system

Abstract

Provide a system. 【Solution means】 Means for receiving a plurality of image information, Analysis means for extracting data from the received image information, Means for receiving and analyzing character information in natural language form, Means for generating a story based on the image information and the character information, Means for creating a visual effect according to the generated story, Means for generating and presenting the visual effect, Means for sharing the visual effect with the user via a dedicated terminal, A system including the above.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] Recording memories and personal episodes as visual animations without requiring specialized skills is difficult for many people. Conventional methods require advanced design techniques and knowledge of video editing, and the procedures are complicated and time-consuming, so they are not easily available to general users. In addition, there is also a lack of specialized means for automatically generating stories from photos and texts and creating relevant animations. Therefore, there is a need for an efficient technology for easily and vividly reproducing and storing individual memories.

Means for Solving the Problems

[0005] This invention provides a system for receiving and analyzing multiple image data and associated text data. This system uses an image recognition module to extract features from the image data and performs natural language processing on the text data to identify emotions and events. This allows the system to generate a narrative based on the images and text, and automatically generate animations corresponding to that narrative. Furthermore, the generated animations are presented to the user's device and provided in a shareable format. These means enable users to animate their memories without requiring specialized knowledge.

[0006] "Image data" refers to visual information recorded in still image format, such as JPEG and PNG formats.

[0007] "Analysis means" refers to a function or process for processing input data and extracting structured information.

[0008] "Natural language text data" refers to written information in a language that humans normally use, and is provided as a story or episode.

[0009] "Means of generating narratives" refers to the process or function of constructing a consistent scenario or storyline based on analyzed data.

[0010] "Means of creating animation" refers to the process or function for producing visual and dynamic content based on a generated narrative.

[0011] "Animation data" refers to information that is visually and dynamically represented, and is usually stored or distributed in video format.

[0012] An "image recognition module" refers to a technology or algorithm for detecting and identifying specific features from image data.

[0013] "Sentiment analysis" refers to natural language processing techniques used to identify and classify emotions contained in text data. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0017] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

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

[0024] As shown in Figure 1, the 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 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0031] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the 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 processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention relates to a system that receives multiple image data and natural language text data provided by a user, analyzes them to generate a consistent narrative, and creates an animation based on that narrative. This system consists of a user, a server, and a terminal.

[0036] First, the user uses a device to input multiple image files and story text through a dedicated application or web interface. The device then organizes the photos selected by the user and sends the input text to the server.

[0037] Next, the server analyzes the received data. For image data, it initializes an image recognition module and extracts features such as people, landscapes, and objects from each image. This image recognition process identifies important elements in the images being analyzed. For text data, a natural language processing engine is used for analysis, and keywords and overall sentiment are extracted.

[0038] Once the analysis is complete, the server uses a story generation module to construct a storyline based on the image and text analysis results. This module determines the main scenes and plot developments of the story according to the order of the data provided by the user. It also incorporates the sentiment analysis results of the text to set an appropriate emotional tone for each scene.

[0039] The server then activates an animation generation engine based on the generated story. This engine automatically generates character visuals and backgrounds from images and constructs scenes based on templates. Appropriate music and sound effects are selected from the sound library, enriching the animation experience.

[0040] Finally, the generated animation data is converted into a video format, and the server sends this data to the user's device. The user can not only watch this animation on their device but also easily share it with friends and family.

[0041] As a concrete example, consider a scenario where a user inputs several family travel photos and the accompanying text, "A fun memory from a family trip three summers ago." In this case, the server animates the travel scenes based on the scenery and people captured in the photos. As a result, an emotionally rich animation is generated in which the family members during the trip come alive as characters. This animation is enhanced with music and backgrounds that evoke the atmosphere of that summer. This allows users to visually recreate their memories without using specialized software.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] Users select and upload multiple image files and associated text data using a dedicated application or web interface via their device. Users choose photos related to memories, enter an episode, and press the submit button.

[0045] Step 2:

[0046] The server receives image data and text data sent by the user. The received data is converted into an appropriate format for the analysis process.

[0047] Step 3:

[0048] The server activates the image recognition module and analyzes the image data. It performs tasks such as facial recognition of people, identification of objects, and identification of landscapes, and extracts features from each image.

[0049] Step 4:

[0050] The server uses a natural language processing engine to analyze text data. This involves keyword extraction, sentiment analysis, and contextual analysis to identify the information necessary for story generation.

[0051] Step 5:

[0052] The server uses a story generation module to construct a storyline based on the analyzed image and text data. It evaluates the relationship between images and text to design the sequence of scenes and the emotional flow.

[0053] Step 6:

[0054] The server starts the animation generation engine and creates animations according to the storyline. It automatically generates character visuals and scene backgrounds, and produces dynamic content based on templates.

[0055] Step 7:

[0056] The server selects music and sound effects and incorporates them into the animation. Using an audio library, it chooses music and effects appropriate for the scene and places them on the timeline to fit.

[0057] Step 8:

[0058] The server converts the completed animation data into a video format and generates a downloadable link for the user's device.

[0059] Step 9:

[0060] Users receive a link from the server via their device and watch the animation by downloading or streaming it. Users can then play this animation on their own devices and share it with family and friends.

[0061] (Example 1)

[0062] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0063] Traditionally, integrating user-provided image and text data into a cohesive narrative or animation has been complex, requiring advanced expertise and software. As a result, it has been difficult for users to easily visualize and share personal memories and stories. This invention aims to solve this problem and provide a system that allows users to easily generate, play, and share animations based on their own data.

[0064] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0065] In this invention, the server includes means for receiving multiple image data and natural language text data via a data input device; analysis means including an image analysis module for analyzing the received image data to identify the content of a scene; and analysis means including a natural language processing engine for analyzing the received text data to extract emotions and keywords. This makes it possible to automatically create a story and animation based on data provided by the user, and to play it back on their digital device and share it with others.

[0066] A "data input device" is a device for receiving multiple image data and text data in natural language format from a user.

[0067] An "image analysis module" is a program or piece of hardware that has the function of analyzing received image data to identify the content and main features of a scene.

[0068] A "natural language processing engine" is a mechanism that analyzes received text data and extracts emotions and keywords from it.

[0069] A "generation engine" is a system that automatically constructs a story scenario based on the results of analyzing image and text data.

[0070] An "animation generation device" is a device that automatically creates visual and sound elements based on a generated scenario and integrates them to construct an animation.

[0071] "Encoding" is the process of converting generated animation data into a digital format that can be played on the user's device.

[0072] This invention is a system that automatically generates animations based on multiple image data and natural language text data, utilizing a user, server, and terminal. First, the user inputs image data and text data using a terminal via a dedicated application or web interface. The data input device is designed to allow the user to easily select and upload data. This allows the user to provide data through prompts such as, for example, "Upload photos from a family trip and enter the story of memories associated with the photos."

[0073] Next, the terminal organizes the data entered by the user and sends it to the server over the network. Image data and text data are compressed into packet format and sent to the specified API endpoint.

[0074] The server analyzes the received data. Specifically, it uses image recognition modules such as TENSORFLOW® and OpenCV to analyze image data and identify people, landscapes, and objects contained in photographs. It also uses natural language processing engines such as NLTK and Transformers to extract keywords from text data and perform sentiment analysis. Based on these analyses, the generation engine starts up, and a story scenario is automatically constructed using a generative AI model.

[0075] The server then controls the animation generation device, using software such as Blender and Unity to generate animations. During this process, characters and backgrounds are created as 3D models based on the analyzed image data, and appropriate sound elements are selected from the sound library. Finally, the generated animation is encoded in digital format and sent to the user's terminal.

[0076] This system allows users to experience rich animations using their own data without requiring complex operations or specialized knowledge. For example, if a user inputs a story such as "fun memories of a family trip three summers ago," the scenes from that time will be recreated and visualized as an emotionally rich animation. This allows users to visually recreate personal memories and share them with others.

[0077] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0078] Step 1:

[0079] Users input image and text data using a dedicated application or web interface via their terminal. The data uploaded by users may take the form of, for example, "photos from a family trip" or "stories about travel memories." The input data is received by a data entry device and organized for transmission.

[0080] Step 2:

[0081] The terminal transmits image and text data provided by the user to the server over the network. At this stage, each data is compressed and transmitted using the appropriate communication protocol. The input here is the data provided by the user, and the output is the packet-format data sent to the server.

[0082] Step 3:

[0083] The server receives image data sent from the terminal and launches an image analysis module to analyze the data. Here, image processing libraries such as TensorFlow and OpenCV are used to identify people, landscapes, and objects within the image. The input is the received raw image data, and the output is the analysis result including image features.

[0084] Step 4:

[0085] The server receives text data and performs analysis using a natural language processing engine. It extracts keywords and sentiment from the text using NLTK and Transformers. In this process, raw text data is the input, and keywords and sentiment analysis results are the output.

[0086] Step 5:

[0087] The server generates a story based on the analysis results of images and text. A scenario generation engine constructs the storyline using a generative AI model. The input is the analysis results of images and text, and the output is the constructed scenario. This scenario includes the main scenes and developments of the story.

[0088] Step 6:

[0089] The server activates an animation generation device based on the generated scenario. This device uses Blender or Unity to create 3D characters and backgrounds, and adds music and sound effects. Digitized animation data is output, resulting in a state where visuals and sound are integrated.

[0090] Step 7:

[0091] The server encodes the generated animation into a video format and sends it to the terminal. The terminal plays this animation using a dedicated media player, where the user can view the result. The input is the completed animation data, and the output is a video file that the user can view.

[0092] (Application Example 1)

[0093] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0094] Generating consistent and engaging narratives based on personal photos and experiences, and presenting them in a visually enjoyable format, has traditionally required specialized knowledge and tools, making it a high-barrier challenge for the average user. Furthermore, there was a lack of features to easily share the generated content.

[0095] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0096] In this invention, the server includes means for receiving multiple image information, means for analyzing data to extract from the received image information, and means for receiving and analyzing text information in natural language form. This makes it possible for individuals to easily generate stories from photographs and text and visualize them as animations.

[0097] "Image information" refers to visual data such as photographs and illustrations, which are processed and analyzed by computers.

[0098] "Analysis means" refers to programs or algorithms used to analyze received data and extract specific information.

[0099] "Textual information" refers to text data expressed in natural language, and includes forms such as sentences and phrases.

[0100] "Visual effects" refer to dynamic visual representations such as animations and videos generated based on image and text information.

[0101] A "dedicated device" refers to a device designed to use specific functions or applications, and includes smartphones and tablets.

[0102] An "image analysis module" refers to a program or hardware configuration used to extract characteristics from image information.

[0103] "Characteristics" refer to the features and attributes contained in image information, including objects, locations, and colors.

[0104] "Sentiment analysis" refers to the technique of determining emotions and feelings from textual information, and involves identifying positive and negative elements.

[0105] The system for carrying out the present invention aims to generate consistent visual effects based on image information and text information. Users input image information, such as photographs, and text information written in natural language using a dedicated device such as a smartphone or tablet. This data is transmitted to a cloud-based server.

[0106] The server first uses OpenCV and TensorFlow as image recognition software to analyze image information. It initializes the image analysis module and extracts specific characteristics, such as elements of people or landscapes. Next, it uses the NLTK library as a natural language processing engine to identify emotions and important keywords in text information.

[0107] A story is generated based on the extracted data. The story generation uses a dedicated program to construct the storyline, automatically determining the main scenes and plot developments according to the order of the information provided by the user. During this process, the results of sentiment analysis are applied to determine the emotional tone of each scene.

[0108] Based on the generated story, visual effects are automatically created using Unity or Blender. This visual effects creation process involves building characters and backgrounds based on images, and selecting appropriate music and sound effects from a sound library. Finally, the generated visual effects are sent to the user's dedicated device, where the user can view or share them with others.

[0109] For example, if a user inputs text information such as "photos from a child's birthday party" and "a fun day," the AI ​​model analyzes the characteristics of the image and generates a cheerful birthday visual effect. This includes animated images of family and friends, party decorations, and music that evokes a birthday. In this way, users can enrich their personal memories without needing specialized knowledge or advanced tools.

[0110] Example of a prompt:

[0111] "Please create an animation based on photos from a child's birthday party, depicting their happy birthday memories."

[0112] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0113] Step 1:

[0114] Users launch the application from a dedicated terminal and input image information (e.g., photo data) and text information (e.g., text memories). This data is formatted within the terminal and prepared as an integrated dataset. Once input is complete, the data is immediately sent to a cloud-based server.

[0115] Step 2:

[0116] The server prepares to analyze the received dataset. For image information, it starts image analysis using the OpenCV and TensorFlow libraries. It extracts specific characteristics (e.g., people or objects) and outputs them as a list of feature datasets. Specifically, the server scans the pixel data of the image to recognize the position and shape of objects.

