system

Abstract

We provide the system. [Solution] Natural language processing tools, A means for generating an animation data structure based on the analyzed information, A means of automatically generating animations using generation technology based on the generated data structure, A means of rendering the generated animation, A means of outputting the rendered animation, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a 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] Conventional animation production tools have problems such as restrictions on templates and styles, which limit the creativity of creators. In addition, there are many manual production processes, which require time and labor, so there has been a demand for a system that can achieve efficient and diverse animation expressions.

Means for Solving the Problems

[0005] This invention provides a system that understands user requests using natural language processing and generates animation data structures based on those requests. It includes means for automatically generating animations using generation techniques and then rendering them for visualization. Furthermore, it has the capability to regenerate and adjust animations based on feedback, and enables efficient and diverse animation production by transmitting the generated animations to remote terminals via a network.

[0006] "Natural language processing" refers to a technology that analyzes natural language information input by a user and extracts useful keywords and concepts from it.

[0007] An "animation data structure" is a collection of data containing the elements and attributes necessary for animation generation, created based on the analyzed information.

[0008] "Generative technology" refers to the technology used to automatically generate animations based on pre-built models.

[0009] "Rendering" is the process of representing the generated animation data in a visual format, and it is the process of creating the final animation file.

[0010] "User feedback" refers to information that shows users' evaluations, opinions for improvement, and requests regarding the generated animations.

[0011] "Means of regenerating or adjusting" refers to a function that, based on user feedback, regenerates existing animations or adjusts specific elements.

[0012] "Means of transmission via a network" refers to technologies for transferring generated animations to terminals in other locations via communication networks such as the Internet. [Brief explanation of the drawing]

[0013] [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] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] An example of an embodiment of the system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, the 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.

[0017] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0019] 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).

[0020] 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."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] This invention relates to a system in which a user inputs animation production requests in natural language, and a server analyzes these requests and automatically generates diverse and high-quality animations. The system executes a series of processes on the server, including natural language analysis, data structure generation, animation generation, rendering, and user interaction.

[0035] The user first uses their device to input their specific animation request in natural language. For example, they might request, "We need a dynamic animation that emphasizes technological innovation for the promotion of our new product." This information is then sent to the server.

[0036] The server uses natural language processing (NLP) to analyze the received natural language requests. This extracts important keywords and concepts from the requests and defines the elements necessary for animation generation.

[0037] Next, the server uses the generated elements to create the animation's data structure. This data structure includes specific elements that make up the animation, such as background, style, color, and character movement.

[0038] The server then automatically generates animations using generation technology. The generated animations are designed to meet the user's requirements, adhering to specified styles and themes.

[0039] Once generation is complete, the server renders the animation, creating a high-quality visual representation. This rendered animation is then sent to the user's device, where it can be previewed and downloaded.

[0040] Users can review the animations sent to their devices and send feedback to the server if necessary. The server has the ability to regenerate or fine-tune the animations based on this feedback. This allows users to efficiently create a wide variety of animations.

[0041] In this invention, network communication between the server and the user terminal is smooth, enabling rapid animation generation and verification. This allows creators to achieve more creative and diverse expressions.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The user enters their animation request in natural language on their device. The entered request is sent to the server through the application.

[0045] Step 2:

[0046] The server uses natural language processing to analyze the user's request. This analysis extracts keywords and important concepts from the input text.

[0047] Step 3:

[0048] The server generates an animation data structure based on the extracted information. This data structure defines the elements and attributes that make up the animation and organizes the generation conditions.

[0049] Step 4:

[0050] The server activates the generation technology and automatically generates animations using the organized data structure as input. In this generation step, a deep learning model is used to create a variety of visual styles.

[0051] Step 5:

[0052] The server renders the generated animation. High-quality graphics processing is performed, and the final animation video file is formed.

[0053] Step 6:

[0054] The server sends the rendered animation to the user's device over the network. The user can then view this animation on their device.

[0055] Step 7:

[0056] Users review the animation on their device and send feedback to the server as needed. This feedback includes requests for adjustments and changes.

[0057] Step 8:

[0058] The server regenerates or adjusts the animation based on user feedback. The server then sends the revised animation back to the user for confirmation.

[0059] (Example 1)

[0060] 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."

[0061] In modern content creation, there is a growing need for rapid and diverse animation generation. However, traditional methods require specialized knowledge and complex processes, posing challenges in terms of time and effort. Furthermore, it is difficult to make flexible adjustments that reflect user feedback. There is a need for a new system that can effectively solve these problems.

[0062] 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.

[0063] In this invention, the server includes means for analyzing natural language and extracting information, means for generating a data model based on the analyzed information, and means for automatically generating a visual representation from the data model using generative AI technology. This allows users to quickly generate diverse and high-quality animations without requiring specialized knowledge, and to further adjust them based on feedback.

[0064] "Methods for analyzing natural language and extracting information" refers to technologies that process natural language input from users and extract useful keywords and concepts.

[0065] "Means for generating data models based on analyzed information" refers to techniques for constructing a data structure that forms the basis for creating visual representations, based on extracted information.

[0066] "Methods for automatically generating visual representations from data models using generative AI technology" refers to technologies that use generative models to directly create animations and graphics from data models.

[0067] "Means for converting automatically generated visual representations through computational processing" refers to techniques that perform computational processing to change the generated visual representations into the optimal format.

[0068] "Means for transmitting the converted visual representation to an external device" refers to a technology for transmitting the processed visual representation to a user's terminal or other device.

[0069] "A means of receiving input from a user and sending information to a system" refers to the technology for receiving user input and sending that information to a server.

[0070] "Means of modifying visual representations based on feedback received from input information" refers to technologies for regenerating or adjusting existing visual representations based on user opinions and requests.

[0071] The embodiments for carrying out the present invention are described below.

[0072] The user first inputs their animation production requirements in natural language via their terminal. At this time, the user uses prompt phrases such as, "We need a dynamic animation that emphasizes technological innovation for the promotion of our new product." This input is then sent from the user's terminal to the server.

[0073] The server analyzes the received request using natural language processing (NLP) techniques. This process utilizes natural language processing technology. Specifically, it extracts keywords and concepts using text analysis software. This analysis defines the elements necessary for generating the animation.

[0074] Next, the server generates a data model based on the analyzed information. This data model includes the elements that make up the visual representation, such as background, color scheme, and character movements. The software used here is data structure generation software integrated with a database system.

[0075] Next, the server uses a generative AI model to automatically generate animations from the generated data model. The generative AI model utilizes machine learning algorithms and designs animations using patterns learned from past data. In this process, the animations are created to adhere to specified styles and themes.

[0076] The server then renders the animation using a high-performance graphics processor (GPU). Real-time rendering technology is used to obtain results quickly and with high quality. This rendered animation is generated in a digital video file format.

[0077] The completed animation is sent from the server to the user's terminal, where the user can freely preview and download it. The terminal uses an appropriate media player to display the received digital content.

[0078] When a user reviews an animation and provides feedback, that feedback is sent back from the device to the server. The server then regenerates or adjusts the animation based on the feedback. This process supports iterative work to obtain the final animation desired by the user.

[0079] Through the methods described above, users can efficiently create diverse and high-quality animations without requiring specialized knowledge.

[0080] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0081] Step 1:

[0082] The user inputs their animation request in natural language through the terminal. The prompt text the user enters might be something like, "We need a dynamic animation that emphasizes technological innovation for the promotion of our new product." Once the user confirms their input, the terminal sends the data to the server.

[0083] Step 2:

[0084] The server analyzes requests received from terminals using natural language processing (NLP) techniques. The input data includes a prompt, which the server analyzes using NLP to extract keywords and key concepts, such as "technological innovation" or "dynamic." This analysis result then serves as input for the next process.

[0085] Step 3:

[0086] The server generates a data model based on the analyzed information. The input data consists of extracted keywords and concepts, which the server uses to construct a data structure containing each element of the animation (e.g., background, style, character movement). The generated data structure serves as the foundational data for automatically generating animations.

[0087] Step 4:

[0088] The server uses this data model as input to automatically generate animations using a generative AI model. The generative AI model leverages machine learning algorithms and designs appropriate scenes and movements using patterns learned from past data. The output of this process is an initial version of the completed animation.

[0089] Step 5:

[0090] The server renders the generated animation to ensure high quality. The input data is the initial animation, which the server visually optimizes using a dedicated graphics processor (GPU). The rendered animation is then processed into a format that the user can view.

[0091] Step 6:

[0092] The rendered animation is sent from the server to the user's device. The device uses an appropriate media player to play the received animation, providing the user with an environment where they can smoothly preview it.

[0093] Step 7:

[0094] Users view the animation on their device and send feedback to the server as needed. User opinions and requests for modifications regarding the played animation are transmitted to the server via the device.

[0095] Step 8:

[0096] The server receives feedback from the user, performs necessary data processing and calculations, and regenerates or fine-tunes the animation. The adjustments are determined by the input feedback, and the process is repeated to create the final animation that meets the user's requirements.

[0097] (Application Example 1)

[0098] 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."

[0099] Current advertising production processes require the rapid and efficient generation of high-quality animations. However, traditional methods require significant time, effort, and specialized knowledge, making them difficult to implement. Furthermore, customization to meet specific user requests is challenging, often resulting in animations that do not meet expectations. To address these issues, a system is needed that can rapidly and automatically generate high-quality animations for advertising based on natural language instructions from users, and that can be adjusted based on user feedback.

[0100] 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.

[0101] In this invention, the server includes a natural language analysis means, a means for generating an animation information structure based on the analyzed information, and a means for automatically generating a video representation using generation technology based on the generated information structure. This makes it possible to automatically generate high-quality animations based on specific requests entered by the user in natural language, thereby streamlining the advertising production process.

[0102] A "natural language processing method" is a technique for analyzing natural language text entered by a user and clearly extracting its meaning and intent.

[0103] "Means for generating the information structure of animation" refers to a function that creates a data structure to represent the components and characteristics of animation based on the analysis results.

[0104] "Means for automatically generating visual representations using generation technology" refers to technology for automatically converting animations into visual representations based on data structures.

[0105] "Means of creating visual representations" refers to the function of processing and outputting generated visual representations in a way that humans can visually recognize.

[0106] "Means for constructing video expression for the purpose of advertising production based on input information" refers to a technology that constructs video content in a form optimized for advertising according to user input information.

[0107] "Means of receiving user evaluation information" refers to a function that allows users to provide feedback and evaluations of the generated animations.

[0108] "Means for regenerating or adjusting visual expression based on evaluation information" refers to a function for regenerating animations by making improvements and corrections in accordance with user evaluations.

[0109] "Means of transmitting to a remote information terminal via a communication network" refers to technology that transmits generated video representations to a user's terminal in another location via a network.

[0110] The system that implements this technology consists of elements such as users, servers, and terminals. Users input requests for the creation of promotional animations for advertising purposes in natural language through their terminals. These requests are then transmitted to the server via the network.

[0111] The server utilizes generative AI models and natural language processing techniques to analyze user requests. Specifically, it uses natural language processing models such as GPT-3 (registered trademark) to extract important keywords and intentions from the input language information.

[0112] Based on the analyzed information, the server generates an information structure for the animation. This involves assembling necessary elements such as background, style, color, and movement into a data structure. After this, generation technology is applied to automatically generate the visual representation based on the information structure. At this stage, high-precision rendering is performed using WebGL.

[0113] The generated video is delivered to the user's device. The user can visually review the animation and provide feedback. This feedback is sent back to the server, which has the capability to regenerate the animation and make further adjustments as needed.

[0114] This system enables efficient and high-quality animation generation in advertising production. For example, when a user enters a prompt such as "Create an animation highlighting the features of an environmentally friendly product," the AI ​​generates a sophisticated advertising animation based on this prompt. This approach allows users to obtain effective advertising content in a short amount of time.

[0115] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0116] Step 1:

[0117] The user inputs their animation production requests in natural language via their device. These requests are then transmitted to the server via the network. In this case, the user inputs a specific animation request based on a "generating AI model and prompt text." The server receives natural language data as output for analysis.

[0118] Step 2:

[0119] The server analyzes the received natural language data using natural language processing (NLP) tools. Here, natural language processing models such as BERT and GPT-3 are used to extract important keywords and concepts from the input text, and based on these, the elements necessary for animation generation are identified. The output consists of the analyzed keywords and structured data.

