System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving natural language instructions from a user; means for parsing the natural language instructions into animation requirements; means for generating an animation based on the translated requirements; means for providing a preview of the generated animation to a user; means for receiving feedback from the user and reflecting the feedback to the generating AI means; means for generating a final animation that reflects the feedback; and means for providing the final animation to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Many current business animation production tools rely on limited styles and templates, which means that the animations created by users tend to be monotonous. Furthermore, for users without specialized skills, the operation of the tools is complex, making it difficult to create high-quality animations. Therefore, a new system is needed that allows users to easily create high-quality animations with a variety of graphic styles. [Means for solving the problem]

[0005] The present invention is a system that receives natural language instructions from a user, analyzes the instructions, and converts them into animation requirements. The system uses a generation AI to generate animation based on the requirements and provides the user with a preview of the generated animation. The system also receives feedback from the user and reflects it in the generation AI to generate the final animation. The final animation is provided to the user via a download link. This allows users to easily create high-quality animations in a wide variety of styles simply by issuing instructions without having to move their hands.

[0006] A "user" is an individual or group that operates the system and provides instructions necessary for animation production.

[0007] A "natural language" is a language that humans use in their daily lives and that does not depend on any particular format or structure.

[0008] "Instructions" are information that the user uses to communicate to the system his or her requests and wishes regarding animation production.

[0009] A "server" is a computer system that receives instructions from a user, analyzes the instructions, and performs the necessary processing.

[0010] "Parsing" is the process of understanding natural language instructions and translating them into animation requirements.

[0011] "Animation requirements" are specific conditions and specifications for generating animation based on user instructions.

[0012] "Generative AI" is an artificial intelligence-based system that automatically generates animations based on given requirements.

[0013] "Generated animation" refers to animation content generated by a generation AI based on user requirements.

[0014] A "preview" is a display that shows intermediate results of the generated animation to the user to obtain confirmation and feedback.

[0015] "Feedback" refers to opinions and correction requests provided by users regarding the preview.

[0016] "Final animation" refers to the completed animation content after incorporating user feedback.

[0017] "Download Link" means a URL or hyperlink that provides access over the Internet for a user to obtain the final animation. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9]1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0019] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0020] First, the terms used in the following description will be explained.

[0021] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0022] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0023] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0024] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0031] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0038] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0039] This invention is a system that generates animations by analyzing and converting instructions entered by the user in natural language. This system enables the creation of high-quality and diverse animations without forcing the user to perform specific operations.

[0040] User instruction input

[0041] First, the user uses the device to send instructions in natural language to the system. For example, the user might enter the following instruction: "I want to create a 30-second animation showcasing our new smartwatch. I want to create a moving scene with characters." Once this instruction is entered, the device sends it to the server.

[0042] Receiving and parsing instructions

[0043] The server receives instructions sent by the user and analyzes them using a natural language processing (NLP) engine. The NLP engine extracts animation requirements from the instructions and generates a list of requirements. This list of requirements includes specific conditions such as "introduce the smartwatch," "use of characters," "scenes with movement," and "30 seconds."

[0044] Transforming and optimizing animation requirements

[0045] The server converts the generated requirements list into a format suitable for the generating AI and optimizes it, so that all the information the generating AI needs is prepared.

[0046] Generate initial animation

[0047] The server then sends the optimized requirements list to the generative AI engine, which generates initial animations based on the given requirements, including character modeling, basic scene setup, and dynamic actions.

[0048] Identification of intermediate products

[0049] The generated initial animation is provided as a preview to the user's device from the server. The user can check this preview and provide feedback. For example, the user can send correction instructions such as "I want the character's clothing to look more business-like" to the server via their device.

[0050] Receiving and incorporating feedback

[0051] The server receives user feedback, analyzes it again using NLP, and converts it into specific modification requirements, which are then sent back to the generation AI, which then modifies the animation based on this.

[0052] Generating the final animation

[0053] Once the final animation is generated, the server retrieves the completed animation data and generates a download link for the user, who can then download and use the final animation.

[0054] As a concrete example, when generating a 30-second animation introducing a new smartwatch, the user first inputs instructions such as, "I want to create an animation that introduces the smartwatch and highlights its features." The server analyzes these instructions, sends the necessary requirements to the generation AI, provides the generated preview to the user, makes corrections based on feedback, and finally provides the user with a download link. This series of processes allows users to easily and efficiently create high-quality animations.

[0055] The processing flow will be explained below.

[0056] Step 1:

[0057] The user uses the device to input instructions for animation production in natural language. For example, they might input, "I want to create a 30-second animation introducing our new smartwatch." The device then sends the input instructions to the server as text data.

[0058] Step 2:

[0059] The server receives the instruction data sent by the user and passes it to a natural language processing (NLP) engine for analysis. This analysis extracts animation requirements from the user's instructions. For example, the instructions may be analyzed to identify the requirements: "Introduce the smartwatch," "Use a character," "Movement scene," and "30 seconds."

[0060] Step 3:

[0061] The server converts the extracted requirements into a format suitable for generative AI, generates a requirements list, and then sends the optimized requirements list to the generative AI engine.

[0062] Step 4:

[0063] The generation AI generates initial animations based on a list of requirements sent from the server, which includes character modeling, basic scene setup, and actions. The generated initial animations are returned to the server.

[0064] Step 5:

[0065] The server provides a preview of the generated initial animation to the user's device, allowing the user to view the intermediate animation results and provide feedback.

[0066] Step 6:

[0067] The user can use the device to input feedback on the previewed animation, such as "I'd like the character's clothing to look more business-like," and the device will then send this feedback to the server.

[0068] Step 7:

[0069] The server receives the feedback from the user, analyzes it again using the NLP engine, generates specific correction requirements based on the feedback, and sends them to the generation AI.

[0070] Step 8:

[0071] The generation AI regenerates the animation based on the modified requirements and returns the modified animation data to the server, which then retrieves this data and prepares it as the final animation.

[0072] Step 9:

[0073] The server generates a download link to provide the completed final animation to the user, and the download link is sent to the user's device, allowing the user to obtain the final animation through the link.

[0074] By following the above steps, users can easily create high-quality animations with a variety of graphic styles by simply issuing instructions without moving their hands.

[0075] Example 1

[0076] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0077] Conventional animation production systems require users to have detailed operations and technical knowledge, making it difficult to efficiently create high-quality animations. It is also difficult to quickly and reliably incorporate feedback into the process of understanding user instructions and generating animations that reflect those instructions. To solve these problems, a system is needed that can accurately analyze users' natural language instructions and efficiently embody them as animations.

[0078] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0079] In this invention, the server includes means for receiving natural language instructions from a user, means for analyzing the natural language instructions and converting them into animation requirements, means for converting the converted requirements into a format understandable by a generation AI engine and optimizing them, generation AI means for generating an animation based on the optimized requirements, means for providing a preview of the generated animation to the user, means for receiving feedback from the user and reflecting it in the generation AI means, means for generating a final animation that reflects the feedback, and means for generating a download link for providing the final animation to the user. This enables users to create high-quality animations with simple instructions in natural language and to quickly and reliably modify and complete animations that reflect feedback.

[0080] A "user" is an entity that inputs instructions to the system in natural language and generates animations.

[0081] A "natural language instruction" is a request or command entered by a user in a natural language, such as text or voice.

[0082] The "analysis means" is a means having a function for analyzing instructions in natural language and converting them into animation requirements.

[0083] "Animation requirements" refers to the conditions and components necessary for generating animation extracted by the analysis means.

[0084] A "generative AI engine" is an artificial intelligence engine that generates animations based on the animation requirements.

[0085] "Generative AI means" refers to means including functions and processes for generating animations using a generative AI engine.

[0086] An "optimization means" is a means that has the function of converting the converted requirements into a format that can be understood by the generative AI engine and optimizing them.

[0087] The "preview providing means" is a means having a function for providing a preview of the generated animation to the user.

[0088] "Feedback" refers to opinions and instructions that a user submits to the system after checking the preview and inputting any necessary corrections or improvements.

[0089] The "feedback receiving means" is a means that has the function of receiving feedback from the user and reflecting it in the generating AI means.

[0090] "Final animation" refers to the animation that has been revised and completed based on user feedback.

[0091] The "download link generating means" is a means having a function for generating a download link for providing the final animation to the user.

[0092] System Configuration

[0093] This invention is a system that generates animations by analyzing and converting instructions entered by the user in natural language. This system enables the creation of high-quality, diverse animations without forcing the user to perform specific operations.

[0094] Hardware and Software

[0095] This system uses the following hardware and software:

[0096] 1. Hardware:

[0097] Device: A computer, smartphone, tablet, etc., through which a user inputs instructions.

[0098] Server: A high-performance server that performs instruction analysis and animation generation processing.

[0099] 2. Software:

[0100] Natural language processing engine (NLP engine): Analyzes the user's natural language instructions and extracts animation requirements. As a specific example, we use Google Cloud Natural Language API.

[0101] Generative AI engine: An artificial intelligence engine for generating animations. As a specific example, we will use DALL-E from OpenAI (registered trademark).

[0102] Program processing description

[0103] 1. User input

[0104] The user uses the device to send instructions in natural language to the system. For example, the user might enter the following instruction: "I want to create a 30-second animation showcasing a new smartwatch. I want to create a moving scene with characters." Once this instruction is entered, the device sends it to the server.

[0105] 2. Receiving and analyzing instructions

[0106] The server receives instructions sent by the user and analyzes them using a natural language processing engine. The NLP engine extracts animation requirements from the instructions and generates a list of requirements. This list of requirements includes specific conditions such as "introduce the smartwatch," "use of characters," "scenes with movement," and "30 seconds."

[0107] 3. Transforming and optimizing animation requirements

[0108] The server converts the generated requirements list into a format that the generative AI engine can understand and optimizes it, ensuring that all the information the generative AI engine needs is prepared.

[0109] 4. Generating the initial animation

[0110] The server then sends the optimized requirements list to the generative AI engine, which generates initial animations based on the given requirements, including character modeling, basic scene settings, and dynamic actions.

[0111] 5. Identification of intermediate products

[0112] The generated initial animation is provided as a preview from the server to the user's device. The user can check this preview and provide feedback. For example, the user can send correction instructions such as "I want the character's clothing to look more business-like" to the server via their device.

[0113] 6. Receiving and implementing feedback

[0114] The server receives user feedback, analyzes it again using a natural language processing engine, and converts it into specific modification requirements, which are then sent back to the generative AI engine, which then modifies the animation based on the results.

[0115] 7. Generating the final animation

[0116] Once the final animation is generated, the server retrieves the completed animation data and generates a download link for the user, who can then download and use the final animation.

[0117] Specific examples

[0118] For example, to generate a 30-second animation introducing a new smartwatch, a user first inputs instructions such as, "I want to create an animation that introduces the smartwatch and highlights its features." The server analyzes these instructions, sends the necessary requirements to the generation AI engine, and provides the generated preview to the user. The user then checks the preview, makes any necessary corrections, and finally receives a download link. This process allows users to create high-quality animations easily and efficiently.

[0119] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0120] Step 1: User input

[0121] The user uses the device to input instructions for animation production in natural language. This input is done using the text box or voice input function of a dedicated application. Specifically, the user enters instructions such as, "I want to create a 30-second animation introducing our new smartwatch product. I want to create a scene with moving characters." The input data is sent in text format.

[0122] Step 2: Sending instruction data

[0123] The terminal sends the natural language instructions entered by the user to the server using an HTTP POST request, with the data packaged in JSON format. The input data is the user's instruction text, and the output data is the JSON data sent to the server.