[0117] Step 3:

[0118] Text information is processed using NLTK on the server. Keywords and emotions are extracted from the input text, and the emotional state of the text is analyzed. This generates a dataset containing emotional indicators and major themes from the text data. Specifically, words in the text are divided and analyzed as tokens, and an emotion score is calculated.

[0119] Step 4:

[0120] The server integrates the results of image and text analysis and generates a storyline using a narrative generation module. In this process, it automatically constructs a narrative scenario by weaving together extracted features and emotions. The output includes episode data for each scene. Specifically, it constructs a temporal sequence and determines the actions of the characters and the background setting in each scene.

[0121] Step 5:

[0122] The server launches Unity or Blender and creates visual effects based on the generated storyline. It uses automatically generated characters and backgrounds from images to construct the animation. It selects music and sound effects that match the scene from the sound library and combines them with the visual effects. The output is the completed animation data. Specifically, the character data and background data are combined and the animation is rendered along the timeline.

[0123] Step 6:

[0124] The generated visual effects are encoded into a video format and sent to the user's device. The user can then view the completed animation on their device. They can also share it with friends and family using the application's sharing function. Specifically, the encoded data is converted into a streamable format and transferred according to the communication protocol.

[0125] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0126] This invention is a system that generates a story based on image and text data provided by the user, and then creates an animation based on that story, while reflecting the user's emotions. The system mainly consists of a user's terminal, a central processing server, and an emotion engine that recognizes the user's emotions.

[0127] First, users upload image data and text data from their devices using a dedicated application or web interface. Users enter relevant photos and emotional stories for personal episodes.

[0128] When the server receives data from the user, it analyzes the image using an image recognition module and extracts key features. Simultaneously, it analyzes the text data using natural language processing techniques to identify keywords and emotions. This provides the foundational data needed to generate a story from the combination of images and text.

[0129] Next, the emotion engine analyzes the voice and facial expression image data provided by the user, and based on the analysis results, identifies the user's emotions in real time. This emotion data is reflected in the emotional tone of the storyline and scenes generated by the server. In this process, the user's emotional state influences the progression of the story and the selection of music.

[0130] Subsequently, the server activates an animation generation engine based on the generated story and information derived from the user's emotions. This engine draws characters, sets the background, and constructs the scene while considering the user's emotions. It also selects music and sound effects to enhance the emotional atmosphere.

[0131] The completed animation is converted into video data on the server and delivered to the user's device via a download link. By watching this animation, users can visually preserve memories that reflect their own emotions.

[0132] For example, if a user inputs a photo of a "birthday party" and text describing their joy at the time, the system will identify the user's current emotions from their facial expressions and tone of voice. The emotional state identified by the emotion engine—"joy"—is then reflected in cheerful music and fun scene effects, generating an animation that emphasizes the joyful atmosphere. This allows the user to enjoy the animation as a more personal experience.

[0133] The following describes the processing flow.

[0134] Step 1:

[0135] Users access a dedicated application or web interface using their device to select and upload multiple image data and natural language text data related to their memories. Users are then presented with options to express their emotions and can provide audio data and facial expression captures as needed.

[0136] Step 2:

[0137] The device sends image data, text data, and emotion expression data from the user to the server. This ensures that all relevant data reaches the server for central processing.

[0138] Step 3:

[0139] The server operates an image recognition module and analyzes the received image data. This analysis includes face recognition, object recognition, and landscape identification, and the resulting features are collected in a database.

[0140] Step 4:

[0141] The server activates a natural language processing engine and analyzes the text data provided by the user. This process involves keyword extraction and sentiment analysis to identify the main points and associated emotions of the text.

[0142] Step 5:

[0143] The emotion engine analyzes the user's voice data and facial expressions in real time to identify the user's emotional state. The emotion engine identifies emotions such as joy, sadness, and surprise, and feeds that data back to the server.

[0144] Step 6:

[0145] The server uses a narrative generation module to construct scenarios based on images, text, and sentiment data. The user's emotional state directly influences the narrative, adjusting the emotional tone and sequence of scenes.

[0146] Step 7:

[0147] The server uses an animation generation engine to create animations according to the scenario. It uses emotional data to set character movements, facial expressions, and background music, giving each scene emotional depth.

[0148] Step 8:

[0149] The server converts the generated animation into a video format and sends an access link to the completed video file to the user's terminal.

[0150] Step 9:

[0151] The user opens the provided link on their device and watches the generated animation. The animation reflects the user's current emotions in addition to their original memories, enriching the viewing experience in a personal and emotional way.

[0152] (Example 2)

[0153] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0154] Traditional content generation systems based on image and text data have faced the challenge of creating personalized stories and animations that reflect the emotions of individual users. In particular, there is a need for technology that can effectively analyze users' emotional states and reflect them in the content of stories and animations to provide more unique and emotionally rich content.

[0155] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0156] In this invention, the server includes means for receiving and analyzing visual data, means for receiving and analyzing audio data, means for analyzing and reflecting user emotion data, and means for generating moving images. This makes it possible to generate stories based on data provided by the user and to provide moving image content that reflects the user's emotions.

[0157] "Visual data" refers to digital information that includes images or video information.

[0158] "Feature information" refers to identifiable elements such as objects and patterns extracted from visual data.

[0159] "Natural language format audio data" refers to information that has been digitized as audio by recording the words spoken by the user.

[0160] "Means of generating narratives" refers to methods and techniques for constructing a continuous story based on information obtained from visual and audio data.

[0161] "Methods for analyzing emotional data and reflecting it in the story" refers to methods of analyzing emotional information obtained from users and using the results of this analysis to influence the content and tone of the story.

[0162] "Moving images" refer to digital information in which still images are displayed in a sequence that creates a moving image.

[0163] This invention is a system that generates a story based on visual data and natural language audio data provided by the user, and generates moving image content that reflects the user's emotional state.

[0164] Users upload visual data (e.g., photos and videos) and natural language audio data from their devices using a dedicated application or web interface. This can be done using a smartphone or computer.

[0165] The server first analyzes the uploaded visual data. Visual recognition technologies (e.g., machine learning models and image recognition algorithms) are typically used to extract feature information from the visual data. This identifies key objects and patterns within the image. Furthermore, the server analyzes audio data using natural language processing technologies. Generative AI models are used in this process to extract keywords, contextual information, and emotional states from the audio.

[0166] The emotion engine uses voice and facial expression data to analyze the user's emotional data. This allows it to identify the user's emotional state in real time. For example, emotion analysis technology utilizes machine learning models to understand the user's laughter and changes in facial expressions.

[0167] Based on the analysis results, the server generates a story. It integrates information obtained from visual and audio data to construct a storyline that reflects the user's emotional state. This results in a story that reflects the user's personal experience.

[0168] Next, the server creates video content based on the generated story. During this process, it runs a video generation engine and sets character movements, backgrounds, and music according to the story's scenario. Animation creation software is often used for this process.

[0169] The completed video content is converted to a video format and delivered to the user's device via a download link. This allows the user to watch and save the animation that reflects their own emotions.

[0170] For example, if a user uploads photos from a birthday party and an audio recording describing a happy experience, the system will use this to generate a story and video that conveys the atmosphere of the event and the user's joy. An example of a prompt for the generating AI model might be: "Generate a story from the images and text data provided by the user. The image data is photos from a birthday party, and the text data describes the enjoyable experience at that time. Analyze the user's emotions from the audio data and reflect them in the animation."

[0171] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0172] Step 1:

[0173] Users upload visual data (images and videos) and audio data using their devices. This input data is collected based on the user's personal experiences and stories. The uploaded data is stored in a format that can be transmitted to the server.

[0174] Step 2:

[0175] The server uses image recognition technology to analyze the received visual data. It takes visual data as input and extracts key features from it. For example, it identifies people and objects within an image and outputs them in an identifiable format. Machine learning algorithms may be used for this analysis.

[0176] Step 3:

[0177] Simultaneously, the server analyzes the audio data using natural language processing techniques. Taking the audio data as input, it extracts keywords and emotional information. As output, text data is generated, providing information useful for determining emotions and understanding context. A generative AI model is used in this process.

[0178] Step 4:

[0179] The emotion engine analyzes voice and, if necessary, facial expression data to identify the user's emotional state. Input is the user's voice and video data, and output is an estimate of the emotion type and intensity. This analysis result is determined in real time based on the user's experience.

[0180] Step 5:

[0181] Next, the server generates a story based on the analysis results so far. It integrates all the visual, audio, and emotional data to construct the storyline. As output, a text version of the story is generated that reflects the user's personal experience. In this step, a generative AI model is used to create the story.

[0182] Step 6:

[0183] Ultimately, the server creates a video based on the generated story. Using the story scenario as input, the animation generation engine selects character movements, backgrounds, and music to produce the video. The output is a video file format playable on the user's device. The generated content is completed to reflect the user's emotions.

[0184] (Application Example 2)

[0185] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0186] There is a challenge in generating content that is tailored to the emotions and personalities of individual users and providing a visually and emotionally rich experience. Therefore, it is necessary to recognize users' emotions in real time and reflect those emotions in animation and storytelling to provide more personal and emotionally appealing content.

[0187] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0188] In this invention, the server includes means for receiving multiple visual data, means for analyzing the received visual data to extract features, and means for receiving and analyzing data in linguistic form. This enables the generation of customized stories and videos that respond to the user's individual emotions and experiences.

[0189] "Visual data" refers to digital data that represents visual information, including image data and video data.

[0190] A "feature" refers to the main elements or patterns of data that are extracted from visual or linguistic data.

[0191] "Linguistic data" refers to text data that includes sentences and keywords written in natural language.

[0192] A "story" is a storyline and its content that is constructed based on visual and linguistic data.

[0193] "Motion images" are digital videos that visually represent the content of a story as animation.

[0194] "Emotional state" refers to the type and intensity of emotions recognized in real time from the user's voice and facial expressions.

[0195] "Means of presentation" refers to a mechanism for providing the generated video data to the user and making it viewable.

[0196] In order to implement this invention, it is necessary for a system to be built through the cooperation of three parties: a server, a terminal, and a user. First, the terminal provides an interface for receiving visual data and linguistic data input by the user. The user uses a dedicated application to input visual data and linguistic data (for example, images and text messages).

[0197] The server uses an image recognition module to analyze visual data received from the terminal. This module extracts features from the visual data and identifies key elements using software libraries such as OpenCV and TensorFlow. Simultaneously, linguistic data is analyzed using natural language processing techniques. Specifically, natural language processing libraries such as Transformers are used to perform keyword extraction and sentiment analysis.

[0198] Furthermore, the server uses an emotion recognition engine to identify the user's emotional state in real time from their voice and facial expression data. This emotional state is sent to an animation generation engine, which then incorporates it into the narrative and scene structure of the generated animation. This engine utilizes animation production software such as Blender and Unity to create personalized animations based on the user's characteristics and emotions.

[0199] The generated video is stored as video data on the server and delivered to the user using a presentation method. The user can view this video on their device and enjoy content that reflects their individual emotions.

[0200] As a concrete example, consider the following prompt: "Based on the image and text entered by the user, generate a spring picnic animation that incorporates his / her emotions." Based on this prompt, the system can generate a natural and emotional animation and provide it to the user.

[0201] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0202] Step 1:

[0203] The device receives visual and linguistic data uploaded by the user. This input includes images selected by the user and text messages entered. The device converts these into digital format and prepares them for transmission to the server.

[0204] Step 2:

[0205] The server receives visual data sent from the terminal and analyzes the information using an image recognition module. The input is visual data, and features are extracted using OpenCV or TensorFlow. The output is the main elements and patterns in the data.

[0206] Step 3:

[0207] The server uses a natural language processing engine to analyze linguistic data. The input is text data from the user, and keyword extraction and sentiment analysis are performed using the Transformers library. The output includes relevant keywords from the text data and the user's sentiment.

[0208] Step 4:

[0209] The server runs an emotion recognition engine to identify the user's emotional state. This engine uses voice and facial expression data as input. It analyzes the user's emotions in real time and outputs the result as an emotional state. This information is then reflected in the animation's tone and storyline.

[0210] Step 5:

[0211] The server runs an animation generation engine to produce animated images based on the user's characteristics and emotional state. The input consists of extracted characteristics, keywords, and emotional states, which are then used to create personalized animated images using Blender or Unity. The output is the completed animation.

[0212] Step 6:

[0213] The server saves the generated video as a digital file and provides it to the user via the terminal. The user receives this file on the terminal and uses an interface to make it viewable. The input is a video file, and the output is the visual experience for the user.