[0120] Step 3:

[0121] The server generates the animation's information structure based on the analyzed data. In this step, it uses the extracted elements to assemble a data structure that includes details such as background, style, color, and character movement. The input is the data analyzed in the previous step, and the output is the animation's renderable information structure.

[0122] Step 4:

[0123] The server automatically generates visual representations using generation technology. Specifically, it uses WebGL to visually render information structures. The input is the information structure, and the output is an animation visualized for the user.

[0124] Step 5:

[0125] The server sends the generated video representation to the user's terminal. The user can preview the animation on their terminal and check the overall composition and movement. The input is the rendered animation, and the output is the viewable animation provided to the user.

[0126] Step 6:

[0127] The user returns feedback to the server based on the animation preview. This feedback may include suggestions for improvement or additional requests. The input is the previewed animation, and the output is the feedback data.

[0128] Step 7:

[0129] The server regenerates or adjusts the animation based on user feedback. Necessary corrections are made, and an improved animation is generated. In this step, the feedback is analyzed, and a new information structure is generated and rendered. The input is the feedback data, and the output is the adjusted new animation.

[0130] This series of processes enables users to efficiently create high-quality advertising animations.

[0131] 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.

[0132] This invention provides a system that, in addition to allowing users to input animation production requests in natural language, recognizes the user's emotions using an emotion engine and reflects that information in the generated animation. This system operates on a server and provides a process for receiving input from the user terminal and generating and adjusting the animation.

[0133] The user first inputs their animation request in natural language using their device. This request provides specific instructions regarding the content and style of the animation, and may include something like, "I want a cheerful animation that will please customers." In addition, the emotion engine analyzes the user's emotional state through their input and subsequent interactions. This emotion analysis is performed based on factors such as voice tone, text content, and the user's physical reactions.

[0134] The server analyzes the received information using natural language processing techniques and generates an animation data structure based on the keywords and emotional states obtained. This data structure reflects the output from the emotion engine and includes elements to adjust the overall tone, such as incorporating bright colors and cheerful music if the user is expressing joy.

[0135] Subsequently, the server automatically generates animations using generative technology. In this step, the outputs of a general generative engine and an emotion engine are integrated to form an animation optimized for the user's emotions. The generated animation is then rendered by the server, resulting in a high-quality visual representation.

[0136] The completed animation is sent from the server to the user's device, where the user can review it. The user can review the animation and send feedback to the server. This feedback includes requests for regeneration or adjustment of the animation based on re-evaluation by the emotion engine. Based on this feedback, the server will start the animation regeneration process as needed and ask the user for confirmation again.

[0137] Thus, the present invention adds an emotion recognition element to the conventional animation generation process, enabling the creation of more personalized animations that respond to the user's emotions. This allows users to easily generate more sophisticated and emotionally appealing expressions.

[0138] The following describes the processing flow.

[0139] Step 1:

[0140] The user uses their device to input animation requests in natural language. This input includes the animation style, theme, and desired emotional effect.

[0141] Step 2:

[0142] The terminal sends the entered request data to the server. Here, the request is encoded as digital data.

[0143] Step 3:

[0144] The server uses natural language processing to analyze the submitted request. Key keywords and themes are extracted from the analysis results.

[0145] Step 4:

[0146] The emotion engine analyzes the user's emotions through their device, camera, and microphone. Voice tone, facial expressions, and input content are used for emotion analysis.

[0147] Step 5:

[0148] The server receives the sentiment analysis results and integrates them with the natural language analysis results to generate an animation data structure. This data structure includes visual and musical requirements that reflect the emotional state.

[0149] Step 6:

[0150] The server's generation technology automatically generates animations based on the created data structure. The generated animations will be tailored to emotions and themes.

[0151] Step 7:

[0152] The server-generated animation is rendered to create the final visual content. The rendering process includes high-quality graphics and sound processing.

[0153] Step 8:

[0154] The server sends the rendered animation to the user's device. The user can then view and review it.

[0155] Step 9:

[0156] Users can review animations generated using their devices. They can also send feedback to the server regarding any dissatisfaction or areas for improvement.

[0157] Step 10:

[0158] The server regenerates or adjusts animations based on user feedback. If necessary, the generated content is revised by re-evaluating the emotion engine.

[0159] (Example 2)

[0160] 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".

[0161] Traditional animation generation processes have struggled to efficiently create personalized animations that reflect user emotions. In particular, there has been a need to quickly incorporate natural emotional changes and feedback based on user requests. Therefore, an automated animation generation system incorporating emotion recognition is required.

[0162] 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.

[0163] In this invention, the server includes a natural language processing means, a means for recognizing an emotional state based on the analyzed information, and a means for generating an animation data structure that reflects the recognized emotional state. This enables the automatic generation of animations that respond to the user's emotions and the adjustment of animations based on individual feedback.

[0164] "Natural language processing" is a processing technology that interprets text data entered by users and understands its meaning.

[0165] "Means for recognizing emotional states" refers to technologies or devices that analyze and determine a user's emotions based on user input and interaction.

[0166] "Means for generating animation data structures" refers to a process or technique for defining and assembling animation materials and components based on analysis results and emotional states.

[0167] "Generative technology" refers to methods and techniques for processing information based on specific inputs or instructions, and for automatically generating content as a result.

[0168] "Rendering means" refers to a technology or device for visually or cinematically representing the generated animation or graphics.

[0169] "Communication means" refers to technology or equipment for sending and receiving information, and has the function of transmitting data to a remote information processing device via a network.

[0170] This invention is a system that allows users to input animation requests and generates personalized animations that reflect those emotions. The system is primarily server-based, receiving and processing input from the user's terminal.

[0171] The user inputs their animation request in natural language via their terminal. This input is sent to the server as a prompt. For example, a prompt might say, "I would like an animation set in a peaceful winter mountain landscape." Based on this prompt, the server uses natural language processing to analyze the text.

[0172] The server uses an emotion engine to recognize the analyzed information and emotional state. The emotion engine identifies the user's emotions while considering the content of the text. Next, it generates an animation data structure based on the recognized emotional state and the results of natural language analysis.

[0173] Using generative technology, the server automatically creates animations. At this stage, a generative AI model is utilized to build animations optimized for the user's emotions. The generated animations are then visualized as high-quality visuals through rendering methods.

[0174] The completed animation is sent from the server to the user's terminal, where the user can view it. For example, the system can generate and provide an animation featuring a snowy landscape and gentle music in response to the user's prompts. In this way, the system can provide unique animations that reflect the user's emotions and desires.

[0175] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0176] Step 1:

[0177] Users input their animation requests in natural language through their terminals. This input is sent to the server as a prompt. For example, a user might input, "I want an animation set in a peaceful winter mountain landscape." The entered text is treated as important information for understanding the user's intent.

[0178] Step 2:

[0179] The server analyzes the prompt text using natural language processing (NLP) techniques. This analysis extracts keywords and themes from the text. For example, keywords such as "winter mountain" and "calm" are extracted. The analyzed data is then used as input for the next sentiment analysis step.

[0180] Step 3:

[0181] The server uses an emotion engine to analyze the emotional state expressed by the user. Input includes keywords obtained from natural language processing and the overall tone of the text. If audio data is included, voice tone analysis is also performed. This helps identify the likelihood that the user is relaxed. Based on this information, the emotional elements necessary for the animation are determined.

[0182] Step 4:

[0183] The server generates an animation data structure based on the recognized emotional state and analysis results. Based on the input keywords and emotional information, the structure selects the background and music. For example, a winter mountain background and calm music elements might be incorporated into the data.

[0184] Step 5:

[0185] The server uses a generative AI model to automatically generate animations from the data structure. This creates animation sequences optimized for user emotions and prompts. The generated animations are then sent to the subsequent rendering process.

[0186] Step 6:

[0187] The server renders the animation and outputs it as high-quality video. This results in an animation that is visually appealing and matches the user's desires and emotions.

[0188] Step 7:

[0189] The completed animation is sent from the server to the user's device. The user views the animation on their device to see the overall picture. This is an important process because the user's impressions and feedback on the provided animation will lead to the next step.

[0190] Step 8:

[0191] After viewing an animation, users send feedback from their device to the server. Based on this feedback, the server regenerates or adjusts the animation as needed. The feedback system allows the process to flexibly adapt to ensure the optimal output is tailored to the user's satisfaction level.

[0192] (Application Example 2)

[0193] 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 device 14 will be referred to as the "terminal."

[0194] Conventional animation generation systems struggle to provide content that resonates with individual users' emotions, resulting in a uniform and unpersonalized viewing experience. Furthermore, they lack mechanisms for efficiently incorporating user feedback, making individual content optimization difficult.

[0195] 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.

[0196] In this invention, the server includes means for natural language processing, means for generating animation structures based on the processed information, and means for analyzing the user's emotional state and forming animations that reflect those emotions. This makes it possible to automatically generate personalized animations that respond to the user's emotions and provide a personalized visual experience tailored to the viewer.

[0197] "Natural language processing means" refers to technology that analyzes natural language data entered by a user, understands its content, and extracts information necessary for animation generation.

[0198] "Means for generating animation structure" refers to techniques for forming the data structure that forms the framework of an animation based on analyzed information.

[0199] "A means of analyzing a user's emotional state and creating animations that reflect those emotions" refers to a technology that detects a user's emotions and reflects those emotions in animations that visually represent those emotions.

[0200] "Methods for automatically generating animations using generative technology" refers to technologies that automatically create animations using artificial methods by utilizing the generated data structure.

[0201] "Means of converting into visual expression" refers to the technology that processes the generated animation into a viewable format and outputs it as a final video.

[0202] "Means of outputting visual representations" refers to technologies that use appropriate output methods to provide users with visually complete animations.

[0203] "A means of transmitting animations to a user's electronic device and providing a personalized visual experience" refers to a technology that delivers generated animations to the user's terminal via a network, providing a visual experience tailored to the user's individual needs.

[0204] To implement this invention, a system integrating natural language processing technology, emotion recognition technology, generation technology, and communication technology is required. The server first uses natural language processing means to analyze the user's natural language input received from the terminal. Through this analysis, information regarding the content and style of the animation desired by the user is extracted, and the necessary animation structure is generated.

[0205] Next, the server analyzes the user's emotional state using emotion recognition technology based on further input or continuous interaction from the terminal. This allows the server to determine the atmosphere and tone of the animation in a way that aligns with the user's emotions. Then, using generation technology, it automatically generates the animation based on the data structure and emotional information.

[0206] The generated visual content is converted into a visual representation and transmitted to the user's device via a communication network. The device receives this content and provides it to the user in a viewable format, thereby offering the user a personalized visual experience.

[0207] For example, when a user enters a prompt such as "I want an animation to reduce stress," the server can analyze the request and generate content incorporating brighter colors and calming music that will shift the user's emotions toward a more relaxed state. In this way, the system can easily provide a visual experience that resonates with the user's emotions.

[0208] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0209] Step 1:

[0210] The user enters natural language prompts using a terminal. These prompts express the user's animation requests. The entered prompts are then sent from the terminal to the server.

[0211] Step 2:

[0212] The server analyzes the received prompt using natural language processing. From the analyzed data, it extracts keywords related to the animation's content and style. Based on this keyword information, the initial data structure for the animation is generated.

[0213] Step 3:

[0214] The user provides emotion-related data through an emotion recognition sensor or tracking device installed in their device. The server receives this feedback and analyzes the user's emotional state using emotion recognition technology. The user's emotional state is output as a result of the analysis.

[0215] Step 4:

[0216] The server automatically generates animations using a generative AI model based on the generated animation's data structure and analyzed emotional state. This generation method adjusts the animation's colors, music, character movements, and other elements to match the user's emotions.

[0217] Step 5:

[0218] The generated animation is converted into a visual representation on the server. This visual representation is then completed with video and audio elements, making it viewable.

[0219] Step 6:

[0220] The server sends the generated visual representation to the terminal via the network. The terminal receives the animation, and the user can view this content. The user can also send feedback to the server during viewing and request further adjustments.

[0221] 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.

[0222] Data generation model 58 is a 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 the following. 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 indicated 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.

[0223] 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.

[0224] [Second Embodiment]

[0225] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0226] 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.

