphone to collect emotional data from the user's facial expressions and voice. The emotional data is sent to the emotion engine and analyzed. For example, information such as "the user is having fun" or "the parent is excited" can be obtained. This emotional data is reflected in the generation of the next ending.

[0747] The server filters the generated endings to check for consistency and suitability for the user's age and interests. The server then sends the endings that pass the filter to the user's device. The user's device displays the received ending to the user, allowing them to enjoy the continuation of the story.

[0748] After reading the story, the user's device displays a feedback screen, allowing the user to input their thoughts and opinions. The device sends the collected feedback to the server, which stores it and reflects it in the creation of the next ending. For example, a comment like "The ending was really interesting!" will influence the creation of future stories.

[0749] A system configured in this way allows users' emotional data and feedback to be reflected in the ending generation, making it possible to provide consistent and personalized endings.

[0750] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0751] Step 1:

[0752] The user selects a picture book. The user launches the picture book app and selects a title, for example, "Adventure Forest." The user's device notifies the server of this selection as input and waits for a response from the server.

[0753] Step 2:

[0754] The server provides the basic story. The server receives a request from the user's device and searches for the basic storyline of the relevant picture book. It processes this storyline and sends it to the user's device. The user's device displays the downloaded basic story as output to the user. For example, it may display a story about children who get lost and meet various characters.

[0755] Step 3:

[0756] The user reads the basic story. The user reads the story on a tablet or smartphone and reaches the climax.

[0757] Step 4:

[0758] The device sends a request to generate an ending. When the device recognizes that the user has reached the climax of the story, it sends a request to the server to generate a new ending.

[0759] Step 5:

[0760] The server generates the ending. The server receives the request and launches the generative AI model. Using the story's context information and past feedback data as input, it provides a prompt to the generative AI. For example, the prompt "In the Forest of Adventure, the children are lost. We're now reaching the climax. What happens next?" is input to the generative AI. The generative AI performs data calculations based on the input prompt, generates a new ending, and outputs it to the server. For example, the ending output is "The children find a magical lake deep in the forest and are saved by the lake fairy."

[0761] Step 6:

[0762] The device collects the user's emotional data. The device uses a camera and microphone to obtain emotional data from the user's facial expressions and voice. Specifically, the camera captures the user's facial expressions and the microphone records their voice tone. These data are sent as input to the emotion engine.

[0763] Step 7:

[0764] The emotion engine analyzes the emotion data. The emotion engine analyzes the input emotion data and outputs information such as "The user is having fun" or "The parent is excited." This output data is used to generate the next ending.

[0765] Step 8:

[0766] The server filters the endings. The server filters the generated endings to evaluate their consistency and suitability for the user's age and interests. The endings that pass this filtering are sent to the user's device as the final output.

[0767] Step 9:

[0768] The device displays the ending. The user device displays the received ending to the user as a continuation of the story. For example, the tablet screen may show an ending in which the children find a magical lake deep in the forest and are saved by a lake fairy.

[0769] Step 10:

[0770] The device collects feedback. After reading the story, the user's device displays a feedback screen, allowing the user to enter their thoughts and opinions.

[0771] Step 11:

[0772] The server saves the feedback and reflects it in the next ending. The device sends the collected feedback to the server, which saves it. This allows the user's feedback to be reflected in the next ending generation.

[0773] (Application example 2)

[0774] 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."

[0775] In conventional storytelling systems, the ending is fixed, making it difficult to provide a new experience when revisiting the same story. Furthermore, because the ending is generated without taking into account the user's emotions or feedback, it is limited in providing individually personalized stories. This leads to user boredom and reduces the value of replaying the story.

[0776] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0777] In this invention, the server includes means for downloading the basic story to the user terminal, means for transmitting the generated ending to the user terminal, means for generating a different ending each time using a generation AI, means for collecting feedback from the user, means for saving the collected feedback and reflecting it in generating the next ending, means for collecting the user's facial expressions and voice to recognize the user's emotions, and means for analyzing the collected emotional data and reflecting it in generating the ending. This makes it possible to generate a different, personalized ending each time based on the user's emotions and feedback, providing a new reading experience.

[0778] The "basic story" is the main flow and structure of the story, and is the content that the user views first.

[0779] A "user terminal" is an electronic device that a user operates to view information.

[0780] A "generated ending" is the conclusion of a story created by a generative AI.

[0781] "Generative AI" is a system that generates text and data using artificial intelligence technology.

[0782] "Feedback" refers to information such as impressions, evaluations, and opinions collected from users.

[0783] "Emotion data" is emotional information collected from the user's facial expressions and voice.

[0784] "Personalization" means tailoring content to the interests and circumstances of individual users.

[0785] "Filtering" refers to the process of selecting content so that the generated ending remains consistent with the basic story.

[0786] The present invention provides a system that downloads a basic story and generates a different ending each time based on emotional data and feedback, in order to provide a new reading experience to the user. Specific embodiments for carrying out the present invention will be described below.

[0787] 1. Download the basic story

[0788] The server stores basic stories and provides a means for downloading them to user devices. A user selects a basic story through a device such as smart glasses, and the story is downloaded to the device. For example, if a user selects a picture book titled "Adventure Forest," the basic story is downloaded.

[0789] 2. Generating the ending

[0790] As the user reads the basic story, the device sends a request to the server when it's time to generate an ending. The server's AI analyzes this request, the story's context information, and past feedback data to generate a new ending.

[0791] 3. Emotional Data Collection and Analysis

[0792] The user device (such as smart glasses) uses a camera and microphone to collect the user's facial expressions and voice. This emotional data is sent to the emotion engine for analysis. The results of this analysis are reflected in the ending generation process. For example, if the user is enjoying the story, the ending will be more positive.

[0793] 4. Sending and displaying the ending

[0794] The generated ending is sent from the server to the user's device. The device displays the received ending to the user. This ending is filtered to maintain consistency with the basic story. For example, an ending may be generated in which the children find a magical lake deep in the forest and are saved by a lake fairy.

[0795] 5. Gather and incorporate feedback

[0796] After the user finishes reading the story, the device displays a feedback screen to collect the user's thoughts and opinions. The device then sends this feedback to the server, which then reflects it in the generation of the next ending. This allows for a personalized experience for each user.

[0797] Examples and prompts

[0798] For example, in the story "Adventure Forest," children discover a magical lake, but the ending that awaits them is different each time. An example of a prompt sentence in this case would be, "The children enter the adventure forest and encounter one mysterious event after another. They eventually reach the magical lake, but the ending that awaits them is..."

[0799] This invention uses libraries such as OpenCV to perform facial expression analysis, and a Python program to realize data communication and processing between the server and the device. Furthermore, it uses a generative AI model (e.g., GPT-3) to generate text in real time. In this way, it is possible to provide users with a new storytelling experience.

[0800] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0801] Step 1:

[0802] The server stores the basic stories and provides a means for downloading them to user terminals.

[0803] Input: A request for a selected story from the user

[0804] Data processing: The server reads the story and converts it into a data format for sending to the device.

[0805] Output: Reformatted basic story

[0806] Specific operation: The user selects "Adventure Forest" using the smart glasses, and the request is sent to the server. The server prepares the basic story for download and sends it to the user's device.

[0807] Step 2:

[0808] The terminal displays the basic story to the user and allows the user to read through the story.

[0809] Input: Downloaded base story

[0810] Data processing: Converting story data into a format suitable for display on the user screen.

[0811] Output: The basic story shown on the display

[0812] Specific behavior: The device displays the downloaded story and the user reads it. Example: "A story about children who get lost and meet various characters."

[0813] Step 3:

[0814] The terminal sends a request to the server when it is time to generate the ending.

[0815] Input: Current story progress

[0816] Data calculation: Generates data to send an ending generation request to the server based on the progress

[0817] Output: Ending generation request data

[0818] Specific operation: As the story progresses and approaches its climax, the device sends a request to the server to generate an ending.

[0819] Step 4:

[0820] The server generates new endings using a generation AI.

[0821] Input: Ending generation request, story context, past feedback data

[0822] Data computation: Generate new endings using generative AI (e.g., GPT-3)

[0823] Output: The generated ending text

[0824] How it works: The server's generation AI generates a new ending based on the "Forest of Adventure" and past feedback, such as "The children find a magical lake deep in the forest."

[0825] Step 5:

[0826] The device collects the user's facial expressions and voice and sends them to the emotion engine.

[0827] Input: User's facial expressions and voice data

[0828] Data processing: Collect data using the camera and microphone and send it to the emotion engine

[0829] Output: Emotion data for analysis

[0830] Specific operation: The device's camera and microphone collect the user's emotional state and send it to the emotion engine.

[0831] Step 6:

[0832] The emotion engine analyzes the emotion data and sends it to the server.

[0833] Input: User's facial expressions and voice data

[0834] Data Computing: Identifying emotional states using emotion data analysis algorithms

[0835] Output: Parsed emotion information

[0836] Specific operation: The emotion engine analyzes emotional information such as "the user is having fun" or "the user is excited" and sends this to the server.

[0837] Step 7:

[0838] The server fine-tunes the ending based on the analyzed emotional data.

[0839] Input: Analyzed emotion information, generated ending

[0840] Data calculation: Adjusting the ending text based on emotional information

[0841] Output: Emotionally tweaked ending

[0842] Specific operation: The server generates a positive ending that reflects the "enjoying" state based on emotional data.

[0843] Step 8:

[0844] The server transmits the filtered ending to the user terminal.

[0845] Input: Tweaked ending

[0846] Data calculations: checking consistency with the basic story and filtering

[0847] Output: Filtered ending

[0848] Specific operation: The server uses a recognition engine to check the consistency of the ending and sends it to the device.

[0849] Step 9:

[0850] The terminal displays the filtered ending to the user.

[0851] Input: Filtered ending

[0852] Data processing: converting the ending text into a suitable format for display to the user

[0853] Output: The ending displayed on the user's device display

[0854] Specific action: The device displays the ending "The children find a magical lake deep in the forest and are saved by the lake fairy."

[0855] Step 10:

[0856] The terminal collects feedback from the user and transmits it to the server.

[0857] Input: User feedback

[0858] Data processing: Converting user-entered feedback into data format

[0859] Output: Feedback data sent to the server

[0860] Specific operation: The device displays a feedback screen for the user to enter their thoughts and opinions, and the collected feedback data is sent to the server and stored.

[0861] 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.

[0862] 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.

[0863] 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.

[0864] [Third embodiment]

[0865] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0866] 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.

[0867] 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).

[0868] 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.

[0869] 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.

[0870] 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).

[0871] 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.

[0872] 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.

[0873] 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.

[0874] 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.

[0875] 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.

[0876] 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."

[0877] The present invention is a system that downloads a basic story to a user's device, generates a different ending each time using a generation AI, and sends the generated ending to the user's device. The system also includes a means for collecting feedback from users and reflecting that feedback in generating the next ending.

[0878] System configuration

[0879] 1. Providing a basic story

[0880] The server stores the basic storyline for a particular picture book application and provides the basic story upon request from the user.

[0881] The terminal requests the basic story of the picture book selected by the user from the server and displays the downloaded basic story to the user.

[0882] 2. Generating the ending

[0883] After reading the basic story, the device sends a request to the server to generate a new ending when it approaches the ending.