[0214] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0215] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0216] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0217] [Second Embodiment]

[0218] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0219] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0220] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0221] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0222] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0223] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0224] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0225] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0226] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0227] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0228] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0229] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0230] This invention relates to a system that receives multiple image data and natural language text data provided by a user, analyzes them to generate a consistent narrative, and creates an animation based on that narrative. This system consists of a user, a server, and a terminal.

[0231] First, the user uses a device to input multiple image files and story text through a dedicated application or web interface. The device then organizes the photos selected by the user and sends the input text to the server.

[0232] Next, the server analyzes the received data. For image data, it initializes an image recognition module and extracts features such as people, landscapes, and objects from each image. This image recognition process identifies important elements in the images being analyzed. For text data, a natural language processing engine is used for analysis, and keywords and overall sentiment are extracted.

[0233] Once the analysis is complete, the server uses a story generation module to construct a storyline based on the image and text analysis results. This module determines the main scenes and plot developments of the story according to the order of the data provided by the user. It also incorporates the sentiment analysis results of the text to set an appropriate emotional tone for each scene.

[0234] The server then activates an animation generation engine based on the generated story. This engine automatically generates character visuals and backgrounds from images and constructs scenes based on templates. Appropriate music and sound effects are selected from the sound library, enriching the animation experience.

[0235] Finally, the generated animation data is converted into a video format, and the server sends this data to the user's device. The user can not only watch this animation on their own device, but also easily share it with friends and family.

[0236] As a concrete example, consider a scenario where a user inputs several family travel photos and the accompanying text, "A fun memory from a family trip three summers ago." In this case, the server animates the travel scenes based on the scenery and people captured in the photos. As a result, an emotionally rich animation is generated in which the family members during the trip come alive as characters. This animation is enhanced with music and backgrounds that evoke the atmosphere of that summer. This allows users to visually recreate their memories without using specialized software.

[0237] The following describes the processing flow.

[0238] Step 1:

[0239] Users select and upload multiple image files and associated text data using a dedicated application or web interface via their device. Users choose photos related to memories, enter an episode, and press the submit button.

[0240] Step 2:

[0241] The server receives image data and text data sent by the user. The received data is converted into an appropriate format for the analysis process.

[0242] Step 3:

[0243] The server activates the image recognition module and analyzes the image data. It performs tasks such as facial recognition of people, identification of objects, and identification of landscapes, and extracts features from each image.

[0244] Step 4:

[0245] The server uses a natural language processing engine to analyze the text data. This involves keyword extraction, sentiment analysis, and contextual analysis to identify the information necessary for story generation.

[0246] Step 5:

[0247] The server uses a story generation module to construct a storyline based on the analyzed image and text data. It evaluates the relationship between images and text to design the sequence of scenes and the emotional flow.

[0248] Step 6:

[0249] The server starts the animation generation engine and creates animations according to the storyline. It automatically generates character visuals and scene backgrounds, and produces dynamic content based on templates.

[0250] Step 7:

[0251] The server selects music and sound effects and incorporates them into the animation. Using an audio library, it chooses music and effects appropriate for the scene and places them on the timeline to fit.

[0252] Step 8:

[0253] The server converts the completed animation data into a video format and generates a downloadable link for the user's device.

[0254] Step 9:

[0255] Users receive a link from the server via their device and watch the animation by downloading or streaming it. Users can then play this animation on their own devices and share it with family and friends.

[0256] (Example 1)

[0257] Next, we will describe Example 1. 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."

[0258] Traditionally, integrating user-provided image and text data into a cohesive narrative or animation has been complex, requiring advanced expertise and software. As a result, it has been difficult for users to easily visualize and share personal memories and stories. This invention aims to solve this problem and provide a system that allows users to easily generate, play, and share animations based on their own data.

[0259] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0260] In this invention, the server includes means for receiving multiple image data and natural language text data via a data input device; analysis means including an image analysis module for analyzing the received image data to identify the content of a scene; and analysis means including a natural language processing engine for analyzing the received text data to extract emotions and keywords. This makes it possible to automatically create a story and animation based on data provided by the user, and to play it back on their digital device and share it with others.

[0261] A "data input device" is a device for receiving multiple image data and text data in natural language format from a user.

[0262] An "image analysis module" is a program or piece of hardware that has the function of analyzing received image data to identify the content and main features of a scene.

[0263] A "natural language processing engine" is a mechanism that analyzes received text data and extracts emotions and keywords from it.

[0264] A "generation engine" is a system that automatically constructs a story scenario based on the results of analyzing image and text data.

[0265] An "animation generation device" is a device that automatically creates visual and sound elements based on a generated scenario and integrates them to construct an animation.

[0266] "Encoding" is the process of converting generated animation data into a digital format that can be played on the user's device.

[0267] This invention is a system that automatically generates animations based on multiple image data and natural language text data, utilizing a user, server, and terminal. First, the user inputs image data and text data using a terminal via a dedicated application or web interface. The data input device is designed to allow the user to easily select and upload data. This allows the user to provide data through prompts such as, for example, "Upload photos from a family trip and enter the story of memories associated with the photos."

[0268] Next, the terminal organizes the data entered by the user and sends it to the server over the network. Image data and text data are compressed into packet format and sent to the specified API endpoint.

[0269] The server analyzes the received data. Specifically, it uses image recognition modules such as TensorFlow and OpenCV to analyze image data and identify people, landscapes, and objects contained in photographs. It also uses natural language processing engines such as NLTK and Transformers to extract keywords from text data and perform sentiment analysis. Based on these analyses, the generation engine starts up, and a story scenario is automatically constructed using a generative AI model.

[0270] The server then controls the animation generation device, using software such as Blender and Unity to generate animations. During this process, characters and backgrounds are created as 3D models based on the analyzed image data, and appropriate sound elements are selected from the sound library. Finally, the generated animation is encoded in digital format and sent to the user's terminal.

[0271] This system allows users to experience rich animations using their own data without requiring complex operations or specialized knowledge. For example, if a user inputs a story such as "fun memories of a family trip three summers ago," the scenes from that time will be recreated and visualized as an emotionally rich animation. This allows users to visually recreate personal memories and share them with others.

[0272] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0273] Step 1:

[0274] Users input image and text data using a dedicated application or web interface via their terminal. The data uploaded by users may take the form of, for example, "photos from a family trip" or "stories about travel memories." The input data is received by a data entry device and organized for transmission.

[0275] Step 2:

[0276] The terminal transmits image and text data provided by the user to the server over the network. At this stage, each data is compressed and transmitted using the appropriate communication protocol. The input here is the data provided by the user, and the output is the packet-format data sent to the server.

[0277] Step 3:

[0278] The server receives image data sent from the terminal and launches an image analysis module to analyze the data. Here, image processing libraries such as TensorFlow and OpenCV are used to identify people, landscapes, and objects within the image. The input is the received raw image data, and the output is the analysis result including image features.

[0279] Step 4:

[0280] The server receives text data and analyzes it using a natural language processing engine. It extracts keywords and emotions from the text using NLTK or Transformers. In this process, the raw text data is the input, and the keywords and sentiment analysis results are the output.

[0281] Step 5:

[0282] The server generates a story based on the analysis results of the image and text. It utilizes a generative AI model, and a scenario generation engine constructs the storyline. The input is the analysis results of the image and text, and the output is the constructed scenario. This scenario includes the main scenes and developments of the story.

[0283] Step 6:

[0284] The server activates an animation generation device based on the generated scenario. This device uses Blender or Unity to create three-dimensional characters and backgrounds and add music and sound effects. The digitized animation data is output, with vision and sound integrated.

[0285] Step 7:

[0286] The server encodes the generated animation into video format and transmits it to the terminal. The terminal uses a dedicated media player to play this animation, and the user can view the results there. The input is the completed animation data, and the output is a video file that the user can view.

[0287] (Application Example 1)

[0288] Next, Application Example 1 will be described. In the following description, the data processing device ˈ12ˈ is referred to as the ˈserverˈ, and the smart glasses ˈ214ˈ are referred to as the ˈterminalˈ.

[0289] Generating consistent and engaging narratives based on personal photos and experiences, and presenting them in a visually enjoyable format, has traditionally required specialized knowledge and tools, making it a high-barrier challenge for the average user. Furthermore, there was a lack of features to easily share the generated content.

[0290] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0291] In this invention, the server includes means for receiving multiple image information, means for analyzing data to extract from the received image information, and means for receiving and analyzing text information in natural language form. This makes it possible for individuals to easily generate stories from photographs and text and visualize them as animations.

[0292] "Image information" refers to visual data such as photographs and illustrations, which are processed and analyzed by computers.

[0293] "Analysis means" refers to programs or algorithms used to analyze received data and extract specific information.

[0294] "Textual information" refers to text data expressed in natural language, and includes forms such as sentences and phrases.

[0295] "Visual effects" refer to dynamic visual representations such as animations and videos generated based on image and text information.

[0296] A "dedicated device" refers to a device designed to use specific functions or applications, and includes smartphones and tablets.

[0297] An "image analysis module" refers to a program or hardware configuration used to extract characteristics from image information.

[0298] "Characteristics" refer to the features and attributes contained in image information, including objects, locations, and colors.

[0299] "Sentiment analysis" refers to the technique of determining emotions and feelings from textual information, and involves identifying positive and negative elements.

[0300] The system for carrying out the present invention aims to generate consistent visual effects based on image information and text information. Users input image information, such as photographs, and text information written in natural language using a dedicated device such as a smartphone or tablet. This data is transmitted to a cloud-based server.

[0301] The server first uses OpenCV and TensorFlow as image recognition software to analyze image information. It initializes the image analysis module and extracts specific characteristics, such as elements of people or landscapes. Next, it uses the NLTK library as a natural language processing engine to identify emotions and important keywords in text information.

[0302] A story is generated based on the extracted data. The story generation uses a dedicated program to construct the storyline, automatically determining the main scenes and plot developments according to the order of the information provided by the user. During this process, the results of sentiment analysis are applied to determine the emotional tone of each scene.

[0303] Based on the generated story, visual effects are automatically created using Unity or Blender. This visual effects creation process involves building characters and backgrounds based on images, and selecting appropriate music and sound effects from a sound library. Finally, the generated visual effects are sent to the user's dedicated device, where the user can view or share them with others.

[0304] As a specific example, when a user inputs character information such as "Photos of a child's birthday party" and "A fun day", the generative AI model analyzes the characteristics of the image and generates a visually appealing birthday effect. This includes animated images of family and friends, party decorations, and music that evokes the birthday. In this way, the user can experience their personal memories more richly without the need for specialized knowledge or advanced tools.

[0305] Example of a prompt sentence:

[0306] "Please animate the happy birthday memories based on the photos of the child's birthday party."

[0307] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0308] Step 1:

[0309] The user launches the application from a dedicated terminal and inputs image information (e.g., photo data) and character information (e.g., text memories). These data are formatted within the terminal and prepared as an integrated dataset. Once the input is complete, the data is immediately sent to a cloud-based server.

[0310] Step 2:

[0311] The server prepares to analyze the received dataset. For the image information, image analysis is started using the OpenCV and TensorFlow libraries. Specific characteristics (e.g., people or objects) are extracted and output as a list of feature datasets. As a specific operation on the server, the pixel data of the image is scanned to recognize the position and shape of the object.

[0312] Step 3:

[0313] Text information is processed using NLTK on the server. Keywords and emotions are extracted from the input text, and the emotional state of the text is analyzed. This generates a dataset containing emotional indicators and major themes from the text data. Specifically, words in the text are divided and analyzed as tokens, and an emotion score is calculated.

[0314] Step 4:

[0315] The server integrates the results of image and text analysis and generates a storyline using a narrative generation module. In this process, it automatically constructs a narrative scenario by weaving together extracted features and emotions. The output includes episode data for each scene. Specifically, it constructs a temporal sequence and determines the actions of the characters and the background setting in each scene.

[0316] Step 5:

[0317] The server launches Unity or Blender and creates visual effects based on the generated storyline. It uses automatically generated characters and backgrounds from images to construct the animation. It selects music and sound effects that match the scene from the sound library and combines them with the visual effects. The output is the completed animation data. Specifically, the character data and background data are combined and the animation is rendered along the timeline.

[0318] Step 6:

[0319] The generated visual effects are encoded into a video format and sent to the user's device. The user can then view the completed animation on their device. They can also share it with friends and family using the application's sharing function. Specifically, the encoded data is converted into a streamable format and transferred according to the communication protocol.

[0320] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0321] This invention is a system that generates a story based on image and text data provided by the user, and then creates an animation based on that story, while reflecting the user's emotions. The system mainly consists of a user's terminal, a central processing server, and an emotion engine that recognizes the user's emotions.