[0227] 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).

[0228] 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.

[0229] 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.

[0230] 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).

[0231] 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.

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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.

[0236] 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".

[0237] This invention relates to a system in which a user inputs animation production requests in natural language, and a server analyzes these requests and automatically generates diverse and high-quality animations. The system executes a series of processes on the server, including natural language analysis, data structure generation, animation generation, rendering, and user interaction.

[0238] The user first uses their device to input their specific animation request in natural language. For example, they might request, "We need a dynamic animation that emphasizes technological innovation for the promotion of our new product." This information is then sent to the server.

[0239] The server uses natural language processing (NLP) to analyze the received natural language requests. This extracts important keywords and concepts from the requests and defines the elements necessary for animation generation.

[0240] Next, the server uses the generated elements to create the animation's data structure. This data structure includes specific elements that make up the animation, such as background, style, color, and character movement.

[0241] The server then automatically generates animations using generation technology. The generated animations are designed to meet the user's requirements, adhering to specified styles and themes.

[0242] Once generation is complete, the server renders the animation, creating a high-quality visual representation. This rendered animation is then sent to the user's device, where it can be previewed and downloaded.

[0243] Users can review the animations sent to their devices and send feedback to the server if necessary. The server has the ability to regenerate or fine-tune the animations based on this feedback. This allows users to efficiently create a wide variety of animations.

[0244] In this invention, network communication between the server and the user terminal is smooth, enabling rapid animation generation and verification. This allows creators to achieve more creative and diverse expressions.

[0245] The following describes the processing flow.

[0246] Step 1:

[0247] The user enters their animation request in natural language on their device. The entered request is sent to the server through the application.

[0248] Step 2:

[0249] The server uses natural language processing to analyze the user's request. This analysis extracts keywords and important concepts from the input text.

[0250] Step 3:

[0251] The server generates an animation data structure based on the extracted information. This data structure defines the elements and attributes that make up the animation and organizes the generation conditions.

[0252] Step 4:

[0253] The server activates the generation technology and automatically generates animations using the organized data structure as input. In this generation step, a deep learning model is used to create a variety of visual styles.

[0254] Step 5:

[0255] The server renders the generated animation. High-quality graphics processing is performed, and the final animation video file is formed.

[0256] Step 6:

[0257] The server sends the rendered animation to the user's device over the network. The user can then view this animation on their device.

[0258] Step 7:

[0259] Users review the animation on their device and send feedback to the server as needed. This feedback includes requests for adjustments and changes.

[0260] Step 8:

[0261] The server regenerates or adjusts the animation based on user feedback. The server then sends the revised animation back to the user for confirmation.

[0262] (Example 1)

[0263] 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."

[0264] In modern content creation, there is a growing need for rapid and diverse animation generation. However, traditional methods require specialized knowledge and complex processes, posing challenges in terms of time and effort. Furthermore, it is difficult to make flexible adjustments that reflect user feedback. There is a need for a new system that can effectively solve these problems.

[0265] 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.

[0266] In this invention, the server includes means for analyzing natural language and extracting information, means for generating a data model based on the analyzed information, and means for automatically generating a visual representation from the data model using generative AI technology. This allows users to quickly generate diverse and high-quality animations without requiring specialized knowledge, and to further adjust them based on feedback.

[0267] "Methods for analyzing natural language and extracting information" refers to technologies that process natural language input from users and extract useful keywords and concepts.

[0268] "Means for generating data models based on analyzed information" refers to techniques for constructing a data structure that forms the basis for creating visual representations, based on extracted information.

[0269] "Methods for automatically generating visual representations from data models using generative AI technology" refers to technologies that use generative models to directly create animations and graphics from data models.

[0270] "Means for converting automatically generated visual representations through computational processing" refers to techniques that perform computational processing to change the generated visual representations into the optimal format.

[0271] "Means for transmitting the converted visual representation to an external device" refers to a technology for transmitting the processed visual representation to a user's terminal or other device.

[0272] "A means of receiving input from a user and sending information to a system" refers to the technology for receiving user input and sending that information to a server.

[0273] "Means of modifying visual representations based on feedback received from input information" refers to technologies for regenerating or adjusting existing visual representations based on user opinions and requests.

[0274] The embodiments for carrying out the present invention are described below.

[0275] The user first inputs their animation production requirements in natural language via their terminal. At this time, the user uses prompt phrases such as, "We need a dynamic animation that emphasizes technological innovation for the promotion of our new product." This input is then sent from the user's terminal to the server.

[0276] The server analyzes the received request using natural language processing (NLP) techniques. This process utilizes natural language processing technology. Specifically, it extracts keywords and concepts using text analysis software. This analysis defines the elements necessary for generating the animation.

[0277] Next, the server generates a data model based on the analyzed information. This data model includes the elements that make up the visual representation, such as background, color scheme, and character movements. The software used here is data structure generation software integrated with a database system.

[0278] Next, the server uses a generative AI model to automatically generate animations from the generated data model. The generative AI model utilizes machine learning algorithms and designs animations using patterns learned from past data. In this process, the animations are created to adhere to specified styles and themes.

[0279] The server then renders the animation using a high-performance graphics processor (GPU). Real-time rendering technology is used to obtain results quickly and with high quality. This rendered animation is generated in a digital video file format.

[0280] The completed animation is sent from the server to the user's terminal, where the user can freely preview and download it. The terminal uses an appropriate media player to display the received digital content.

[0281] When a user reviews an animation and provides feedback, that feedback is sent back from the device to the server. The server then regenerates or adjusts the animation based on the feedback. This process supports iterative work to obtain the final animation desired by the user.

[0282] With the above method, users can efficiently create diverse and high-quality animations without the need for specialized knowledge.

[0283] The flow of the specific process in Example 1 will be described using FIG. 11.

[0284] Step 1:

[0285] The user inputs an animation request in natural language through the terminal. At this time, the prompt sentence input by the user is something like "A dynamic animation highlighting technological innovation is required for the promotion of new products." When the user's input is finalized, the terminal sends the data to the server.

[0286] Step 2:

[0287] The server analyzes the request received from the terminal using natural language analysis means. The input data includes the prompt sentence, and the server analyzes this sentence using natural language processing technology to extract keywords and important concepts, such as "technological innovation" and "dynamic". The analysis result becomes the input for the next process.

[0288] Step 3:

[0289] The server generates a data model based on the analyzed information. The input data is the extracted keywords and concepts, and the server uses these to construct a data structure including each element of the animation (e.g., background, style, character movement). The generated data structure becomes the basic data for automatically generating the animation.

[0290] Step 4:

[0291] The server uses this data model as input to automatically generate animations using a generative AI model. The generative AI model leverages machine learning algorithms and designs appropriate scenes and movements using patterns learned from past data. The output of this process is an initial version of the completed animation.

[0292] Step 5:

[0293] The server renders the generated animation to ensure high quality. The input data is the initial animation, which the server visually optimizes using a dedicated graphics processor (GPU). The rendered animation is then processed into a format that the user can view.

[0294] Step 6:

[0295] The rendered animation is sent from the server to the user's device. The device uses an appropriate media player to play the received animation, providing the user with an environment where they can smoothly preview it.

[0296] Step 7:

[0297] Users view the animation on their device and send feedback to the server as needed. User opinions and requests for modifications regarding the played animation are transmitted to the server via the device.

[0298] Step 8:

[0299] The server receives feedback from the user, performs necessary data processing and calculations, and regenerates or fine-tunes the animation. The adjustments are determined by the input feedback, and the process is repeated to create the final animation that meets the user's requirements.

[0300] (Application Example 1)

[0301] 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 glasses 214 will be referred to as the "terminal."

[0302] Current advertising production processes require the rapid and efficient generation of high-quality animations. However, traditional methods require significant time, effort, and specialized knowledge, making them difficult to implement. Furthermore, customization to meet specific user requests is challenging, often resulting in animations that do not meet expectations. To address these issues, a system is needed that can rapidly and automatically generate high-quality animations for advertising based on natural language instructions from users, and that can be adjusted based on user feedback.

[0303] 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.

[0304] In this invention, the server includes a natural language analysis means, a means for generating an animation information structure based on the analyzed information, and a means for automatically generating a video representation using generation technology based on the generated information structure. This makes it possible to automatically generate high-quality animations based on specific requests entered by the user in natural language, thereby streamlining the advertising production process.

[0305] A "natural language processing method" is a technique for analyzing natural language text entered by a user and clearly extracting its meaning and intent.

[0306] "Means for generating the information structure of animation" refers to a function that creates a data structure to represent the components and characteristics of animation based on the analysis results.

[0307] "Means for automatically generating visual representations using generation technology" refers to technology for automatically converting animations into visual representations based on data structures.

[0308] The "means for visual representation" is a function that processes and outputs the generated video representation in a form that can be visually recognized by humans.

[0309] The "means for constructing a video representation for advertising production based on input information" is a technology that constructs the content of a video in a form optimized for advertising according to the input information of the user.

[0310] The "means for receiving evaluation information from the user" is a function that receives feedback and evaluation provided by the user for the generated animation.

[0311] The "means for regenerating or adjusting a video representation based on evaluation information" is a function for performing improvements and corrections according to the evaluation of the user and regenerating the animation.

[0312] The "means for transmitting to a remote information terminal through a communication network" is a technology that transmits the generated video representation to the terminal of a user in another location via a network.

[0313] The system that realizes this technology is composed of elements such as a user, a server, and a terminal. The user inputs a request for producing a promotional animation for advertising in natural language through the terminal. This request is transmitted to the server via the network.

[0314] The server utilizes a generation AI model and analyzes the user's request using natural language analysis means. Specifically, it uses a natural language processing model such as GPT-3 to extract important keywords and intentions from the input language information.

[0315] Based on the analyzed information, the server generates an information structure for the animation. This involves assembling necessary elements such as background, style, color, and movement into a data structure. After this, generation technology is applied to automatically generate the visual representation based on the information structure. At this stage, high-precision rendering is performed using WebGL.

[0316] The generated video is delivered to the user's device. The user can visually review the animation and provide feedback. This feedback is sent back to the server, which has the capability to regenerate the animation and make further adjustments as needed.

[0317] This system enables efficient and high-quality animation generation in advertising production. For example, when a user enters a prompt such as "Create an animation highlighting the features of an environmentally friendly product," the AI ​​generates a sophisticated advertising animation based on this prompt. This approach allows users to obtain effective advertising content in a short amount of time.

[0318] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0319] Step 1:

[0320] The user inputs their animation production requests in natural language via their device. These requests are then transmitted to the server via the network. In this case, the user inputs a specific animation request based on a "generating AI model and prompt text." The server receives natural language data as output for analysis.

[0321] Step 2:

[0322] The server analyzes the received natural language data using natural language processing (NLP) tools. Here, natural language processing models such as BERT and GPT-3 are used to extract important keywords and concepts from the input text, and based on these, the elements necessary for animation generation are identified. The output consists of the analyzed keywords and structured data.

[0323] Step 3:

[0324] The server generates the animation's information structure based on the analyzed data. In this step, it uses the extracted elements to assemble a data structure that includes details such as background, style, color, and character movement. The input is the data analyzed in the previous step, and the output is the animation's renderable information structure.

[0325] Step 4:

[0326] The server automatically generates visual representations using generation technology. Specifically, it uses WebGL to visually render information structures. The input is the information structure, and the output is an animation visualized for the user.

[0327] Step 5:

[0328] The server sends the generated video representation to the user's terminal. The user can preview the animation on their terminal and check the overall composition and movement. The input is the rendered animation, and the output is the viewable animation provided to the user.

[0329] Step 6:

[0330] The user returns feedback to the server based on the animation preview. This feedback may include suggestions for improvement or additional requests. The input is the previewed animation, and the output is the feedback data.

[0331] Step 7:

[0332] The server regenerates or adjusts the animation based on user feedback. Necessary corrections are made, and an improved animation is generated. In this step, the feedback is analyzed, and a new information structure is generated and rendered. The input is the feedback data, and the output is the adjusted new animation.

[0333] This series of processes enables users to efficiently create high-quality advertising animations.

[0334] 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.