[0884] The server's generation AI analyzes the request and the contextual information of the story, and generates a new ending based on that.

[0885] 3. Sending and displaying the ending

[0886] The server filters the generated endings to check whether they are consistent with the basic story and appropriate for the user's age and interests. Endings that pass the filter are sent to the device.

[0887] The terminal displays the received ending to the user as a continuation of the story.

[0888] 4. Gather and incorporate feedback

[0889] After the user has finished reading the picture book, the device displays a feedback screen where the user can enter their thoughts and opinions.

[0890] The terminal sends this collected feedback to the server, which then reflects this feedback in generating subsequent endings.

[0891] Specific examples

[0892] Scenario: "Forest of Adventure"

[0893] 1. User Access

[0894] A parent and child launch the app on a tablet and select a picture book titled "Adventure Forest." The device then notifies the server of the selection.

[0895] 2. Loading the Basic Story

[0896] The server sends the basic story of "Adventure Forest" to the device, such as a story about children getting lost and meeting various characters.

[0897] The device displays the downloaded basic story to the parent and child.

[0898] 3. Ending Generation Request

[0899] When the forest adventure reaches its climax, the device sends a request to the server to generate a new ending.

[0900] 4. Processing and sending the generated AI

[0901] The server's generation AI analyzes the context information and generates a new ending, such as "The children find a magical lake deep in the forest and are saved by a lake fairy."

[0902] This ending is filtered and then sent to the terminal.

[0903] The device will display this new ending to the parent and child.

[0904] 5. Gathering Feedback

[0905] After finishing reading the picture book, the device displays a feedback screen where parents and children can enter their impressions and opinions.

[0906] The device sends the collected feedback to the server, which then reflects it in the next ending generation.

[0907] With this type of structure and operation, a system allows parents and children to enjoy a different ending every night, continuously stimulating children's interest and curiosity.

[0908] The processing flow will be explained below.

[0909] Step 1:

[0910] The user launches the picture book app on their device, and the app interface is displayed on the device.

[0911] Step 2:

[0912] The user selects the picture book they want to read from the list of picture books in the app. After selection, the device requests the basic story of the selected picture book from the server.

[0913] Step 3:

[0914] The server receives the request for the selected picture book and sends the corresponding basic story data to the device. The data sent is in JSON format.

[0915] Step 4:

[0916] The device parses the received basic story and displays it to the user in an easy-to-read format, for example, by displaying the story page by page.

[0917] Step 5:

[0918] As the user reads through the basic story and approaches the ending, the device sends a request to the server to generate a new ending.

[0919] Step 6:

[0920] The server receives a request to generate an ending and analyzes the story's context information (basic story content).

[0921] Step 7:

[0922] The server-based AI generates a new ending based on the analyzed context information, taking into account past feedback data.

[0923] Step 8:

[0924] The generated endings go through a filtering process where the server checks whether the endings are consistent with the underlying storyline and appropriate for the user's age and interests.

[0925] Step 9:

[0926] The filtered ending is sent from the server to the device, and the data sent is properly formatted.

[0927] Step 10:

[0928] The device displays the ending it has received to the user. The ending is displayed as a continuation of the basic story, so it is positioned so that it does not feel out of place.

[0929] Step 11:

[0930] After the user finishes reading the picture book, the device displays a feedback screen where the user can enter their impressions and opinions.

[0931] Step 12:

[0932] When the user inputs feedback and presses the send button, the terminal transmits the feedback data to the server.

[0933] Step 13:

[0934] The server stores the received feedback data and reflects it in the ending generation process from the next time onwards. The feedback may be incorporated into the generation AI model as a re-learning process.

[0935] Example 1

[0936] 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."

[0937] Conventional story delivery systems often repeat the same ending, making it difficult to sustain user interest. Furthermore, they lack the ability to reflect user feedback, making it difficult to provide endings that are appropriate for each individual user. Furthermore, the consistency and personalization of the generated endings remain issues.

[0938] 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.

[0939] In this invention, the server includes a means for downloading the basic story to the user terminal, a means for transmitting the generated ending to the user terminal, and a means for generating a different ending each time using a generation AI. This makes it possible to provide a different ending for each user and maintain the user's interest. The server also includes a means for collecting feedback from the user and reflecting this in the next ending generation, a means for filtering the generated ending to ensure consistency with the basic story, a means for personalizing the content of the generated ending based on the user's interests and age, a means in the user terminal for transmitting an ending generation request to the server, and a means for inputting a prompt sentence into the generation AI model. This makes it possible to provide a high-quality, personalized ending that reflects the feedback.

[0940] The "basic story" refers to the main parts of the original story provided to the user, such as the prologue and middle chapters, and includes the story parts excluding the ending.

[0941] "User terminal" refers to a computing device used by a user, and specifically includes tablets, smartphones, personal computers, etc.

[0942] "Generated ending" refers to one of several different endings generated by the generation AI as the conclusion of the basic story.

[0943] "Generative AI" refers to algorithms or programs that use artificial intelligence techniques to generate new sentences or story structures based on input data.

[0944] "Feedback" refers to opinions and impressions provided by users after use, and specifically includes written comments and evaluations.

[0945] "Filtering" refers to the process of reviewing the content of the generated endings and determining whether they are appropriate according to certain criteria.

[0946] "Personalization" refers to the process of tailoring content to a user based on individual information such as the user's interests or age.

[0947] An "ending generation request" refers to a message sent from a user terminal to a server requesting the generation of a new ending.

[0948] "Generative AI model" refers to a model trained to perform a specific task using artificial intelligence algorithms, and specifically includes natural language generation models.

[0949] A "prompt sentence" is a portion of text that is input to a generative AI model and contains the information that forms the basis of the generated output.

[0950] The system of the present invention downloads a basic story to a user's device, generates a different ending each time using a generation AI, and sends the generated ending to the user's device. This system also includes a function to collect feedback from users and reflect it in the generation of the next ending.

[0951] System Configuration

[0952] server:

[0953] The server stores the basic story and provides it in response to user requests. The server is equipped with a generative AI that generates new endings based on ending generation requests. It also stores collected feedback and reflects it in the next ending generation. Specific generative AI models that can be used include OpenAI's ChatGPT.

[0954] User device:

[0955] A user terminal is a computing device such as a tablet or smartphone. The user terminal requests the basic story of a picture book selected by the user from the server and displays the downloaded basic story to the user. When the story reaches its ending, the user terminal also sends a request to the server to generate an ending, receives the generated ending, and displays it to the user. The user terminal is also used to collect feedback.

[0956] Hardware and software used

[0957] Server: A high performance computing device or cloud server

[0958] Generative AI models: such as OpenAI's ChatGPT

[0959] User devices: tablets, smartphones, computers

[0960] Data processing and calculation

[0961] The server retrieves the basic story from the database and sends it to the user's device. The generative AI model generates a new ending based on the input prompt. This generation process uses a natural language generation algorithm to output an appropriate ending based on context information.

[0962] The user terminal displays the received basic story and the generated ending to the user, and transmits the user's feedback to the server.

[0963] Specific examples

[0964] Scenario: "Forest of Adventure"

[0965] 1. User Access:

[0966] A parent and child launch the app on a tablet and select a picture book titled "Adventure Forest." The device then notifies the server of the selection.

[0967] 2. Load the basic story:

[0968] The server sends the basic story of "Adventure Forest" to the device, such as a story about children getting lost and meeting various characters.

[0969] The device displays the downloaded basic story to the parent and child.

[0970] 3. Ending Generation Request:

[0971] When the forest adventure reaches its climax, the device sends a request to the server to generate a new ending.

[0972] 4. Processing and sending the generated AI:

[0973] The server's generation AI analyzes the context information and generates a new ending, such as "The children find a magical lake deep in the forest and are saved by a lake fairy."

[0974] This ending is filtered and then sent to the terminal.

[0975] The device will display this new ending to the parent and child.

[0976] 5. Gathering Feedback:

[0977] After finishing reading the picture book, the device displays a feedback screen where parents and children can enter their impressions and opinions.

[0978] The device sends the collected feedback to the server, which then reflects it in the next ending generation.

[0979] Prompt Sentence Examples

[0980] An example of a prompt used to generate an ending is the text, "In the basic story, the children get lost deep in the forest. What happens next?" Based on this prompt, the generative AI model generates a new ending.

[0981] The above is an embodiment of the present invention. This system allows the user to enjoy a new ending every time, and can maintain the user's interest and curiosity.

[0982] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0983] Step 1:

[0984] User selection of picture book and request submission

[0985] The user launches a dedicated picture book app using a tablet or smartphone and selects the title of the picture book they want to read. The device sends this selection information to the server as a request. This request includes the picture book title and user ID. The input is the user's selection information, and the output is a request including the picture book title and user ID. Specifically, it sends an HTTP request to the server's API endpoint.

[0986] Step 2:

[0987] Get and send basic stories

[0988] The server receives the request and retrieves the basic story of the specified picture book from the database. It then sends the retrieved basic story to the device. The input is the request received in step 1, and the output is the basic story. Specifically, it executes a database query and returns the retrieved data to the device.

[0989] Step 3:

[0990] Viewing the Basic Story

[0991] The terminal displays the basic story received from the server to the user. The input is the basic story received from the server, and the output is the story displayed to the user. Specifically, the terminal renders the text and images of the basic story on the user interface.

[0992] Step 4:

[0993] Sending an ending generation request

[0994] As the user reads the basic story and approaches the ending, the device sends a request to the server to generate a new ending. The request includes the user's input data and story context information. The input is the context information of the story the user has read, and the output is a request to generate an ending. Specifically, the HTTP request is sent when an event is triggered by user operation.

[0995] Step 5:

[0996] Generating the ending

[0997] The server's generation AI analyzes the received request information and context information and inputs the prompt text into the generation AI model. The generation AI model (e.g., OpenAI's ChatGPT) generates a new ending based on this prompt text. The input is the prompt text, and the output is the generated ending. Specifically, the prompt text is sent to the API endpoint of the generation AI model, and the generated ending is obtained.

[0998] Step 6:

[0999] Filtering and sending endings

[1000] The server filters the generated endings to check whether they are consistent with the basic story and appropriate for the user's age and interests. The filtered endings are then sent to the device. The input is the generated ending, and the output is the filtered ending. Specifically, the server applies a rule-based filtering algorithm to check whether the ending matches the filter criteria.

[1001] Step 7:

[1002] Displaying the ending

[1003] The device displays the received ending to the user as a continuation of the story. The input is the filtered ending, and the output is the ending displayed to the user. Specifically, it renders the ending text and images on the user interface.

[1004] Step 8:

[1005] Gathering feedback

[1006] After finishing reading the picture book, the device displays a feedback screen for users to enter their thoughts and opinions. The user enters their feedback, and the device sends it to the server. The input is the user's feedback, and the output is the feedback sent to the server. Specifically, the device displays an input form on the user interface and sends the user's input to the server's API endpoint.

[1007] Step 9:

[1008] Reflecting feedback

[1009] The server reflects the received feedback in the next ending generation. The input is the user's feedback, and the output is the ending generation process that reflects the feedback. Specific operations include adding the feedback information to the training data of the generative AI model and adjusting the generation rules.