[0322] First, users upload image data and text data from their devices using a dedicated application or web interface. Users enter relevant photos and emotional stories for personal episodes.

[0323] When the server receives data from the user, it analyzes the image using an image recognition module and extracts key features. Simultaneously, it analyzes the text data using natural language processing techniques to identify keywords and emotions. This provides the foundational data needed to generate a story from the combination of images and text.

[0324] Next, the emotion engine analyzes the voice and facial expression image data provided by the user, and based on the analysis results, identifies the user's emotions in real time. This emotion data is reflected in the emotional tone of the storyline and scenes generated by the server. In this process, the user's emotional state influences the progression of the story and the selection of music.

[0325] Subsequently, the server activates an animation generation engine based on the generated story and information derived from the user's emotions. This engine draws characters, sets the background, and constructs the scene while considering the user's emotions. It also selects music and sound effects to enhance the emotional atmosphere.

[0326] The completed animation is converted into video data on the server and delivered to the user's device via a download link. By watching this animation, users can visually preserve memories that reflect their own emotions.

[0327] For example, if a user inputs a photo of a "birthday party" and text describing their joy at the time, the system will identify the user's current emotions from their facial expressions and tone of voice. The emotional state identified by the emotion engine—"joy"—is then reflected in cheerful music and fun scene effects, generating an animation that emphasizes the joyful atmosphere. This allows the user to enjoy the animation as a more personal experience.

[0328] The following describes the processing flow.

[0329] Step 1:

[0330] Users access a dedicated application or web interface using their device to select and upload multiple image data and natural language text data related to their memories. Users are then presented with options to express their emotions and can provide audio data and facial expression captures as needed.

[0331] Step 2:

[0332] The device sends image data, text data, and emotion expression data from the user to the server. This ensures that all relevant data reaches the server for central processing.

[0333] Step 3:

[0334] The server operates an image recognition module and analyzes the received image data. This analysis includes face recognition, object recognition, and landscape identification, and the resulting features are collected in a database.

[0335] Step 4:

[0336] The server activates a natural language processing engine and analyzes the text data provided by the user. This process involves keyword extraction and sentiment analysis to identify the main points and associated emotions of the text.

[0337] Step 5:

[0338] The emotion engine analyzes the user's voice data and facial expressions in real time to identify the user's emotional state. The emotion engine identifies emotions such as joy, sadness, and surprise, and feeds that data back to the server.

[0339] Step 6:

[0340] The server uses a narrative generation module to construct scenarios based on images, text, and sentiment data. The user's emotional state directly influences the narrative, adjusting the emotional tone and sequence of scenes.

[0341] Step 7:

[0342] The server uses an animation generation engine to create animations according to the scenario. It uses emotional data to set character movements, facial expressions, and background music, giving each scene emotional depth.

[0343] Step 8:

[0344] The server converts the generated animation into a video format and sends an access link to the completed video file to the user's terminal.

[0345] Step 9:

[0346] The user opens the provided link on their device and watches the generated animation. The animation reflects the user's current emotions in addition to their original memories, enriching the viewing experience in a personal and emotional way.

[0347] (Example 2)

[0348] Next, we will describe Example 2. 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".

[0349] Traditional content generation systems based on image and text data have faced the challenge of creating personalized stories and animations that reflect the emotions of individual users. In particular, there is a need for technology that can effectively analyze users' emotional states and reflect them in the content of stories and animations to provide more unique and emotionally rich content.

[0350] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0351] In this invention, the server includes means for receiving and analyzing visual data, means for receiving and analyzing audio data, means for analyzing and reflecting user emotion data, and means for generating moving images. This makes it possible to generate stories based on data provided by the user and to provide moving image content that reflects the user's emotions.

[0352] "Visual data" refers to digital information that includes images or video information.

[0353] "Feature information" refers to identifiable elements such as objects and patterns extracted from visual data.

[0354] "Natural language format audio data" refers to information that has been digitized as audio by recording the words spoken by the user.

[0355] "Means of generating narratives" refers to methods and techniques for constructing a continuous story based on information obtained from visual and audio data.

[0356] "Methods for analyzing emotional data and reflecting it in the story" refers to methods of analyzing emotional information obtained from users and using the results of this analysis to influence the content and tone of the story.

[0357] "Moving images" refer to digital information in which still images are displayed in a sequence that creates a moving image.

[0358] This invention is a system that generates a story based on visual data and natural language audio data provided by the user, and generates moving image content that reflects the user's emotional state.

[0359] Users upload visual data (e.g., photos and videos) and natural language audio data from their devices using a dedicated application or web interface. This can be done using a smartphone or computer.

[0360] The server first analyzes the uploaded visual data. Visual recognition technologies (e.g., machine learning models and image recognition algorithms) are typically used to extract feature information from the visual data. This identifies key objects and patterns within the image. Furthermore, the server analyzes audio data using natural language processing technologies. Generative AI models are used in this process to extract keywords, contextual information, and emotional states from the audio.

[0361] The emotion engine uses voice and facial expression data to analyze the user's emotional data. This allows it to identify the user's emotional state in real time. For example, emotion analysis technology utilizes machine learning models to understand the user's laughter and changes in facial expressions.

[0362] Based on the analysis results, the server generates a story. It integrates information obtained from visual and audio data to construct a storyline that reflects the user's emotional state. This results in a story that reflects the user's personal experience.

[0363] Next, the server creates video content based on the generated story. During this process, it runs a video generation engine and sets character movements, backgrounds, and music according to the story's scenario. Animation creation software is often used for this process.

[0364] The completed video content is converted to a video format and delivered to the user's device via a download link. This allows the user to watch and save the animation that reflects their own emotions.

[0365] For example, if a user uploads photos from a birthday party and an audio recording describing a happy experience, the system will use this to generate a story and video that conveys the atmosphere of the event and the user's joy. An example of a prompt for the generating AI model might be: "Generate a story from the images and text data provided by the user. The image data is photos from a birthday party, and the text data describes the enjoyable experience at that time. Analyze the user's emotions from the audio data and reflect them in the animation."

[0366] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0367] Step 1:

[0368] Users upload visual data (images and videos) and audio data using their devices. This input data is collected based on the user's personal experiences and stories. The uploaded data is stored in a format that can be transmitted to the server.

[0369] Step 2:

[0370] The server uses image recognition technology to analyze the received visual data. It takes visual data as input and extracts key features from it. For example, it identifies people and objects within an image and outputs them in an identifiable format. Machine learning algorithms may be used for this analysis.

[0371] Step 3:

[0372] Simultaneously, the server analyzes the audio data using natural language processing techniques. Taking the audio data as input, it extracts keywords and emotional information. As output, text data is generated, providing information useful for determining emotions and understanding context. A generative AI model is used in this process.

[0373] Step 4:

[0374] The emotion engine analyzes voice and, if necessary, facial expression data to identify the user's emotional state. Input is the user's voice and video data, and output is an estimate of the emotion type and intensity. This analysis result is determined in real time based on the user's experience.

[0375] Step 5:

[0376] Next, the server generates a story based on the analysis results so far. It integrates all the visual, audio, and emotional data to construct the storyline. As output, a text version of the story is generated that reflects the user's personal experience. In this step, a generative AI model is used to create the story.

[0377] Step 6:

[0378] Ultimately, the server creates a video based on the generated story. Using the story scenario as input, the animation generation engine selects character movements, backgrounds, and music to produce the video. The output is a video file format playable on the user's device. The generated content is completed to reflect the user's emotions.

[0379] (Application Example 2)

[0380] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0381] There is a challenge in generating content that is tailored to the emotions and personalities of individual users and providing a visually and emotionally rich experience. Therefore, it is necessary to recognize users' emotions in real time and reflect those emotions in animation and storytelling to provide more personal and emotionally appealing content.

[0382] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0383] In this invention, the server includes means for receiving multiple visual data, means for analyzing the received visual data to extract features, and means for receiving and analyzing data in linguistic form. This enables the generation of customized stories and videos that respond to the user's individual emotions and experiences.

[0384] "Visual data" refers to digital data that represents visual information, including image data and video data.

[0385] A "feature" refers to the main elements or patterns of data that are extracted from visual or linguistic data.

[0386] "Linguistic data" refers to text data that includes sentences and keywords written in natural language.

[0387] A "story" is a storyline and its content that is constructed based on visual and linguistic data.

[0388] "Motion images" are digital videos that visually represent the content of a story as animation.

[0389] "Emotional state" refers to the type and intensity of emotions recognized in real time from the user's voice and facial expressions.

[0390] "Means of presentation" refers to a mechanism for providing the generated video data to the user and making it viewable.

[0391] In order to implement this invention, it is necessary for a system to be built through the cooperation of three parties: a server, a terminal, and a user. First, the terminal provides an interface for receiving visual data and linguistic data input by the user. The user uses a dedicated application to input visual data and linguistic data (for example, images and text messages).

[0392] The server uses an image recognition module to analyze visual data received from the terminal. This module extracts features from the visual data and identifies key elements using software libraries such as OpenCV and TensorFlow. Simultaneously, linguistic data is analyzed using natural language processing techniques. Specifically, natural language processing libraries such as Transformers are used to perform keyword extraction and sentiment analysis.

[0393] Furthermore, the server uses an emotion recognition engine to identify the user's emotional state in real time from their voice and facial expression data. This emotional state is sent to an animation generation engine, which then incorporates it into the narrative and scene structure of the generated animation. This engine utilizes animation production software such as Blender and Unity to create personalized animations based on the user's characteristics and emotions.

[0394] The generated video is stored as video data on the server and delivered to the user using a presentation method. The user can view this video on their device and enjoy content that reflects their individual emotions.

[0395] As a concrete example, consider the following prompt: "Based on the image and text entered by the user, generate a spring picnic animation that incorporates his / her emotions." Based on this prompt, the system can generate a natural and emotional animation and provide it to the user.

[0396] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0397] Step 1:

[0398] The device receives visual and linguistic data uploaded by the user. This input includes images selected by the user and text messages entered. The device converts these into digital format and prepares them for transmission to the server.

[0399] Step 2:

[0400] The server receives visual data sent from the terminal and analyzes the information using an image recognition module. The input is visual data, and features are extracted using OpenCV or TensorFlow. The output is the main elements and patterns in the data.

[0401] Step 3:

[0402] The server uses a natural language processing engine to analyze linguistic data. The input is text data from the user, and keyword extraction and sentiment analysis are performed using the Transformers library. The output includes relevant keywords from the text data and the user's sentiment.

[0403] Step 4:

[0404] The server runs an emotion recognition engine to identify the user's emotional state. This engine uses voice and facial expression data as input. It analyzes the user's emotions in real time and outputs the result as an emotional state. This information is then reflected in the animation's tone and storyline.

[0405] Step 5:

[0406] The server runs an animation generation engine to produce animated images based on the user's characteristics and emotional state. The input consists of extracted characteristics, keywords, and emotional states, which are then used to create personalized animated images using Blender or Unity. The output is the completed animation.

[0407] Step 6:

[0408] The server saves the generated video as a digital file and provides it to the user via the terminal. The user receives this file on the terminal and uses an interface to view it. The input is a video file, and the output is the visual experience for the user.

[0409] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0410] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0411] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0412] [Third Embodiment]

[0413] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0414] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0415] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0416] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0417] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0418] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0419] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0420] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0421] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0422] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0423] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0424] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0425] This invention relates to a system that receives multiple image data and natural language text data provided by a user, analyzes them to generate a consistent narrative, and creates an animation based on that narrative. This system consists of a user, a server, and a terminal.

[0426] First, the user uses a device to input multiple image files and story text through a dedicated application or web interface. The device then organizes the photos selected by the user and sends the input text to the server.

[0427] Next, the server analyzes the received data. For image data, it initializes an image recognition module and extracts features such as people, landscapes, and objects from each image. This image recognition process identifies important elements in the images being analyzed. For text data, a natural language processing engine is used for analysis, and keywords and overall sentiment are extracted.

[0428] Once the analysis is complete, the server uses a story generation module to construct a storyline based on the image and text analysis results. This module determines the main scenes and plot developments of the story according to the order of the data provided by the user. It also incorporates the sentiment analysis results of the text to set an appropriate emotional tone for each scene.

[0429] The server then activates an animation generation engine based on the generated story. This engine automatically generates character visuals and backgrounds from images and constructs scenes based on templates. Appropriate music and sound effects are selected from the sound library, enriching the animation experience.

[0430] Finally, the generated animation data is converted into a video format, and the server sends this data to the user's device. The user can not only watch this animation on their own device, but also easily share it with friends and family.