[0335] This invention provides a system that, in addition to allowing users to input animation production requests in natural language, recognizes the user's emotions using an emotion engine and reflects that information in the generated animation. This system operates on a server and provides a process for receiving input from the user terminal and generating and adjusting the animation.

[0336] The user first inputs their animation request in natural language using their device. This request provides specific instructions regarding the content and style of the animation, and may include something like, "I want a cheerful animation that will please customers." In addition, the emotion engine analyzes the user's emotional state through their input and subsequent interactions. This emotion analysis is performed based on factors such as voice tone, text content, and the user's physical reactions.

[0337] The server analyzes the received information using natural language processing techniques and generates an animation data structure based on the keywords and emotional states obtained. This data structure reflects the output from the emotion engine and includes elements to adjust the overall tone, such as incorporating bright colors and cheerful music if the user is expressing joy.

[0338] Subsequently, the server automatically generates animations using generative technology. In this step, the outputs of a general generative engine and an emotion engine are integrated to form an animation optimized for the user's emotions. The generated animation is then rendered by the server, resulting in a high-quality visual representation.

[0339] The completed animation is sent from the server to the user's device, where the user can review it. The user can review the animation and send feedback to the server. This feedback includes requests for regeneration or adjustment of the animation based on re-evaluation by the emotion engine. Based on this feedback, the server will start the animation regeneration process as needed and ask the user for confirmation again.

[0340] Thus, the present invention adds an emotion recognition element to the conventional animation generation process, enabling the creation of more personalized animations that respond to the user's emotions. This allows users to easily generate more sophisticated and emotionally appealing expressions.

[0341] The following describes the processing flow.

[0342] Step 1:

[0343] The user uses their device to input animation requests in natural language. This input includes the animation style, theme, and desired emotional effect.

[0344] Step 2:

[0345] The terminal sends the entered request data to the server. Here, the request is encoded as digital data.

[0346] Step 3:

[0347] The server uses natural language processing to analyze the submitted request. Key keywords and themes are extracted from the analysis results.

[0348] Step 4:

[0349] The emotion engine analyzes the user's emotions through their device, camera, and microphone. Voice tone, facial expressions, and input content are used for emotion analysis.

[0350] Step 5:

[0351] The server receives the sentiment analysis results and integrates them with the natural language analysis results to generate an animation data structure. This data structure includes visual and musical requirements that reflect the emotional state.

[0352] Step 6:

[0353] The server's generation technology automatically generates animations based on the created data structure. The generated animations will be tailored to emotions and themes.

[0354] Step 7:

[0355] The server-generated animation is rendered to create the final visual content. The rendering process includes high-quality graphics and sound processing.

[0356] Step 8:

[0357] The server sends the rendered animation to the user's device. The user can then view and review it.

[0358] Step 9:

[0359] Users can review animations generated using their devices. They can also send feedback to the server regarding any dissatisfaction or areas for improvement.

[0360] Step 10:

[0361] The server regenerates or adjusts animations based on user feedback. If necessary, the generated content is revised by re-evaluating the emotion engine.

[0362] (Example 2)

[0363] 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".

[0364] Traditional animation generation processes have struggled to efficiently create personalized animations that reflect user emotions. In particular, there has been a need to quickly incorporate natural emotional changes and feedback based on user requests. Therefore, an automated animation generation system incorporating emotion recognition is required.

[0365] 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.

[0366] In this invention, the server includes a natural language processing means, a means for recognizing an emotional state based on the analyzed information, and a means for generating an animation data structure that reflects the recognized emotional state. This enables the automatic generation of animations that respond to the user's emotions and the adjustment of animations based on individual feedback.

[0367] "Natural language processing" is a processing technology that interprets text data entered by users and understands its meaning.

[0368] "Means for recognizing emotional states" refers to technologies or devices that analyze and determine a user's emotions based on user input and interaction.

[0369] "Means for generating animation data structures" refers to a process or technique for defining and assembling animation materials and components based on analysis results and emotional states.

[0370] "Generative technology" refers to methods and techniques for processing information based on specific inputs or instructions, and for automatically generating content as a result.

[0371] "Rendering means" refers to a technology or device for visually or cinematically representing the generated animation or graphics.

[0372] "Communication means" refers to technology or equipment for sending and receiving information, and has the function of transmitting data to a remote information processing device via a network.

[0373] This invention is a system that allows users to input animation requests and generates personalized animations that reflect those emotions. The system is primarily server-based, receiving and processing input from the user's terminal.

[0374] The user inputs their animation request in natural language via their terminal. This input is sent to the server as a prompt. For example, a prompt might say, "I would like an animation set in a peaceful winter mountain landscape." Based on this prompt, the server uses natural language processing to analyze the text.

[0375] The server uses an emotion engine to recognize the analyzed information and emotional state. The emotion engine identifies the user's emotions while considering the content of the text. Next, it generates an animation data structure based on the recognized emotional state and the results of natural language analysis.

[0376] Using generative technology, the server automatically creates animations. At this stage, a generative AI model is utilized to build animations optimized for the user's emotions. The generated animations are then visualized as high-quality visuals through rendering methods.

[0377] The completed animation is sent from the server to the user's terminal, where the user can view it. For example, the system can generate and provide an animation featuring a snowy landscape and gentle music in response to the user's prompts. In this way, the system can provide unique animations that reflect the user's emotions and desires.

[0378] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0379] Step 1:

[0380] Users input their animation requests in natural language through their terminals. This input is sent to the server as a prompt. For example, a user might input, "I want an animation set in a peaceful winter mountain landscape." The entered text is treated as important information for understanding the user's intent.

[0381] Step 2:

[0382] The server analyzes the prompt text using natural language processing (NLP) techniques. This analysis extracts keywords and themes from the text. For example, keywords such as "winter mountain" and "calm" are extracted. The analyzed data is then used as input for the next sentiment analysis step.

[0383] Step 3:

[0384] The server uses an emotion engine to analyze the emotional state expressed by the user. Input includes keywords obtained from natural language processing and the overall tone of the text. If audio data is included, voice tone analysis is also performed. This helps identify the likelihood that the user is relaxed. Based on this information, the emotional elements necessary for the animation are determined.

[0385] Step 4:

[0386] The server generates an animation data structure based on the recognized emotional state and analysis results. Based on the input keywords and emotional information, the structure selects the background and music. For example, a winter mountain background and calm music elements might be incorporated into the data.

[0387] Step 5:

[0388] The server uses a generative AI model to automatically generate animations from the data structure. This creates animation sequences optimized for user emotions and prompts. The generated animations are then sent to the subsequent rendering process.

[0389] Step 6:

[0390] The server renders the animation and outputs it as high-quality video. This results in an animation that is visually appealing and matches the user's desires and emotions.

[0391] Step 7:

[0392] The completed animation is sent from the server to the user's device. The user views the animation on their device to see the overall picture. This is an important process because the user's impressions and feedback on the provided animation will lead to the next step.

[0393] Step 8:

[0394] After viewing an animation, users send feedback from their device to the server. Based on this feedback, the server regenerates or adjusts the animation as needed. The feedback system allows the process to flexibly adapt to ensure the optimal output is tailored to the user's satisfaction level.

[0395] (Application Example 2)

[0396] 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."

[0397] Conventional animation generation systems struggle to provide content that resonates with individual users' emotions, resulting in a uniform and unpersonalized viewing experience. Furthermore, they lack mechanisms for efficiently incorporating user feedback, making individual content optimization difficult.

[0398] 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.

[0399] In this invention, the server includes means for natural language processing, means for generating animation structures based on the processed information, and means for analyzing the user's emotional state and forming animations that reflect those emotions. This makes it possible to automatically generate personalized animations that respond to the user's emotions and provide a personalized visual experience tailored to the viewer.

[0400] "Natural language processing means" refers to technology that analyzes natural language data entered by a user, understands its content, and extracts information necessary for animation generation.

[0401] "Means for generating animation structure" refers to techniques for forming the data structure that forms the framework of an animation based on analyzed information.

[0402] "A means of analyzing a user's emotional state and creating animations that reflect those emotions" refers to a technology that detects a user's emotions and reflects those emotions in animations that visually represent those emotions.

[0403] "Methods for automatically generating animations using generative technology" refers to technologies that automatically create animations using artificial methods by utilizing the generated data structure.

[0404] "Means of converting into visual expression" refers to the technology that processes the generated animation into a viewable format and outputs it as a final video.

[0405] "Means of outputting visual representations" refers to technologies that use appropriate output methods to provide users with visually complete animations.

[0406] "A means of transmitting animations to a user's electronic device and providing a personalized visual experience" refers to a technology that delivers generated animations to the user's terminal via a network, providing a visual experience tailored to the user's individual needs.

[0407] To implement this invention, a system integrating natural language processing technology, emotion recognition technology, generation technology, and communication technology is required. The server first uses natural language processing means to analyze the user's natural language input received from the terminal. Through this analysis, information regarding the content and style of the animation desired by the user is extracted, and the necessary animation structure is generated.

[0408] Next, the server analyzes the user's emotional state using emotion recognition technology based on further input or continuous interaction from the terminal. This allows the server to determine the atmosphere and tone of the animation in a way that aligns with the user's emotions. Then, using generation technology, it automatically generates the animation based on the data structure and emotional information.

[0409] The generated visual content is converted into a visual representation and transmitted to the user's device via a communication network. The device receives this content and provides it to the user in a viewable format, thereby offering the user a personalized visual experience.

[0410] For example, when a user enters a prompt such as "I want an animation to reduce stress," the server can analyze the request and generate content incorporating brighter colors and calming music that will shift the user's emotions toward a more relaxed state. In this way, the system can easily provide a visual experience that resonates with the user's emotions.

[0411] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0412] Step 1:

[0413] The user enters natural language prompts using a terminal. These prompts express the user's animation requests. The entered prompts are then sent from the terminal to the server.

[0414] Step 2:

[0415] The server analyzes the received prompt using natural language processing. From the analyzed data, it extracts keywords related to the animation's content and style. Based on this keyword information, the initial data structure for the animation is generated.

[0416] Step 3:

[0417] The user provides emotion-related data through an emotion recognition sensor or tracking device installed in their device. The server receives this feedback and analyzes the user's emotional state using emotion recognition technology. The user's emotional state is output as a result of the analysis.

[0418] Step 4:

[0419] The server automatically generates animations using a generative AI model based on the generated animation's data structure and analyzed emotional state. This generation method adjusts the animation's colors, music, character movements, and other elements to match the user's emotions.

[0420] Step 5:

[0421] The generated animation is converted into a visual representation on the server. This visual representation is then completed with video and audio elements, making it viewable.

[0422] Step 6:

[0423] The server sends the generated visual representation to the terminal via the network. The terminal receives the animation, and the user can view this content. The user can also send feedback to the server during viewing and request further adjustments.

[0424] 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.

[0425] 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 the following. 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 indicated 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.

[0426] 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.

[0427] [Third Embodiment]

[0428] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0429] 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.

[0430] 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).

[0431] 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.

[0432] 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.

[0433] 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).

[0434] 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.

[0435] 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.

[0436] 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.

[0437] 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.

[0438] 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.

[0439] 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".

[0440] This invention relates to a system in which a user inputs animation production requests in natural language, and a server analyzes these requests and automatically generates diverse and high-quality animations. The system executes a series of processes on the server, including natural language analysis, data structure generation, animation generation, rendering, and user interaction.

[0441] The user first uses their device to input their specific animation request in natural language. For example, they might request, "We need a dynamic animation that emphasizes technological innovation for the promotion of our new product." This information is then sent to the server.

[0442] The server uses natural language processing (NLP) to analyze the received natural language requests. This extracts important keywords and concepts from the requests and defines the elements necessary for animation generation.

[0443] Next, the server uses the generated elements to create the animation's data structure. This data structure includes specific elements that make up the animation, such as background, style, color, and character movement.

[0444] The server then automatically generates animations using generation technology. The generated animations are designed to meet the user's requirements, adhering to specified styles and themes.

[0445] Once generation is complete, the server renders the animation, creating a high-quality visual representation. This rendered animation is then sent to the user's device, where it can be previewed and downloaded.

[0446] Users can review the animations sent to their devices and send feedback to the server if necessary. The server has the ability to regenerate or fine-tune the animations based on this feedback. This allows users to efficiently create a wide variety of animations.