[0124] Step 3: Analyze the instruction data

[0125] The server analyzes the received instruction data. Specifically, it uses a natural language processing engine (e.g., Google Cloud Natural Language API) to extract animation requirements from the instruction text. The input data is the user's instruction text, and the output data is a list of requirements. This list of requirements includes specific conditions such as "introduce the smartwatch," "use of a character," "scene with movement," and "30 seconds."

[0126] Step 4: Generate a requirements list

[0127] The server generates a requirements list based on the analysis results obtained from the NLP engine. Here, the extracted requirements are organized into a list format and converted into a format that can be understood by the generation AI engine. The input data is the analysis results, and the output data is the requirements list.

[0128] Step 5: Transform and optimize your requirements list

[0129] The server converts the generated requirement list into a prompt that can be referenced by the generation AI engine and performs optimization. Specifically, it formats the requirement list into something like "introduce a smartwatch, use a character, include a scene with movement, 30 seconds." The input data is the requirement list, and the output data is a prompt for the generation AI.

[0130] Step 6: Generate the initial animation

[0131] The server sends the optimized prompt to the AI ​​engine, which then generates the initial animation based on the prompt. The initial creation includes character modeling and basic scene settings. The input data is the prompt, and the output data is the initial animation file.

[0132] Step 7: Check the intermediate products

[0133] The server provides the generated initial animation as a preview to the user's device. The device displays this animation in a playable format. The user visually checks the preview and provides feedback as needed. The input data is the initial animation file, and the output data is the user's feedback.

[0134] Step 8: Getting user feedback

[0135] After checking the preview, the user can submit feedback for corrections and improvements. Specifically, the user can enter feedback such as "I would like the character's clothing to be more business-like." The device then sends this feedback to the server. The input data is the user's feedback, and the output data is the feedback's JSON data.

[0136] Step 9: Analyze and transform feedback

[0137] The server analyzes the feedback received from the user again using a natural language processing engine and converts it into specific revision requirements. The input data is the user feedback, and the output data is a list of revision requirements.

[0138] Step 10: Modifying the animation

[0139] Based on the feedback, the server sends modification requirements to the generative AI engine to modify the animation. The generative AI engine regenerates the animation based on the new requirements. The input data is the list of modification requirements, and the output data is the modified animation file.

[0140] Step 11: Generate the final animation

[0141] Once the final animation is generated, the server retrieves the completed animation data and generates a download link to provide to the user. The input data is the modified animation file, and the output data is the download link.

[0142] Step 12: Provide a download link

[0143] The server sends the generated download link to the user's device. The user can use this link to download and use the final animation. The input data is the download link, and the output data is the user's download action.

[0144] (Application example 1)

[0145] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0146] Conventional animation generation systems require specialized knowledge and skills, making it difficult for average users to easily generate high-quality animations. Furthermore, in order to respond quickly to advertising campaigns, a means for easily creating high-quality animated advertisements is required. Furthermore, there is a lack of a means for smoothly previewing generated animations and incorporating feedback, preventing an efficient animation production process.

[0147] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0148] In this invention, the server includes a means for receiving natural language instructions from a user, a means for analyzing the natural language instructions and converting them into animation requirements, and a generation AI means for generating animations based on the converted requirements. This allows even general users to easily create high-quality animated advertisements in natural language. Furthermore, by including a means for providing a preview of the generated animation and a means for receiving and incorporating user feedback, an efficient animation production process can be realized, allowing animations for advertising campaigns to be quickly provided.

[0149] The "means for receiving instructions in natural language from the user" refers to an interface and function that allows the user to input instructions for animation production in natural language and for the system to receive them.

[0150] "Means for analyzing natural language instructions and converting them into animation requirements" refers to the function and process of converting natural language instructions received from a user into a format that a machine can understand and extracting specific production requirements for the animation.

[0151] The "generative AI means for generating animations based on converted requirements" refers to an artificial intelligence engine and related technologies that automatically generate animations based on analyzed requirements.

[0152] The "means for providing a user with a preview of the generated animation" refers to a function and interface that displays the initially generated animation so that the user can check it.

[0153] "Means for receiving feedback from users and reflecting it in the generating AI means" is a function that receives correction requests provided by the user after checking the preview, and sends them back to the generating AI engine to be reflected in the animation.

[0154] The "means for generating a final animation that reflects feedback" refers to the process and technique for generating a final animation after reflecting user feedback.

[0155] The "means for providing the final animation to the user" refers to the functionality and interface that provides the completed animation so that the user can download or view it.

[0156] "Means for creating high-quality animated advertisements for advertising campaigns in natural language on a user terminal" refers to a process and technology that allows a user to input instructions for creating advertising animations in natural language using a terminal, and the system generates high-quality advertising animations based on those instructions.

[0157] The "means for transmitting advertisement production instructions in natural language from the user to the server" refers to a function and interface for transmitting advertisement production instructions entered by the user to the server via the network.

[0158] The "means for the server to analyze instructions and extract requirements for advertising animation" refers to the functions and processes for analyzing received natural language advertising production instructions and extracting specific requirements for advertising animation.

[0159] "Generative AI means for generating animations suitable for advertising purposes based on requirements" refers to an artificial intelligence engine and related technologies that automatically generate animations that meet advertising purposes based on extracted requirements.

[0160] "Means for sending a preview link of the generated animation to a user terminal and receiving user confirmation and feedback" refers to a function and interface for displaying a preview of the generated animation on a user terminal and receiving confirmation and feedback.

[0161] The "means for providing a download link for the final animation to a user terminal" refers to a function and interface that provides the completed final animation to a user terminal as a download link.

[0162] DETAILED DESCRIPTION OF THE INVENTION In the preferred embodiment of the present invention, a system is described that allows for easy generation of high quality animated advertisements in natural language for advertising campaigns.

[0163] First, a user uses a device such as a smartphone or tablet to input instructions for animation production in natural language. For example, they might input instructions like, "I want to create a 30-second animated commercial that conveys the features and appeal of a newly released smartphone. It should include a scene in which a character uses the smartphone to explain its convenient functions."

[0164] The input natural language instructions are sent from the device to the server. At this time, data is sent as an HTTP request using API communication. The server analyzes the received instructions using a natural language processing (NLP) engine and extracts the requirements for animation production. For natural language processing, a Python NLP library (such as NLTK or spaCy) is used, for example.

[0165] Next, the server optimizes the extracted requirements and converts them into a format suitable for the generative AI engine. During this process, the requirements are converted and optimized using a data processing script. The converted requirements are then sent to the generative AI engine, which generates the initial animation. The generative AI means used for this is, for example, OpenAI's API or DALL-E.

[0166] The generated initial animation is sent from the server to the user's device as a preview link. The user can check the animation through this preview link and provide feedback. For example, the user can input a command such as "I want the character's clothes to look more business-like."

[0167] The server again uses a natural language processing engine to analyze the user's feedback and convert it into specific revision requirements, which are then sent to a generative AI engine to revise the animation. This process is repeated until the user is satisfied.

[0168] Once the final animation is generated, the server generates a download link to provide the completed animation to the user's device, where the user can download the final animation and use it in their advertising campaign.

[0169] For example, when introducing a new smartwatch, a user can enter a specific prompt such as, "I want to create an animation that introduces the smartwatch and highlights its features," and the system will generate a high-quality animation based on this instruction.

[0170] The system allows users to easily generate high-quality animations that can be used in advertising campaigns using natural language, without requiring specialized skills.

[0171] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0172] Step 1:

[0173] The user uses a terminal to input instructions for animation production in natural language. For example, they might input, "I want to create a 30-second animated commercial that conveys the features and appeal of a newly released smartphone. It should include a scene in which a character uses the smartphone to explain its convenient functions." This input is received by the system and sent to the next step.

[0174] Step 2:

[0175] The device sends input instructions in natural language to the server. The input data is natural language text and is sent to the server as an HTTP request. The server receives the request and converts it into a usable format for analysis.

[0176] Step 3:

[0177] The server parses the received natural language instructions using a natural language processing (NLP) engine. The input data is natural language text, which is parsed using an NLP engine (e.g., spaCy or NLTK) to extract the information needed for animation production requirements. The output is a list of requirements.

[0178] Step 4:

[0179] The server optimizes the extracted requirements list and converts it into a format suitable for the generative AI engine. The input data is the extracted requirements list, which is converted into the optimal format using a data processing script (e.g., Python). The output is formatted data to be sent to the generative AI engine.

[0180] Step 5:

[0181] The server sends the optimized requirement list to the generative AI engine to generate the initial animation. The input data is formatted data, and the generative AI engine (e.g., OpenAI API or DALL-E) generates the animation. The output is the initial generated animation data.

[0182] Step 6:

[0183] The server sends the generated initial animation to the user's device as a preview link. The input data is the initially generated animation data, which is sent to the user's device as an HTTP request. The user can check the animation using the preview link.

[0184] Step 7:

[0185] The user checks the preview and provides feedback. The input is natural language text, which is sent from the device to the server. For example, the user might input a command such as, "I want the character's clothing to look more business-like."

[0186] Step 8:

[0187] The server again uses a natural language processing engine to analyze the user's feedback and convert it into specific correction requirements. The input data is the natural language text of the feedback, and the NLP engine extracts the correction requirements. The output is a list of correction requirements.

[0188] Step 9:

[0189] The server sends modification requirements to the generative AI engine to modify the animation. The input data is a list of modification requirements, and the generative AI engine is used to regenerate the animation. The output is the modified animation data.

[0190] Step 10:

[0191] Once the final animation is generated, the server generates a download link to provide the completed animation to the user and sends it to the user's device. The input data is the final animation data, which is sent to the user's device as an HTTP request. The user can download the final animation via this link and use it in their advertising campaign.

[0192] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0193] This invention is a system that automatically generates high-quality and diverse animations using natural language instructions from the user and an emotion engine that analyzes the user's emotions. In particular, it recognizes the user's emotions and adjusts the animation requirements based on them to provide more personalized animations.

[0194] User instruction input

[0195] The user uses the device to input instructions for animation production in natural language. For example, they might input, "I want to create a 30-second animation introducing our new smartwatch product. I want to create a scene with characters in motion." The input instructions are sent from the device to the server.

[0196] Receiving and parsing instructions

[0197] The server receives the instruction data sent by the user and analyzes it using a natural language processing (NLP) engine. The NLP engine extracts animation requirements from the instructions and generates a list of specific requirements. For example, requirements such as "introduce the smartwatch," "use of characters," "moving scenes," and "30 seconds" are extracted.

[0198] Applying the Emotion Engine

[0199] The server also passes the received instruction data to the emotion engine, which analyzes the user's emotions. The emotion engine recognizes emotions (e.g., joy, excitement, tension, etc.) from the user's language and context, and reflects the extracted emotional information in the animation requirements. For example, if the user is excited, it can add more dynamic movements and vivid colors to the requirements.

[0200] Transforming and optimizing animation requirements

[0201] The server integrates the extracted requirements and emotion information and converts it into a format suitable for the generative AI, thereby providing all the information necessary for the generative AI and optimizing the requirements list.

[0202] Generate initial animation

[0203] The server then sends the optimized requirement list to the generative AI engine, which generates initial animations based on the given requirements and emotion information. This stage includes character modeling, basic scene setup, and actions. The generated initial animations are returned to the server.

[0204] Identification of intermediate products

[0205] The generated initial animation is provided as a preview from the server to the user's device. The user can check this preview and provide feedback. For example, the user can send correction instructions such as "I want the character's clothing to look more business-like" to the server via their device.

[0206] Receiving and incorporating feedback

[0207] The server receives the user's feedback and analyzes it again using the NLP engine and emotion engine. Taking into account the content of the feedback as well as the user's emotions, it generates specific correction requirements and sends them to the generation AI.

[0208] Generating the final animation

[0209] The generation AI regenerates the animation based on the modification requirements and emotion information, and returns the modified animation data to the server, which then retrieves this data and prepares it as the final animation.