[0431] As a concrete example, consider a scenario where a user inputs several family travel photos and the accompanying text, "A fun memory from a family trip three summers ago." In this case, the server animates the travel scenes based on the scenery and people captured in the photos. As a result, an emotionally rich animation is generated in which the family members during the trip come alive as characters. This animation is enhanced with music and backgrounds that evoke the atmosphere of that summer. This allows users to visually recreate their memories without using specialized software.

[0432] The following describes the processing flow.

[0433] Step 1:

[0434] Users select and upload multiple image files and associated text data using a dedicated application or web interface via their device. Users choose photos related to memories, enter an episode, and press the submit button.

[0435] Step 2:

[0436] The server receives image data and text data sent by the user. The received data is converted into an appropriate format for the analysis process.

[0437] Step 3:

[0438] The server activates the image recognition module and analyzes the image data. It performs tasks such as facial recognition of people, identification of objects, and identification of landscapes, and extracts features from each image.

[0439] Step 4:

[0440] The server uses a natural language processing engine to analyze the text data. This involves keyword extraction, sentiment analysis, and contextual analysis to identify the information necessary for story generation.

[0441] Step 5:

[0442] The server uses a story generation module to construct a storyline based on the analyzed image and text data. It evaluates the relationship between images and text to design the sequence of scenes and the emotional flow.

[0443] Step 6:

[0444] The server starts the animation generation engine and creates animations according to the storyline. It automatically generates character visuals and scene backgrounds, and produces dynamic content based on templates.

[0445] Step 7:

[0446] The server selects music and sound effects and incorporates them into the animation. Using an audio library, it chooses music and effects appropriate for the scene and places them on the timeline to fit.

[0447] Step 8:

[0448] The server converts the completed animation data into a video format and generates a downloadable link for the user's device.

[0449] Step 9:

[0450] Users receive a link from the server via their device and watch the animation by downloading or streaming it. Users can then play this animation on their own devices and share it with family and friends.

[0451] (Example 1)

[0452] Next, we will describe Example 1. 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."

[0453] Traditionally, integrating user-provided image and text data into a cohesive narrative or animation has been complex, requiring advanced expertise and software. As a result, it has been difficult for users to easily visualize and share personal memories and stories. This invention aims to solve this problem and provide a system that allows users to easily generate, play, and share animations based on their own data.

[0454] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0455] In this invention, the server includes means for receiving multiple image data and natural language text data via a data input device; analysis means including an image analysis module for analyzing the received image data to identify the content of a scene; and analysis means including a natural language processing engine for analyzing the received text data to extract emotions and keywords. This makes it possible to automatically create a story and animation based on data provided by the user, and to play it back on their digital device and share it with others.

[0456] A "data input device" is a device for receiving multiple image data and text data in natural language format from a user.

[0457] An "image analysis module" is a program or piece of hardware that has the function of analyzing received image data to identify the content and main features of a scene.

[0458] A "natural language processing engine" is a mechanism that analyzes received text data and extracts emotions and keywords from it.

[0459] A "generation engine" is a system that automatically constructs a story scenario based on the results of analyzing image and text data.

[0460] An "animation generation device" is a device that automatically creates visual and sound elements based on a generated scenario and integrates them to construct an animation.

[0461] "Encoding" is the process of converting generated animation data into a digital format that can be played on the user's device.

[0462] This invention is a system that automatically generates animations based on multiple image data and natural language text data, utilizing a user, server, and terminal. First, the user inputs image data and text data using a terminal via a dedicated application or web interface. The data input device is designed to allow the user to easily select and upload data. This allows the user to provide data through prompts such as, for example, "Upload photos from a family trip and enter the story of memories associated with the photos."

[0463] Next, the terminal organizes the data entered by the user and sends it to the server over the network. Image data and text data are compressed into packet format and sent to the specified API endpoint.

[0464] The server analyzes the received data. Specifically, it uses image recognition modules such as TensorFlow and OpenCV to analyze image data and identify people, landscapes, and objects contained in photographs. It also uses natural language processing engines such as NLTK and Transformers to extract keywords from text data and perform sentiment analysis. Based on these analyses, the generation engine starts up, and a story scenario is automatically constructed using a generative AI model.

[0465] The server then controls the animation generation device, using software such as Blender and Unity to generate animations. During this process, characters and backgrounds are created as 3D models based on the analyzed image data, and appropriate sound elements are selected from the sound library. Finally, the generated animation is encoded in digital format and sent to the user's terminal.

[0466] This system allows users to experience rich animations using their own data without requiring complex operations or specialized knowledge. For example, if a user inputs a story such as "fun memories of a family trip three summers ago," the scenes from that time will be recreated and visualized as an emotionally rich animation. This allows users to visually recreate personal memories and share them with others.

[0467] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0468] Step 1:

[0469] Users input image and text data using a dedicated application or web interface via their terminal. The data uploaded by users may take the form of, for example, "photos from a family trip" or "stories about travel memories." The input data is received by a data entry device and organized for transmission.

[0470] Step 2:

[0471] The terminal transmits image and text data provided by the user to the server over the network. At this stage, each data is compressed and transmitted using the appropriate communication protocol. The input here is the data provided by the user, and the output is the packet-format data sent to the server.

[0472] Step 3:

[0473] The server receives image data sent from the terminal and launches an image analysis module to analyze the data. Here, image processing libraries such as TensorFlow and OpenCV are used to identify people, landscapes, and objects within the image. The input is the received raw image data, and the output is the analysis result including image features.

[0474] Step 4:

[0475] The server receives text data and performs analysis using a natural language processing engine. It extracts keywords and sentiment from the text using NLTK and Transformers. In this process, raw text data is the input, and keywords and sentiment analysis results are the output.

[0476] Step 5:

[0477] The server generates a story based on the analysis results of images and text. A scenario generation engine constructs the storyline using a generative AI model. The input is the analysis results of images and text, and the output is the constructed scenario. This scenario includes the main scenes and developments of the story.

[0478] Step 6:

[0479] The server activates an animation generation device based on the generated scenario. This device uses Blender or Unity to create 3D characters and backgrounds, and adds music and sound effects. Digitized animation data is output, resulting in a state where visuals and sound are integrated.

[0480] Step 7:

[0481] The server encodes the generated animation into a video format and sends it to the terminal. The terminal plays this animation using a dedicated media player, where the user can view the result. The input is the completed animation data, and the output is a video file that the user can view.

[0482] (Application Example 1)

[0483] Next, we will explain Application Example 1. In the following explanation, 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."

[0484] Generating consistent and engaging narratives based on personal photos and experiences, and presenting them in a visually enjoyable format, has traditionally required specialized knowledge and tools, making it a high-barrier challenge for the average user. Furthermore, there was a lack of features to easily share the generated content.

[0485] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0486] In this invention, the server includes means for receiving multiple image information, means for analyzing data to extract from the received image information, and means for receiving and analyzing text information in natural language form. This makes it possible for individuals to easily generate stories from photographs and text and visualize them as animations.

[0487] "Image information" refers to visual data such as photographs and illustrations, which are processed and analyzed by computers.

[0488] "Analysis means" refers to programs or algorithms used to analyze received data and extract specific information.

[0489] "Textual information" refers to text data expressed in natural language, and includes forms such as sentences and phrases.

[0490] "Visual effects" refer to dynamic visual representations such as animations and videos generated based on image and text information.

[0491] A "dedicated device" refers to a device designed to use specific functions or applications, and includes smartphones and tablets.

[0492] An "image analysis module" refers to a program or hardware configuration used to extract characteristics from image information.

[0493] "Characteristics" refer to the features and attributes contained in image information, including objects, locations, and colors.

[0494] "Sentiment analysis" refers to the technique of determining emotions and feelings from textual information, and involves identifying positive and negative elements.

[0495] The system for carrying out the present invention aims to generate consistent visual effects based on image information and text information. Users input image information, such as photographs, and text information written in natural language using a dedicated device such as a smartphone or tablet. This data is transmitted to a cloud-based server.

[0496] The server first uses OpenCV and TensorFlow as image recognition software to analyze image information. It initializes the image analysis module and extracts specific characteristics, such as elements of people or landscapes. Next, it uses the NLTK library as a natural language processing engine to identify emotions and important keywords in text information.

[0497] A story is generated based on the extracted data. The story generation uses a dedicated program to construct the storyline, automatically determining the main scenes and plot developments according to the order of the information provided by the user. During this process, the results of sentiment analysis are applied to determine the emotional tone of each scene.

[0498] Based on the generated story, visual effects are automatically created using Unity or Blender. This visual effects creation process involves building characters and backgrounds based on images, and selecting appropriate music and sound effects from a sound library. Finally, the generated visual effects are sent to the user's dedicated device, where the user can view or share them with others.

[0499] For example, if a user inputs text information such as "photos from a child's birthday party" and "a fun day," the AI ​​model analyzes the characteristics of the image and generates a cheerful birthday visual effect. This includes animated images of family and friends, party decorations, and music that evokes a birthday. In this way, users can enrich their personal memories without needing specialized knowledge or advanced tools.

[0500] Example of a prompt:

[0501] "Please create an animation based on photos from a child's birthday party, depicting their happy birthday memories."

[0502] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0503] Step 1:

[0504] Users launch the application from a dedicated terminal and input image information (e.g., photo data) and text information (e.g., text memories). This data is formatted within the terminal and prepared as an integrated dataset. Once input is complete, the data is immediately sent to a cloud-based server.

[0505] Step 2:

[0506] The server prepares to analyze the received dataset. For image information, it starts image analysis using the OpenCV and TensorFlow libraries. It extracts specific characteristics (e.g., people or objects) and outputs them as a list of feature datasets. Specifically, the server scans the pixel data of the image to recognize the position and shape of objects.

[0507] Step 3:

[0508] Text information is processed using NLTK on the server. Keywords and emotions are extracted from the input text, and the emotional state of the text is analyzed. This generates a dataset containing emotional indicators and major themes from the text data. Specifically, words in the text are divided and analyzed as tokens, and an emotion score is calculated.

[0509] Step 4:

[0510] The server integrates the results of image and text analysis and generates a storyline using a narrative generation module. In this process, it automatically constructs a narrative scenario by weaving together extracted features and emotions. The output includes episode data for each scene. Specifically, it constructs a temporal sequence and determines the actions of the characters and the background setting in each scene.

[0511] Step 5:

[0512] The server launches Unity or Blender and creates visual effects based on the generated storyline. It uses automatically generated characters and backgrounds from images to construct the animation. It selects music and sound effects that match the scene from the sound library and combines them with the visual effects. The output is the completed animation data. Specifically, the character data and background data are combined and the animation is rendered along the timeline.

[0513] Step 6:

[0514] The generated visual effects are encoded into a video format and sent to the user's device. The user can then view the completed animation on their device. They can also share it with friends and family using the application's sharing function. Specifically, the encoded data is converted into a streamable format and transferred according to the communication protocol.

[0515] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0516] This invention is a system that generates a story based on image and text data provided by the user, and then creates an animation based on that story, while reflecting the user's emotions. The system mainly consists of a user's terminal, a central processing server, and an emotion engine that recognizes the user's emotions.

[0517] First, users upload image data and text data from their devices using a dedicated application or web interface. Users enter relevant photos and emotional stories for personal episodes.

[0518] When the server receives data from the user, it analyzes the image using an image recognition module and extracts key features. Simultaneously, it analyzes the text data using natural language processing techniques to identify keywords and emotions. This provides the foundational data needed to generate a story from the combination of images and text.

[0519] Next, the emotion engine analyzes the voice and facial expression image data provided by the user, and based on the analysis results, identifies the user's emotions in real time. This emotion data is reflected in the emotional tone of the storyline and scenes generated by the server. In this process, the user's emotional state influences the progression of the story and the selection of music.

[0520] Subsequently, the server activates an animation generation engine based on the generated story and information derived from the user's emotions. This engine draws characters, sets the background, and constructs the scene while considering the user's emotions. It also selects music and sound effects to enhance the emotional atmosphere.

[0521] The completed animation is converted into video data on the server and delivered to the user's device via a download link. By watching this animation, users can visually preserve memories that reflect their own emotions.

[0522] For example, if a user inputs a photo of a "birthday party" and text describing their joy at the time, the system will identify the user's current emotions from their facial expressions and tone of voice. The emotional state identified by the emotion engine—"joy"—is then reflected in cheerful music and fun scene effects, generating an animation that emphasizes the joyful atmosphere. This allows the user to enjoy the animation as a more personal experience.

[0523] The following describes the processing flow.

[0524] Step 1:

[0525] Users access a dedicated application or web interface using their device to select and upload multiple image data and natural language text data related to their memories. Users are then presented with options to express their emotions and can provide audio data and facial expression captures as needed.