[1010] (Application example 1)

[1011] 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."

[1012] Conventional story delivery systems have the problem that once a user finishes reading a story, the story loses its freshness. Stories that have been read once are rarely read again, making it difficult to sustain the user's interest and curiosity. In addition, there is a lack of a mechanism for utilizing user feedback to evolve the story, and personalization for each individual user is not adequately implemented.

[1013] 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.

[1014] In this invention, the server includes means for downloading the basic story to the user terminal, means for transmitting the generated ending to the user terminal, means for generating a different ending each time using a generation AI, means for collecting feedback from the user, means for saving the collected feedback and reflecting it in the next ending generation, means for transmitting the generated ending to the user terminal after passing through the server's filtering, means for transmitting context information for ending generation from the user terminal to the server, and means for personalizing the ending based on the user's interests and age. This allows the user to enjoy a fresh and interesting story each time, and makes it possible to personalize the ending based on the user's feedback.

[1015] The "base story" refers to the main plot or storyline that forms the basis of the story, and is the initial introduction that gets users started reading the story.

[1016] A "user terminal" is an electronic device used by a user to read a story, including a smartphone, tablet, or PC.

[1017] A "generated ending" is a different story ending each time created using generative AI, providing users with new surprises.

[1018] The term "means" refers to a method or apparatus for achieving a specific purpose, and is a component for realizing each function in this invention.

[1019] "Generative AI" is a system that uses artificial intelligence technology to generate text and story content, and is used to generate endings.

[1020] "Feedback" refers to opinions and impressions collected from users, and is information that can be used to generate the next ending.

[1021] A "server" is a computer system that provides data over a network and returns responses in response to user requests.

[1022] "Filtering" is a process to ensure that the generated ending is consistent with the basic story and appropriate for the user's interests and age.

[1023] "Contextual information" refers to information such as the story's progress, setting, and character background, and is an element necessary for generating an ending.

[1024] "Personalization" is the process of customizing an ending based on a particular user's interests and age.

[1025] This invention is a story provision system that provides a new ending to the user each time, and is realized using a server, terminals, and generation AI. The main components include providing the basic story, generating and displaying endings, and collecting and incorporating feedback.

[1026] Providing the basic story

[1027] The server stores the basic story and sends it to the device in response to a user request. The specific software used is a RESTful API, and the basic story is sent in JSON format via an HTTP request.

[1028] Ending generation and display

[1029] After reading the basic story, when the device approaches the ending, it sends a request to the server to generate a new ending. Specifically, the request, including contextual information, is sent to the server via a RESTful API. On the server, a generative AI model analyzes this request and generates a new ending.

[1030] The generated endings are filtered on the server to ensure consistency with the basic story and suitability for the user's interests and age. This filtering uses natural language processing technology and rule-based algorithms. Endings that pass the filtering are sent to the device and displayed to the user.

[1031] Gathering and implementing feedback

[1032] After the user finishes reading the story, the device provides a feedback screen to collect the user's impressions and opinions. The collected feedback is sent back to the server and reflected in the next ending generation. For this purpose, the feedback data is stored in a database and used as training data for the generation AI model.

[1033] Specific examples

[1034] For example, if a user selects the basic story "Adventure Library" and reads it, a new ending will be generated at the climax. One example of a generated ending is a story in which the protagonists interact with an ancient book and discover hidden knowledge.

[1035] Prompt Sentence Examples

[1036] Use this example prompt to have a generative AI model generate a new ending.

[1037] "Our heroes arrive at an old library and find an ancient book. They open it in search of ancient knowledge."

[1038] User Interests: Adventure, Fantasy

[1039] This system allows users to experience a new ending every time, allowing for a more personalized narrative experience that incorporates feedback.

[1040] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1041] Step 1:

[1042] The server stores basic stories and receives requests from user devices. The device sends a request for a basic story to the server along with a specific story ID. This request is made via a RESTful API, and the data format is JSON. After receiving the request, the server retrieves the corresponding basic story from the database and responds to the device in JSON format. The device then retrieves the basic story and displays it to the user.

[1043] Step 2:

[1044] The device displays the basic story to the user, and when the story reaches its climax, it sends a request to the server to generate a new ending. This request includes current context information (such as the progress of the basic story and character backgrounds). The request data from the device is again in JSON format.

[1045] Step 3:

[1046] The server analyzes the contextual information received from the device and inputs it into a generative AI model. The generative AI model uses natural language processing technology to generate a new ending. This process takes into account the contextual information and data such as the user's interests and age. The generative AI model generates an ending based on the contextual information and returns the generated result to the server in JSON format.

[1047] Step 4:

[1048] The server then filters the generated endings to ensure they maintain consistency with the basic story and are appropriate for the user's interests and age. Endings that pass the filtering process are then sent back to the device in JSON format. Rule-based algorithms and natural language processing techniques are used for filtering.

[1049] Step 5:

[1050] The terminal receives the generated ending sent from the server and displays it to the user, allowing the user to enjoy the newly generated ending.

[1051] Step 6:

[1052] After the user finishes reading the story, the device displays a feedback screen to collect the user's thoughts and opinions, which are then sent to the server in JSON format and stored in a database.

[1053] Step 7:

[1054] The server analyzes the collected feedback data and reflects it in the next ending generation. Specifically, the feedback data is used as training data for the generation AI model. This allows the generated endings to continue evolving based on user preferences.

[1055] This process allows users to enjoy a new ending every time, providing a more personalized narrative experience that reflects their feedback.

[1056] 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.

[1057] The present invention is a system that downloads a basic story to a user's device, generates a different ending each time using a generation AI, and sends the generated ending to the user's device. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system also incorporates the user's emotional data into the ending generation. The system also includes a means for collecting feedback from the user and reflecting that feedback in the next ending generation.

[1058] System configuration

[1059] 1. Providing a basic story

[1060] The server stores the basic storyline for a particular picture book application and provides the basic story upon request from the user.

[1061] The terminal requests the basic story of the picture book selected by the user from the server and displays the downloaded basic story to the user.

[1062] 2. Generating the ending

[1063] After reading the basic story, the device sends a request to the server to generate a new ending when it approaches the ending.

[1064] The server's generation AI analyzes the request, contextual information about the story, and past feedback data, and generates a new ending based on that.

[1065] 3. Emotion Recognition by Emotion Engine

[1066] The device collects emotion data from the user's facial expressions and voice and sends it to the emotion engine.

[1067] The emotion engine analyzes the collected emotional data and reflects the results in the ending generation process.

[1068] 4. Sending and displaying the ending

[1069] The server filters the generated endings to check whether they are consistent with the basic story and appropriate for the user's age and interests. Endings that pass the filter are sent to the device.

[1070] The terminal displays the received ending to the user as a continuation of the story.

[1071] 5. Gather and incorporate feedback

[1072] After the user has finished reading the picture book, the terminal displays a feedback screen on which the user can input their impressions and opinions.

[1073] The device sends the collected feedback to the server, which then reflects it in generating the next and subsequent endings.

[1074] Specific examples

[1075] Scenario: "Forest of Adventure"

[1076] 1. User Access

[1077] A parent and child launch the app on a tablet and select a picture book titled "Adventure Forest." The device then notifies the server of the selection.

[1078] 2. Loading the Basic Story

[1079] The server sends the basic story of "Adventure Forest" to the device, such as a story about children getting lost and meeting various characters.

[1080] The device displays the downloaded basic story to the parent and child.

[1081] 3. Ending Generation Request

[1082] When the forest adventure reaches its climax, the device sends a request to the server to generate a new ending.

[1083] 4. Processing and sending the generated AI

[1084] The server's generation AI analyzes the context information and generates a new ending, such as "The children find a magical lake deep in the forest and are saved by a lake fairy."

[1085] This ending is filtered and then sent to the terminal.

[1086] The device will display this new ending to the parent and child.

[1087] 5. Emotion Recognition by Emotion Engine

[1088] The device collects emotional data from the parent and child's facial expressions and voices, for example, using a camera or microphone.

[1089] The emotion engine analyzes this emotional data and obtains information such as "the child is having fun" or "the parent is excited." This information is reflected in the generation of the next ending.

[1090] 6. Gathering Feedback

[1091] After finishing reading the picture book, the device displays a feedback screen where parents and children can enter their thoughts and opinions.

[1092] The terminal sends the collected feedback to the server, which stores it and uses it to generate the next ending.

[1093] This system allows the user's emotional data and feedback to be reflected in the ending generation, enabling more personalized and engaging storytelling for the user.

[1094] The processing flow will be explained below.

[1095] Specific processing steps of the system based on the embodiment for implementing the invention

[1096] Step 1:

[1097] The user launches the picture book app on their device, and the app interface appears on the device screen.

[1098] Step 2:

[1099] The user selects the picture book they want to read from the list of picture books in the app. After selection, the device requests the basic story of the selected picture book from the server.

[1100] Step 3:

[1101] The server receives a request for the selected picture book and sends the corresponding basic story data in JSON format to the terminal.

[1102] Step 4:

[1103] The device analyzes the basic story it receives and displays it to the user in an easy-to-read format, page by page.

[1104] Step 5:

[1105] As the user reads the basic story, the device collects the user's facial expressions and voice and sends this data to the emotion engine.

[1106] Step 6:

[1107] The emotion engine analyzes the user's facial expression data and voice data sent from the device and determines the user's emotional state (e.g., happy, excited, surprised, etc.).

[1108] Step 7:

[1109] When the user reaches the end of the basic story, the device sends a request to the server to generate a new ending, and at the same time, emotion data from the emotion engine is also sent to the server.

[1110] Step 8:

[1111] The server's generation AI analyzes the basic story's contextual information, past feedback data, and emotional data, and generates a new ending based on that.

[1112] Step 9:

[1113] The generated endings go through a filtering process where the server checks whether the endings are consistent with the underlying storyline and appropriate for the user's age and interests.

[1114] Step 10:

[1115] The filtered ending is sent from the server to the device, and the data sent is properly formatted.

[1116] Step 11:

[1117] The device displays the ending it has received to the user. The ending is displayed as a continuation of the basic story, so it is positioned so that it does not feel out of place.

[1118] Step 12:

[1119] After the user has finished reading the picture book, the device displays a feedback screen for the user to enter their impressions and opinions.

[1120] Step 13:

[1121] When the user inputs feedback and presses the send button, the terminal transmits the feedback data to the server.

[1122] Step 14:

[1123] The server stores the received feedback data and reflects it in the ending generation process from the next time onwards. The feedback may be incorporated into the generation AI model as a re-learning process.

[1124] Specific examples

[1125] Scenario: "Forest of Adventure"

[1126] Step 1:

[1127] A parent and child launch the app on a tablet and select a picture book titled "Adventure Forest." The device then notifies the server of the selection.

[1128] Step 2:

[1129] The server sends the basic story of "Adventure Forest" to the device, which then displays the downloaded basic story to the parent and child.

[1130] Step 3:

[1131] As the parent and child read, the device uses a camera and microphone to collect the user's facial expressions and voice.

[1132] Step 4:

[1133] The emotion engine analyzes the collected data and determines the user's emotional state, for example, determining "fun" based on smiles and tone of voice.