[0210] Providing the final animation

[0211] The server generates a download link to provide the completed final animation to the user, and the download link is sent to the user's device, allowing the user to obtain the final animation through the link.

[0212] As a concrete example, when generating a 30-second animation introducing a new smartwatch product, the user inputs instructions such as, "I want to create an animation that introduces the smartwatch and highlights its features." The server analyzes these instructions, uses an emotion engine to recognize the user's emotions (e.g., excitement), and generates a list of requirements based on these. The generation AI generates an initial animation and then reflects the user's feedback and emotional information to create the final animation. This series of processes allows users to easily and efficiently create personalized, high-quality animations.

[0213] The processing flow will be explained below.

[0214] Step 1:

[0215] The user uses the device to input instructions for animation production in natural language. For example, they might input, "I want to create a 30-second animation introducing our new smartwatch product. I want to create a scene with characters and movement." The device then sends the input instructions to the server.

[0216] Step 2:

[0217] The server receives the instruction data sent by the user and passes it to a natural language processing (NLP) engine for analysis. The NLP engine extracts animation requirements from the instructions. The extracted requirements include "introduce the smartwatch," "use of characters," "moving scenes," and "30 seconds."

[0218] Step 3:

[0219] The server passes the received instruction data to the emotion engine, which analyzes the user's emotions. For example, if the user is excited, the emotion engine recognizes this and extracts emotion information such as "excited" or "positive."

[0220] Step 4:

[0221] The server integrates the extracted requirement list and emotion information and converts it into a format suitable for generative AI, including adjusting the animation style based on the emotion (e.g., color usage and movement emphasis).

[0222] Step 5:

[0223] The server sends the optimized requirement list to the generation AI engine, which generates an initial animation based on the requirement list and emotion information. This initial animation includes basic character modeling, scene setup, and basic movements. The generated initial animation is returned to the server.

[0224] Step 6:

[0225] The server sends a preview of the generated initial animation to the user's device, where the user can view the preview and provide feedback, such as "I'd like the character's clothing to look more business-like."

[0226] Step 7:

[0227] The device sends the user's feedback data to the server, which then receives the feedback data and analyzes it again using the NLP engine and emotion engine. Specific correction requirements are generated based on the feedback content.

[0228] Step 8:

[0229] The server reflects the feedback requirements and emotional information and sends it to the generation AI means. The generation AI regenerates the animation based on this. This regeneration process includes corrections specified in the feedback and style adjustments based on the emotional information. The corrected animation data is returned to the server.

[0230] Step 9:

[0231] The server prepares the final version of the modified animation and generates a download link for the user, which is then sent to the user's device.

[0232] Step 10:

[0233] The user can then use the provided download link to download the final animation from their device, allowing them to receive the final product introduction animation.

[0234] By following the above steps, the user can easily create a variety of high-quality animations based on the user's emotions, simply by issuing instructions without moving their hands.

[0235] Example 2

[0236] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0237] Current animation generation systems struggle to efficiently generate personalized, high-quality animations that meet user needs. In particular, they lack a process for generating animations that takes user emotions into account, resulting in generated animations that do not adequately reflect user expectations and emotions. Furthermore, the process of making corrections based on user feedback is cumbersome and time-consuming, and improvements are needed to increase user satisfaction.

[0238] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0239] In this invention, the server includes means for receiving natural language instructions from a user, means for analyzing the natural language instructions and converting them into animation requirements, means for analyzing the user's emotions from the natural language instructions, generation AI means for generating animation based on the converted requirements and the analyzed emotional information, means for providing a preview of the generated animation to the user, means for receiving feedback from the user and reflecting it in the generation AI means, means for generating a final animation that reflects the feedback and emotional information, and means for providing the final animation to the user. This enables the generation of personalized, high-quality animation that takes user instructions and emotions into consideration.

[0240] A "user" is a person who operates the system to input animation instructions and checks and provides feedback on the generated animation.

[0241] "Natural language instructions" refer to instructions written in sentence format that are input by a user through a terminal.

[0242] "Analysis" is the process of using a natural language processing engine and an emotion engine to understand the user's instructions and emotions from the context and convert them into specific data.

[0243] "Animation requirements" are specific conditions and elements for generating animations, extracted from the analyzed natural language instructions and emotional information.

[0244] "Emotion information" is data about the user's emotions (e.g., joy, excitement, tension) extracted from the user's natural language instructions.

[0245] The "generative AI means" is an artificial intelligence system that automatically generates animations based on the extracted animation requirements and emotional information.

[0246] A "preview" is a short video that allows the user to see an early version of the generated animation.

[0247] "Feedback" refers to correction instructions and evaluations provided by the user after checking the preview.

[0248] The "final animation" refers to the final animation that reflects the user's feedback and emotional information.

[0249] The "server" is a computer system that executes various processing means, manages and analyzes instructions and feedback from users, and generates and provides the final animation.

[0250] A "terminal" is a device that a user uses to input natural language instructions, see a preview of the generated animation, and provide feedback.

[0251] The present invention is a system that automatically generates high-quality, personalized animations by utilizing natural language instructions from a user and a generative AI model with an emotion engine. The following describes an embodiment of the system.

[0252] User instruction input

[0253] A user uses a device (e.g., a PC or smartphone) to access a dedicated application or website and input instructions for animation production in natural language. For example, they might input instructions such as, "I want to create a 30-second animation introducing our new smartwatch product. I want to create a scene with characters in motion." These input instructions are then sent from the device to the server.

[0254] Receiving and parsing instructions

[0255] The server receives instruction data sent by the user. This data is automatically passed to a natural language processing (NLP) engine for analysis. The NLP engine extracts animation requirements from the user's instructions and generates a list of specific requirements. For example, requirements such as "introduce the smartwatch," "use of characters," "moving scenes," and "30 seconds" are extracted from the instructions.

[0256] Applying the Emotion Engine

[0257] At the same time, the server passes the received instruction data to the emotion engine, which analyzes the user's emotions. The emotion engine recognizes emotions (e.g., joy, excitement, tension) from the user's context and vocabulary, and reflects this emotional information in the animation requirements. For example, if the user is excited, more dynamic movements and vivid colors are added to the requirements.

[0258] Transforming and optimizing animation requirements

[0259] The server then integrates the extracted requirements list with the emotion information and converts it into a format suitable for the generative AI model. This process ensures that all the information required by the generative AI is gathered and the requirements list is optimized. Specifically, the requirements list is converted into a data structure such as JSON format.

[0260] Generate initial animation

[0261] The server sends the optimized requirement list to the generative AI engine, which then models the character, sets up the basic scene, plans the action, and generates the initial animation based on the requirements and emotion information. Once this series of processes is complete, the generated initial animation data is sent back to the server.

[0262] Identification of intermediate products

[0263] The generated initial animation is provided as a preview from the server to the user's device. The user can check the preview on their device and provide feedback on any points of concern or changes they would like to make. For example, they can send detailed correction instructions, such as "I would like the character's clothing to be more business-like," to the server from their device.

[0264] Receiving and incorporating feedback

[0265] The server receives feedback from the user. The received feedback is analyzed again by the NLP engine and emotion engine to generate specific correction requirements. In addition, the user's latest emotional information is also reflected. This information is then sent again to the generative AI engine.

[0266] Generating the final animation

[0267] The generative AI engine regenerates the animation based on the user's modification requirements and emotional information. The final animation data reflecting the modification requests is sent back to the server, which then retrieves this data and prepares the final animation.

[0268] Providing the final animation

[0269] The server generates a download link for providing the completed final animation to the user, and the download link is sent to the user's device, allowing the user to download and obtain the final animation through the link.

[0270] Specific examples

[0271] For example, when generating a 30-second animation introducing a new smartwatch product, the user inputs instructions such as, "I want to create an animation that introduces the smartwatch and highlights its features." The server analyzes these instructions, uses an emotion engine to recognize the user's emotions (e.g., excitement), and generates a list of requirements based on those emotions. The generative AI generates an initial animation and then reflects the user's feedback and emotional information to create the final animation. This series of processes allows users to easily and efficiently create personalized, high-quality animations.

[0272] Prompt Sentence Examples

[0273] "Create a 30-second animation showcasing a new smartwatch. I'd like it to be animated with characters and incorporate emotions that excite the user."

[0274] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0275] Step 1:

[0276] User instruction input

[0277] The user uses a device to access a dedicated application or website and inputs instructions for animation production in natural language. For example, they might input, "I want to create a 30-second animation introducing our new smartwatch. I want to create a scene with characters in motion." This input is then sent from the device to the server.

[0278] Input: Natural language animation instructions

[0279] Output: Instruction data sent from the terminal to the server

[0280] Step 2:

[0281] Receiving and parsing instructions

[0282] The server receives instruction data sent by the user. This data is automatically passed to a natural language processing (NLP) engine for analysis. The NLP engine extracts animation requirements from the user's instructions and generates a list of specific requirements. For example, it extracts requirements such as "introduce a smartwatch," "use of characters," "scenes with movement," and "30 seconds."

[0283] Input: Instruction data sent by the user

[0284] Data processing: Analysis using a natural language processing engine

[0285] Output: Extracted animation requirements list

[0286] Step 3:

[0287] Applying the Emotion Engine

[0288] At the same time, the server passes the received instruction data to the emotion engine, which analyzes the user's emotions. The emotion engine recognizes emotions (e.g., joy, excitement, tension) from the user's context and vocabulary, and reflects this emotional information in the animation requirements. For example, if the user is excited, more dynamic movements and vivid colors are added to the requirements.

[0289] Input: Instruction data to be analyzed

[0290] Data processing: Emotion analysis using an emotion engine

[0291] Output: Parsed emotion information

[0292] Step 4:

[0293] Transforming and optimizing animation requirements

[0294] The server then integrates the extracted requirements list with the emotion information and converts it into a format suitable for the generative AI model. This process ensures that all the information required by the generative AI is gathered and the requirements list is optimized. Specifically, the requirements list is converted into a data structure such as JSON format.

[0295] Input: Requirement list and sentiment information

[0296] Data processing: requirements optimization and format conversion

[0297] Output: An optimized requirements list for a generative AI model

[0298] Step 5:

[0299] Generate initial animation

[0300] The server sends the optimized requirement list to the generative AI engine, which then models the character, sets up the basic scene, and plans the movement based on the requirements and emotion information, generating the initial animation. Once this series of processes is complete, the generated initial animation data is sent back to the server.

[0301] Input: Optimized requirements list

[0302] Data processing: Generative AI animation generation

[0303] Output: Initial animation data

[0304] Step 6:

[0305] Identification of intermediate products

[0306] The generated initial animation is sent as a preview from the server to the user's device. The user can check the preview on their device and provide feedback on any areas of concern or changes they would like to see. For example, they can send detailed correction instructions, such as "I would like the character's clothing to look more business-like," to the server.

[0307] Input: Initial animation preview

[0308] Data processing: User feedback

[0309] Output: List of modified requirements

[0310] Step 7:

[0311] Receiving and incorporating feedback

[0312] The server receives feedback from the user. The received feedback is analyzed again by the NLP engine and emotion engine. Specific correction requirements are generated, and the user's latest emotional information is also reflected. This information is then sent back to the generative AI engine.

[0313] Input: User feedback

[0314] Data processing: Analysis of feedback and generation of revised requirements

[0315] Output: Modified requirement list and sentiment information

[0316] Step 8:

[0317] Generating the final animation

[0318] The generative AI engine regenerates the animation based on the user's modification requirements and emotional information. The final animation data reflecting the modification requests is sent back to the server. The server receives this data and prepares the final animation.