[0526] Step 2:

[0527] The device sends image data, text data, and emotion expression data from the user to the server. This ensures that all relevant data reaches the server for central processing.

[0528] Step 3:

[0529] The server operates an image recognition module and analyzes the received image data. This analysis includes face recognition, object recognition, and landscape identification, and the resulting features are collected in a database.

[0530] Step 4:

[0531] The server activates a natural language processing engine and analyzes the text data provided by the user. This process involves keyword extraction and sentiment analysis to identify the main points and associated emotions of the text.

[0532] Step 5:

[0533] The emotion engine analyzes the user's voice data and facial expressions in real time to identify the user's emotional state. The emotion engine identifies emotions such as joy, sadness, and surprise, and feeds that data back to the server.

[0534] Step 6:

[0535] The server uses a narrative generation module to construct scenarios based on images, text, and sentiment data. The user's emotional state directly influences the narrative, adjusting the emotional tone and sequence of scenes.

[0536] Step 7:

[0537] The server uses an animation generation engine to create animations according to the scenario. It uses emotional data to set character movements, facial expressions, and background music, giving each scene emotional depth.

[0538] Step 8:

[0539] The server converts the generated animation into a video format and sends an access link to the completed video file to the user's terminal.

[0540] Step 9:

[0541] The user opens the provided link on their device and watches the generated animation. The animation reflects the user's current emotions in addition to their original memories, enriching the viewing experience in a personal and emotional way.

[0542] (Example 2)

[0543] Next, we will describe Example 2. 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."

[0544] Traditional content generation systems based on image and text data have faced the challenge of creating personalized stories and animations that reflect the emotions of individual users. In particular, there is a need for technology that can effectively analyze users' emotional states and reflect them in the content of stories and animations to provide more unique and emotionally rich content.

[0545] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0546] In this invention, the server includes means for receiving and analyzing visual data, means for receiving and analyzing audio data, means for analyzing and reflecting user emotion data, and means for generating moving images. This makes it possible to generate stories based on data provided by the user and to provide moving image content that reflects the user's emotions.

[0547] "Visual data" refers to digital information that includes images or video information.

[0548] "Feature information" refers to identifiable elements such as objects and patterns extracted from visual data.

[0549] "Natural language format audio data" refers to information that has been digitized as audio by recording the words spoken by the user.

[0550] "Means of generating narratives" refers to methods and techniques for constructing a continuous story based on information obtained from visual and audio data.

[0551] "Methods for analyzing emotional data and reflecting it in the story" refers to methods of analyzing emotional information obtained from users and using the results of this analysis to influence the content and tone of the story.

[0552] "Moving images" refer to digital information in which still images are displayed in a sequence that creates a moving image.

[0553] This invention is a system that generates a story based on visual data and natural language audio data provided by the user, and generates moving image content that reflects the user's emotional state.

[0554] Users upload visual data (e.g., photos and videos) and natural language audio data from their devices using a dedicated application or web interface. This can be done using a smartphone or computer.

[0555] The server first analyzes the uploaded visual data. Visual recognition technologies (e.g., machine learning models and image recognition algorithms) are typically used to extract feature information from the visual data. This identifies key objects and patterns within the image. Furthermore, the server analyzes audio data using natural language processing technologies. Generative AI models are used in this process to extract keywords, contextual information, and emotional states from the audio.

[0556] The emotion engine uses voice and facial expression data to analyze the user's emotional data. This allows it to identify the user's emotional state in real time. For example, emotion analysis technology utilizes machine learning models to understand the user's laughter and changes in facial expressions.

[0557] Based on the analysis results, the server generates a story. It integrates information obtained from visual and audio data to construct a storyline that reflects the user's emotional state. This results in a story that reflects the user's personal experience.

[0558] Next, the server creates video content based on the generated story. During this process, it runs a video generation engine and sets character movements, backgrounds, and music according to the story's scenario. Animation creation software is often used for this process.

[0559] The completed video content is converted to a video format and delivered to the user's device via a download link. This allows the user to watch and save the animation that reflects their own emotions.

[0560] For example, if a user uploads photos from a birthday party and an audio recording describing a happy experience, the system will use this to generate a story and video that conveys the atmosphere of the event and the user's joy. An example of a prompt for the generating AI model might be: "Generate a story from the images and text data provided by the user. The image data is photos from a birthday party, and the text data describes the enjoyable experience at that time. Analyze the user's emotions from the audio data and reflect them in the animation."

[0561] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0562] Step 1:

[0563] Users upload visual data (images and videos) and audio data using their devices. This input data is collected based on the user's personal experiences and stories. The uploaded data is stored in a format that can be transmitted to the server.

[0564] Step 2:

[0565] The server uses image recognition technology to analyze the received visual data. It takes visual data as input and extracts key features from it. For example, it identifies people and objects within an image and outputs them in an identifiable format. Machine learning algorithms may be used for this analysis.

[0566] Step 3:

[0567] Simultaneously, the server analyzes the audio data using natural language processing techniques. Taking the audio data as input, it extracts keywords and emotional information. As output, text data is generated, providing information useful for determining emotions and understanding context. A generative AI model is used in this process.

[0568] Step 4:

[0569] The emotion engine analyzes voice and, if necessary, facial expression data to identify the user's emotional state. Input is the user's voice and video data, and output is an estimate of the emotion type and intensity. This analysis result is determined in real time based on the user's experience.

[0570] Step 5:

[0571] Next, the server generates a story based on the analysis results so far. It integrates all the visual, audio, and emotional data to construct the storyline. As output, a text version of the story is generated that reflects the user's personal experience. In this step, a generative AI model is used to create the story.

[0572] Step 6:

[0573] Ultimately, the server creates a video based on the generated story. Using the story scenario as input, the animation generation engine selects character movements, backgrounds, and music to produce the video. The output is a video file format playable on the user's device. The generated content is completed to reflect the user's emotions.

[0574] (Application Example 2)

[0575] Next, we will explain application example 2. In the following explanation, 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."

[0576] There is a challenge in generating content that is tailored to the emotions and personalities of individual users and providing a visually and emotionally rich experience. Therefore, it is necessary to recognize users' emotions in real time and reflect those emotions in animation and storytelling to provide more personal and emotionally appealing content.

[0577] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0578] In this invention, the server includes means for receiving multiple visual data, means for analyzing the received visual data to extract features, and means for receiving and analyzing data in linguistic form. This enables the generation of customized stories and videos that respond to the user's individual emotions and experiences.

[0579] "Visual data" refers to digital data that represents visual information, including image data and video data.

[0580] A "feature" refers to the main elements or patterns of data that are extracted from visual or linguistic data.

[0581] "Linguistic data" refers to text data that includes sentences and keywords written in natural language.

[0582] A "story" is a storyline and its content that is constructed based on visual and linguistic data.

[0583] "Motion images" are digital videos that visually represent the content of a story as animation.

[0584] "Emotional state" refers to the type and intensity of emotions recognized in real time from the user's voice and facial expressions.

[0585] "Means of presentation" refers to a mechanism for providing the generated video data to the user and making it viewable.

[0586] In order to implement this invention, it is necessary for a system to be built through the cooperation of three parties: a server, a terminal, and a user. First, the terminal provides an interface for receiving visual data and linguistic data input by the user. The user uses a dedicated application to input visual data and linguistic data (for example, images and text messages).

[0587] The server uses an image recognition module to analyze visual data received from the terminal. This module extracts features from the visual data and identifies key elements using software libraries such as OpenCV and TensorFlow. Simultaneously, linguistic data is analyzed using natural language processing techniques. Specifically, natural language processing libraries such as Transformers are used to perform keyword extraction and sentiment analysis.

[0588] Furthermore, the server uses an emotion recognition engine to identify the user's emotional state in real time from their voice and facial expression data. This emotional state is sent to an animation generation engine, which then incorporates it into the narrative and scene structure of the generated animation. This engine utilizes animation production software such as Blender and Unity to create personalized animations based on the user's characteristics and emotions.

[0589] The generated video is stored as video data on the server and delivered to the user using a presentation method. The user can view this video on their device and enjoy content that reflects their individual emotions.

[0590] As a concrete example, consider the following prompt: "Based on the image and text entered by the user, generate a spring picnic animation that incorporates his / her emotions." Based on this prompt, the system can generate a natural and emotional animation and provide it to the user.

[0591] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0592] Step 1:

[0593] The device receives visual and linguistic data uploaded by the user. This input includes images selected by the user and text messages entered. The device converts these into digital format and prepares them for transmission to the server.

[0594] Step 2:

[0595] The server receives visual data sent from the terminal and analyzes the information using an image recognition module. The input is visual data, and features are extracted using OpenCV or TensorFlow. The output is the main elements and patterns in the data.

[0596] Step 3:

[0597] The server uses a natural language processing engine to analyze linguistic data. The input is text data from the user, and keyword extraction and sentiment analysis are performed using the Transformers library. The output includes relevant keywords from the text data and the user's sentiment.

[0598] Step 4:

[0599] The server runs an emotion recognition engine to identify the user's emotional state. This engine uses voice and facial expression data as input. It analyzes the user's emotions in real time and outputs the result as an emotional state. This information is then reflected in the animation's tone and storyline.

[0600] Step 5:

[0601] The server runs an animation generation engine to produce animated images based on the user's characteristics and emotional state. The input consists of extracted characteristics, keywords, and emotional states, which are then used to create personalized animated images using Blender or Unity. The output is the completed animation.

[0602] Step 6:

[0603] The server saves the generated video as a digital file and provides it to the user via the terminal. The user receives this file on the terminal and uses an interface to view it. The input is a video file, and the output is the visual experience for the user.

[0604] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0605] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0606] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0607] [Fourth Embodiment]

[0608] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0609] As shown in Figure 7, the 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.

[0610] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0611] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0612] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0613] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0614] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0615] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0616] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0617] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0618] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0619] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0620] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0621] This invention relates to a system that receives multiple image data and natural language text data provided by a user, analyzes them to generate a consistent narrative, and creates an animation based on that narrative. This system consists of a user, a server, and a terminal.

[0622] First, the user uses a device to input multiple image files and story text through a dedicated application or web interface. The device then organizes the photos selected by the user and sends the input text to the server.

[0623] Next, the server analyzes the received data. For image data, it initializes an image recognition module and extracts features such as people, landscapes, and objects from each image. This image recognition process identifies important elements in the images being analyzed. For text data, a natural language processing engine is used for analysis, and keywords and overall sentiment are extracted.

[0624] Once the analysis is complete, the server uses a story generation module to construct a storyline based on the image and text analysis results. This module determines the main scenes and plot developments of the story according to the order of the data provided by the user. It also incorporates the sentiment analysis results of the text to set an appropriate emotional tone for each scene.

[0625] The server then activates an animation generation engine based on the generated story. This engine automatically generates character visuals and backgrounds from images and constructs scenes based on templates. Appropriate music and sound effects are selected from the sound library, enriching the animation experience.

[0626] Finally, the generated animation data is converted into a video format, and the server sends this data to the user's device. The user can not only watch this animation on their own device, but also easily share it with friends and family.

[0627] As a concrete example, consider a scenario where a user inputs several family travel photos and the accompanying text, "A fun memory from a family trip three summers ago." In this case, the server animates the travel scenes based on the scenery and people captured in the photos. As a result, an emotionally rich animation is generated in which the family members during the trip come alive as characters. This animation is enhanced with music and backgrounds that evoke the atmosphere of that summer. This allows users to visually recreate their memories without using specialized software.

[0628] The following describes the processing flow.

[0629] Step 1:

[0630] Users select and upload multiple image files and associated text data using a dedicated application or web interface via their device. Users choose photos related to memories, enter an episode, and press the submit button.

[0631] Step 2:

[0632] The server receives image data and text data sent by the user. The received data is converted into an appropriate format for the analysis process.

[0633] Step 3:

[0634] The server activates the image recognition module and analyzes the image data. It performs tasks such as facial recognition of people, identification of objects, and identification of landscapes, and extracts features from each image.

[0635] Step 4:

[0636] The server uses a natural language processing engine to analyze the text data. This involves keyword extraction, sentiment analysis, and contextual analysis to identify the information necessary for story generation.

[0637] Step 5:

[0638] The server uses a story generation module to construct a storyline based on the analyzed image and text data. It evaluates the relationship between images and text to design the sequence of scenes and the emotional flow.

[0639] Step 6:

[0640] The server starts the animation generation engine and creates animations according to the storyline. It automatically generates character visuals and scene backgrounds, and produces dynamic content based on templates.

[0641] Step 7:

[0642] The server selects music and sound effects and incorporates them into the animation. Using an audio library, it chooses music and effects appropriate for the scene and places them on the timeline to fit.

[0643] Step 8:

[0644] The server converts the completed animation data into a video format and generates a downloadable link for the user's device.