[1134] Step 5:

[1135] Just before the end of the basic story, the device sends a request to the server to generate a new ending. At the same time, emotion data from the emotion engine is also sent to the server.

[1136] Step 6:

[1137] The server's generation AI generates new endings based on the basic story content, past feedback, and emotional data.

[1138] Step 7:

[1139] The generated endings go through a filtering process to ensure consistency and appropriateness with the basic story.

[1140] Step 8:

[1141] The filtered ending is sent from the server to the terminal.

[1142] Step 9:

[1143] The device will then display the new ending to the parent and child, for example, "The children find a magical lake deep in the forest and are rescued by the lake fairy."

[1144] Step 10:

[1145] After the parent and child finish reading the picture book, the device displays a feedback screen where the parent and child can enter their thoughts and opinions.

[1146] Step 11:

[1147] The device sends the collected feedback to the server, which stores it and uses it to generate the next ending.

[1148] In this way, the user's emotional data and feedback are reflected in the ending generation, resulting in more personalized and engaging storytelling for the user.

[1149] Example 2

[1150] 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."

[1151] Conventional storytelling systems have had difficulty generating endings that reflect the user's needs and emotions. This has resulted in inconsistent or uninteresting endings that fail to increase user satisfaction. Furthermore, mechanisms for evolving the story by regenerating it based on effective use of user feedback have been inadequate, making it difficult to personalize the story to meet individual user needs.

[1152] 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.

[1153] In this invention, the server includes means for downloading the basic story to the user terminal, means for transmitting the generated ending to the user terminal, means for generating a different ending each time using a generation AI, means for collecting and analyzing emotional data from the user's facial expressions and voice, means for reflecting the collected emotional data in generating the next ending, means for collecting feedback from the user, and means for saving the collected feedback and reflecting it in generating the next ending. This makes it possible to provide a consistent, personalized ending that reflects the user's emotions and feedback.

[1154] "Base story" refers to the main plot or content of the story selected by the user.

[1155] A "user terminal" is an electronic device used by a user, and includes, for example, a tablet or smartphone.

[1156] "Generated ending" refers to the conclusion of a story generated by the generation AI based on the basic story.

[1157] "Generative AI" refers to technology that uses artificial intelligence to generate text or story endings.

[1158] "Emotion data" refers to information about emotions acquired from the user's facial expressions, voice, etc.

[1159] An "emotion engine" refers to a technology that analyzes emotional data and reflects the results in specific processing.

[1160] "Feedback" refers to the thoughts and opinions that users provide after reading a story.

[1161] "Filtering means" refers to a method for evaluating the consistency and suitability of the generated endings and eliminating inappropriate content.

[1162] "Personalization" refers to the individual adjustment of content based on the user's interests and age.

[1163] This invention is a system that provides users with personalized endings. This system is based on a server and a user terminal, and by incorporating a generative AI and an emotion engine, it provides a more advanced user experience.

[1164] This system is configured as follows:

[1165] First, the server has a means for downloading basic stories to user terminals. The server transmits pre-stored basic storylines in response to requests from each user terminal. The user terminal receives the basic storylines and displays them to the user. For example, the story "Forest of Adventure" includes a basic story in which children get lost and meet various characters.

[1166] As the user reads the story and reaches the climax, the user device sends a request to the server to generate a new ending. The server receives this request and uses a generative AI model to generate a new ending. The generative AI model generates an ending based on the story's context information and past feedback data. For example, the following prompt might be used: "In the Adventure Forest, the children get lost. We've now reached the climax. What happens next?" Based on this prompt, the generative AI generates an ending in which "the children find a magical lake deep in the forest and are saved by the lake fairy."

[1167] Furthermore, the user device uses a camera and microphone to collect emotional data from the user's facial expressions and voice. The emotional data is sent to the emotion engine and analyzed. For example, information such as "the user is having fun" or "the parent is excited" can be obtained. This emotional data is reflected in the generation of the next ending.

[1168] The server filters the generated endings to check for consistency and suitability for the user's age and interests. The server then sends the endings that pass the filter to the user's device. The user's device displays the received ending to the user, allowing them to enjoy the continuation of the story.

[1169] After reading the story, the user's device displays a feedback screen, allowing the user to input their thoughts and opinions. The device sends the collected feedback to the server, which stores it and reflects it in the creation of the next ending. For example, a comment like "The ending was really interesting!" will influence the creation of future stories.

[1170] A system configured in this way allows users' emotional data and feedback to be reflected in the ending generation, making it possible to provide consistent and personalized endings.

[1171] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1172] Step 1:

[1173] The user selects a picture book. The user launches the picture book app and selects a title, for example, "Adventure Forest." The user's device notifies the server of this selection as input and waits for a response from the server.

[1174] Step 2:

[1175] The server provides the basic story. The server receives a request from the user's device and searches for the basic storyline of the relevant picture book. It processes this storyline and sends it to the user's device. The user's device displays the downloaded basic story as output to the user. For example, it may display a story about children who get lost and meet various characters.

[1176] Step 3:

[1177] The user reads the basic story. The user reads the story on a tablet or smartphone and reaches the climax.

[1178] Step 4:

[1179] The device sends a request to generate an ending. When the device recognizes that the user has reached the climax of the story, it sends a request to the server to generate a new ending.

[1180] Step 5:

[1181] The server generates the ending. The server receives the request and launches the generative AI model. Using the story's context information and past feedback data as input, it provides a prompt to the generative AI. For example, the prompt "In the Forest of Adventure, the children are lost. We're now reaching the climax. What happens next?" is input to the generative AI. The generative AI performs data calculations based on the input prompt, generates a new ending, and outputs it to the server. For example, the ending output is "The children find a magical lake deep in the forest and are saved by the lake fairy."

[1182] Step 6:

[1183] The device collects the user's emotional data. The device uses a camera and microphone to obtain emotional data from the user's facial expressions and voice. Specifically, the camera captures the user's facial expressions and the microphone records their voice tone. These data are sent as input to the emotion engine.

[1184] Step 7:

[1185] The emotion engine analyzes the emotion data. The emotion engine analyzes the input emotion data and outputs information such as "The user is having fun" or "The parent is excited." This output data is used to generate the next ending.

[1186] Step 8:

[1187] The server filters the endings. The server filters the generated endings to evaluate their consistency and suitability for the user's age and interests. The endings that pass this filtering are sent to the user's device as the final output.

[1188] Step 9:

[1189] The device displays the ending. The user device displays the received ending to the user as a continuation of the story. For example, the tablet screen may show an ending in which the children find a magical lake deep in the forest and are saved by a lake fairy.

[1190] Step 10:

[1191] The device collects feedback. After reading the story, the user's device displays a feedback screen, allowing the user to enter their thoughts and opinions.

[1192] Step 11:

[1193] The server saves the feedback and reflects it in the next ending. The device sends the collected feedback to the server, which saves it. This allows the user's feedback to be reflected in the next ending generation.

[1194] (Application example 2)

[1195] 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."

[1196] In conventional storytelling systems, the ending is fixed, making it difficult to provide a new experience when revisiting the same story. Furthermore, because the ending is generated without taking into account the user's emotions or feedback, it is limited in providing individually personalized stories. This leads to user boredom and reduces the value of replaying the story.

[1197] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1198] In this invention, the server includes means for downloading the basic story to the user terminal, means for transmitting the generated ending to the user terminal, means for generating a different ending each time using a generation AI, means for collecting feedback from the user, means for saving the collected feedback and reflecting it in generating the next ending, means for collecting the user's facial expressions and voice to recognize the user's emotions, and means for analyzing the collected emotional data and reflecting it in generating the ending. This makes it possible to generate a different, personalized ending each time based on the user's emotions and feedback, providing a new reading experience.

[1199] The "basic story" is the main flow and structure of the story, and is the content that the user views first.

[1200] A "user terminal" is an electronic device that a user operates to view information.

[1201] A "generated ending" is the conclusion of a story created by a generative AI.

[1202] "Generative AI" is a system that generates text and data using artificial intelligence technology.

[1203] "Feedback" refers to information such as impressions, evaluations, and opinions collected from users.

[1204] "Emotion data" is emotional information collected from the user's facial expressions and voice.

[1205] "Personalization" means tailoring content to the interests and circumstances of individual users.

[1206] "Filtering" refers to the process of selecting content so that the generated ending remains consistent with the basic story.

[1207] The present invention provides a system that downloads a basic story and generates a different ending each time based on emotional data and feedback, in order to provide a new reading experience to the user. Specific embodiments for carrying out the present invention will be described below.

[1208] 1. Download the basic story

[1209] The server stores basic stories and provides a means for downloading them to user devices. A user selects a basic story through a device such as smart glasses, and the story is downloaded to the device. For example, if a user selects a picture book titled "Adventure Forest," the basic story is downloaded.

[1210] 2. Generating the ending

[1211] As the user reads the basic story, the device sends a request to the server when it's time to generate an ending. The server's AI analyzes this request, the story's context information, and past feedback data to generate a new ending.

[1212] 3. Emotional Data Collection and Analysis

[1213] The user device (such as smart glasses) uses a camera and microphone to collect the user's facial expressions and voice. This emotional data is sent to the emotion engine for analysis. The results of this analysis are reflected in the ending generation process. For example, if the user is enjoying the story, the ending will be more positive.

[1214] 4. Sending and displaying the ending

[1215] The generated ending is sent from the server to the user's device. The device displays the received ending to the user. This ending is filtered to maintain consistency with the basic story. For example, an ending may be generated in which the children find a magical lake deep in the forest and are saved by a lake fairy.

[1216] 5. Gather and incorporate feedback

[1217] After the user finishes reading the story, the device displays a feedback screen to collect the user's thoughts and opinions. The device then sends this feedback to the server, which then reflects it in the generation of the next ending. This allows for a personalized experience for each user.

[1218] Examples and prompts

[1219] For example, in the story "Adventure Forest," children discover a magical lake, but the ending that awaits them is different each time. An example of a prompt sentence in this case would be, "The children enter the adventure forest and encounter one mysterious event after another. They eventually reach the magical lake, but the ending that awaits them is..."

[1220] This invention uses libraries such as OpenCV to perform facial expression analysis, and a Python program to realize data communication and processing between the server and the device. Furthermore, it uses a generative AI model (e.g., GPT-3) to generate text in real time. In this way, it is possible to provide users with a new storytelling experience.

[1221] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1222] Step 1:

[1223] The server stores the basic stories and provides a means for downloading them to user terminals.

[1224] Input: A request for a selected story from the user

[1225] Data processing: The server reads the story and converts it into a data format for sending to the device.

[1226] Output: Reformatted basic story

[1227] Specific operation: The user selects "Adventure Forest" using the smart glasses, and the request is sent to the server. The server prepares the basic story for download and sends it to the user's device.

[1228] Step 2:

[1229] The terminal displays the basic story to the user and allows the user to read through the story.

[1230] Input: Downloaded base story

[1231] Data processing: Converting story data into a format suitable for display on the user screen.

[1232] Output: The basic story shown on the display

[1233] Specific behavior: The device displays the downloaded story and the user reads it. Example: "A story about children who get lost and meet various characters."

[1234] Step 3:

[1235] The terminal sends a request to the server when it is time to generate the ending.