[0319] Input: Modified requirement list and sentiment information

[0320] Data processing: Regenerating animations using generative AI

[0321] Output: Final animation data

[0322] Step 9:

[0323] Providing the final animation

[0324] The server generates a download link for the completed final animation to provide the user with the animation, and the download link is sent to the user's device, allowing the user to download and obtain the final animation through the link.

[0325] Input: Final animation data

[0326] Data processing: Generate download links

[0327] Output: Send a download link to the user's device

[0328] (Application example 2)

[0329] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0330] Conventional animation production systems make it difficult for users to easily reflect individual emotions and specific instructions, resulting in a cumbersome process for creating personalized, high-quality animations. Furthermore, there is a lack of effective means for quickly and intuitively generating animations in specific fields such as advertising. There is a need for a system that can solve these problems and automatically generate high-quality animations that reflect individual emotions based on natural language instructions from users.

[0331] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving natural language instructions from a user; means for analyzing the natural language instructions and converting them into animation requirements; means for reading the user's emotions from the analyzed natural language instructions and generating animation requirements that reflect the emotions; generation AI means for generating animation based on the converted requirements; means for providing a preview of the generated animation to the user; means for receiving feedback from the user and reflecting it in the generation AI means; means for generating a final animation that reflects the feedback and the read emotions; and means for providing the final animation to the user. This makes it possible to quickly generate personalized, high-quality animation that reflects the user's emotions.

[0332] The "means for receiving instructions in natural language from a user" refers to a device or interface for recognizing instructions input in natural language by a user and transmitting the instructions to a server.

[0333] The "means for parsing natural language instructions and converting them into animation requirements" refers to software or algorithms that parse natural language instructions entered by a user and convert those instructions into specific animation requirements.

[0334] "Means for reading the user's emotions from the analyzed natural language instructions and generating animation requirements that reflect those emotions" is an algorithm that extracts the user's emotions from the analyzed instructions and generates animation requirements taking those emotions into consideration.

[0335] "Generative AI means" refers to an artificial intelligence system that automatically generates initial and final animations based on the requirements of the converted animation.

[0336] The "means for providing a preview to the user" refers to a system or interface for visually displaying to the user intermediate and final results of the generated animation.

[0337] The "means for receiving feedback and reflecting it in the generating AI means" is an algorithm for receiving feedback provided by the user, analyzing that feedback, and reflecting it in the generating AI.

[0338] The "means for generating final animation" is an AI system that generates the final animation based on user feedback and emotional information.

[0339] The "means for providing the final animation to the user" refers to a system or interface that allows the user to download or view the completed final animation.

[0340] This invention is a system for quickly and effectively generating animations for advertising. This system includes a series of processes that receive natural language instructions from a user, analyze them, and generate animations that reflect the user's emotions.

[0341] First, the user inputs instructions for animation production in natural language via a device such as a smartphone. These instructions are then sent from the device to the server. For example, a user might say, "I want to create a 30-second animated advertisement introducing our new lunch menu. I want to give it a seasonal feel."

[0342] The server receives the instruction data sent by the user and analyzes it using a natural language processing engine (e.g., Google Cloud Natural Language API). During this analysis, animation requirements are extracted from the instructions. For example, from the above instructions, requirements such as "new lunch menu," "seasonal feel," and "30-second animation" are extracted.

[0343] Next, the server uses an emotion analysis engine (e.g., IBM Watson® Tone Analyzer) to analyze the user's emotions. In this process, emotions (e.g., excitement, joy, etc.) are recognized from the user's language and context, and the extracted emotional information is reflected in the animation requirements. For example, if the user excitedly inputs a command such as "I want to create a sense of the season," animation requirements with more dynamic color usage and movement are added.

[0344] The server integrates these animation requirements and emotion information and converts them into a format suitable for a generative AI model (e.g., DALL-E or GPT-4®). This production AI model generates an initial animation based on the given requirements. The generated initial animation is then provided as a preview from the server to the user's device.

[0345] The user checks the preview and provides feedback for corrections, such as "I'd like the background of the scene to be a warmer color." This feedback is sent from the device to the server, where it is again subjected to natural language processing and sentiment analysis to generate specific correction requirements.

[0346] The generative AI model regenerates the animation based on the modified requirements to create the final animation, which is then provided as a download link from the server to the user's device, allowing the user to download the animation through this link.

[0347] As a concrete example, the prompt text for "If you want to create an advertising animation for the new menu item 'Special Japanese-style Hamburger Steak'" is as follows:

[0348] "We'd like to create a 30-second animated ad to promote our new special Japanese-style hamburger lunch. Emphasize the autumn feel with warm colors and dynamic movements."

[0349] The present invention allows users to quickly generate personalized, emotionally-driven, and high-quality advertising animations.

[0350] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0351] Step 1:

[0352] The user uses a terminal to input instructions for animation production in natural language. For example, the instructions might be, "I want to create a 30-second animated advertisement introducing our new special Japanese-style hamburger steak lunch. Please emphasize the autumnal feeling with warm colors and dynamic movements." After input, this data is sent from the terminal to the server.

[0353] Step 2:

[0354] The server sends the received instruction data to a natural language processing engine (e.g., Google Cloud Natural Language API) for analysis. The input for the analysis is the user's natural language instruction, and the output is a list of requirements such as "new special Japanese-style hamburger lunch," "warm colors," "dynamic movements," "autumn seasonal feel," and "30-second animation."

[0355] Step 3:

[0356] The server sends the acquired requirement list and instruction data to an emotion analysis engine (e.g., IBM Watson Tone Analyzer) to extract the user's emotion. The input is the instruction data, and the output is the recognized emotion information (e.g., joy, excitement). This adds the emotion information to the requirement list.

[0357] Step 4:

[0358] The server integrates and optimizes the converted requirement list and emotion information into a format suitable for the generative AI model (e.g., DALL-E or GPT-4). The input of this process is the requirement list and emotion information, and the output is data in a format that can be interpreted by the generative AI model.

[0359] Step 5:

[0360] The server sends the optimized data to the generative AI model to generate the initial animation. The input is the optimized data, and the output is the initial animation. The generated initial animation is returned to the server.

[0361] Step 6:

[0362] The server provides a preview of the initial animation to the user's device, and the user can view the preview and provide feedback in natural language, such as "I'd like the background color to be warmer."

[0363] Step 7:

[0364] The server receives feedback from the user and passes it back to the natural language processing engine and sentiment analysis engine for analysis. The input is the feedback, and the output is the correction requirements and sentiment information.

[0365] Step 8:

[0366] The server issues regeneration instructions to the generative AI model based on the modification requirements, generating the final animation. The input is the modification requirements and emotion information, and the output is the final animation.

[0367] Step 9:

[0368] The final animation is provided to the user's device as a download link from the server, and the user can obtain the final animation through the link.

[0369] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0370] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0371] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0372] [Second embodiment]

[0373] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0374] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0375] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0376] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0377] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0378] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0379] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0380] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0381] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0382] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0383] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0384] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0385] This invention is a system that generates animations by analyzing and converting instructions entered by the user in natural language. This system enables the creation of high-quality and diverse animations without forcing the user to perform specific operations.

[0386] User instruction input

[0387] First, the user uses the device to send instructions in natural language to the system. For example, the user might enter the following instruction: "I want to create a 30-second animation showcasing our new smartwatch. I want to create a moving scene with characters." Once this instruction is entered, the device sends it to the server.

[0388] Receiving and parsing instructions

[0389] The server receives instructions sent by the user and analyzes them using a natural language processing (NLP) engine. The NLP engine extracts animation requirements from the instructions and generates a list of requirements. This list of requirements includes specific conditions such as "introduce the smartwatch," "use of characters," "scenes with movement," and "30 seconds."

[0390] Transforming and optimizing animation requirements

[0391] The server converts the generated requirements list into a format suitable for the generating AI and optimizes it, so that all the information the generating AI needs is prepared.

[0392] Generate initial animation

[0393] The server then sends the optimized requirements list to the generative AI engine, which generates initial animations based on the given requirements, including character modeling, basic scene setup, and dynamic actions.

[0394] Identification of intermediate products

[0395] The generated initial animation is provided as a preview to the user's device from the server. The user can check this preview and provide feedback. For example, the user can send correction instructions such as "I want the character's clothing to look more business-like" to the server via their device.

[0396] Receiving and incorporating feedback

[0397] The server receives user feedback, analyzes it again using NLP, and converts it into specific modification requirements, which are then sent back to the generation AI, which then modifies the animation based on this.

[0398] Generating the final animation

[0399] Once the final animation is generated, the server retrieves the completed animation data and generates a download link for the user, who can then download and use the final animation.

[0400] As a concrete example, when generating a 30-second animation introducing a new smartwatch, the user first inputs instructions such as, "I want to create an animation that introduces the smartwatch and highlights its features." The server analyzes these instructions, sends the necessary requirements to the generation AI, provides the generated preview to the user, makes corrections based on feedback, and finally provides the user with a download link. This series of processes allows users to easily and efficiently create high-quality animations.

[0401] The processing flow will be explained below.

[0402] Step 1:

[0403] The user uses the device to input instructions for animation production in natural language. For example, they might input, "I want to create a 30-second animation introducing our new smartwatch." The device then sends the input instructions to the server as text data.

[0404] Step 2:

[0405] The server receives the instruction data sent by the user and passes it to a natural language processing (NLP) engine for analysis. This analysis extracts animation requirements from the user's instructions. For example, the instructions may be analyzed to identify the requirements: "Introduce the smartwatch," "Use a character," "Movement scene," and "30 seconds."

[0406] Step 3:

[0407] The server converts the extracted requirements into a format suitable for generative AI, generates a requirements list, and then sends the optimized requirements list to the generative AI engine.

[0408] Step 4:

[0409] The generation AI generates initial animations based on a list of requirements sent from the server, which includes character modeling, basic scene setup, and actions. The generated initial animations are returned to the server.

[0410] Step 5:

[0411] The server provides a preview of the generated initial animation to the user's device, allowing the user to view the intermediate animation results and provide feedback.

[0412] Step 6:

[0413] The user can use the device to input feedback on the previewed animation, such as "I'd like the character's clothing to look more business-like," and the device will then send this feedback to the server.

[0414] Step 7:

[0415] The server receives the feedback from the user, analyzes it again using the NLP engine, generates specific correction requirements based on the feedback, and sends them to the generation AI.

[0416] Step 8:

[0417] The generation AI regenerates the animation based on the modified requirements and returns the modified animation data to the server, which then retrieves this data and prepares it as the final animation.

[0418] Step 9:

[0419] The server generates a download link to provide the completed final animation to the user, and the download link is sent to the user's device, allowing the user to obtain the final animation through the link.

[0420] By following the above steps, users can easily create high-quality animations with a variety of graphic styles by simply issuing instructions without moving their hands.

[0421] Example 1

[0422] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0423] Conventional animation production systems require users to have detailed operations and technical knowledge, making it difficult to efficiently create high-quality animations. It is also difficult to quickly and reliably incorporate feedback into the process of understanding user instructions and generating animations that reflect those instructions. To solve these problems, a system is needed that can accurately analyze users' natural language instructions and efficiently embody them as animations.

[0424] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0425] In this invention, the server includes means for receiving natural language instructions from a user, means for analyzing the natural language instructions and converting them into animation requirements, means for converting the converted requirements into a format understandable by a generation AI engine and optimizing them, generation AI means for generating an animation based on the optimized requirements, means for providing a preview of the generated animation to the user, means for receiving feedback from the user and reflecting it in the generation AI means, means for generating a final animation that reflects the feedback, and means for generating a download link for providing the final animation to the user. This enables users to create high-quality animations with simple instructions in natural language and to quickly and reliably modify and complete animations that reflect feedback.

[0426] A "user" is an entity that inputs instructions to the system in natural language and generates animations.

[0427] A "natural language instruction" is a request or command entered by a user in a natural language, such as text or voice.