[0645] Step 9:

[0646] Users receive a link from the server via their device and watch the animation by downloading or streaming it. Users can then play this animation on their own devices and share it with family and friends.

[0647] (Example 1)

[0648] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0649] Traditionally, integrating user-provided image and text data into a cohesive narrative or animation has been complex, requiring advanced expertise and software. As a result, it has been difficult for users to easily visualize and share personal memories and stories. This invention aims to solve this problem and provide a system that allows users to easily generate, play, and share animations based on their own data.

[0650] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0651] In this invention, the server includes means for receiving multiple image data and natural language text data via a data input device; analysis means including an image analysis module for analyzing the received image data to identify the content of a scene; and analysis means including a natural language processing engine for analyzing the received text data to extract emotions and keywords. This makes it possible to automatically create a story and animation based on data provided by the user, and to play it back on their digital device and share it with others.

[0652] A "data input device" is a device for receiving multiple image data and text data in natural language format from a user.

[0653] An "image analysis module" is a program or piece of hardware that has the function of analyzing received image data to identify the content and main features of a scene.

[0654] A "natural language processing engine" is a mechanism that analyzes received text data and extracts emotions and keywords from it.

[0655] A "generation engine" is a system that automatically constructs a story scenario based on the results of analyzing image and text data.

[0656] An "animation generation device" is a device that automatically creates visual and sound elements based on a generated scenario and integrates them to construct an animation.

[0657] "Encoding" is the process of converting generated animation data into a digital format that can be played on the user's device.

[0658] This invention is a system that automatically generates animations based on multiple image data and natural language text data, utilizing a user, server, and terminal. First, the user inputs image data and text data using a terminal via a dedicated application or web interface. The data input device is designed to allow the user to easily select and upload data. This allows the user to provide data through prompts such as, for example, "Upload photos from a family trip and enter the story of memories associated with the photos."

[0659] Next, the terminal organizes the data entered by the user and sends it to the server over the network. Image data and text data are compressed into packet format and sent to the specified API endpoint.

[0660] The server analyzes the received data. Specifically, it uses image recognition modules such as TensorFlow and OpenCV to analyze image data and identify people, landscapes, and objects contained in photographs. It also uses natural language processing engines such as NLTK and Transformers to extract keywords from text data and perform sentiment analysis. Based on these analyses, the generation engine starts up, and a story scenario is automatically constructed using a generative AI model.

[0661] The server then controls the animation generation device, using software such as Blender and Unity to generate animations. During this process, characters and backgrounds are created as 3D models based on the analyzed image data, and appropriate sound elements are selected from the sound library. Finally, the generated animation is encoded in digital format and sent to the user's terminal.

[0662] This system allows users to experience rich animations using their own data without requiring complex operations or specialized knowledge. For example, if a user inputs a story such as "fun memories of a family trip three summers ago," the scenes from that time will be recreated and visualized as an emotionally rich animation. This allows users to visually recreate personal memories and share them with others.

[0663] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0664] Step 1:

[0665] Users input image and text data using a dedicated application or web interface via their terminal. The data uploaded by users may take the form of, for example, "photos from a family trip" or "stories about travel memories." The input data is received by a data entry device and organized for transmission.

[0666] Step 2:

[0667] The terminal transmits image and text data provided by the user to the server over the network. At this stage, each data is compressed and transmitted using the appropriate communication protocol. The input here is the data provided by the user, and the output is the packet-format data sent to the server.

[0668] Step 3:

[0669] The server receives image data sent from the terminal and launches an image analysis module to analyze the data. Here, image processing libraries such as TensorFlow and OpenCV are used to identify people, landscapes, and objects within the image. The input is the received raw image data, and the output is the analysis result including image features.

[0670] Step 4:

[0671] The server receives text data and performs analysis using a natural language processing engine. It extracts keywords and sentiment from the text using NLTK and Transformers. In this process, raw text data is the input, and keywords and sentiment analysis results are the output.

[0672] Step 5:

[0673] The server generates a story based on the analysis results of images and text. A scenario generation engine constructs the storyline using a generative AI model. The input is the analysis results of images and text, and the output is the constructed scenario. This scenario includes the main scenes and developments of the story.

[0674] Step 6:

[0675] The server activates an animation generation device based on the generated scenario. This device uses Blender or Unity to create 3D characters and backgrounds, and adds music and sound effects. Digitized animation data is output, resulting in a state where visuals and sound are integrated.

[0676] Step 7:

[0677] The server encodes the generated animation into a video format and sends it to the terminal. The terminal plays this animation using a dedicated media player, where the user can view the result. The input is the completed animation data, and the output is a video file that the user can view.

[0678] (Application Example 1)

[0679] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0680] Generating consistent and engaging narratives based on personal photos and experiences, and presenting them in a visually enjoyable format, has traditionally required specialized knowledge and tools, making it a high-barrier challenge for the average user. Furthermore, there was a lack of features to easily share the generated content.

[0681] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0682] In this invention, the server includes means for receiving multiple image information, means for analyzing data to extract from the received image information, and means for receiving and analyzing text information in natural language form. This makes it possible for individuals to easily generate stories from photographs and text and visualize them as animations.

[0683] "Image information" refers to visual data such as photographs and illustrations, which are processed and analyzed by computers.

[0684] "Analysis means" refers to programs or algorithms used to analyze received data and extract specific information.

[0685] "Textual information" refers to text data expressed in natural language, and includes forms such as sentences and phrases.

[0686] "Visual effects" refer to dynamic visual representations such as animations and videos generated based on image and text information.

[0687] A "dedicated device" refers to a device designed to use specific functions or applications, and includes smartphones and tablets.

[0688] An "image analysis module" refers to a program or hardware configuration used to extract characteristics from image information.

[0689] "Characteristics" refer to the features and attributes contained in image information, including objects, locations, and colors.

[0690] "Sentiment analysis" refers to the technique of determining emotions and feelings from textual information, and involves identifying positive and negative elements.

[0691] The system for carrying out the present invention aims to generate consistent visual effects based on image information and text information. Users input image information, such as photographs, and text information written in natural language using a dedicated device such as a smartphone or tablet. This data is transmitted to a cloud-based server.

[0692] The server first uses OpenCV and TensorFlow as image recognition software to analyze image information. It initializes the image analysis module and extracts specific characteristics, such as elements of people or landscapes. Next, it uses the NLTK library as a natural language processing engine to identify emotions and important keywords in text information.

[0693] A story is generated based on the extracted data. The story generation uses a dedicated program to construct the storyline, automatically determining the main scenes and plot developments according to the order of the information provided by the user. During this process, the results of sentiment analysis are applied to determine the emotional tone of each scene.

[0694] Based on the generated story, visual effects are automatically created using Unity or Blender. This visual effects creation process involves building characters and backgrounds based on images, and selecting appropriate music and sound effects from a sound library. Finally, the generated visual effects are sent to the user's dedicated device, where the user can view or share them with others.

[0695] For example, if a user inputs text information such as "photos from a child's birthday party" and "a fun day," the AI ​​model analyzes the characteristics of the image and generates a cheerful birthday visual effect. This includes animated images of family and friends, party decorations, and music that evokes a birthday. In this way, users can enrich their personal memories without needing specialized knowledge or advanced tools.

[0696] Example of a prompt:

[0697] "Please create an animation based on photos from a child's birthday party, depicting their happy birthday memories."

[0698] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0699] Step 1:

[0700] Users launch the application from a dedicated terminal and input image information (e.g., photo data) and text information (e.g., text memories). This data is formatted within the terminal and prepared as an integrated dataset. Once input is complete, the data is immediately sent to a cloud-based server.

[0701] Step 2:

[0702] The server prepares to analyze the received dataset. For image information, it starts image analysis using the OpenCV and TensorFlow libraries. It extracts specific characteristics (e.g., people or objects) and outputs them as a list of feature datasets. Specifically, the server scans the pixel data of the image to recognize the position and shape of objects.

[0703] Step 3:

[0704] Text information is processed using NLTK on the server. Keywords and emotions are extracted from the input text, and the emotional state of the text is analyzed. This generates a dataset containing emotional indicators and major themes from the text data. Specifically, words in the text are divided and analyzed as tokens, and an emotion score is calculated.

[0705] Step 4:

[0706] The server integrates the results of image and text analysis and generates a storyline using a narrative generation module. In this process, it automatically constructs a narrative scenario by weaving together extracted features and emotions. The output includes episode data for each scene. Specifically, it constructs a temporal sequence and determines the actions of the characters and the background setting in each scene.

[0707] Step 5:

[0708] The server launches Unity or Blender and creates visual effects based on the generated storyline. It uses automatically generated characters and backgrounds from images to construct the animation. It selects music and sound effects that match the scene from the sound library and combines them with the visual effects. The output is the completed animation data. Specifically, the character data and background data are combined and the animation is rendered along the timeline.

[0709] Step 6:

[0710] The generated visual effects are encoded into a video format and sent to the user's device. The user can then view the completed animation on their device. They can also share it with friends and family using the application's sharing function. Specifically, the encoded data is converted into a streamable format and transferred according to the communication protocol.

[0711] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0712] This invention is a system that generates a story based on image and text data provided by the user, and then creates an animation based on that story, while reflecting the user's emotions. The system mainly consists of a user's terminal, a central processing server, and an emotion engine that recognizes the user's emotions.

[0713] First, users upload image data and text data from their devices using a dedicated application or web interface. Users enter relevant photos and emotional stories for personal episodes.

[0714] When the server receives data from the user, it analyzes the image using an image recognition module and extracts key features. Simultaneously, it analyzes the text data using natural language processing techniques to identify keywords and emotions. This provides the foundational data needed to generate a story from the combination of images and text.

[0715] Next, the emotion engine analyzes the voice and facial expression image data provided by the user, and based on the analysis results, identifies the user's emotions in real time. This emotion data is reflected in the emotional tone of the storyline and scenes generated by the server. In this process, the user's emotional state influences the progression of the story and the selection of music.

[0716] Subsequently, the server activates an animation generation engine based on the generated story and information derived from the user's emotions. This engine draws characters, sets the background, and constructs the scene while considering the user's emotions. It also selects music and sound effects to enhance the emotional atmosphere.

[0717] The completed animation is converted into video data on the server and delivered to the user's device via a download link. By watching this animation, users can visually preserve memories that reflect their own emotions.

[0718] For example, if a user inputs a photo of a "birthday party" and text describing their joy at the time, the system will identify the user's current emotions from their facial expressions and tone of voice. The emotional state identified by the emotion engine—"joy"—is then reflected in cheerful music and fun scene effects, generating an animation that emphasizes the joyful atmosphere. This allows the user to enjoy the animation as a more personal experience.

[0719] The following describes the processing flow.

[0720] Step 1:

[0721] Users access a dedicated application or web interface using their device to select and upload multiple image data and natural language text data related to their memories. Users are then presented with options to express their emotions and can provide audio data and facial expression captures as needed.

[0722] Step 2:

[0723] The device sends image data, text data, and emotion expression data from the user to the server. This ensures that all relevant data reaches the server for central processing.

[0724] Step 3:

[0725] The server operates an image recognition module and analyzes the received image data. This analysis includes face recognition, object recognition, and landscape identification, and the resulting features are collected in a database.

[0726] Step 4:

[0727] The server activates a natural language processing engine and analyzes the text data provided by the user. This process involves keyword extraction and sentiment analysis to identify the main points and associated emotions of the text.

[0728] Step 5:

[0729] The emotion engine analyzes the user's voice data and facial expressions in real time to identify the user's emotional state. The emotion engine identifies emotions such as joy, sadness, and surprise, and feeds that data back to the server.

[0730] Step 6:

[0731] The server uses a narrative generation module to construct scenarios based on images, text, and sentiment data. The user's emotional state directly influences the narrative, adjusting the emotional tone and sequence of scenes.

[0732] Step 7:

[0733] The server uses an animation generation engine to create animations according to the scenario. It uses emotional data to set character movements, facial expressions, and background music, giving each scene emotional depth.

[0734] Step 8:

[0735] The server converts the generated animation into a video format and sends an access link to the completed video file to the user's terminal.

[0736] Step 9:

[0737] The user opens the provided link on their device and watches the generated animation. The animation reflects the user's current emotions in addition to their original memories, enriching the viewing experience in a personal and emotional way.

[0738] (Example 2)

[0739] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0740] Traditional content generation systems based on image and text data have faced the challenge of creating personalized stories and animations that reflect the emotions of individual users. In particular, there is a need for technology that can effectively analyze users' emotional states and reflect them in the content of stories and animations to provide more unique and emotionally rich content.