[0447] In this invention, network communication between the server and the user terminal is smooth, enabling rapid animation generation and verification. This allows creators to achieve more creative and diverse expressions.

[0448] The following describes the processing flow.

[0449] Step 1:

[0450] The user enters their animation request in natural language on their device. The entered request is sent to the server through the application.

[0451] Step 2:

[0452] The server uses natural language processing to analyze the user's request. This analysis extracts keywords and important concepts from the input text.

[0453] Step 3:

[0454] The server generates an animation data structure based on the extracted information. This data structure defines the elements and attributes that make up the animation and organizes the generation conditions.

[0455] Step 4:

[0456] The server activates the generation technology and automatically generates animations using the organized data structure as input. In this generation step, a deep learning model is used to create a variety of visual styles.

[0457] Step 5:

[0458] The server renders the generated animation. High-quality graphics processing is performed, and the final animation video file is formed.

[0459] Step 6:

[0460] The server sends the rendered animation to the user's device over the network. The user can then view this animation on their device.

[0461] Step 7:

[0462] Users review the animation on their device and send feedback to the server as needed. This feedback includes requests for adjustments and changes.

[0463] Step 8:

[0464] The server regenerates or adjusts the animation based on user feedback. The server then sends the revised animation back to the user for confirmation.

[0465] (Example 1)

[0466] 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."

[0467] In modern content creation, there is a growing need for rapid and diverse animation generation. However, traditional methods require specialized knowledge and complex processes, posing challenges in terms of time and effort. Furthermore, it is difficult to make flexible adjustments that reflect user feedback. There is a need for a new system that can effectively solve these problems.

[0468] 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.

[0469] In this invention, the server includes means for analyzing natural language and extracting information, means for generating a data model based on the analyzed information, and means for automatically generating a visual representation from the data model using generative AI technology. This allows users to quickly generate diverse and high-quality animations without requiring specialized knowledge, and to further adjust them based on feedback.

[0470] "Methods for analyzing natural language and extracting information" refers to technologies that process natural language input from users and extract useful keywords and concepts.

[0471] "Means for generating data models based on analyzed information" refers to techniques for constructing a data structure that forms the basis for creating visual representations, based on extracted information.

[0472] "Methods for automatically generating visual representations from data models using generative AI technology" refers to technologies that use generative models to directly create animations and graphics from data models.

[0473] "Means for converting automatically generated visual representations through computational processing" refers to techniques that perform computational processing to change the generated visual representations into the optimal format.

[0474] "Means for transmitting the converted visual representation to an external device" refers to a technology for transmitting the processed visual representation to a user's terminal or other device.

[0475] "A means of receiving input from a user and sending information to a system" refers to the technology for receiving user input and sending that information to a server.

[0476] "Means of modifying visual representations based on feedback received from input information" refers to technologies for regenerating or adjusting existing visual representations based on user opinions and requests.

[0477] The embodiments for carrying out the present invention are described below.

[0478] The user first inputs their animation production requirements in natural language via their terminal. At this time, the user uses prompt phrases such as, "We need a dynamic animation that emphasizes technological innovation for the promotion of our new product." This input is then sent from the user's terminal to the server.

[0479] The server analyzes the received request using natural language processing (NLP) techniques. This process utilizes natural language processing technology. Specifically, it extracts keywords and concepts using text analysis software. This analysis defines the elements necessary for generating the animation.

[0480] Next, the server generates a data model based on the analyzed information. This data model includes the elements that make up the visual representation, such as background, color scheme, and character movements. The software used here is data structure generation software integrated with a database system.

[0481] Next, the server uses a generative AI model to automatically generate animations from the generated data model. The generative AI model utilizes machine learning algorithms and designs animations using patterns learned from past data. In this process, the animations are created to adhere to specified styles and themes.

[0482] The server then renders the animation using a high-performance graphics processor (GPU). Real-time rendering technology is used to obtain results quickly and with high quality. This rendered animation is generated in a digital video file format.

[0483] The completed animation is sent from the server to the user's terminal, where the user can freely preview and download it. The terminal uses an appropriate media player to display the received digital content.

[0484] When a user reviews an animation and provides feedback, that feedback is sent back from the device to the server. The server then regenerates or adjusts the animation based on the feedback. This process supports iterative work to obtain the final animation desired by the user.

[0485] Through the methods described above, users can efficiently create diverse and high-quality animations without requiring specialized knowledge.

[0486] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0487] Step 1:

[0488] The user inputs their animation request in natural language through the terminal. The prompt text the user enters might be something like, "We need a dynamic animation that emphasizes technological innovation for the promotion of our new product." Once the user confirms their input, the terminal sends the data to the server.

[0489] Step 2:

[0490] The server analyzes requests received from terminals using natural language processing (NLP) techniques. The input data includes a prompt, which the server analyzes using NLP to extract keywords and key concepts, such as "technological innovation" or "dynamic." This analysis result then serves as input for the next process.

[0491] Step 3:

[0492] The server generates a data model based on the analyzed information. The input data consists of extracted keywords and concepts, which the server uses to construct a data structure containing each element of the animation (e.g., background, style, character movement). The generated data structure serves as the foundational data for automatically generating animations.

[0493] Step 4:

[0494] The server uses this data model as input to automatically generate animations using a generative AI model. The generative AI model leverages machine learning algorithms and designs appropriate scenes and movements using patterns learned from past data. The output of this process is an initial version of the completed animation.

[0495] Step 5:

[0496] The server renders the generated animation to ensure high quality. The input data is the initial animation, which the server visually optimizes using a dedicated graphics processor (GPU). The rendered animation is then processed into a format that the user can view.

[0497] Step 6:

[0498] The rendered animation is sent from the server to the user's device. The device uses an appropriate media player to play the received animation, providing the user with an environment where they can smoothly preview it.

[0499] Step 7:

[0500] Users view the animation on their device and send feedback to the server as needed. User opinions and requests for modifications regarding the played animation are transmitted to the server via the device.

[0501] Step 8:

[0502] The server receives feedback from the user, performs necessary data processing and calculations, and regenerates or fine-tunes the animation. The adjustments are determined by the input feedback, and the process is repeated to create the final animation that meets the user's requirements.

[0503] (Application Example 1)

[0504] 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."

[0505] Current advertising production processes require the rapid and efficient generation of high-quality animations. However, traditional methods require significant time, effort, and specialized knowledge, making them difficult to implement. Furthermore, customization to meet specific user requests is challenging, often resulting in animations that do not meet expectations. To address these issues, a system is needed that can rapidly and automatically generate high-quality animations for advertising based on natural language instructions from users, and that can be adjusted based on user feedback.

[0506] 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.

[0507] In this invention, the server includes a natural language analysis means, a means for generating an animation information structure based on the analyzed information, and a means for automatically generating a video representation using generation technology based on the generated information structure. This makes it possible to automatically generate high-quality animations based on specific requests entered by the user in natural language, thereby streamlining the advertising production process.

[0508] A "natural language processing method" is a technique for analyzing natural language text entered by a user and clearly extracting its meaning and intent.

[0509] "Means for generating the information structure of animation" refers to a function that creates a data structure to represent the components and characteristics of animation based on the analysis results.

[0510] "Means for automatically generating visual representations using generation technology" refers to technology for automatically converting animations into visual representations based on data structures.

[0511] "Means of creating visual representations" refers to the function of processing and outputting generated visual representations in a way that humans can visually recognize.

[0512] "Means for constructing video expression for the purpose of advertising production based on input information" refers to a technology that constructs video content in a form optimized for advertising according to user input information.

[0513] "Means of receiving user evaluation information" refers to a function that allows users to provide feedback and evaluations of the generated animations.

[0514] "Means for regenerating or adjusting visual expression based on evaluation information" refers to a function for regenerating animations by making improvements and corrections in accordance with user evaluations.

[0515] "Means of transmitting to a remote information terminal via a communication network" refers to technology that transmits generated video representations to a user's terminal in another location via a network.

[0516] The system that implements this technology consists of elements such as users, servers, and terminals. Users input requests for the creation of promotional animations for advertising purposes in natural language through their terminals. These requests are then transmitted to the server via the network.

[0517] The server utilizes generative AI models and natural language processing techniques to analyze user requests. Specifically, it uses natural language processing models such as GPT-3 to extract important keywords and intentions from the input language information.

[0518] Based on the analyzed information, the server generates an information structure for the animation. This involves assembling necessary elements such as background, style, color, and movement into a data structure. After this, generation technology is applied to automatically generate the visual representation based on the information structure. At this stage, high-precision rendering is performed using WebGL.

[0519] The generated video is delivered to the user's device. The user can visually review the animation and provide feedback. This feedback is sent back to the server, which has the capability to regenerate the animation and make further adjustments as needed.

[0520] This system enables efficient and high-quality animation generation in advertising production. For example, when a user enters a prompt such as "Create an animation highlighting the features of an environmentally friendly product," the AI ​​generates a sophisticated advertising animation based on this prompt. This approach allows users to obtain effective advertising content in a short amount of time.

[0521] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0522] Step 1:

[0523] The user inputs their animation production requests in natural language via their device. These requests are then transmitted to the server via the network. In this case, the user inputs a specific animation request based on a "generating AI model and prompt text." The server receives natural language data as output for analysis.

[0524] Step 2:

[0525] The server analyzes the received natural language data using natural language processing (NLP) tools. Here, natural language processing models such as BERT and GPT-3 are used to extract important keywords and concepts from the input text, and based on these, the elements necessary for animation generation are identified. The output consists of the analyzed keywords and structured data.

[0526] Step 3:

[0527] The server generates the animation's information structure based on the analyzed data. In this step, it uses the extracted elements to assemble a data structure that includes details such as background, style, color, and character movement. The input is the data analyzed in the previous step, and the output is the animation's renderable information structure.

[0528] Step 4:

[0529] The server automatically generates visual representations using generation technology. Specifically, it uses WebGL to visually render information structures. The input is the information structure, and the output is an animation visualized for the user.

[0530] Step 5:

[0531] The server sends the generated video representation to the user's terminal. The user can preview the animation on their terminal and check the overall composition and movement. The input is the rendered animation, and the output is the viewable animation provided to the user.

[0532] Step 6:

[0533] The user returns feedback to the server based on the animation preview. This feedback may include suggestions for improvement or additional requests. The input is the previewed animation, and the output is the feedback data.

[0534] Step 7:

[0535] The server regenerates or adjusts the animation based on user feedback. Necessary corrections are made, and an improved animation is generated. In this step, the feedback is analyzed, and a new information structure is generated and rendered. The input is the feedback data, and the output is the adjusted new animation.

[0536] This series of processes enables users to efficiently create high-quality advertising animations.

[0537] 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.

[0538] This invention provides a system that, in addition to allowing users to input animation production requests in natural language, recognizes the user's emotions using an emotion engine and reflects that information in the generated animation. This system operates on a server and provides a process for receiving input from the user terminal and generating and adjusting the animation.

[0539] The user first inputs their animation request in natural language using their device. This request provides specific instructions regarding the content and style of the animation, and may include something like, "I want a cheerful animation that will please customers." In addition, the emotion engine analyzes the user's emotional state through their input and subsequent interactions. This emotion analysis is performed based on factors such as voice tone, text content, and the user's physical reactions.

[0540] The server analyzes the received information using natural language processing techniques and generates an animation data structure based on the keywords and emotional states obtained. This data structure reflects the output from the emotion engine and includes elements to adjust the overall tone, such as incorporating bright colors and cheerful music if the user is expressing joy.

[0541] Subsequently, the server automatically generates animations using generative technology. In this step, the outputs of a general generative engine and an emotion engine are integrated to form an animation optimized for the user's emotions. The generated animation is then rendered by the server, resulting in a high-quality visual representation.

[0542] The completed animation is sent from the server to the user's device, where the user can review it. The user can review the animation and send feedback to the server. This feedback includes requests for regeneration or adjustment of the animation based on re-evaluation by the emotion engine. Based on this feedback, the server will start the animation regeneration process as needed and ask the user for confirmation again.

[0543] Thus, the present invention adds an emotion recognition element to the conventional animation generation process, enabling the creation of more personalized animations that respond to the user's emotions. This allows users to easily generate more sophisticated and emotionally appealing expressions.

[0544] The following describes the processing flow.