[1236] Input: Current story progress

[1237] Data calculation: Generates data to send an ending generation request to the server based on the progress

[1238] Output: Ending generation request data

[1239] Specific operation: As the story progresses and approaches its climax, the device sends a request to the server to generate an ending.

[1240] Step 4:

[1241] The server generates new endings using a generation AI.

[1242] Input: Ending generation request, story context, past feedback data

[1243] Data computation: Generate new endings using generative AI (e.g., GPT-3)

[1244] Output: The generated ending text

[1245] How it works: The server's generation AI generates a new ending based on the "Forest of Adventure" and past feedback, such as "The children find a magical lake deep in the forest."

[1246] Step 5:

[1247] The device collects the user's facial expressions and voice and sends them to the emotion engine.

[1248] Input: User's facial expressions and voice data

[1249] Data processing: Collect data using the camera and microphone and send it to the emotion engine

[1250] Output: Emotion data for analysis

[1251] Specific operation: The device's camera and microphone collect the user's emotional state and send it to the emotion engine.

[1252] Step 6:

[1253] The emotion engine analyzes the emotion data and sends it to the server.

[1254] Input: User's facial expressions and voice data

[1255] Data Computing: Identifying emotional states using emotion data analysis algorithms

[1256] Output: Parsed emotion information

[1257] Specific operation: The emotion engine analyzes emotional information such as "the user is having fun" or "the user is excited" and sends this to the server.

[1258] Step 7:

[1259] The server fine-tunes the ending based on the analyzed emotional data.

[1260] Input: Analyzed emotion information, generated ending

[1261] Data calculation: Adjusting the ending text based on emotional information

[1262] Output: Emotionally tweaked ending

[1263] Specific operation: The server generates a positive ending that reflects the "enjoying" state based on emotional data.

[1264] Step 8:

[1265] The server transmits the filtered ending to the user terminal.

[1266] Input: Tweaked ending

[1267] Data calculations: checking consistency with the basic story and filtering

[1268] Output: Filtered ending

[1269] Specific operation: The server uses a recognition engine to check the consistency of the ending and sends it to the device.

[1270] Step 9:

[1271] The terminal displays the filtered ending to the user.

[1272] Input: Filtered ending

[1273] Data processing: converting the ending text into a suitable format for display to the user

[1274] Output: The ending displayed on the user's device display

[1275] Specific action: The device displays the ending "The children find a magical lake deep in the forest and are saved by the lake fairy."

[1276] Step 10:

[1277] The terminal collects feedback from the user and transmits it to the server.

[1278] Input: User feedback

[1279] Data processing: Converting user-entered feedback into data format

[1280] Output: Feedback data sent to the server

[1281] Specific operation: The device displays a feedback screen for the user to enter their thoughts and opinions, and the collected feedback data is sent to the server and stored.

[1282] 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.

[1283] 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.

[1284] 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.

[1285] [Fourth embodiment]

[1286] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1287] 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.

[1288] 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).

[1289] 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.

[1290] 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.

[1291] 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).

[1292] 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.

[1293] 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.

[1294] 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.

[1295] 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.

[1296] 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.

[1297] 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.

[1298] 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."

[1299] The present invention is a system that downloads a basic story to a user's device, generates a different ending each time using a generation AI, and sends the generated ending to the user's device. The system also includes a means for collecting feedback from users and reflecting that feedback in generating the next ending.

[1300] System configuration

[1301] 1. Providing a basic story

[1302] The server stores the basic storyline for a particular picture book application and provides the basic story upon request from the user.

[1303] The terminal requests the basic story of the picture book selected by the user from the server and displays the downloaded basic story to the user.

[1304] 2. Generating the ending

[1305] After reading the basic story, the device sends a request to the server to generate a new ending when it approaches the ending.

[1306] The server's generation AI analyzes the request and the contextual information of the story, and generates a new ending based on that.

[1307] 3. Sending and displaying the ending

[1308] The server filters the generated endings to check whether they are consistent with the basic story and appropriate for the user's age and interests. Endings that pass the filter are sent to the device.

[1309] The terminal displays the received ending to the user as a continuation of the story.

[1310] 4. Gather and incorporate feedback

[1311] After the user has finished reading the picture book, the device displays a feedback screen where the user can enter their thoughts and opinions.

[1312] The terminal sends this collected feedback to the server, which then reflects this feedback in generating subsequent endings.

[1313] Specific examples

[1314] Scenario: "Forest of Adventure"

[1315] 1. User Access

[1316] A parent and child launch the app on a tablet and select a picture book titled "Adventure Forest." The device then notifies the server of the selection.

[1317] 2. Loading the Basic Story

[1318] The server sends the basic story of "Adventure Forest" to the device, such as a story about children getting lost and meeting various characters.

[1319] The device displays the downloaded basic story to the parent and child.

[1320] 3. Ending Generation Request

[1321] When the forest adventure reaches its climax, the device sends a request to the server to generate a new ending.

[1322] 4. Processing and sending the generated AI

[1323] The server's generation AI analyzes the context information and generates a new ending, such as "The children find a magical lake deep in the forest and are saved by a lake fairy."

[1324] This ending is filtered and then sent to the terminal.

[1325] The device will display this new ending to the parent and child.

[1326] 5. Gathering Feedback

[1327] After finishing reading the picture book, the device displays a feedback screen where parents and children can enter their impressions and opinions.

[1328] The device sends the collected feedback to the server, which then reflects it in the next ending generation.

[1329] With this type of structure and operation, a system allows parents and children to enjoy a different ending every night, continuously stimulating children's interest and curiosity.

[1330] The processing flow will be explained below.

[1331] Step 1:

[1332] The user launches the picture book app on their device, and the app interface is displayed on the device.

[1333] Step 2:

[1334] The user selects the picture book they want to read from the list of picture books in the app. After selection, the device requests the basic story of the selected picture book from the server.

[1335] Step 3:

[1336] The server receives the request for the selected picture book and sends the corresponding basic story data to the device. The data sent is in JSON format.

[1337] Step 4:

[1338] The device parses the received basic story and displays it to the user in an easy-to-read format, for example, by displaying the story page by page.

[1339] Step 5:

[1340] As the user reads through the basic story and approaches the ending, the device sends a request to the server to generate a new ending.

[1341] Step 6:

[1342] The server receives a request to generate an ending and analyzes the story's context information (basic story content).

[1343] Step 7:

[1344] The server-based AI generates a new ending based on the analyzed context information, taking into account past feedback data.

[1345] Step 8:

[1346] The generated endings go through a filtering process where the server checks whether the endings are consistent with the underlying storyline and appropriate for the user's age and interests.

[1347] Step 9:

[1348] The filtered ending is sent from the server to the device, and the data sent is properly formatted.

[1349] Step 10:

[1350] The device displays the ending it has received to the user. The ending is displayed as a continuation of the basic story, so it is positioned so that it does not feel out of place.

[1351] Step 11:

[1352] After the user finishes reading the picture book, the device displays a feedback screen where the user can enter their impressions and opinions.

[1353] Step 12:

[1354] When the user inputs feedback and presses the send button, the terminal transmits the feedback data to the server.

[1355] Step 13:

[1356] The server stores the received feedback data and reflects it in the ending generation process from the next time onwards. The feedback may be incorporated into the generation AI model as a re-learning process.

[1357] Example 1

[1358] 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."

[1359] Conventional story delivery systems often repeat the same ending, making it difficult to sustain user interest. Furthermore, they lack the ability to reflect user feedback, making it difficult to provide endings that are appropriate for each individual user. Furthermore, the consistency and personalization of the generated endings remain issues.

[1360] 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.

[1361] In this invention, the server includes a means for downloading the basic story to the user terminal, a means for transmitting the generated ending to the user terminal, and a means for generating a different ending each time using a generation AI. This makes it possible to provide a different ending for each user and maintain the user's interest. The server also includes a means for collecting feedback from the user and reflecting this in the next ending generation, a means for filtering the generated ending to ensure consistency with the basic story, a means for personalizing the content of the generated ending based on the user's interests and age, a means in the user terminal for transmitting an ending generation request to the server, and a means for inputting a prompt sentence into the generation AI model. This makes it possible to provide a high-quality, personalized ending that reflects the feedback.

[1362] The "basic story" refers to the main parts of the original story provided to the user, such as the prologue and middle chapters, and includes the story parts excluding the ending.

[1363] "User terminal" refers to a computing device used by a user, and specifically includes tablets, smartphones, personal computers, etc.

[1364] "Generated ending" refers to one of several different endings generated by the generation AI as the conclusion of the basic story.

[1365] "Generative AI" refers to algorithms or programs that use artificial intelligence techniques to generate new sentences or story structures based on input data.

[1366] "Feedback" refers to opinions and impressions provided by users after use, and specifically includes written comments and evaluations.

[1367] "Filtering" refers to the process of reviewing the content of the generated endings and determining whether they are appropriate according to certain criteria.

[1368] "Personalization" refers to the process of tailoring content to a user based on individual information such as the user's interests or age.

[1369] An "ending generation request" refers to a message sent from a user terminal to a server requesting the generation of a new ending.

[1370] "Generative AI model" refers to a model trained to perform a specific task using artificial intelligence algorithms, and specifically includes natural language generation models.

[1371] A "prompt sentence" is a portion of text that is input to a generative AI model and contains the information that forms the basis of the generated output.

[1372] The system of the present invention downloads a basic story to a user's device, generates a different ending each time using a generation AI, and sends the generated ending to the user's device. This system also includes a function to collect feedback from users and reflect it in the generation of the next ending.

[1373] System Configuration

[1374] server:

[1375] The server stores the basic story and provides it in response to user requests. The server is equipped with a generative AI that generates new endings based on ending generation requests. It also stores collected feedback and reflects it in the next ending generation. Specific generative AI models that can be used include OpenAI's ChatGPT.

[1376] User device:

[1377] A user terminal is a computing device such as a tablet or smartphone. The user terminal requests the basic story of a picture book selected by the user from the server and displays the downloaded basic story to the user. When the story reaches its ending, the user terminal also sends a request to the server to generate an ending, receives the generated ending, and displays it to the user. The user terminal is also used to collect feedback.

[1378] Hardware and software used

[1379] Server: A high performance computing device or cloud server

[1380] Generative AI models: such as OpenAI's ChatGPT

[1381] User devices: tablets, smartphones, computers

[1382] Data processing and calculation

[1383] The server retrieves the basic story from the database and sends it to the user's device. The generative AI model generates a new ending based on the input prompt. This generation process uses a natural language generation algorithm to output an appropriate ending based on context information.

[1384] The user terminal displays the received basic story and the generated ending to the user, and transmits the user's feedback to the server.

[1385] Specific examples

[1386] Scenario: "Forest of Adventure"

[1387] 1. User Access:

[1388] A parent and child launch the app on a tablet and select a picture book titled "Adventure Forest." The device then notifies the server of the selection.

[1389] 2. Load the basic story:

[1390] The server sends the basic story of "Adventure Forest" to the device, such as a story about children getting lost and meeting various characters.

[1391] The device displays the downloaded basic story to the parent and child.

[1392] 3. Ending Generation Request:

[1393] When the forest adventure reaches its climax, the device sends a request to the server to generate a new ending.