[0741] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0742] In this invention, the server includes means for receiving and analyzing visual data, means for receiving and analyzing audio data, means for analyzing and reflecting user emotion data, and means for generating moving images. This makes it possible to generate stories based on data provided by the user and to provide moving image content that reflects the user's emotions.

[0743] "Visual data" refers to digital information that includes images or video information.

[0744] "Feature information" refers to identifiable elements such as objects and patterns extracted from visual data.

[0745] "Natural language format audio data" refers to information that has been digitized as audio by recording the words spoken by the user.

[0746] "Means of generating narratives" refers to methods and techniques for constructing a continuous story based on information obtained from visual and audio data.

[0747] "Methods for analyzing emotional data and reflecting it in the story" refers to methods of analyzing emotional information obtained from users and using the results of this analysis to influence the content and tone of the story.

[0748] "Moving images" refer to digital information in which still images are displayed in a sequence that creates a moving image.

[0749] This invention is a system that generates a story based on visual data and natural language audio data provided by the user, and generates moving image content that reflects the user's emotional state.

[0750] Users upload visual data (e.g., photos and videos) and natural language audio data from their devices using a dedicated application or web interface. This can be done using a smartphone or computer.

[0751] The server first analyzes the uploaded visual data. Visual recognition technologies (e.g., machine learning models and image recognition algorithms) are typically used to extract feature information from the visual data. This identifies key objects and patterns within the image. Furthermore, the server analyzes audio data using natural language processing technologies. Generative AI models are used in this process to extract keywords, contextual information, and emotional states from the audio.

[0752] The emotion engine uses voice and facial expression data to analyze the user's emotional data. This allows it to identify the user's emotional state in real time. For example, emotion analysis technology utilizes machine learning models to understand the user's laughter and changes in facial expressions.

[0753] Based on the analysis results, the server generates a story. It integrates information obtained from visual and audio data to construct a storyline that reflects the user's emotional state. This results in a story that reflects the user's personal experience.

[0754] Next, the server creates video content based on the generated story. During this process, it runs a video generation engine and sets character movements, backgrounds, and music according to the story's scenario. Animation creation software is often used for this process.

[0755] The completed video content is converted to a video format and delivered to the user's device via a download link. This allows the user to watch and save the animation that reflects their own emotions.

[0756] For example, if a user uploads photos from a birthday party and an audio recording describing a happy experience, the system will use this to generate a story and video that conveys the atmosphere of the event and the user's joy. An example of a prompt for the generating AI model might be: "Generate a story from the images and text data provided by the user. The image data is photos from a birthday party, and the text data describes the enjoyable experience at that time. Analyze the user's emotions from the audio data and reflect them in the animation."

[0757] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0758] Step 1:

[0759] Users upload visual data (images and videos) and audio data using their devices. This input data is collected based on the user's personal experiences and stories. The uploaded data is stored in a format that can be transmitted to the server.

[0760] Step 2:

[0761] The server uses image recognition technology to analyze the received visual data. It takes visual data as input and extracts key features from it. For example, it identifies people and objects within an image and outputs them in an identifiable format. Machine learning algorithms may be used for this analysis.

[0762] Step 3:

[0763] Simultaneously, the server analyzes the audio data using natural language processing techniques. Taking the audio data as input, it extracts keywords and emotional information. As output, text data is generated, providing information useful for determining emotions and understanding context. A generative AI model is used in this process.

[0764] Step 4:

[0765] The emotion engine analyzes voice and, if necessary, facial expression data to identify the user's emotional state. Input is the user's voice and video data, and output is an estimate of the emotion type and intensity. This analysis result is determined in real time based on the user's experience.

[0766] Step 5:

[0767] Next, the server generates a story based on the analysis results so far. It integrates all the visual, audio, and emotional data to construct the storyline. As output, a text version of the story is generated that reflects the user's personal experience. In this step, a generative AI model is used to create the story.

[0768] Step 6:

[0769] Ultimately, the server creates a video based on the generated story. Using the story scenario as input, the animation generation engine selects character movements, backgrounds, and music to produce the video. The output is a video file format playable on the user's device. The generated content is completed to reflect the user's emotions.

[0770] (Application Example 2)

[0771] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0772] There is a challenge in generating content that is tailored to the emotions and personalities of individual users and providing a visually and emotionally rich experience. Therefore, it is necessary to recognize users' emotions in real time and reflect those emotions in animation and storytelling to provide more personal and emotionally appealing content.

[0773] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0774] In this invention, the server includes means for receiving multiple visual data, means for analyzing the received visual data to extract features, and means for receiving and analyzing data in linguistic form. This enables the generation of customized stories and videos that respond to the user's individual emotions and experiences.

[0775] "Visual data" refers to digital data that represents visual information, including image data and video data.

[0776] A "feature" refers to the main elements or patterns of data that are extracted from visual or linguistic data.

[0777] "Linguistic data" refers to text data that includes sentences and keywords written in natural language.

[0778] A "story" is a storyline and its content that is constructed based on visual and linguistic data.

[0779] "Motion images" are digital videos that visually represent the content of a story as animation.

[0780] "Emotional state" refers to the type and intensity of emotions recognized in real time from the user's voice and facial expressions.

[0781] "Means of presentation" refers to a mechanism for providing the generated video data to the user and making it viewable.

[0782] In order to implement this invention, it is necessary for a system to be built through the cooperation of three parties: a server, a terminal, and a user. First, the terminal provides an interface for receiving visual data and linguistic data input by the user. The user uses a dedicated application to input visual data and linguistic data (for example, images and text messages).

[0783] The server uses an image recognition module to analyze visual data received from the terminal. This module extracts features from the visual data and identifies key elements using software libraries such as OpenCV and TensorFlow. Simultaneously, linguistic data is analyzed using natural language processing techniques. Specifically, natural language processing libraries such as Transformers are used to perform keyword extraction and sentiment analysis.

[0784] Furthermore, the server uses an emotion recognition engine to identify the user's emotional state in real time from their voice and facial expression data. This emotional state is sent to an animation generation engine, which then incorporates it into the narrative and scene structure of the generated animation. This engine utilizes animation production software such as Blender and Unity to create personalized animations based on the user's characteristics and emotions.

[0785] The generated video is stored as video data on the server and delivered to the user using a presentation method. The user can view this video on their device and enjoy content that reflects their individual emotions.

[0786] As a concrete example, consider the following prompt: "Based on the image and text entered by the user, generate a spring picnic animation that incorporates his / her emotions." Based on this prompt, the system can generate a natural and emotional animation and provide it to the user.

[0787] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0788] Step 1:

[0789] The device receives visual and linguistic data uploaded by the user. This input includes images selected by the user and text messages entered. The device converts these into digital format and prepares them for transmission to the server.

[0790] Step 2:

[0791] The server receives visual data sent from the terminal and analyzes the information using an image recognition module. The input is visual data, and features are extracted using OpenCV or TensorFlow. The output is the main elements and patterns in the data.

[0792] Step 3:

[0793] The server uses a natural language processing engine to analyze linguistic data. The input is text data from the user, and keyword extraction and sentiment analysis are performed using the Transformers library. The output includes relevant keywords from the text data and the user's sentiment.

[0794] Step 4:

[0795] The server runs an emotion recognition engine to identify the user's emotional state. This engine uses voice and facial expression data as input. It analyzes the user's emotions in real time and outputs the result as an emotional state. This information is then reflected in the animation's tone and storyline.

[0796] Step 5:

[0797] The server runs an animation generation engine to produce animated images based on the user's characteristics and emotional state. The input consists of extracted characteristics, keywords, and emotional states, which are then used to create personalized animated images using Blender or Unity. The output is the completed animation.

[0798] Step 6:

[0799] The server saves the generated video as a digital file and provides it to the user via the terminal. The user receives this file on the terminal and uses an interface to view it. The input is a video file, and the output is the visual experience for the user.

[0800] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0801] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0802] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0803] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0804] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0805] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0806] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0807] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0808] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0809] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0810] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0811] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0812] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0813] 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.

[0814] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0815] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0816] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0817] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0818] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0819] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0820] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0821] The following is further disclosed regarding the embodiments described above.

[0822] (Claim 1)

[0823] A means for receiving multiple image data,

[0824] An analysis means for extracting information from received image data,

[0825] A means for receiving and analyzing text data in natural language format,

[0826] A means of generating a story based on image data and text data,

[0827] A means of creating animations according to the generated story,

[0828] Means for generating and presenting animation data,

[0829] A system that includes this.

[0830] (Claim 2)

[0831] The system according to claim 1, comprising an image recognition module for identifying features based on image data, and further using these features to draw an object in animation.

[0832] (Claim 3)

[0833] The system according to claim 1, comprising means for performing sentiment analysis on text data and adjusting the animation scenario based on the results of this analysis.

[0834] "Example 1"

[0835] (Claim 1)

[0836] A means for receiving multiple image data and natural language text data via a data input device,

[0837] An analysis means including an image analysis module for analyzing received image data to identify the content of a scene,

[0838] An analysis means including a natural language processing engine that analyzes received text data to extract emotions and keywords,

[0839] A means for using a generation engine to generate a story scenario based on the results of analyzing image data and text data,

[0840] A means of creating an animation by driving an animation generation device that automatically generates specified visual and sound elements based on a generated scenario,

[0841] A means for encoding and presenting the generated animation data in a digital format for transmission to the user terminal,

[0842] A system that includes this.

[0843] (Claim 2)

[0844] The system according to claim 1, which represents characters and backgrounds as three-dimensional structures based on features extracted using an image analysis module, and integrates them into an animation.

[0845] (Claim 3)

[0846] The system according to claim 1, which uses information obtained from sentiment analysis of text data to adjust the emotional tone of a story specified by a story generation engine and apply it to each scene.

[0847] "Application Example 1"

[0848] (Claim 1)

[0849] A means for receiving multiple image information,

[0850] An analysis means for extracting data from received image information,

[0851] A means for receiving and analyzing textual information in natural language form,

[0852] A means of generating a story based on image information and text information,

[0853] Means for creating visual effects according to the generated narrative,

[0854] Means for generating and presenting visual effects,

[0855] A means of sharing visual effects with users via a dedicated terminal,

[0856] A system that includes this.

[0857] (Claim 2)

[0858] The system according to claim 1, comprising an image analysis module for identifying characteristics based on image information, and further using these characteristics to draw objects within a visual effect.

[0859] (Claim 3)

[0860] The system according to claim 1, comprising means for performing sentiment analysis of textual information and adjusting the visual effect scenario based on the results of this analysis.

[0861] "Example 2 of combining an emotion engine"

[0862] (Claim 1)

[0863] A means for receiving multiple visual data,

[0864] An analysis means for extracting feature information from received visual data,

[0865] A means for receiving and analyzing speech data in natural language format,

[0866] A means of generating a story based on visual and audio data,

[0867] A means of analyzing user emotional data and reflecting it in the story,

[0868] A means of creating moving images according to the generated story,

[0869] A means for generating and presenting moving image data,

[0870] A system that includes this.

[0871] (Claim 2)

[0872] The system according to claim 1, comprising a visual recognition module for identifying an object based on visual data, and further using this object to draw a character in a moving image.

[0873] (Claim 3)

[0874] The system according to claim 1, comprising means for performing emotion analysis on audio data and adjusting the story of a video based on the results of this analysis.

[0875] "Application example 2 when combining with an emotional engine"

[0876] (Claim 1)

[0877] A means for receiving multiple visual data,

[0878] An analysis means for extracting features from received visual data,

[0879] Means for receiving and analyzing data in language format,

[0880] A means of generating a story based on visual data and linguistic data,

[0881] A means of creating moving images according to the generated story,

[0882] A means for generating and presenting moving image data,

[0883] A means of recognizing emotional states and reflecting them in narratives and moving images,

[0884] A system that includes this.

[0885] (Claim 2)

[0886] The system according to claim 1, comprising means for drawing an object in a moving image using features determined based on visual data, and further for selecting audio and sound effects.

[0887] (Claim 3)

[0888] The system according to claim 1, comprising means for personalizing the progression of a story and the scenario of a moving image based on emotional analysis of linguistic data. [Explanation of symbols]

[0889] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for receiving multiple image information, An analysis means for extracting data from received image information, A means for receiving and analyzing textual information in natural language form, A means of generating a story based on image information and text information, Means for creating visual effects according to the generated narrative, Means for generating and presenting visual effects, A means of sharing visual effects with users via a dedicated terminal, A system that includes this.

2. The system according to claim 1, comprising an image analysis module for identifying characteristics based on image information, and further using these characteristics to draw an object within a visual effect.

3. The system according to claim 1, comprising means for performing sentiment analysis of textual information and adjusting the visual effect scenario based on the results of this analysis.

Images