[0545] Step 1:

[0546] The user uses their device to input animation requests in natural language. This input includes the animation style, theme, and desired emotional effect.

[0547] Step 2:

[0548] The terminal sends the entered request data to the server. Here, the request is encoded as digital data.

[0549] Step 3:

[0550] The server uses natural language processing to analyze the submitted request. Key keywords and themes are extracted from the analysis results.

[0551] Step 4:

[0552] The emotion engine analyzes the user's emotions through their device, camera, and microphone. Voice tone, facial expressions, and input content are used for emotion analysis.

[0553] Step 5:

[0554] The server receives the sentiment analysis results and integrates them with the natural language analysis results to generate an animation data structure. This data structure includes visual and musical requirements that reflect the emotional state.

[0555] Step 6:

[0556] The server's generation technology automatically generates animations based on the created data structure. The generated animations will be tailored to emotions and themes.

[0557] Step 7:

[0558] The server-generated animation is rendered to create the final visual content. The rendering process includes high-quality graphics and sound processing.

[0559] Step 8:

[0560] The server sends the rendered animation to the user's device. The user can then view and review it.

[0561] Step 9:

[0562] Users can review animations generated using their devices. They can also send feedback to the server regarding any dissatisfaction or areas for improvement.

[0563] Step 10:

[0564] The server regenerates or adjusts animations based on user feedback. If necessary, the generated content is revised by re-evaluating the emotion engine.

[0565] (Example 2)

[0566] 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."

[0567] Traditional animation generation processes have struggled to efficiently create personalized animations that reflect user emotions. In particular, there has been a need to quickly incorporate natural emotional changes and feedback based on user requests. Therefore, an automated animation generation system incorporating emotion recognition is required.

[0568] 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.

[0569] In this invention, the server includes a natural language processing means, a means for recognizing an emotional state based on the analyzed information, and a means for generating an animation data structure that reflects the recognized emotional state. This enables the automatic generation of animations that respond to the user's emotions and the adjustment of animations based on individual feedback.

[0570] "Natural language processing" is a processing technology that interprets text data entered by users and understands its meaning.

[0571] "Means for recognizing emotional states" refers to technologies or devices that analyze and determine a user's emotions based on user input and interaction.

[0572] "Means for generating animation data structures" refers to a process or technique for defining and assembling animation materials and components based on analysis results and emotional states.

[0573] "Generative technology" refers to methods and techniques for processing information based on specific inputs or instructions, and for automatically generating content as a result.

[0574] "Rendering means" refers to a technology or device for visually or cinematically representing the generated animation or graphics.

[0575] "Communication means" refers to technology or equipment for sending and receiving information, and has the function of transmitting data to a remote information processing device via a network.

[0576] This invention is a system that allows users to input animation requests and generates personalized animations that reflect those emotions. The system is primarily server-based, receiving and processing input from the user's terminal.

[0577] The user inputs their animation request in natural language via their terminal. This input is sent to the server as a prompt. For example, a prompt might say, "I would like an animation set in a peaceful winter mountain landscape." Based on this prompt, the server uses natural language processing to analyze the text.

[0578] The server uses an emotion engine to recognize the analyzed information and emotional state. The emotion engine identifies the user's emotions while considering the content of the text. Next, it generates an animation data structure based on the recognized emotional state and the results of natural language analysis.

[0579] Using generative technology, the server automatically creates animations. At this stage, a generative AI model is utilized to build animations optimized for the user's emotions. The generated animations are then visualized as high-quality visuals through rendering methods.

[0580] The completed animation is sent from the server to the user's terminal, where the user can view it. For example, the system can generate and provide an animation featuring a snowy landscape and gentle music in response to the user's prompts. In this way, the system can provide unique animations that reflect the user's emotions and desires.

[0581] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0582] Step 1:

[0583] Users input their animation requests in natural language through their terminals. This input is sent to the server as a prompt. For example, a user might input, "I want an animation set in a peaceful winter mountain landscape." The entered text is treated as important information for understanding the user's intent.

[0584] Step 2:

[0585] The server analyzes the prompt text using natural language processing (NLP) techniques. This analysis extracts keywords and themes from the text. For example, keywords such as "winter mountain" and "calm" are extracted. The analyzed data is then used as input for the next sentiment analysis step.

[0586] Step 3:

[0587] The server uses an emotion engine to analyze the emotional state expressed by the user. Input includes keywords obtained from natural language processing and the overall tone of the text. If audio data is included, voice tone analysis is also performed. This helps identify the likelihood that the user is relaxed. Based on this information, the emotional elements necessary for the animation are determined.

[0588] Step 4:

[0589] The server generates an animation data structure based on the recognized emotional state and analysis results. Based on the input keywords and emotional information, the structure selects the background and music. For example, a winter mountain background and calm music elements might be incorporated into the data.

[0590] Step 5:

[0591] The server uses a generative AI model to automatically generate animations from the data structure. This creates animation sequences optimized for user emotions and prompts. The generated animations are then sent to the subsequent rendering process.

[0592] Step 6:

[0593] The server renders the animation and outputs it as high-quality video. This results in an animation that is visually appealing and matches the user's desires and emotions.

[0594] Step 7:

[0595] The completed animation is sent from the server to the user's device. The user views the animation on their device to see the overall picture. This is an important process because the user's impressions and feedback on the provided animation will lead to the next step.

[0596] Step 8:

[0597] After viewing an animation, users send feedback from their device to the server. Based on this feedback, the server regenerates or adjusts the animation as needed. The feedback system allows the process to flexibly adapt to ensure the optimal output is tailored to the user's satisfaction level.

[0598] (Application Example 2)

[0599] 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."

[0600] Conventional animation generation systems struggle to provide content that resonates with individual users' emotions, resulting in a uniform and unpersonalized viewing experience. Furthermore, they lack mechanisms for efficiently incorporating user feedback, making individual content optimization difficult.

[0601] 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.

[0602] In this invention, the server includes means for natural language processing, means for generating animation structures based on the processed information, and means for analyzing the user's emotional state and forming animations that reflect those emotions. This makes it possible to automatically generate personalized animations that respond to the user's emotions and provide a personalized visual experience tailored to the viewer.

[0603] "Natural language processing means" refers to technology that analyzes natural language data entered by a user, understands its content, and extracts information necessary for animation generation.

[0604] "Means for generating animation structure" refers to techniques for forming the data structure that forms the framework of an animation based on analyzed information.

[0605] "A means of analyzing a user's emotional state and creating animations that reflect those emotions" refers to a technology that detects a user's emotions and reflects those emotions in animations that visually represent those emotions.

[0606] "Methods for automatically generating animations using generative technology" refers to technologies that automatically create animations using artificial methods by utilizing the generated data structure.

[0607] "Means of converting into visual expression" refers to the technology that processes the generated animation into a viewable format and outputs it as a final video.

[0608] "Means of outputting visual representations" refers to technologies that use appropriate output methods to provide users with visually complete animations.

[0609] "A means of transmitting animations to a user's electronic device and providing a personalized visual experience" refers to a technology that delivers generated animations to the user's terminal via a network, providing a visual experience tailored to the user's individual needs.

[0610] To implement this invention, a system integrating natural language processing technology, emotion recognition technology, generation technology, and communication technology is required. The server first uses natural language processing means to analyze the user's natural language input received from the terminal. Through this analysis, information regarding the content and style of the animation desired by the user is extracted, and the necessary animation structure is generated.

[0611] Next, the server analyzes the user's emotional state using emotion recognition technology based on further input or continuous interaction from the terminal. This allows the server to determine the atmosphere and tone of the animation in a way that aligns with the user's emotions. Then, using generation technology, it automatically generates the animation based on the data structure and emotional information.

[0612] The generated visual content is converted into a visual representation and transmitted to the user's device via a communication network. The device receives this content and provides it to the user in a viewable format, thereby offering the user a personalized visual experience.

[0613] For example, when a user enters a prompt such as "I want an animation to reduce stress," the server can analyze the request and generate content incorporating brighter colors and calming music that will shift the user's emotions toward a more relaxed state. In this way, the system can easily provide a visual experience that resonates with the user's emotions.

[0614] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0615] Step 1:

[0616] The user enters natural language prompts using a terminal. These prompts express the user's animation requests. The entered prompts are then sent from the terminal to the server.

[0617] Step 2:

[0618] The server analyzes the received prompt using natural language processing. From the analyzed data, it extracts keywords related to the animation's content and style. Based on this keyword information, the initial data structure for the animation is generated.

[0619] Step 3:

[0620] The user provides emotion-related data through an emotion recognition sensor or tracking device installed in their device. The server receives this feedback and analyzes the user's emotional state using emotion recognition technology. The user's emotional state is output as a result of the analysis.

[0621] Step 4:

[0622] The server automatically generates animations using a generative AI model based on the generated animation's data structure and analyzed emotional state. This generation method adjusts the animation's colors, music, character movements, and other elements to match the user's emotions.

[0623] Step 5:

[0624] The generated animation is converted into a visual representation on the server. This visual representation is then completed with video and audio elements, making it viewable.

[0625] Step 6:

[0626] The server sends the generated visual representation to the terminal via the network. The terminal receives the animation, and the user can view this content. The user can also send feedback to the server during viewing and request further adjustments.

[0627] 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.

[0628] 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 the following. 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 indicated 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.

[0629] 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.

[0630] [Fourth Embodiment]

[0631] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0632] 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.

[0633] 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).

[0634] 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.

[0635] 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.

[0636] 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).

[0637] 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.

[0638] 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.

[0639] 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.

[0640] 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.

[0641] 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.

[0642] 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.

[0643] 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".

[0644] This invention relates to a system in which a user inputs animation production requests in natural language, and a server analyzes these requests and automatically generates diverse and high-quality animations. The system executes a series of processes on the server, including natural language analysis, data structure generation, animation generation, rendering, and user interaction.

[0645] The user first uses their device to input their specific animation request in natural language. For example, they might request, "We need a dynamic animation that emphasizes technological innovation for the promotion of our new product." This information is then sent to the server.

[0646] The server uses natural language processing (NLP) to analyze the received natural language requests. This extracts important keywords and concepts from the requests and defines the elements necessary for animation generation.

[0647] Next, the server uses the generated elements to create the animation's data structure. This data structure includes specific elements that make up the animation, such as background, style, color, and character movement.

[0648] The server then automatically generates animations using generation technology. The generated animations are designed to meet the user's requirements, adhering to specified styles and themes.

[0649] Once generation is complete, the server renders the animation, creating a high-quality visual representation. This rendered animation is then sent to the user's device, where it can be previewed and downloaded.

[0650] Users can review the animations sent to their devices and send feedback to the server if necessary. The server has the ability to regenerate or fine-tune the animations based on this feedback. This allows users to efficiently create a wide variety of animations.

[0651] In this invention, network communication between the server and the user terminal is smooth, enabling rapid animation generation and verification. This allows creators to achieve more creative and diverse expressions.

[0652] The following describes the processing flow.

[0653] Step 1:

[0654] The user enters their animation request in natural language on their device. The entered request is sent to the server through the application.

[0655] Step 2:

[0656] The server uses natural language processing to analyze the user's request. This analysis extracts keywords and important concepts from the input text.

[0657] Step 3:

[0658] The server generates an animation data structure based on the extracted information. This data structure defines the elements and attributes that make up the animation and organizes the generation conditions.

[0659] Step 4:

[0660] The server activates the generation technology and automatically generates animations using the organized data structure as input. In this generation step, a deep learning model is used to create a variety of visual styles.

[0661] Step 5:

[0662] The server renders the generated animation. High-quality graphics processing is performed, and the final animation video file is formed.

[0663] Step 6:

[0664] The server sends the rendered animation to the user's device over the network. The user can then view this animation on their device.

[0665] Step 7:

[0666] Users review the animation on their device and send feedback to the server as needed. This feedback includes requests for adjustments and changes.

[0667] Step 8:

[0668] The server regenerates or adjusts the animation based on user feedback. The server then sends the revised animation back to the user for confirmation.

[0669] (Example 1)

[0670] 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".

[0671] In modern content creation, there is a growing need for rapid and diverse animation generation. However, traditional methods require specialized knowledge and complex processes, posing challenges in terms of time and effort. Furthermore, it is difficult to make flexible adjustments that reflect user feedback. There is a need for a new system that can effectively solve these problems.