[0428] The "analysis means" is a means having a function for analyzing instructions in natural language and converting them into animation requirements.

[0429] "Animation requirements" refers to the conditions and components necessary for generating animation extracted by the analysis means.

[0430] A "generative AI engine" is an artificial intelligence engine that generates animations based on the animation requirements.

[0431] "Generative AI means" refers to means including functions and processes for generating animations using a generative AI engine.

[0432] An "optimization means" is a means that has the function of converting the converted requirements into a format that can be understood by the generative AI engine and optimizing them.

[0433] The "preview providing means" is a means having a function for providing a preview of the generated animation to the user.

[0434] "Feedback" refers to opinions and instructions that a user submits to the system after checking the preview and inputting any necessary corrections or improvements.

[0435] The "feedback receiving means" is a means that has the function of receiving feedback from the user and reflecting it in the generating AI means.

[0436] "Final animation" refers to the animation that has been revised and completed based on user feedback.

[0437] The "download link generating means" is a means having a function for generating a download link for providing the final animation to the user.

[0438] System Configuration

[0439] This invention is a system that generates animations by analyzing and converting instructions entered by the user in natural language. This system enables the creation of high-quality, diverse animations without forcing the user to perform specific operations.

[0440] Hardware and Software

[0441] This system uses the following hardware and software:

[0442] 1. Hardware:

[0443] Device: A computer, smartphone, tablet, etc., through which a user inputs instructions.

[0444] Server: A high-performance server that performs instruction analysis and animation generation processing.

[0445] 2. Software:

[0446] Natural language processing engine (NLP engine): Analyzes the user's natural language instructions and extracts animation requirements. As a concrete example, we use the Google Cloud Natural Language API.

[0447] Generative AI engine: An artificial intelligence engine for generating animations. As a specific example, we will use OpenAI's DALL-E.

[0448] Program processing description

[0449] 1. User input

[0450] The user uses the device to send instructions in natural language to the system. For example, the user might enter the following instruction: "I want to create a 30-second animation showcasing a new smartwatch. I want to create a moving scene with characters." Once this instruction is entered, the device sends it to the server.

[0451] 2. Receiving and analyzing instructions

[0452] The server receives instructions sent by the user and analyzes them using a natural language processing engine. The NLP engine extracts animation requirements from the instructions and generates a list of requirements. This list of requirements includes specific conditions such as "introduce the smartwatch," "use of characters," "scenes with movement," and "30 seconds."

[0453] 3. Transforming and optimizing animation requirements

[0454] The server converts the generated requirements list into a format that the generative AI engine can understand and optimizes it, ensuring that all the information the generative AI engine needs is prepared.

[0455] 4. Generating the initial animation

[0456] The server then sends the optimized requirements list to the generative AI engine, which generates initial animations based on the given requirements, including character modeling, basic scene settings, and dynamic actions.

[0457] 5. Identification of intermediate products

[0458] The generated initial animation is provided as a preview from the server to the user's device. The user can check this preview and provide feedback. For example, the user can send correction instructions such as "I want the character's clothing to look more business-like" to the server via their device.

[0459] 6. Receiving and implementing feedback

[0460] The server receives user feedback, analyzes it again using a natural language processing engine, and converts it into specific modification requirements, which are then sent back to the generative AI engine, which then modifies the animation based on the results.

[0461] 7. Generating the final animation

[0462] Once the final animation is generated, the server retrieves the completed animation data and generates a download link for the user, who can then download and use the final animation.

[0463] Specific examples

[0464] For example, to generate a 30-second animation introducing a new smartwatch, a user first inputs instructions such as, "I want to create an animation that introduces the smartwatch and highlights its features." The server analyzes these instructions, sends the necessary requirements to the generation AI engine, and provides the generated preview to the user. The user then checks the preview, makes any necessary corrections, and finally receives a download link. This process allows users to create high-quality animations easily and efficiently.

[0465] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0466] Step 1: User input

[0467] The user uses the device to input instructions for animation production in natural language. This input is done using the text box or voice input function of a dedicated application. Specifically, the user enters instructions such as, "I want to create a 30-second animation introducing our new smartwatch product. I want to create a scene with moving characters." The input data is sent in text format.

[0468] Step 2: Sending instruction data

[0469] The terminal sends the natural language instructions entered by the user to the server using an HTTP POST request, with the data packaged in JSON format. The input data is the user's instruction text, and the output data is the JSON data sent to the server.

[0470] Step 3: Analyze the instruction data

[0471] The server analyzes the received instruction data. Specifically, it uses a natural language processing engine (e.g., Google Cloud Natural Language API) to extract animation requirements from the instruction text. The input data is the user's instruction text, and the output data is a list of requirements. This list of requirements includes specific conditions such as "introduce the smartwatch," "use of a character," "scene with movement," and "30 seconds."

[0472] Step 4: Generate a requirements list

[0473] The server generates a requirements list based on the analysis results obtained from the NLP engine. Here, the extracted requirements are organized into a list format and converted into a format that can be understood by the generation AI engine. The input data is the analysis results, and the output data is the requirements list.

[0474] Step 5: Transform and optimize your requirements list

[0475] The server converts the generated requirement list into a prompt that can be referenced by the generation AI engine and performs optimization. Specifically, it formats the requirement list into something like "introduce a smartwatch, use a character, include a scene with movement, 30 seconds." The input data is the requirement list, and the output data is a prompt for the generation AI.

[0476] Step 6: Generate the initial animation

[0477] The server sends the optimized prompt to the AI ​​engine, which then generates the initial animation based on the prompt. The initial creation includes character modeling and basic scene settings. The input data is the prompt, and the output data is the initial animation file.

[0478] Step 7: Check the intermediate products

[0479] The server provides the generated initial animation as a preview to the user's device. The device displays this animation in a playable format. The user visually checks the preview and provides feedback as needed. The input data is the initial animation file, and the output data is the user's feedback.

[0480] Step 8: Getting user feedback

[0481] After checking the preview, the user can submit feedback for corrections and improvements. Specifically, the user can enter feedback such as "I would like the character's clothing to be more business-like." The device then sends this feedback to the server. The input data is the user's feedback, and the output data is the feedback's JSON data.

[0482] Step 9: Analyze and transform feedback

[0483] The server analyzes the feedback received from the user again using a natural language processing engine and converts it into specific revision requirements. The input data is the user feedback, and the output data is a list of revision requirements.

[0484] Step 10: Modifying the animation

[0485] Based on the feedback, the server sends modification requirements to the generative AI engine to modify the animation. The generative AI engine regenerates the animation based on the new requirements. The input data is the list of modification requirements, and the output data is the modified animation file.

[0486] Step 11: Generate the final animation

[0487] Once the final animation is generated, the server retrieves the completed animation data and generates a download link to provide to the user. The input data is the modified animation file, and the output data is the download link.

[0488] Step 12: Provide a download link

[0489] The server sends the generated download link to the user's device. The user can use this link to download and use the final animation. The input data is the download link, and the output data is the user's download action.

[0490] (Application example 1)

[0491] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0492] Conventional animation generation systems require specialized knowledge and skills, making it difficult for average users to easily generate high-quality animations. Furthermore, in order to respond quickly to advertising campaigns, a means for easily creating high-quality animated advertisements is required. Furthermore, there is a lack of a means for smoothly previewing generated animations and incorporating feedback, preventing an efficient animation production process.

[0493] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0494] In this invention, the server includes a means for receiving natural language instructions from a user, a means for analyzing the natural language instructions and converting them into animation requirements, and a generation AI means for generating animations based on the converted requirements. This allows even general users to easily create high-quality animated advertisements in natural language. Furthermore, by including a means for providing a preview of the generated animation and a means for receiving and incorporating user feedback, an efficient animation production process can be realized, allowing animations for advertising campaigns to be quickly provided.

[0495] The "means for receiving instructions in natural language from the user" refers to an interface and function that allows the user to input instructions for animation production in natural language and for the system to receive them.

[0496] "Means for analyzing natural language instructions and converting them into animation requirements" refers to the function and process of converting natural language instructions received from a user into a format that a machine can understand and extracting specific production requirements for the animation.

[0497] The "generative AI means for generating animations based on converted requirements" refers to an artificial intelligence engine and related technologies that automatically generate animations based on analyzed requirements.

[0498] The "means for providing a user with a preview of the generated animation" refers to a function and interface that displays the initially generated animation so that the user can check it.

[0499] "Means for receiving feedback from users and reflecting it in the generating AI means" is a function that receives correction requests provided by the user after checking the preview, and sends them back to the generating AI engine to be reflected in the animation.

[0500] The "means for generating a final animation that reflects feedback" refers to the process and technique for generating a final animation after reflecting user feedback.

[0501] The "means for providing the final animation to the user" refers to the functionality and interface that provides the completed animation so that the user can download or view it.

[0502] "Means for creating high-quality animated advertisements for advertising campaigns in natural language on a user terminal" refers to a process and technology that allows a user to input instructions for creating advertising animations in natural language using a terminal, and the system generates high-quality advertising animations based on those instructions.

[0503] The "means for transmitting advertisement production instructions in natural language from the user to the server" refers to a function and interface for transmitting advertisement production instructions entered by the user to the server via the network.

[0504] The "means for the server to analyze instructions and extract requirements for advertising animation" refers to the functions and processes for analyzing received natural language advertising production instructions and extracting specific requirements for advertising animation.

[0505] "Generative AI means for generating animations suitable for advertising purposes based on requirements" refers to an artificial intelligence engine and related technologies that automatically generate animations that meet advertising purposes based on extracted requirements.

[0506] "Means for sending a preview link of the generated animation to a user terminal and receiving user confirmation and feedback" refers to a function and interface for displaying a preview of the generated animation on a user terminal and receiving confirmation and feedback.

[0507] The "means for providing a download link for the final animation to a user terminal" refers to a function and interface that provides the completed final animation to a user terminal as a download link.

[0508] DETAILED DESCRIPTION OF THE INVENTION In the preferred embodiment of the present invention, a system is described that allows for easy generation of high quality animated advertisements in natural language for advertising campaigns.

[0509] First, a user uses a device such as a smartphone or tablet to input instructions for animation production in natural language. For example, they might input instructions like, "I want to create a 30-second animated commercial that conveys the features and appeal of a newly released smartphone. It should include a scene in which a character uses the smartphone to explain its convenient functions."

[0510] The input natural language instructions are sent from the device to the server. At this time, data is sent as an HTTP request using API communication. The server analyzes the received instructions using a natural language processing (NLP) engine and extracts the requirements for animation production. For natural language processing, a Python NLP library (such as NLTK or spaCy) is used, for example.

[0511] Next, the server optimizes the extracted requirements and converts them into a format suitable for the generative AI engine. During this process, the requirements are converted and optimized using a data processing script. The converted requirements are then sent to the generative AI engine, which generates the initial animation. The generative AI means used for this is, for example, OpenAI's API or DALL-E.

[0512] The generated initial animation is sent from the server to the user's device as a preview link. The user can check the animation through this preview link and provide feedback. For example, the user can input a command such as "I want the character's clothes to look more business-like."

[0513] The server again uses a natural language processing engine to analyze the user's feedback and convert it into specific revision requirements, which are then sent to a generative AI engine to revise the animation. This process is repeated until the user is satisfied.

[0514] Once the final animation is generated, the server generates a download link to provide the completed animation to the user's device, where the user can download the final animation and use it in their advertising campaign.

[0515] For example, when introducing a new smartwatch, a user can enter a specific prompt such as, "I want to create an animation that introduces the smartwatch and highlights its features," and the system will generate a high-quality animation based on this instruction.

[0516] The system allows users to easily generate high-quality animations that can be used in advertising campaigns using natural language, without requiring specialized skills.