[1394] 4. Processing and sending the generated AI:

[1395] The server's generation AI analyzes the context information and generates a new ending, such as "The children find a magical lake deep in the forest and are saved by a lake fairy."

[1396] This ending is filtered and then sent to the terminal.

[1397] The device will display this new ending to the parent and child.

[1398] 5. Gathering Feedback:

[1399] After finishing reading the picture book, the device displays a feedback screen where parents and children can enter their impressions and opinions.

[1400] The device sends the collected feedback to the server, which then reflects it in the next ending generation.

[1401] Prompt Sentence Examples

[1402] An example of a prompt used to generate an ending is the text, "In the basic story, the children get lost deep in the forest. What happens next?" Based on this prompt, the generative AI model generates a new ending.

[1403] The above is an embodiment of the present invention. This system allows the user to enjoy a new ending every time, and can maintain the user's interest and curiosity.

[1404] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1405] Step 1:

[1406] User selection of picture book and request submission

[1407] The user launches a dedicated picture book app using a tablet or smartphone and selects the title of the picture book they want to read. The device sends this selection information to the server as a request. This request includes the picture book title and user ID. The input is the user's selection information, and the output is a request including the picture book title and user ID. Specifically, it sends an HTTP request to the server's API endpoint.

[1408] Step 2:

[1409] Get and send basic stories

[1410] The server receives the request and retrieves the basic story of the specified picture book from the database. It then sends the retrieved basic story to the device. The input is the request received in step 1, and the output is the basic story. Specifically, it executes a database query and returns the retrieved data to the device.

[1411] Step 3:

[1412] Viewing the Basic Story

[1413] The terminal displays the basic story received from the server to the user. The input is the basic story received from the server, and the output is the story displayed to the user. Specifically, the terminal renders the text and images of the basic story on the user interface.

[1414] Step 4:

[1415] Sending an ending generation request

[1416] As the user reads the basic story and approaches the ending, the device sends a request to the server to generate a new ending. The request includes the user's input data and story context information. The input is the context information of the story the user has read, and the output is a request to generate an ending. Specifically, the HTTP request is sent when an event is triggered by user operation.

[1417] Step 5:

[1418] Generating the ending

[1419] The server's generation AI analyzes the received request information and context information and inputs the prompt text into the generation AI model. The generation AI model (e.g., OpenAI's ChatGPT) generates a new ending based on this prompt text. The input is the prompt text, and the output is the generated ending. Specifically, the prompt text is sent to the API endpoint of the generation AI model, and the generated ending is obtained.

[1420] Step 6:

[1421] Filtering and sending endings

[1422] The server filters the generated endings to check whether they are consistent with the basic story and appropriate for the user's age and interests. The filtered endings are then sent to the device. The input is the generated ending, and the output is the filtered ending. Specifically, the server applies a rule-based filtering algorithm to check whether the ending matches the filter criteria.

[1423] Step 7:

[1424] Displaying the ending

[1425] The device displays the received ending to the user as a continuation of the story. The input is the filtered ending, and the output is the ending displayed to the user. Specifically, it renders the ending text and images on the user interface.

[1426] Step 8:

[1427] Gathering feedback

[1428] After finishing reading the picture book, the device displays a feedback screen for users to enter their thoughts and opinions. The user enters their feedback, and the device sends it to the server. The input is the user's feedback, and the output is the feedback sent to the server. Specifically, the device displays an input form on the user interface and sends the user's input to the server's API endpoint.

[1429] Step 9:

[1430] Reflecting feedback

[1431] The server reflects the received feedback in the next ending generation. The input is the user's feedback, and the output is the ending generation process that reflects the feedback. Specific operations include adding the feedback information to the training data of the generative AI model and adjusting the generation rules.

[1432] (Application example 1)

[1433] 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."

[1434] Conventional story delivery systems have the problem that once a user finishes reading a story, the story loses its freshness. Stories that have been read once are rarely read again, making it difficult to sustain the user's interest and curiosity. In addition, there is a lack of a mechanism for utilizing user feedback to evolve the story, and personalization for each individual user is not adequately implemented.

[1435] 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.

[1436] In this invention, the server includes means for downloading the basic story to the user terminal, means for transmitting the generated ending to the user terminal, means for generating a different ending each time using a generation AI, means for collecting feedback from the user, means for saving the collected feedback and reflecting it in the next ending generation, means for transmitting the generated ending to the user terminal after passing through the server's filtering, means for transmitting context information for ending generation from the user terminal to the server, and means for personalizing the ending based on the user's interests and age. This allows the user to enjoy a fresh and interesting story each time, and makes it possible to personalize the ending based on the user's feedback.

[1437] The "base story" refers to the main plot or storyline that forms the basis of the story, and is the initial introduction that gets users started reading the story.

[1438] A "user terminal" is an electronic device used by a user to read a story, including a smartphone, tablet, or PC.

[1439] A "generated ending" is a different story ending each time created using generative AI, providing users with new surprises.

[1440] The term "means" refers to a method or apparatus for achieving a specific purpose, and is a component for realizing each function in this invention.

[1441] "Generative AI" is a system that uses artificial intelligence technology to generate text and story content, and is used to generate endings.

[1442] "Feedback" refers to opinions and impressions collected from users, and is information that can be used to generate the next ending.

[1443] A "server" is a computer system that provides data over a network and returns responses in response to user requests.

[1444] "Filtering" is a process to ensure that the generated ending is consistent with the basic story and appropriate for the user's interests and age.

[1445] "Contextual information" refers to information such as the story's progress, setting, and character background, and is an element necessary for generating an ending.

[1446] "Personalization" is the process of customizing an ending based on a particular user's interests and age.

[1447] This invention is a story provision system that provides a new ending to the user each time, and is realized using a server, terminals, and generation AI. The main components include providing the basic story, generating and displaying endings, and collecting and incorporating feedback.

[1448] Providing the basic story

[1449] The server stores the basic story and sends it to the device in response to a user request. The specific software used is a RESTful API, and the basic story is sent in JSON format via an HTTP request.

[1450] Ending generation and display

[1451] After reading the basic story, when the device approaches the ending, it sends a request to the server to generate a new ending. Specifically, the request, including contextual information, is sent to the server via a RESTful API. On the server, a generative AI model analyzes this request and generates a new ending.

[1452] The generated endings are filtered on the server to ensure consistency with the basic story and suitability for the user's interests and age. This filtering uses natural language processing technology and rule-based algorithms. Endings that pass the filtering are sent to the device and displayed to the user.

[1453] Gathering and implementing feedback

[1454] After the user finishes reading the story, the device provides a feedback screen to collect the user's impressions and opinions. The collected feedback is sent back to the server and reflected in the next ending generation. For this purpose, the feedback data is stored in a database and used as training data for the generation AI model.

[1455] Specific examples

[1456] For example, if a user selects the basic story "Adventure Library" and reads it, a new ending will be generated at the climax. One example of a generated ending is a story in which the protagonists interact with an ancient book and discover hidden knowledge.

[1457] Prompt Sentence Examples

[1458] Use this example prompt to have a generative AI model generate a new ending.

[1459] "Our heroes arrive at an old library and find an ancient book. They open it in search of ancient knowledge."

[1460] User Interests: Adventure, Fantasy

[1461] This system allows users to experience a new ending every time, allowing for a more personalized narrative experience that incorporates feedback.

[1462] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1463] Step 1:

[1464] The server stores basic stories and receives requests from user devices. The device sends a request for a basic story to the server along with a specific story ID. This request is made via a RESTful API, and the data format is JSON. After receiving the request, the server retrieves the corresponding basic story from the database and responds to the device in JSON format. The device then retrieves the basic story and displays it to the user.

[1465] Step 2:

[1466] The device displays the basic story to the user, and when the story reaches its climax, it sends a request to the server to generate a new ending. This request includes current context information (such as the progress of the basic story and character backgrounds). The request data from the device is again in JSON format.

[1467] Step 3:

[1468] The server analyzes the contextual information received from the device and inputs it into a generative AI model. The generative AI model uses natural language processing technology to generate a new ending. This process takes into account the contextual information and data such as the user's interests and age. The generative AI model generates an ending based on the contextual information and returns the generated result to the server in JSON format.

[1469] Step 4:

[1470] The server then filters the generated endings to ensure they maintain consistency with the basic story and are appropriate for the user's interests and age. Endings that pass the filtering process are then sent back to the device in JSON format. Rule-based algorithms and natural language processing techniques are used for filtering.

[1471] Step 5:

[1472] The terminal receives the generated ending sent from the server and displays it to the user, allowing the user to enjoy the newly generated ending.

[1473] Step 6:

[1474] After the user finishes reading the story, the device displays a feedback screen to collect the user's thoughts and opinions, which are then sent to the server in JSON format and stored in a database.

[1475] Step 7:

[1476] The server analyzes the collected feedback data and reflects it in the next ending generation. Specifically, the feedback data is used as training data for the generation AI model. This allows the generated endings to continue evolving based on user preferences.

[1477] This process allows users to enjoy a new ending every time, providing a more personalized narrative experience that reflects their feedback.

[1478] 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.

[1479] The present invention is a system that downloads a basic story to a user's device, generates a different ending each time using a generation AI, and sends the generated ending to the user's device. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system also incorporates the user's emotional data into the ending generation. The system also includes a means for collecting feedback from the user and reflecting that feedback in the next ending generation.

[1480] System configuration

[1481] 1. Providing a basic story

[1482] The server stores the basic storyline for a particular picture book application and provides the basic story upon request from the user.

[1483] The terminal requests the basic story of the picture book selected by the user from the server and displays the downloaded basic story to the user.

[1484] 2. Generating the ending

[1485] After reading the basic story, the device sends a request to the server to generate a new ending when it approaches the ending.

[1486] The server's generation AI analyzes the request, contextual information about the story, and past feedback data, and generates a new ending based on that.

[1487] 3. Emotion Recognition by Emotion Engine

[1488] The device collects emotion data from the user's facial expressions and voice and sends it to the emotion engine.

[1489] The emotion engine analyzes the collected emotional data and reflects the results in the ending generation process.

[1490] 4. Sending and displaying the ending

[1491] The server filters the generated endings to check whether they are consistent with the basic story and appropriate for the user's age and interests. Endings that pass the filter are sent to the device.

[1492] The terminal displays the received ending to the user as a continuation of the story.

[1493] 5. Gather and incorporate feedback

[1494] After the user has finished reading the picture book, the terminal displays a feedback screen on which the user can input their impressions and opinions.

[1495] The device sends the collected feedback to the server, which then reflects it in generating the next and subsequent endings.

[1496] Specific examples

[1497] Scenario: "Forest of Adventure"

[1498] 1. User Access

[1499] A parent and child launch the app on a tablet and select a picture book titled "Adventure Forest." The device then notifies the server of the selection.

[1500] 2. Loading the Basic Story

[1501] The server sends the basic story of "Adventure Forest" to the device, such as a story about children getting lost and meeting various characters.

[1502] The device displays the downloaded basic story to the parent and child.

[1503] 3. Ending Generation Request

[1504] When the forest adventure reaches its climax, the device sends a request to the server to generate a new ending.