[0672] 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.

[0673] In this invention, the server includes means for analyzing natural language and extracting information, means for generating a data model based on the analyzed information, and means for automatically generating a visual representation from the data model using generative AI technology. This allows users to quickly generate diverse and high-quality animations without requiring specialized knowledge, and to further adjust them based on feedback.

[0674] "Methods for analyzing natural language and extracting information" refers to technologies that process natural language input from users and extract useful keywords and concepts.

[0675] "Means for generating data models based on analyzed information" refers to techniques for constructing a data structure that forms the basis for creating visual representations, based on extracted information.

[0676] "Methods for automatically generating visual representations from data models using generative AI technology" refers to technologies that use generative models to directly create animations and graphics from data models.

[0677] "Means for converting automatically generated visual representations through computational processing" refers to techniques that perform computational processing to change the generated visual representations into the optimal format.

[0678] "Means for transmitting the converted visual representation to an external device" refers to a technology for transmitting the processed visual representation to a user's terminal or other device.

[0679] "A means of receiving input from a user and sending information to a system" refers to the technology for receiving user input and sending that information to a server.

[0680] "Means of modifying visual representations based on feedback received from input information" refers to technologies for regenerating or adjusting existing visual representations based on user opinions and requests.

[0681] The embodiments for carrying out the present invention are described below.

[0682] The user first inputs their animation production requirements in natural language via their terminal. At this time, the user uses prompt phrases such as, "We need a dynamic animation that emphasizes technological innovation for the promotion of our new product." This input is then sent from the user's terminal to the server.

[0683] The server analyzes the received request using natural language processing (NLP) techniques. This process utilizes natural language processing technology. Specifically, it extracts keywords and concepts using text analysis software. This analysis defines the elements necessary for generating the animation.

[0684] Next, the server generates a data model based on the analyzed information. This data model includes the elements that make up the visual representation, such as background, color scheme, and character movements. The software used here is data structure generation software integrated with a database system.

[0685] Next, the server uses a generative AI model to automatically generate animations from the generated data model. The generative AI model utilizes machine learning algorithms and designs animations using patterns learned from past data. In this process, the animations are created to adhere to specified styles and themes.

[0686] The server then renders the animation using a high-performance graphics processor (GPU). Real-time rendering technology is used to obtain results quickly and with high quality. This rendered animation is generated in a digital video file format.

[0687] The completed animation is sent from the server to the user's terminal, where the user can freely preview and download it. The terminal uses an appropriate media player to display the received digital content.

[0688] When a user reviews an animation and provides feedback, that feedback is sent back from the device to the server. The server then regenerates or adjusts the animation based on the feedback. This process supports iterative work to obtain the final animation desired by the user.

[0689] Through the methods described above, users can efficiently create diverse and high-quality animations without requiring specialized knowledge.

[0690] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0691] Step 1:

[0692] The user inputs their animation request in natural language through the terminal. The prompt text the user enters might be something like, "We need a dynamic animation that emphasizes technological innovation for the promotion of our new product." Once the user confirms their input, the terminal sends the data to the server.

[0693] Step 2:

[0694] The server analyzes requests received from terminals using natural language processing (NLP) techniques. The input data includes a prompt, which the server analyzes using NLP to extract keywords and key concepts, such as "technological innovation" or "dynamic." This analysis result then serves as input for the next process.

[0695] Step 3:

[0696] The server generates a data model based on the analyzed information. The input data consists of extracted keywords and concepts, which the server uses to construct a data structure containing each element of the animation (e.g., background, style, character movement). The generated data structure serves as the foundational data for automatically generating animations.

[0697] Step 4:

[0698] The server uses this data model as input to automatically generate animations using a generative AI model. The generative AI model leverages machine learning algorithms and designs appropriate scenes and movements using patterns learned from past data. The output of this process is an initial version of the completed animation.

[0699] Step 5:

[0700] The server renders the generated animation to ensure high quality. The input data is the initial animation, which the server visually optimizes using a dedicated graphics processor (GPU). The rendered animation is then processed into a format that the user can view.

[0701] Step 6:

[0702] The rendered animation is sent from the server to the user's device. The device uses an appropriate media player to play the received animation, providing the user with an environment where they can smoothly preview it.

[0703] Step 7:

[0704] Users view the animation on their device and send feedback to the server as needed. User opinions and requests for modifications regarding the played animation are transmitted to the server via the device.

[0705] Step 8:

[0706] The server receives feedback from the user, performs necessary data processing and calculations, and regenerates or fine-tunes the animation. The adjustments are determined by the input feedback, and the process is repeated to create the final animation that meets the user's requirements.

[0707] (Application Example 1)

[0708] 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".

[0709] Current advertising production processes require the rapid and efficient generation of high-quality animations. However, traditional methods require significant time, effort, and specialized knowledge, making them difficult to implement. Furthermore, customization to meet specific user requests is challenging, often resulting in animations that do not meet expectations. To address these issues, a system is needed that can rapidly and automatically generate high-quality animations for advertising based on natural language instructions from users, and that can be adjusted based on user feedback.

[0710] 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.

[0711] In this invention, the server includes a natural language analysis means, a means for generating an animation information structure based on the analyzed information, and a means for automatically generating a video representation using generation technology based on the generated information structure. This makes it possible to automatically generate high-quality animations based on specific requests entered by the user in natural language, thereby streamlining the advertising production process.

[0712] A "natural language processing method" is a technique for analyzing natural language text entered by a user and clearly extracting its meaning and intent.

[0713] "Means for generating the information structure of animation" refers to a function that creates a data structure to represent the components and characteristics of animation based on the analysis results.

[0714] "Means for automatically generating visual representations using generation technology" refers to technology for automatically converting animations into visual representations based on data structures.

[0715] "Means of creating visual representations" refers to the function of processing and outputting generated visual representations in a way that humans can visually recognize.

[0716] "Means for constructing video expression for the purpose of advertising production based on input information" refers to a technology that constructs video content in a form optimized for advertising according to user input information.

[0717] "Means of receiving user evaluation information" refers to a function that allows users to provide feedback and evaluations of the generated animations.

[0718] "Means for regenerating or adjusting visual expression based on evaluation information" refers to a function for regenerating animations by making improvements and corrections in accordance with user evaluations.

[0719] "Means of transmitting to a remote information terminal via a communication network" refers to technology that transmits generated video representations to a user's terminal in another location via a network.

[0720] The system that implements this technology consists of elements such as users, servers, and terminals. Users input requests for the creation of promotional animations for advertising purposes in natural language through their terminals. These requests are then transmitted to the server via the network.

[0721] The server utilizes generative AI models and natural language processing techniques to analyze user requests. Specifically, it uses natural language processing models such as GPT-3 to extract important keywords and intentions from the input language information.

[0722] Based on the analyzed information, the server generates an information structure for the animation. This involves assembling necessary elements such as background, style, color, and movement into a data structure. After this, generation technology is applied to automatically generate the visual representation based on the information structure. At this stage, high-precision rendering is performed using WebGL.

[0723] The generated video is delivered to the user's device. The user can visually review the animation and provide feedback. This feedback is sent back to the server, which has the capability to regenerate the animation and make further adjustments as needed.

[0724] This system enables efficient and high-quality animation generation in advertising production. For example, when a user enters a prompt such as "Create an animation highlighting the features of an environmentally friendly product," the AI ​​generates a sophisticated advertising animation based on this prompt. This approach allows users to obtain effective advertising content in a short amount of time.

[0725] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0726] Step 1:

[0727] The user inputs their animation production requests in natural language via their device. These requests are then transmitted to the server via the network. In this case, the user inputs a specific animation request based on a "generating AI model and prompt text." The server receives natural language data as output for analysis.

[0728] Step 2:

[0729] The server analyzes the received natural language data using natural language processing (NLP) tools. Here, natural language processing models such as BERT and GPT-3 are used to extract important keywords and concepts from the input text, and based on these, the elements necessary for animation generation are identified. The output consists of the analyzed keywords and structured data.

[0730] Step 3:

[0731] The server generates the animation's information structure based on the analyzed data. In this step, it uses the extracted elements to assemble a data structure that includes details such as background, style, color, and character movement. The input is the data analyzed in the previous step, and the output is the animation's renderable information structure.

[0732] Step 4:

[0733] The server automatically generates visual representations using generation technology. Specifically, it uses WebGL to visually render information structures. The input is the information structure, and the output is an animation visualized for the user.

[0734] Step 5:

[0735] The server sends the generated video representation to the user's terminal. The user can preview the animation on their terminal and check the overall composition and movement. The input is the rendered animation, and the output is the viewable animation provided to the user.

[0736] Step 6:

[0737] The user returns feedback to the server based on the animation preview. This feedback may include suggestions for improvement or additional requests. The input is the previewed animation, and the output is the feedback data.

[0738] Step 7:

[0739] The server regenerates or adjusts the animation based on user feedback. Necessary corrections are made, and an improved animation is generated. In this step, the feedback is analyzed, and a new information structure is generated and rendered. The input is the feedback data, and the output is the adjusted new animation.

[0740] This series of processes enables users to efficiently create high-quality advertising animations.

[0741] 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.

[0742] This invention provides a system that, in addition to allowing users to input animation production requests in natural language, recognizes the user's emotions using an emotion engine and reflects that information in the generated animation. This system operates on a server and provides a process for receiving input from the user terminal and generating and adjusting the animation.

[0743] The user first inputs their animation request in natural language using their device. This request provides specific instructions regarding the content and style of the animation, and may include something like, "I want a cheerful animation that will please customers." In addition, the emotion engine analyzes the user's emotional state through their input and subsequent interactions. This emotion analysis is performed based on factors such as voice tone, text content, and the user's physical reactions.

[0744] The server analyzes the received information using natural language processing techniques and generates an animation data structure based on the keywords and emotional states obtained. This data structure reflects the output from the emotion engine and includes elements to adjust the overall tone, such as incorporating bright colors and cheerful music if the user is expressing joy.

[0745] Subsequently, the server automatically generates animations using generative technology. In this step, the outputs of a general generative engine and an emotion engine are integrated to form an animation optimized for the user's emotions. The generated animation is then rendered by the server, resulting in a high-quality visual representation.

[0746] The completed animation is sent from the server to the user's device, where the user can review it. The user can review the animation and send feedback to the server. This feedback includes requests for regeneration or adjustment of the animation based on re-evaluation by the emotion engine. Based on this feedback, the server will start the animation regeneration process as needed and ask the user for confirmation again.

[0747] Thus, the present invention adds an emotion recognition element to the conventional animation generation process, enabling the creation of more personalized animations that respond to the user's emotions. This allows users to easily generate more sophisticated and emotionally appealing expressions.

[0748] The following describes the processing flow.

[0749] Step 1:

[0750] The user uses their device to input animation requests in natural language. This input includes the animation style, theme, and desired emotional effect.

[0751] Step 2:

[0752] The terminal sends the entered request data to the server. Here, the request is encoded as digital data.

[0753] Step 3:

[0754] The server uses natural language processing to analyze the submitted request. Key keywords and themes are extracted from the analysis results.

[0755] Step 4:

[0756] The emotion engine analyzes the user's emotions through their device, camera, and microphone. Voice tone, facial expressions, and input content are used for emotion analysis.

[0757] Step 5:

[0758] The server receives the sentiment analysis results and integrates them with the natural language analysis results to generate an animation data structure. This data structure includes visual and musical requirements that reflect the emotional state.

[0759] Step 6:

[0760] The server's generation technology automatically generates animations based on the created data structure. The generated animations will be tailored to emotions and themes.

[0761] Step 7:

[0762] The server-generated animation is rendered to create the final visual content. The rendering process includes high-quality graphics and sound processing.

[0763] Step 8:

[0764] The server sends the rendered animation to the user's device. The user can then view and review it.

[0765] Step 9:

[0766] Users can review animations generated using their devices. They can also send feedback to the server regarding any dissatisfaction or areas for improvement.

[0767] Step 10:

[0768] The server regenerates or adjusts animations based on user feedback. If necessary, the generated content is revised by re-evaluating the emotion engine.

[0769] (Example 2)

[0770] 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".