[0517] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0518] Step 1:

[0519] The user uses a terminal to input instructions for animation production in natural language. For example, they might input, "I want to create a 30-second animated commercial that conveys the features and appeal of a newly released smartphone. It should include a scene in which a character uses the smartphone to explain its convenient functions." This input is received by the system and sent to the next step.

[0520] Step 2:

[0521] The device sends input instructions in natural language to the server. The input data is natural language text and is sent to the server as an HTTP request. The server receives the request and converts it into a usable format for analysis.

[0522] Step 3:

[0523] The server parses the received natural language instructions using a natural language processing (NLP) engine. The input data is natural language text, which is parsed using an NLP engine (e.g., spaCy or NLTK) to extract the information needed for animation production requirements. The output is a list of requirements.

[0524] Step 4:

[0525] The server optimizes the extracted requirements list and converts it into a format suitable for the generative AI engine. The input data is the extracted requirements list, which is converted into the optimal format using a data processing script (e.g., Python). The output is formatted data to be sent to the generative AI engine.

[0526] Step 5:

[0527] The server sends the optimized requirement list to the generative AI engine to generate the initial animation. The input data is formatted data, and the generative AI engine (e.g., OpenAI API or DALL-E) generates the animation. The output is the initial generated animation data.

[0528] Step 6:

[0529] The server sends the generated initial animation to the user's device as a preview link. The input data is the initially generated animation data, which is sent to the user's device as an HTTP request. The user can check the animation using the preview link.

[0530] Step 7:

[0531] The user checks the preview and provides feedback. The input is natural language text, which is sent from the device to the server. For example, the user might input a command such as, "I want the character's clothing to look more business-like."

[0532] Step 8:

[0533] The server again uses a natural language processing engine to analyze the user's feedback and convert it into specific correction requirements. The input data is the natural language text of the feedback, and the NLP engine extracts the correction requirements. The output is a list of correction requirements.

[0534] Step 9:

[0535] The server sends modification requirements to the generative AI engine to modify the animation. The input data is a list of modification requirements, and the generative AI engine is used to regenerate the animation. The output is the modified animation data.

[0536] Step 10:

[0537] Once the final animation is generated, the server generates a download link to provide the completed animation to the user and sends it to the user's device. The input data is the final animation data, which is sent to the user's device as an HTTP request. The user can download the final animation via this link and use it in their advertising campaign.

[0538] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0539] This invention is a system that automatically generates high-quality and diverse animations using natural language instructions from the user and an emotion engine that analyzes the user's emotions. In particular, it recognizes the user's emotions and adjusts the animation requirements based on them to provide more personalized animations.

[0540] User instruction input

[0541] The user uses the device to input instructions for animation production in natural language. For example, they might input, "I want to create a 30-second animation introducing our new smartwatch product. I want to create a scene with characters in motion." The input instructions are sent from the device to the server.

[0542] Receiving and parsing instructions

[0543] The server receives the instruction data sent by the user and analyzes it using a natural language processing (NLP) engine. The NLP engine extracts animation requirements from the instructions and generates a list of specific requirements. For example, requirements such as "introduce the smartwatch," "use of characters," "moving scenes," and "30 seconds" are extracted.

[0544] Applying the Emotion Engine

[0545] The server also passes the received instruction data to the emotion engine, which analyzes the user's emotions. The emotion engine recognizes emotions (e.g., joy, excitement, tension, etc.) from the user's language and context, and reflects the extracted emotional information in the animation requirements. For example, if the user is excited, it can add more dynamic movements and vivid colors to the requirements.

[0546] Transforming and optimizing animation requirements

[0547] The server integrates the extracted requirements and emotion information and converts it into a format suitable for the generative AI, thereby providing all the information necessary for the generative AI and optimizing the requirements list.

[0548] Generate initial animation

[0549] The server then sends the optimized requirement list to the generative AI engine, which generates initial animations based on the given requirements and emotion information. This stage includes character modeling, basic scene setup, and actions. The generated initial animations are returned to the server.

[0550] Identification of intermediate products

[0551] The generated initial animation is provided as a preview from the server to the user's device. The user can check this preview and provide feedback. For example, the user can send correction instructions such as "I want the character's clothing to look more business-like" to the server via their device.

[0552] Receiving and incorporating feedback

[0553] The server receives the user's feedback and analyzes it again using the NLP engine and emotion engine. Taking into account the content of the feedback as well as the user's emotions, it generates specific correction requirements and sends them to the generation AI.

[0554] Generating the final animation

[0555] The generation AI regenerates the animation based on the modification requirements and emotion information, and returns the modified animation data to the server, which then retrieves this data and prepares it as the final animation.

[0556] Providing the final animation

[0557] The server generates a download link to provide the completed final animation to the user, and the download link is sent to the user's device, allowing the user to obtain the final animation through the link.

[0558] As a concrete example, when generating a 30-second animation introducing a new smartwatch product, the user inputs instructions such as, "I want to create an animation that introduces the smartwatch and highlights its features." The server analyzes these instructions, uses an emotion engine to recognize the user's emotions (e.g., excitement), and generates a list of requirements based on these. The generation AI generates an initial animation and then reflects the user's feedback and emotional information to create the final animation. This series of processes allows users to easily and efficiently create personalized, high-quality animations.

[0559] The processing flow will be explained below.

[0560] Step 1:

[0561] The user uses the device to input instructions for animation production in natural language. For example, they might input, "I want to create a 30-second animation introducing our new smartwatch product. I want to create a scene with characters and movement." The device then sends the input instructions to the server.

[0562] Step 2:

[0563] The server receives the instruction data sent by the user and passes it to a natural language processing (NLP) engine for analysis. The NLP engine extracts animation requirements from the instructions. The extracted requirements include "introduce the smartwatch," "use of characters," "moving scenes," and "30 seconds."

[0564] Step 3:

[0565] The server passes the received instruction data to the emotion engine, which analyzes the user's emotions. For example, if the user is excited, the emotion engine recognizes this and extracts emotion information such as "excited" or "positive."

[0566] Step 4:

[0567] The server integrates the extracted requirement list and emotion information and converts it into a format suitable for generative AI, including adjusting the animation style based on the emotion (e.g., color usage and movement emphasis).

[0568] Step 5:

[0569] The server sends the optimized requirement list to the generation AI engine, which generates an initial animation based on the requirement list and emotion information. This initial animation includes basic character modeling, scene setup, and basic movements. The generated initial animation is returned to the server.

[0570] Step 6:

[0571] The server sends a preview of the generated initial animation to the user's device, where the user can view the preview and provide feedback, such as "I'd like the character's clothing to look more business-like."

[0572] Step 7:

[0573] The device sends the user's feedback data to the server, which then receives the feedback data and analyzes it again using the NLP engine and emotion engine. Specific correction requirements are generated based on the feedback content.

[0574] Step 8:

[0575] The server reflects the feedback requirements and emotional information and sends it to the generation AI means. The generation AI regenerates the animation based on this. This regeneration process includes corrections specified in the feedback and style adjustments based on the emotional information. The corrected animation data is returned to the server.

[0576] Step 9:

[0577] The server prepares the final version of the modified animation and generates a download link for the user, which is then sent to the user's device.

[0578] Step 10:

[0579] The user can then use the provided download link to download the final animation from their device, allowing them to receive the final product introduction animation.

[0580] By following the above steps, the user can easily create a variety of high-quality animations based on the user's emotions, simply by issuing instructions without moving their hands.

[0581] Example 2

[0582] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0583] Current animation generation systems struggle to efficiently generate personalized, high-quality animations that meet user needs. In particular, they lack a process for generating animations that takes user emotions into account, resulting in generated animations that do not adequately reflect user expectations and emotions. Furthermore, the process of making corrections based on user feedback is cumbersome and time-consuming, and improvements are needed to increase user satisfaction.

[0584] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0585] In this invention, the server includes means for receiving natural language instructions from a user, means for analyzing the natural language instructions and converting them into animation requirements, means for analyzing the user's emotions from the natural language instructions, generation AI means for generating animation based on the converted requirements and the analyzed emotional information, means for providing a preview of the generated animation to the user, means for receiving feedback from the user and reflecting it in the generation AI means, means for generating a final animation that reflects the feedback and emotional information, and means for providing the final animation to the user. This enables the generation of personalized, high-quality animation that takes user instructions and emotions into consideration.

[0586] A "user" is a person who operates the system to input animation instructions and checks and provides feedback on the generated animation.

[0587] "Natural language instructions" refer to instructions written in sentence format that are input by a user through a terminal.

[0588] "Analysis" is the process of using a natural language processing engine and an emotion engine to understand the user's instructions and emotions from the context and convert them into specific data.

[0589] "Animation requirements" are specific conditions and elements for generating animations, extracted from the analyzed natural language instructions and emotional information.

[0590] "Emotion information" is data about the user's emotions (e.g., joy, excitement, tension) extracted from the user's natural language instructions.

[0591] The "generative AI means" is an artificial intelligence system that automatically generates animations based on the extracted animation requirements and emotional information.

[0592] A "preview" is a short video that allows the user to see an early version of the generated animation.

[0593] "Feedback" refers to correction instructions and evaluations provided by the user after checking the preview.

[0594] The "final animation" refers to the final animation that reflects the user's feedback and emotional information.

[0595] The "server" is a computer system that executes various processing means, manages and analyzes instructions and feedback from users, and generates and provides the final animation.

[0596] A "terminal" is a device that a user uses to input natural language instructions, see a preview of the generated animation, and provide feedback.

[0597] The present invention is a system that automatically generates high-quality, personalized animations by utilizing natural language instructions from a user and a generative AI model with an emotion engine. The following describes an embodiment of the system.

[0598] User instruction input

[0599] A user uses a device (e.g., a PC or smartphone) to access a dedicated application or website and input instructions for animation production in natural language. For example, they might input instructions such as, "I want to create a 30-second animation introducing our new smartwatch product. I want to create a scene with characters in motion." These input instructions are then sent from the device to the server.

[0600] Receiving and parsing instructions

[0601] The server receives instruction data sent by the user. This data is automatically passed to a natural language processing (NLP) engine for analysis. The NLP engine extracts animation requirements from the user's instructions and generates a list of specific requirements. For example, requirements such as "introduce the smartwatch," "use of characters," "moving scenes," and "30 seconds" are extracted from the instructions.

[0602] Applying the Emotion Engine

[0603] At the same time, the server passes the received instruction data to the emotion engine, which analyzes the user's emotions. The emotion engine recognizes emotions (e.g., joy, excitement, tension) from the user's context and vocabulary, and reflects this emotional information in the animation requirements. For example, if the user is excited, more dynamic movements and vivid colors are added to the requirements.

[0604] Transforming and optimizing animation requirements

[0605] The server then integrates the extracted requirements list with the emotion information and converts it into a format suitable for the generative AI model. This process ensures that all the information required by the generative AI is gathered and the requirements list is optimized. Specifically, the requirements list is converted into a data structure such as JSON format.

[0606] Generate initial animation

[0607] The server sends the optimized requirement list to the generative AI engine, which then models the character, sets up the basic scene, plans the action, and generates the initial animation based on the requirements and emotion information. Once this series of processes is complete, the generated initial animation data is sent back to the server.

[0608] Identification of intermediate products

[0609] The generated initial animation is provided as a preview from the server to the user's device. The user can check the preview on their device and provide feedback on any points of concern or changes they would like to make. For example, they can send detailed correction instructions, such as "I would like the character's clothing to be more business-like," to the server from their device.

[0610] Receiving and incorporating feedback

[0611] The server receives feedback from the user. The received feedback is analyzed again by the NLP engine and emotion engine to generate specific correction requirements. In addition, the user's latest emotional information is also reflected. This information is then sent again to the generative AI engine.