[1505] 4. Processing and sending the generated AI

[1506] The server's generation AI analyzes the context information and generates a new ending, such as "The children find a magical lake deep in the forest and are saved by a lake fairy."

[1507] This ending is filtered and then sent to the terminal.

[1508] The device will display this new ending to the parent and child.

[1509] 5. Emotion Recognition by Emotion Engine

[1510] The device collects emotional data from the parent and child's facial expressions and voices, for example, using a camera or microphone.

[1511] The emotion engine analyzes this emotional data and obtains information such as "the child is having fun" or "the parent is excited." This information is reflected in the generation of the next ending.

[1512] 6. Gathering Feedback

[1513] After finishing reading the picture book, the device displays a feedback screen where parents and children can enter their thoughts and opinions.

[1514] The terminal sends the collected feedback to the server, which stores it and uses it to generate the next ending.

[1515] This system allows the user's emotional data and feedback to be reflected in the ending generation, enabling more personalized and engaging storytelling for the user.

[1516] The processing flow will be explained below.

[1517] Specific processing steps of the system based on the embodiment for implementing the invention

[1518] Step 1:

[1519] The user launches the picture book app on their device, and the app interface appears on the device screen.

[1520] Step 2:

[1521] The user selects the picture book they want to read from the list of picture books in the app. After selection, the device requests the basic story of the selected picture book from the server.

[1522] Step 3:

[1523] The server receives a request for the selected picture book and sends the corresponding basic story data in JSON format to the terminal.

[1524] Step 4:

[1525] The device analyzes the basic story it receives and displays it to the user in an easy-to-read format, page by page.

[1526] Step 5:

[1527] As the user reads the basic story, the device collects the user's facial expressions and voice and sends this data to the emotion engine.

[1528] Step 6:

[1529] The emotion engine analyzes the user's facial expression data and voice data sent from the device and determines the user's emotional state (e.g., happy, excited, surprised, etc.).

[1530] Step 7:

[1531] When the user reaches the end of the basic story, the device sends a request to the server to generate a new ending, and at the same time, emotion data from the emotion engine is also sent to the server.

[1532] Step 8:

[1533] The server's generation AI analyzes the basic story's contextual information, past feedback data, and emotional data, and generates a new ending based on that.

[1534] Step 9:

[1535] The generated endings go through a filtering process where the server checks whether the endings are consistent with the underlying storyline and appropriate for the user's age and interests.

[1536] Step 10:

[1537] The filtered ending is sent from the server to the device, and the data sent is properly formatted.

[1538] Step 11:

[1539] The device displays the ending it has received to the user. The ending is displayed as a continuation of the basic story, so it is positioned so that it does not feel out of place.

[1540] Step 12:

[1541] After the user has finished reading the picture book, the device displays a feedback screen for the user to enter their impressions and opinions.

[1542] Step 13:

[1543] When the user inputs feedback and presses the send button, the terminal transmits the feedback data to the server.

[1544] Step 14:

[1545] The server stores the received feedback data and reflects it in the ending generation process from the next time onwards. The feedback may be incorporated into the generation AI model as a re-learning process.

[1546] Specific examples

[1547] Scenario: "Forest of Adventure"

[1548] Step 1:

[1549] A parent and child launch the app on a tablet and select a picture book titled "Adventure Forest." The device then notifies the server of the selection.

[1550] Step 2:

[1551] The server sends the basic story of "Adventure Forest" to the device, which then displays the downloaded basic story to the parent and child.

[1552] Step 3:

[1553] As the parent and child read, the device uses a camera and microphone to collect the user's facial expressions and voice.

[1554] Step 4:

[1555] The emotion engine analyzes the collected data and determines the user's emotional state, for example, determining "fun" based on smiles and tone of voice.

[1556] Step 5:

[1557] Just before the end of the basic story, the device sends a request to the server to generate a new ending. At the same time, emotion data from the emotion engine is also sent to the server.

[1558] Step 6:

[1559] The server's generation AI generates new endings based on the basic story content, past feedback, and emotional data.

[1560] Step 7:

[1561] The generated endings go through a filtering process to ensure consistency and appropriateness with the basic story.

[1562] Step 8:

[1563] The filtered ending is sent from the server to the terminal.

[1564] Step 9:

[1565] The device will then display the new ending to the parent and child, for example, "The children find a magical lake deep in the forest and are rescued by the lake fairy."

[1566] Step 10:

[1567] After the parent and child finish reading the picture book, the device displays a feedback screen where the parent and child can enter their thoughts and opinions.

[1568] Step 11:

[1569] The device sends the collected feedback to the server, which stores it and uses it to generate the next ending.

[1570] In this way, the user's emotional data and feedback are reflected in the ending generation, resulting in more personalized and engaging storytelling for the user.

[1571] Example 2

[1572] 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."

[1573] Conventional storytelling systems have had difficulty generating endings that reflect the user's needs and emotions. This has resulted in inconsistent or uninteresting endings that fail to increase user satisfaction. Furthermore, mechanisms for evolving the story by regenerating it based on effective use of user feedback have been inadequate, making it difficult to personalize the story to meet individual user needs.

[1574] 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.

[1575] In this invention, the server includes means for downloading the basic story to the user terminal, means for transmitting the generated ending to the user terminal, means for generating a different ending each time using a generation AI, means for collecting and analyzing emotional data from the user's facial expressions and voice, means for reflecting the collected emotional data in generating the next ending, means for collecting feedback from the user, and means for saving the collected feedback and reflecting it in generating the next ending. This makes it possible to provide a consistent, personalized ending that reflects the user's emotions and feedback.

[1576] "Base story" refers to the main plot or content of the story selected by the user.

[1577] A "user terminal" is an electronic device used by a user, and includes, for example, a tablet or smartphone.

[1578] "Generated ending" refers to the conclusion of a story generated by the generation AI based on the basic story.

[1579] "Generative AI" refers to technology that uses artificial intelligence to generate text or story endings.

[1580] "Emotion data" refers to information about emotions acquired from the user's facial expressions, voice, etc.

[1581] An "emotion engine" refers to a technology that analyzes emotional data and reflects the results in specific processing.

[1582] "Feedback" refers to the thoughts and opinions that users provide after reading a story.

[1583] "Filtering means" refers to a method for evaluating the consistency and suitability of the generated endings and eliminating inappropriate content.

[1584] "Personalization" refers to the individual adjustment of content based on the user's interests and age.

[1585] This invention is a system that provides users with personalized endings. This system is based on a server and a user terminal, and by incorporating a generative AI and an emotion engine, it provides a more advanced user experience.

[1586] This system is configured as follows:

[1587] First, the server has a means for downloading basic stories to user terminals. The server transmits pre-stored basic storylines in response to requests from each user terminal. The user terminal receives the basic storylines and displays them to the user. For example, the story "Forest of Adventure" includes a basic story in which children get lost and meet various characters.

[1588] As the user reads the story and reaches the climax, the user device sends a request to the server to generate a new ending. The server receives this request and uses a generative AI model to generate a new ending. The generative AI model generates an ending based on the story's context information and past feedback data. For example, the following prompt might be used: "In the Adventure Forest, the children get lost. We've now reached the climax. What happens next?" Based on this prompt, the generative AI generates an ending in which "the children find a magical lake deep in the forest and are saved by the lake fairy."

[1589] Furthermore, the user device uses a camera and microphone to collect emotional data from the user's facial expressions and voice. The emotional data is sent to the emotion engine and analyzed. For example, information such as "the user is having fun" or "the parent is excited" can be obtained. This emotional data is reflected in the generation of the next ending.

[1590] The server filters the generated endings to check for consistency and suitability for the user's age and interests. The server then sends the endings that pass the filter to the user's device. The user's device displays the received ending to the user, allowing them to enjoy the continuation of the story.

[1591] After reading the story, the user's device displays a feedback screen, allowing the user to input their thoughts and opinions. The device sends the collected feedback to the server, which stores it and reflects it in the creation of the next ending. For example, a comment like "The ending was really interesting!" will influence the creation of future stories.

[1592] A system configured in this way allows users' emotional data and feedback to be reflected in the ending generation, making it possible to provide consistent and personalized endings.

[1593] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1594] Step 1:

[1595] The user selects a picture book. The user launches the picture book app and selects a title, for example, "Adventure Forest." The user's device notifies the server of this selection as input and waits for a response from the server.

[1596] Step 2:

[1597] The server provides the basic story. The server receives a request from the user's device and searches for the basic storyline of the relevant picture book. It processes this storyline and sends it to the user's device. The user's device displays the downloaded basic story as output to the user. For example, it may display a story about children who get lost and meet various characters.

[1598] Step 3:

[1599] The user reads the basic story. The user reads the story on a tablet or smartphone and reaches the climax.

[1600] Step 4:

[1601] The device sends a request to generate an ending. When the device recognizes that the user has reached the climax of the story, it sends a request to the server to generate a new ending.

[1602] Step 5:

[1603] The server generates the ending. The server receives the request and launches the generative AI model. Using the story's context information and past feedback data as input, it provides a prompt to the generative AI. For example, the prompt "In the Forest of Adventure, the children are lost. We're now reaching the climax. What happens next?" is input to the generative AI. The generative AI performs data calculations based on the input prompt, generates a new ending, and outputs it to the server. For example, the ending output is "The children find a magical lake deep in the forest and are saved by the lake fairy."

[1604] Step 6:

[1605] The device collects the user's emotional data. The device uses a camera and microphone to obtain emotional data from the user's facial expressions and voice. Specifically, the camera captures the user's facial expressions and the microphone records their voice tone. These data are sent as input to the emotion engine.

[1606] Step 7:

[1607] The emotion engine analyzes the emotion data. The emotion engine analyzes the input emotion data and outputs information such as "The user is having fun" or "The parent is excited." This output data is used to generate the next ending.

[1608] Step 8:

[1609] The server filters the endings. The server filters the generated endings to evaluate their consistency and suitability for the user's age and interests. The endings that pass this filtering are sent to the user's device as the final output.

[1610] Step 9:

[1611] The device displays the ending. The user device displays the received ending to the user as a continuation of the story. For example, the tablet screen may show an ending in which the children find a magical lake deep in the forest and are saved by a lake fairy.

[1612] Step 10:

[1613] The device collects feedback. After reading the story, the user's device displays a feedback screen, allowing the user to enter their thoughts and opinions.

[1614] Step 11:

[1615] The server saves the feedback and reflects it in the next ending. The device sends the collected feedback to the server, which saves it. This allows the user's feedback to be reflected in the next ending generation.

[1616] (Application example 2)

[1617] 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."

[1618] In conventional storytelling systems, the ending is fixed, making it difficult to provide a new experience when revisiting the same story. Furthermore, because the ending is generated without taking into account the user's emotions or feedback, it is limited in providing individually personalized stories. This leads to user boredom and reduces the value of replaying the story.

[1619] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1620] In this invention, the server includes means for downloading the basic story to the user terminal, means for transmitting the generated ending to the user terminal, means for generating a different ending each time using a generation AI, means for collecting feedback from the user, means for saving the collected feedback and reflecting it in generating the next ending, means for collecting the user's facial expressions and voice to recognize the user's emotions, and means for analyzing the collected emotional data and reflecting it in generating the ending. This makes it possible to generate a different, personalized ending each time based on the user's emotions and feedback, providing a new reading experience.