[0771] Traditional animation generation processes have struggled to efficiently create personalized animations that reflect user emotions. In particular, there has been a need to quickly incorporate natural emotional changes and feedback based on user requests. Therefore, an automated animation generation system incorporating emotion recognition is required.

[0772] 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.

[0773] In this invention, the server includes a natural language processing means, a means for recognizing an emotional state based on the analyzed information, and a means for generating an animation data structure that reflects the recognized emotional state. This enables the automatic generation of animations that respond to the user's emotions and the adjustment of animations based on individual feedback.

[0774] "Natural language processing" is a processing technology that interprets text data entered by users and understands its meaning.

[0775] "Means for recognizing emotional states" refers to technologies or devices that analyze and determine a user's emotions based on user input and interaction.

[0776] "Means for generating animation data structures" refers to a process or technique for defining and assembling animation materials and components based on analysis results and emotional states.

[0777] "Generative technology" refers to methods and techniques for processing information based on specific inputs or instructions, and for automatically generating content as a result.

[0778] "Rendering means" refers to a technology or device for visually or cinematically representing the generated animation or graphics.

[0779] "Communication means" refers to technology or equipment for sending and receiving information, and has the function of transmitting data to a remote information processing device via a network.

[0780] This invention is a system that allows users to input animation requests and generates personalized animations that reflect those emotions. The system is primarily server-based, receiving and processing input from the user's terminal.

[0781] The user inputs their animation request in natural language via their terminal. This input is sent to the server as a prompt. For example, a prompt might say, "I would like an animation set in a peaceful winter mountain landscape." Based on this prompt, the server uses natural language processing to analyze the text.

[0782] The server uses an emotion engine to recognize the analyzed information and emotional state. The emotion engine identifies the user's emotions while considering the content of the text. Next, it generates an animation data structure based on the recognized emotional state and the results of natural language analysis.

[0783] Using generative technology, the server automatically creates animations. At this stage, a generative AI model is utilized to build animations optimized for the user's emotions. The generated animations are then visualized as high-quality visuals through rendering methods.

[0784] The completed animation is sent from the server to the user's terminal, where the user can view it. For example, the system can generate and provide an animation featuring a snowy landscape and gentle music in response to the user's prompts. In this way, the system can provide unique animations that reflect the user's emotions and desires.

[0785] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0786] Step 1:

[0787] Users input their animation requests in natural language through their terminals. This input is sent to the server as a prompt. For example, a user might input, "I want an animation set in a peaceful winter mountain landscape." The entered text is treated as important information for understanding the user's intent.

[0788] Step 2:

[0789] The server analyzes the prompt text using natural language processing (NLP) techniques. This analysis extracts keywords and themes from the text. For example, keywords such as "winter mountain" and "calm" are extracted. The analyzed data is then used as input for the next sentiment analysis step.

[0790] Step 3:

[0791] The server uses an emotion engine to analyze the emotional state expressed by the user. Input includes keywords obtained from natural language processing and the overall tone of the text. If audio data is included, voice tone analysis is also performed. This helps identify the likelihood that the user is relaxed. Based on this information, the emotional elements necessary for the animation are determined.

[0792] Step 4:

[0793] The server generates an animation data structure based on the recognized emotional state and analysis results. Based on the input keywords and emotional information, the structure selects the background and music. For example, a winter mountain background and calm music elements might be incorporated into the data.

[0794] Step 5:

[0795] The server uses a generative AI model to automatically generate animations from the data structure. This creates animation sequences optimized for user emotions and prompts. The generated animations are then sent to the subsequent rendering process.

[0796] Step 6:

[0797] The server renders the animation and outputs it as high-quality video. This results in an animation that is visually appealing and matches the user's desires and emotions.

[0798] Step 7:

[0799] The completed animation is sent from the server to the user's device. The user views the animation on their device to see the overall picture. This is an important process because the user's impressions and feedback on the provided animation will lead to the next step.

[0800] Step 8:

[0801] After viewing an animation, users send feedback from their device to the server. Based on this feedback, the server regenerates or adjusts the animation as needed. The feedback system allows the process to flexibly adapt to ensure the optimal output is tailored to the user's satisfaction level.

[0802] (Application Example 2)

[0803] 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".

[0804] Conventional animation generation systems struggle to provide content that resonates with individual users' emotions, resulting in a uniform and unpersonalized viewing experience. Furthermore, they lack mechanisms for efficiently incorporating user feedback, making individual content optimization difficult.

[0805] 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.

[0806] In this invention, the server includes means for natural language processing, means for generating animation structures based on the processed information, and means for analyzing the user's emotional state and forming animations that reflect those emotions. This makes it possible to automatically generate personalized animations that respond to the user's emotions and provide a personalized visual experience tailored to the viewer.

[0807] "Natural language processing means" refers to technology that analyzes natural language data entered by a user, understands its content, and extracts information necessary for animation generation.

[0808] "Means for generating animation structure" refers to techniques for forming the data structure that forms the framework of an animation based on analyzed information.

[0809] "A means of analyzing a user's emotional state and creating animations that reflect those emotions" refers to a technology that detects a user's emotions and reflects those emotions in animations that visually represent those emotions.

[0810] "Methods for automatically generating animations using generative technology" refers to technologies that automatically create animations using artificial methods by utilizing the generated data structure.

[0811] "Means of converting into visual expression" refers to the technology that processes the generated animation into a viewable format and outputs it as a final video.

[0812] "Means of outputting visual representations" refers to technologies that use appropriate output methods to provide users with visually complete animations.

[0813] "A means of transmitting animations to a user's electronic device and providing a personalized visual experience" refers to a technology that delivers generated animations to the user's terminal via a network, providing a visual experience tailored to the user's individual needs.

[0814] To implement this invention, a system integrating natural language processing technology, emotion recognition technology, generation technology, and communication technology is required. The server first uses natural language processing means to analyze the user's natural language input received from the terminal. Through this analysis, information regarding the content and style of the animation desired by the user is extracted, and the necessary animation structure is generated.

[0815] Next, the server analyzes the user's emotional state using emotion recognition technology based on further input or continuous interaction from the terminal. This allows the server to determine the atmosphere and tone of the animation in a way that aligns with the user's emotions. Then, using generation technology, it automatically generates the animation based on the data structure and emotional information.

[0816] The generated visual content is converted into a visual representation and transmitted to the user's device via a communication network. The device receives this content and provides it to the user in a viewable format, thereby offering the user a personalized visual experience.

[0817] For example, when a user enters a prompt such as "I want an animation to reduce stress," the server can analyze the request and generate content incorporating brighter colors and calming music that will shift the user's emotions toward a more relaxed state. In this way, the system can easily provide a visual experience that resonates with the user's emotions.

[0818] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0819] Step 1:

[0820] The user enters natural language prompts using a terminal. These prompts express the user's animation requests. The entered prompts are then sent from the terminal to the server.

[0821] Step 2:

[0822] The server analyzes the received prompt using natural language processing. From the analyzed data, it extracts keywords related to the animation's content and style. Based on this keyword information, the initial data structure for the animation is generated.

[0823] Step 3:

[0824] The user provides emotion-related data through an emotion recognition sensor or tracking device installed in their device. The server receives this feedback and analyzes the user's emotional state using emotion recognition technology. The user's emotional state is output as a result of the analysis.

[0825] Step 4:

[0826] The server automatically generates animations using a generative AI model based on the generated animation's data structure and analyzed emotional state. This generation method adjusts the animation's colors, music, character movements, and other elements to match the user's emotions.

[0827] Step 5:

[0828] The generated animation is converted into a visual representation on the server. This visual representation is then completed with video and audio elements, making it viewable.

[0829] Step 6:

[0830] The server sends the generated visual representation to the terminal via the network. The terminal receives the animation, and the user can view this content. The user can also send feedback to the server during viewing and request further adjustments.

[0831] 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.

[0832] 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 the following. 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 indicated 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.

[0833] 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 robot 414.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] 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.

[0838] 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.

[0839] 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."

[0840] 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.

[0841] 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.

[0842] 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.

[0843] 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.

[0844] 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.

[0845] 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.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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.

[0851] 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 as being incorporated by reference.

[0852] The following is further disclosed regarding the embodiments described above.

[0853] (Claim 1)

[0854] Natural language processing tools,

[0855] A means for generating an animation data structure based on the analyzed information,

[0856] A means of automatically generating animations using generation technology based on the generated data structure,

[0857] A means of rendering the generated animation,

[0858] A means of outputting the rendered animation,

[0859] A system that includes this.

[0860] (Claim 2)

[0861] Means of receiving user feedback,

[0862] Means for regenerating or adjusting the animation based on the feedback received,

[0863] The system according to claim 1, further comprising:

[0864] (Claim 3)

[0865] The system according to claim 1, further comprising means for transmitting the generated animation to a remote terminal over a network.

[0866] "Example 1"

[0867] (Claim 1)

[0868] A method for analyzing natural language and extracting information,

[0869] A means for generating a data model based on the analyzed information,

[0870] A method for automatically generating visual representations from data models using generative AI technology,

[0871] A means of converting automatically generated visual representations through computational processing,

[0872] Means for transmitting the converted visual representation to an external device,

[0873] A means of receiving input from a user and transmitting information to the system,

[0874] A means of modifying the visual representation based on the input information and the feedback received,

[0875] A system that includes this.

[0876] (Claim 2)

[0877] The system according to claim 1, further comprising means for transmitting the product to a remote information processing device.

[0878] (Claim 3)

[0879] The system according to claim 1, further comprising means for analyzing a request received from an external source and updating a data model.

[0880] "Application Example 1"

[0881] (Claim 1)

[0882] Natural language processing tools,

[0883] A means for generating an animation information structure based on the analyzed information,

[0884] A means of automatically generating video representations using generation technology based on the generated information structure,

[0885] Means of turning generated video expressions into visual expressions,

[0886] A means of displaying a visually represented image,

[0887] A means of constructing video expression for the purpose of advertising production based on input information,

[0888] A system that includes this.

[0889] (Claim 2)

[0890] A means of receiving user evaluation information,

[0891] Means for regenerating or adjusting the video expression based on the received evaluation information,

[0892] The system according to claim 1, further comprising:

[0893] (Claim 3)

[0894] The system according to claim 1, further comprising means for transmitting the generated video representation to a remote information terminal via a communication network.

[0895] "Example 2 of combining an emotion engine"

[0896] (Claim 1)

[0897] Natural language processing tools,

[0898] A means of recognizing emotional states based on analyzed information,

[0899] A means for generating an animation data structure that reflects the recognized emotional state,

[0900] A means of automatically generating animations using generation technology based on the generated data structure,

[0901] A means of rendering the generated animation,

[0902] A means of outputting the rendered animation,

[0903] A system that includes this.

[0904] (Claim 2)

[0905] Means of receiving user feedback,

[0906] Means for regenerating or adjusting animations based on received feedback and analyzed emotions,

[0907] The system according to claim 1, further comprising:

[0908] (Claim 3)

[0909] The system according to claim 1, further comprising means for transmitting the generated animation to a remote information processing device via communication means.

[0910] "Application example 2 of combining emotional engines"

[0911] (Claim 1)

[0912] Natural language processing tools,

[0913] A means of generating the animation structure based on the analyzed information,

[0914] A means of analyzing the user's emotional state and creating an animation that reflects that emotion,

[0915] A means of automatically generating animation using generation technology based on the generated structure,

[0916] A means of converting the generated animation into a visual representation,

[0917] Means for outputting visual representations,

[0918] A means of sending animations to a user's electronic device to provide a personalized visual experience,

[0919] A system that includes this.

[0920] (Claim 2)

[0921] The system according to claim 1, further comprising means for receiving user feedback and regenerating or adjusting animations based on the received feedback.

[0922] (Claim 3)

[0923] The system according to claim 1, further comprising means for transmitting the generated animation to a remote device via a communication network. [Explanation of Symbols]

[0924] 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. Natural language processing tools, A means for generating an animation data structure based on the analyzed information, A means of automatically generating animations using generation technology based on the generated data structure, A means of rendering the generated animation, A means of outputting the rendered animation, A system that includes this.

2. Means of receiving user feedback, Means for regenerating or adjusting the animation based on the feedback received, The system according to claim 1, further comprising:

3. The system according to claim 1, further comprising means for transmitting the generated animation to a remote terminal via a network.

Images