[0612] Generating the final animation

[0613] The generative AI engine regenerates the animation based on the user's modification requirements and emotional information. The final animation data reflecting the modification requests is sent back to the server, which then retrieves this data and prepares the final animation.

[0614] Providing the final animation

[0615] The server generates a download link for providing the completed final animation to the user, and the download link is sent to the user's device, allowing the user to download and obtain the final animation through the link.

[0616] Specific examples

[0617] For example, when generating a 30-second animation introducing a new smartwatch product, the user inputs instructions such as, "I want to create an animation that introduces the smartwatch and highlights its features." The server analyzes these instructions, uses an emotion engine to recognize the user's emotions (e.g., excitement), and generates a list of requirements based on those emotions. The generative AI generates an initial animation and then reflects the user's feedback and emotional information to create the final animation. This series of processes allows users to easily and efficiently create personalized, high-quality animations.

[0618] Prompt Sentence Examples

[0619] "Create a 30-second animation showcasing a new smartwatch. I'd like it to be animated with characters and incorporate emotions that excite the user."

[0620] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0621] Step 1:

[0622] User instruction input

[0623] The user uses a device to access a dedicated application or website and inputs instructions for animation production in natural language. For example, they might input, "I want to create a 30-second animation introducing our new smartwatch. I want to create a scene with characters in motion." This input is then sent from the device to the server.

[0624] Input: Natural language animation instructions

[0625] Output: Instruction data sent from the terminal to the server

[0626] Step 2:

[0627] Receiving and parsing instructions

[0628] The server receives instruction data sent by the user. This data is automatically passed to a natural language processing (NLP) engine for analysis. The NLP engine extracts animation requirements from the user's instructions and generates a list of specific requirements. For example, it extracts requirements such as "introduce a smartwatch," "use of characters," "scenes with movement," and "30 seconds."

[0629] Input: Instruction data sent by the user

[0630] Data processing: Analysis using a natural language processing engine

[0631] Output: Extracted animation requirements list

[0632] Step 3:

[0633] Applying the Emotion Engine

[0634] At the same time, the server passes the received instruction data to the emotion engine, which analyzes the user's emotions. The emotion engine recognizes emotions (e.g., joy, excitement, tension) from the user's context and vocabulary, and reflects this emotional information in the animation requirements. For example, if the user is excited, more dynamic movements and vivid colors are added to the requirements.

[0635] Input: Instruction data to be analyzed

[0636] Data processing: Emotion analysis using an emotion engine

[0637] Output: Parsed emotion information

[0638] Step 4:

[0639] Transforming and optimizing animation requirements

[0640] The server then integrates the extracted requirements list with the emotion information and converts it into a format suitable for the generative AI model. This process ensures that all the information required by the generative AI is gathered and the requirements list is optimized. Specifically, the requirements list is converted into a data structure such as JSON format.

[0641] Input: Requirement list and sentiment information

[0642] Data processing: requirements optimization and format conversion

[0643] Output: An optimized requirements list for a generative AI model

[0644] Step 5:

[0645] Generate initial animation

[0646] The server sends the optimized requirement list to the generative AI engine, which then models the character, sets up the basic scene, and plans the movement based on the requirements and emotion information, generating the initial animation. Once this series of processes is complete, the generated initial animation data is sent back to the server.

[0647] Input: Optimized requirements list

[0648] Data processing: Generative AI animation generation

[0649] Output: Initial animation data

[0650] Step 6:

[0651] Identification of intermediate products

[0652] The generated initial animation is sent as a preview from the server to the user's device. The user can check the preview on their device and provide feedback on any areas of concern or changes they would like to see. For example, they can send detailed correction instructions, such as "I would like the character's clothing to look more business-like," to the server.

[0653] Input: Initial animation preview

[0654] Data processing: User feedback

[0655] Output: List of modified requirements

[0656] Step 7:

[0657] Receiving and incorporating feedback

[0658] The server receives feedback from the user. The received feedback is analyzed again by the NLP engine and emotion engine. Specific correction requirements are generated, and the user's latest emotional information is also reflected. This information is then sent back to the generative AI engine.

[0659] Input: User feedback

[0660] Data processing: Analysis of feedback and generation of revised requirements

[0661] Output: Modified requirement list and sentiment information

[0662] Step 8:

[0663] Generating the final animation

[0664] The generative AI engine regenerates the animation based on the user's modification requirements and emotional information. The final animation data reflecting the modification requests is sent back to the server. The server receives this data and prepares the final animation.

[0665] Input: Modified requirement list and sentiment information

[0666] Data processing: Regenerating animations using generative AI

[0667] Output: Final animation data

[0668] Step 9:

[0669] Providing the final animation

[0670] The server generates a download link for the completed final animation to provide the user with the animation, and the download link is sent to the user's device, allowing the user to download and obtain the final animation through the link.

[0671] Input: Final animation data

[0672] Data processing: Generate download links

[0673] Output: Send a download link to the user's device

[0674] (Application example 2)

[0675] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0676] Conventional animation production systems make it difficult for users to easily reflect individual emotions and specific instructions, resulting in a cumbersome process for creating personalized, high-quality animations. Furthermore, there is a lack of effective means for quickly and intuitively generating animations in specific fields such as advertising. There is a need for a system that can solve these problems and automatically generate high-quality animations that reflect individual emotions based on natural language instructions from users.

[0677] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving natural language instructions from a user; means for analyzing the natural language instructions and converting them into animation requirements; means for reading the user's emotions from the analyzed natural language instructions and generating animation requirements that reflect the emotions; generation AI means for generating animation based on the converted requirements; means for providing a preview of the generated animation to the user; means for receiving feedback from the user and reflecting it in the generation AI means; means for generating a final animation that reflects the feedback and the read emotions; and means for providing the final animation to the user. This makes it possible to quickly generate personalized, high-quality animation that reflects the user's emotions.

[0678] The "means for receiving instructions in natural language from a user" refers to a device or interface for recognizing instructions input in natural language by a user and transmitting the instructions to a server.

[0679] The "means for parsing natural language instructions and converting them into animation requirements" refers to software or algorithms that parse natural language instructions entered by a user and convert those instructions into specific animation requirements.

[0680] "Means for reading the user's emotions from the analyzed natural language instructions and generating animation requirements that reflect those emotions" is an algorithm that extracts the user's emotions from the analyzed instructions and generates animation requirements taking those emotions into consideration.

[0681] "Generative AI means" refers to an artificial intelligence system that automatically generates initial and final animations based on the requirements of the converted animation.

[0682] The "means for providing a preview to the user" refers to a system or interface for visually displaying to the user intermediate and final results of the generated animation.

[0683] The "means for receiving feedback and reflecting it in the generating AI means" is an algorithm for receiving feedback provided by the user, analyzing that feedback, and reflecting it in the generating AI.

[0684] The "means for generating final animation" is an AI system that generates the final animation based on user feedback and emotional information.

[0685] The "means for providing the final animation to the user" refers to a system or interface that allows the user to download or view the completed final animation.

[0686] This invention is a system for quickly and effectively generating animations for advertising. This system includes a series of processes that receive natural language instructions from a user, analyze them, and generate animations that reflect the user's emotions.

[0687] First, the user inputs instructions for animation production in natural language via a device such as a smartphone. These instructions are then sent from the device to the server. For example, a user might say, "I want to create a 30-second animated advertisement introducing our new lunch menu. I want to give it a seasonal feel."

[0688] The server receives the instruction data sent by the user and analyzes it using a natural language processing engine (e.g., Google Cloud Natural Language API). During this analysis, animation requirements are extracted from the instructions. For example, from the above instructions, requirements such as "new lunch menu," "seasonal feel," and "30-second animation" are extracted.

[0689] Next, the server uses an emotion analysis engine (e.g., IBM Watson Tone Analyzer) to analyze the user's emotions. In this process, emotions (e.g., excitement, joy, etc.) are recognized from the user's vocabulary and context, and the extracted emotional information is reflected in the animation requirements. For example, if the user excitedly inputs a command such as "I want to create a sense of the season," animation requirements with more dynamic color usage and movement are added.

[0690] The server integrates these animation requirements and emotion information and converts them into a format suitable for a generative AI model (e.g., DALL-E or GPT-4). This production AI model generates an initial animation based on the given requirements. The generated initial animation is then provided as a preview from the server to the user's device.

[0691] The user checks the preview and provides feedback for corrections, such as "I'd like the background of the scene to be a warmer color." This feedback is sent from the device to the server, where it is again subjected to natural language processing and sentiment analysis to generate specific correction requirements.

[0692] The generative AI model regenerates the animation based on the modified requirements to create the final animation, which is then provided as a download link from the server to the user's device, allowing the user to download the animation through this link.

[0693] As a concrete example, the prompt text for "If you want to create an advertising animation for the new menu item 'Special Japanese-style Hamburger Steak'" is as follows:

[0694] "We'd like to create a 30-second animated ad to promote our new special Japanese-style hamburger lunch. Emphasize the autumn feel with warm colors and dynamic movements."

[0695] The present invention allows users to quickly generate personalized, emotionally-driven, and high-quality advertising animations.

[0696] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0697] Step 1:

[0698] The user uses a terminal to input instructions for animation production in natural language. For example, the instructions might be, "I want to create a 30-second animated advertisement introducing our new special Japanese-style hamburger steak lunch. Please emphasize the autumnal feeling with warm colors and dynamic movements." After input, this data is sent from the terminal to the server.

[0699] Step 2:

[0700] The server sends the received instruction data to a natural language processing engine (e.g., Google Cloud Natural Language API) for analysis. The input for the analysis is the user's natural language instruction, and the output is a list of requirements such as "new special Japanese-style hamburger lunch," "warm colors," "dynamic movements," "autumn seasonal feel," and "30-second animation."

[0701] Step 3:

[0702] The server sends the acquired requirement list and instruction data to an emotion analysis engine (e.g., IBM Watson Tone Analyzer) to extract the user's emotion. The input is the instruction data, and the output is the recognized emotion information (e.g., joy, excitement). This adds the emotion information to the requirement list.

[0703] Step 4:

[0704] The server integrates and optimizes the converted requirement list and emotion information into a format suitable for the generative AI model (e.g., DALL-E or GPT-4). The input of this process is the requirement list and emotion information, and the output is data in a format that can be interpreted by the generative AI model.

[0705] Step 5:

[0706] The server sends the optimized data to the generative AI model to generate the initial animation. The input is the optimized data, and the output is the initial animation. The generated initial animation is returned to the server.

[0707] Step 6:

[0708] The server provides a preview of the initial animation to the user's device, and the user can view the preview and provide feedback in natural language, such as "I'd like the background color to be warmer."

[0709] Step 7:

[0710] The server receives feedback from the user and passes it back to the natural language processing engine and sentiment analysis engine for analysis. The input is the feedback, and the output is the correction requirements and sentiment information.

[0711] Step 8:

[0712] The server issues regeneration instructions to the generative AI model based on the modification requirements, generating the final animation. The input is the modification requirements and emotion information, and the output is the final animation.

[0713] Step 9:

[0714] The final animation is provided to the user's device as a download link from the server, and the user can obtain the final animation through the link.

[0715] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0716] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0717] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0718] [Third embodiment]

[0719] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0720] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0721] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0722] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0723] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0724] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0725] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0726] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0727] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0728] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0729] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0730] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0731] This invention is a system that generates animations by analyzing and converting instructions entered by the user in natural language. This system enables the creation of high-quality and diverse animations without forcing the user to perform specific operations.

[0732] User instruction input

[0733] First, the user uses the device to send instructions in natural language to the system. For example, the user might enter the following instruction: "I want to create a 30-second animation showcasing our new smartwatch. I want to create a moving scene with characters." Once this instruction is entered, the device sends it to the server.