[1621] The "basic story" is the main flow and structure of the story, and is the content that the user views first.

[1622] A "user terminal" is an electronic device that a user operates to view information.

[1623] A "generated ending" is the conclusion of a story created by a generative AI.

[1624] "Generative AI" is a system that generates text and data using artificial intelligence technology.

[1625] "Feedback" refers to information such as impressions, evaluations, and opinions collected from users.

[1626] "Emotion data" is emotional information collected from the user's facial expressions and voice.

[1627] "Personalization" means tailoring content to the interests and circumstances of individual users.

[1628] "Filtering" refers to the process of selecting content so that the generated ending remains consistent with the basic story.

[1629] The present invention provides a system that downloads a basic story and generates a different ending each time based on emotional data and feedback, in order to provide a new reading experience to the user. Specific embodiments for carrying out the present invention will be described below.

[1630] 1. Download the basic story

[1631] The server stores basic stories and provides a means for downloading them to user devices. A user selects a basic story through a device such as smart glasses, and the story is downloaded to the device. For example, if a user selects a picture book titled "Adventure Forest," the basic story is downloaded.

[1632] 2. Generating the ending

[1633] As the user reads the basic story, the device sends a request to the server when it's time to generate an ending. The server's AI analyzes this request, the story's context information, and past feedback data to generate a new ending.

[1634] 3. Emotional Data Collection and Analysis

[1635] The user device (such as smart glasses) uses a camera and microphone to collect the user's facial expressions and voice. This emotional data is sent to the emotion engine for analysis. The results of this analysis are reflected in the ending generation process. For example, if the user is enjoying the story, the ending will be more positive.

[1636] 4. Sending and displaying the ending

[1637] The generated ending is sent from the server to the user's device. The device displays the received ending to the user. This ending is filtered to maintain consistency with the basic story. For example, an ending may be generated in which the children find a magical lake deep in the forest and are saved by a lake fairy.

[1638] 5. Gather and incorporate feedback

[1639] After the user finishes reading the story, the device displays a feedback screen to collect the user's thoughts and opinions. The device then sends this feedback to the server, which then reflects it in the generation of the next ending. This allows for a personalized experience for each user.

[1640] Examples and prompts

[1641] For example, in the story "Adventure Forest," children discover a magical lake, but the ending that awaits them is different each time. An example of a prompt sentence in this case would be, "The children enter the adventure forest and encounter one mysterious event after another. They eventually reach the magical lake, but the ending that awaits them is..."

[1642] This invention uses libraries such as OpenCV to perform facial expression analysis, and a Python program to realize data communication and processing between the server and the device. Furthermore, it uses a generative AI model (e.g., GPT-3) to generate text in real time. In this way, it is possible to provide users with a new storytelling experience.

[1643] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1644] Step 1:

[1645] The server stores the basic stories and provides a means for downloading them to user terminals.

[1646] Input: A request for a selected story from the user

[1647] Data processing: The server reads the story and converts it into a data format for sending to the device.

[1648] Output: Reformatted basic story

[1649] Specific operation: The user selects "Adventure Forest" using the smart glasses, and the request is sent to the server. The server prepares the basic story for download and sends it to the user's device.

[1650] Step 2:

[1651] The terminal displays the basic story to the user and allows the user to read through the story.

[1652] Input: Downloaded base story

[1653] Data processing: Converting story data into a format suitable for display on the user screen.

[1654] Output: The basic story shown on the display

[1655] Specific behavior: The device displays the downloaded story and the user reads it. Example: "A story about children who get lost and meet various characters."

[1656] Step 3:

[1657] The terminal sends a request to the server when it is time to generate the ending.

[1658] Input: Current story progress

[1659] Data calculation: Generates data to send an ending generation request to the server based on the progress

[1660] Output: Ending generation request data

[1661] Specific operation: As the story progresses and approaches its climax, the device sends a request to the server to generate an ending.

[1662] Step 4:

[1663] The server generates new endings using a generation AI.

[1664] Input: Ending generation request, story context, past feedback data

[1665] Data computation: Generate new endings using generative AI (e.g., GPT-3)

[1666] Output: The generated ending text

[1667] How it works: The server's generation AI generates a new ending based on the "Forest of Adventure" and past feedback, such as "The children find a magical lake deep in the forest."

[1668] Step 5:

[1669] The device collects the user's facial expressions and voice and sends them to the emotion engine.

[1670] Input: User's facial expressions and voice data

[1671] Data processing: Collect data using the camera and microphone and send it to the emotion engine

[1672] Output: Emotion data for analysis

[1673] Specific operation: The device's camera and microphone collect the user's emotional state and send it to the emotion engine.

[1674] Step 6:

[1675] The emotion engine analyzes the emotion data and sends it to the server.

[1676] Input: User's facial expressions and voice data

[1677] Data Computing: Identifying emotional states using emotion data analysis algorithms

[1678] Output: Parsed emotion information

[1679] Specific operation: The emotion engine analyzes emotional information such as "the user is having fun" or "the user is excited" and sends this to the server.

[1680] Step 7:

[1681] The server fine-tunes the ending based on the analyzed emotional data.

[1682] Input: Analyzed emotion information, generated ending

[1683] Data calculation: Adjusting the ending text based on emotional information

[1684] Output: Emotionally tweaked ending

[1685] Specific operation: The server generates a positive ending that reflects the "enjoying" state based on emotional data.

[1686] Step 8:

[1687] The server transmits the filtered ending to the user terminal.

[1688] Input: Tweaked ending

[1689] Data calculations: checking consistency with the basic story and filtering

[1690] Output: Filtered ending

[1691] Specific operation: The server uses a recognition engine to check the consistency of the ending and sends it to the device.

[1692] Step 9:

[1693] The terminal displays the filtered ending to the user.

[1694] Input: Filtered ending

[1695] Data processing: converting the ending text into a suitable format for display to the user

[1696] Output: The ending displayed on the user's device display

[1697] Specific action: The device displays the ending "The children find a magical lake deep in the forest and are saved by the lake fairy."

[1698] Step 10:

[1699] The terminal collects feedback from the user and transmits it to the server.

[1700] Input: User feedback

[1701] Data processing: Converting user-entered feedback into data format

[1702] Output: Feedback data sent to the server

[1703] Specific operation: The device displays a feedback screen for the user to enter their thoughts and opinions, and the collected feedback data is sent to the server and stored.

[1704] 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.

[1705] 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.

[1706] 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.

[1707] 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.

[1708] 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.

[1709] 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.

[1710] 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).

[1711] 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.

[1712] 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."

[1713] 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.

[1714] 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).

[1715] 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.

[1716] 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.

[1717] 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.

[1718] 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.

[1719] 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.

[1720] 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.

[1721] 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.

[1722] 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.

[1723] 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.

[1724] 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.

[1725] The following is further disclosed regarding the above embodiment.

[1726] (Claim 1)

[1727] A means for downloading the basic story to the user's device;

[1728] means for transmitting the generated ending to a user terminal;

[1729] A means to generate a different ending each time using generation AI,

[1730] a means for collecting feedback from users;

[1731] The system includes a means to store the collected feedback and reflect it in the next ending generation.

[1732] (Claim 2)

[1733] 10. The system of claim 1, further comprising filtering means for maintaining consistency between the base story and the generated ending.

[1734] (Claim 3)

[1735] 10. The system of claim 1, further comprising means for personalizing the content of the generated ending based on the user's interests and age.

[1736] "Example 1"

[1737] (Claim 1)

[1738] A means for downloading the basic story to the user's device;

[1739] means for transmitting the generated ending to a user terminal;

[1740] A means to generate a different ending each time using generation AI,

[1741] a means for collecting feedback from users;

[1742] A means to store the collected feedback and reflect it in the next ending generation,

[1743] A way to filter the generated endings and make them consistent with the base story,

[1744] means for personalizing the content of the generated ending based on the user's interests and age;

[1745] A means in a user terminal for transmitting an ending generation request to a server;

[1746] A system including a means for inputting a prompt sentence to a generative AI model.

[1747] (Claim 2)

[1748] 10. The system of claim 1, further comprising filtering means for maintaining consistency between the base story and the generated ending.

[1749] (Claim 3)

[1750] 10. The system of claim 1, further comprising means for personalizing the content of the generated ending based on the user's interests and age.

[1751] "Application Example 1"

[1752] (Claim 1)

[1753] A means for downloading the basic story to the user's device;

[1754] means for transmitting the generated ending to a user terminal;

[1755] A means to generate a different ending each time using generation AI,

[1756] a means for collecting feedback from users;

[1757] A means to store the collected feedback and reflect it in the next ending generation,

[1758] A means for transmitting the generated ending to a user terminal after passing through filtering by the server;

[1759] means for transmitting context information for generating an ending from a user terminal to a server;

[1760] A way to personalize the ending based on the user's interests and age

[1761] A system including:

[1762] (Claim 2)

[1763] 10. The system of claim 1, further comprising filtering means for maintaining consistency between the base story and the generated ending.

[1764] (Claim 3)

[1765] 10. The system of claim 1, further comprising means for transmitting a request on the user terminal to generate a new ending when the climax of the basic story is reached.

[1766] "Example 2: Combining Emotion Engines"

[1767] (Claim 1)

[1768] A means for downloading the basic story to the user's device;

[1769] means for transmitting the generated ending to a user terminal;

[1770] A means to generate a different ending each time using generation AI,

[1771] A means for collecting and analyzing emotion data from a user's facial expressions and voice;

[1772] A method to reflect the collected emotional data in the next ending generation,

[1773] a means for collecting feedback from users;

[1774] The system includes a means to store the collected feedback and reflect it in the next ending generation.

[1775] (Claim 2)

[1776] 10. The system of claim 1, further comprising filtering means for maintaining consistency between the base story and the generated ending.

[1777] (Claim 3)

[1778] 10. The system of claim 1, further comprising means for personalizing the content of the generated ending based on the user's interests and age.

[1779] "Application example 2 when combining emotion engines"

[1780] (Claim 1)

[1781] A means for downloading the basic story to the user's device;

[1782] means for transmitting the generated ending to a user terminal;

[1783] A means to generate a different ending each time using generation AI,

[1784] a means for collecting feedback from users;

[1785] A means to store the collected feedback and reflect it in the next ending generation,

[1786] A means for collecting facial expressions and voices of a user to recognize the user's emotions;

[1787] A system that includes a means for analyzing collected emotional data and reflecting it in ending generation.

[1788] (Claim 2)

[1789] 10. The system of claim 1, further comprising filtering means for maintaining consistency between the base story and the generated ending.

[1790] (Claim 3)

[1791] 10. The system of claim 1, further comprising means for personalizing the content of the generated ending based on the user's interests and age. [Explanation of symbols]

[1792] 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. A means for downloading the basic story to the user's device; means for transmitting the generated ending to a user terminal; A means to generate a different ending each time using generation AI, a means for collecting feedback from users; The system includes a means to store the collected feedback and reflect it in the next ending generation.

2. 10. The system of claim 1, further comprising filtering means for maintaining consistency between the master story and the generated ending.

3. 10. The system of claim 1, further comprising means for personalizing the content of the generated ending based on the user's interests and age.

Images