[0734] Receiving and parsing instructions

[0735] The server receives instructions sent by the user and analyzes them using a natural language processing (NLP) engine. The NLP engine extracts animation requirements from the instructions and generates a list of requirements. This list of requirements includes specific conditions such as "introduce the smartwatch," "use of characters," "scenes with movement," and "30 seconds."

[0736] Transforming and optimizing animation requirements

[0737] The server converts the generated requirements list into a format suitable for the generating AI and optimizes it, so that all the information the generating AI needs is prepared.

[0738] Generate initial animation

[0739] The server then sends the optimized requirements list to the generative AI engine, which generates initial animations based on the given requirements, including character modeling, basic scene setup, and dynamic actions.

[0740] Identification of intermediate products

[0741] The generated initial animation is provided as a preview to the user's device from the server. The user can check this preview and provide feedback. For example, the user can send correction instructions such as "I want the character's clothing to look more business-like" to the server via their device.

[0742] Receiving and incorporating feedback

[0743] The server receives user feedback, analyzes it again using NLP, and converts it into specific modification requirements, which are then sent back to the generation AI, which then modifies the animation based on this.

[0744] Generating the final animation

[0745] Once the final animation is generated, the server retrieves the completed animation data and generates a download link for the user, who can then download and use the final animation.

[0746] As a concrete example, when generating a 30-second animation introducing a new smartwatch, the user first inputs instructions such as, "I want to create an animation that introduces the smartwatch and highlights its features." The server analyzes these instructions, sends the necessary requirements to the generation AI, provides the generated preview to the user, makes corrections based on feedback, and finally provides the user with a download link. This series of processes allows users to easily and efficiently create high-quality animations.

[0747] The processing flow will be explained below.

[0748] Step 1:

[0749] The user uses the device to input instructions for animation production in natural language. For example, they might input, "I want to create a 30-second animation introducing our new smartwatch." The device then sends the input instructions to the server as text data.

[0750] Step 2:

[0751] The server receives the instruction data sent by the user and passes it to a natural language processing (NLP) engine for analysis. This analysis extracts animation requirements from the user's instructions. For example, the instructions may be analyzed to identify the requirements: "Introduce the smartwatch," "Use a character," "Movement scene," and "30 seconds."

[0752] Step 3:

[0753] The server converts the extracted requirements into a format suitable for generative AI, generates a requirements list, and then sends the optimized requirements list to the generative AI engine.

[0754] Step 4:

[0755] The generation AI generates initial animations based on a list of requirements sent from the server, which includes character modeling, basic scene setup, and actions. The generated initial animations are returned to the server.

[0756] Step 5:

[0757] The server provides a preview of the generated initial animation to the user's device, allowing the user to view the intermediate animation results and provide feedback.

[0758] Step 6:

[0759] The user can use the device to input feedback on the previewed animation, such as "I'd like the character's clothing to look more business-like," and the device will then send this feedback to the server.

[0760] Step 7:

[0761] The server receives the feedback from the user, analyzes it again using the NLP engine, generates specific correction requirements based on the feedback, and sends them to the generation AI.

[0762] Step 8:

[0763] The generation AI regenerates the animation based on the modified requirements and returns the modified animation data to the server, which then retrieves this data and prepares it as the final animation.

[0764] Step 9:

[0765] The server generates a download link to provide the completed final animation to the user, and the download link is sent to the user's device, allowing the user to obtain the final animation through the link.

[0766] By following the above steps, users can easily create high-quality animations with a variety of graphic styles by simply issuing instructions without moving their hands.

[0767] Example 1

[0768] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0769] Conventional animation production systems require users to have detailed operations and technical knowledge, making it difficult to efficiently create high-quality animations. It is also difficult to quickly and reliably incorporate feedback into the process of understanding user instructions and generating animations that reflect those instructions. To solve these problems, a system is needed that can accurately analyze users' natural language instructions and efficiently embody them as animations.

[0770] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0771] In this invention, the server includes means for receiving natural language instructions from a user, means for analyzing the natural language instructions and converting them into animation requirements, means for converting the converted requirements into a format understandable by a generation AI engine and optimizing them, generation AI means for generating an animation based on the optimized requirements, means for providing a preview of the generated animation to the user, means for receiving feedback from the user and reflecting it in the generation AI means, means for generating a final animation that reflects the feedback, and means for generating a download link for providing the final animation to the user. This enables users to create high-quality animations with simple instructions in natural language and to quickly and reliably modify and complete animations that reflect feedback.

[0772] A "user" is an entity that inputs instructions to the system in natural language and generates animations.

[0773] A "natural language instruction" is a request or command entered by a user in a natural language, such as text or voice.

[0774] The "analysis means" is a means having a function for analyzing instructions in natural language and converting them into animation requirements.

[0775] "Animation requirements" refers to the conditions and components necessary for generating animation extracted by the analysis means.

[0776] A "generative AI engine" is an artificial intelligence engine that generates animations based on the animation requirements.

[0777] "Generative AI means" refers to means including functions and processes for generating animations using a generative AI engine.

[0778] An "optimization means" is a means that has the function of converting the converted requirements into a format that can be understood by the generative AI engine and optimizing them.

[0779] The "preview providing means" is a means having a function for providing a preview of the generated animation to the user.

[0780] "Feedback" refers to opinions and instructions that a user submits to the system after checking the preview and inputting any necessary corrections or improvements.

[0781] The "feedback receiving means" is a means that has the function of receiving feedback from the user and reflecting it in the generating AI means.

[0782] "Final animation" refers to the animation that has been revised and completed based on user feedback.

[0783] The "download link generating means" is a means having a function for generating a download link for providing the final animation to the user.

[0784] System Configuration

[0785] This invention is a system that generates animations by analyzing and converting instructions entered by the user in natural language. This system enables the creation of high-quality, diverse animations without forcing the user to perform specific operations.

[0786] Hardware and Software

[0787] This system uses the following hardware and software:

[0788] 1. Hardware:

[0789] Device: A computer, smartphone, tablet, etc., through which a user inputs instructions.

[0790] Server: A high-performance server that performs instruction analysis and animation generation processing.

[0791] 2. Software:

[0792] Natural language processing engine (NLP engine): Analyzes the user's natural language instructions and extracts animation requirements. As a concrete example, we use the Google Cloud Natural Language API.

[0793] Generative AI engine: An artificial intelligence engine for generating animations. As a specific example, we will use OpenAI's DALL-E.

[0794] Program processing description

[0795] 1. User input

[0796] The user uses the device to send instructions in natural language to the system. For example, the user might enter the following instruction: "I want to create a 30-second animation showcasing a new smartwatch. I want to create a moving scene with characters." Once this instruction is entered, the device sends it to the server.

[0797] 2. Receiving and analyzing instructions

[0798] The server receives instructions sent by the user and analyzes them using a natural language processing engine. The NLP engine extracts animation requirements from the instructions and generates a list of requirements. This list of requirements includes specific conditions such as "introduce the smartwatch," "use of characters," "scenes with movement," and "30 seconds."

[0799] 3. Transforming and optimizing animation requirements

[0800] The server converts the generated requirements list into a format that the generative AI engine can understand and optimizes it, ensuring that all the information the generative AI engine needs is prepared.

[0801] 4. Generating the initial animation

[0802] The server then sends the optimized requirements list to the generative AI engine, which generates initial animations based on the given requirements, including character modeling, basic scene settings, and dynamic actions.

[0803] 5. Identification of intermediate products

[0804] The generated initial animation is provided as a preview from the server to the user's device. The user can check this preview and provide feedback. For example, the user can send correction instructions such as "I want the character's clothing to look more business-like" to the server via their device.

[0805] 6. Receiving and implementing feedback

[0806] The server receives user feedback, analyzes it again using a natural language processing engine, and converts it into specific modification requirements, which are then sent back to the generative AI engine, which then modifies the animation based on the results.

[0807] 7. Generating the final animation

[0808] Once the final animation is generated, the server retrieves the completed animation data and generates a download link for the user, who can then download and use the final animation.

[0809] Specific examples

[0810] For example, to generate a 30-second animation introducing a new smartwatch, a user first inputs instructions such as, "I want to create an animation that introduces the smartwatch and highlights its features." The server analyzes these instructions, sends the necessary requirements to the generation AI engine, and provides the generated preview to the user. The user then checks the preview, makes any necessary corrections, and finally receives a download link. This process allows users to create high-quality animations easily and efficiently.

[0811] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0812] Step 1: User input

[0813] The user uses the device to input instructions for animation production in natural language. This input is done using the text box or voice input function of a dedicated application. Specifically, the user enters instructions such as, "I want to create a 30-second animation introducing our new smartwatch product. I want to create a scene with moving characters." The input data is sent in text format.

[0814] Step 2: Sending instruction data

[0815] The terminal sends the natural language instructions entered by the user to the server using an HTTP POST request, with the data packaged in JSON format. The input data is the user's instruction text, and the output data is the JSON data sent to the server.

[0816] Step 3: Analyze the instruction data

[0817] The server analyzes the received instruction data. Specifically, it uses a natural language processing engine (e.g., Google Cloud Natural Language API) to extract animation requirements from the instruction text. The input data is the user's instruction text, and the output data is a list of requirements. This list of requirements includes specific conditions such as "introduce the smartwatch," "use of a character," "scene with movement," and "30 seconds."

[0818] Step 4: Generate a requirements list

[0819] The server generates a requirements list based on the analysis results obtained from the NLP engine. Here, the extracted requirements are organized into a list format and converted into a format that can be understood by the generation AI engine. The input data is the analysis results, and the output data is the requirements list.

[0820] Step 5: Transform and optimize your requirements list

[0821] The server converts the generated requirement list into a prompt that can be referenced by the generation AI engine and performs optimization. Specifically, it formats the requirement list into something like "introduce a smartwatch, use a character, include a scene with movement, 30 seconds." The input data is the requirement list, and the output data is a prompt for the generation AI.

[0822] Step 6: Generate the initial animation

[0823] The server sends the optimized prompt to the AI ​​engine, which then generates the initial animation based on the prompt. The initial creation includes character modeling and basic scene settings. The input data is the prompt, and the output data is the initial animation file.

[0824] Step 7: Check the intermediate products

[0825] The server provides the generated initial animation as a preview to the user's device. The device displays this animation in a playable format. The user visually checks the preview and provides feedback as needed. The input data is the initial animation file, and the output data is the user's feedback.

[0826] Step 8: Getting user feedback

[0827] After checking the preview, the user can submit feedback for corrections and improvements. Specifically, the user can enter feedback such as "I would like the character's clothing to be more business-like." The device then sends this feedback to the server. The input data is the user's feedback, and the output data is the feedback's JSON data.

[0828] Step 9: Analyze and transform feedback

[0829] The server analyzes the feedback received from the user again using a natural language processing engine and converts it into specific revision requirements. The input data is the user feedback, and the output data is a list of revision requirements.

[0830] Step 10: Modifying the animation

[0831] Based on the feedback, the server sends modification requirements to the generative AI engine to modify the animation. The generative AI engine regenerates the animation based on the new requirements. The input data is the list of modification requirements, and the output data is the modified animation file.

[0832] Step 11: Generate the final animation

[0833] Once the final animation is generated, the server retrieves the completed animation data and generates a download link to provide to the user. The input data is the modified animation file, and the output data is the download link.

[0834] Step 12: Provide a download link

[0835] The server sends the generated download link to the user's device. The user can use this link to download and use the final animation. The input data is the download link, and the output data is the user's download action.

[0836] (Application example 1)

[0837] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0838] Conventional animation generation systems require specialized knowledge and skills, making it difficult for average users to easily generate high-quality animations. Furthermore, in order to respond quickly to advertising campaigns, a means for easily creating high-quality animated advertisements is required. Furthermore, there is a lack of a means for smoothly previewing generated animations and incorporating feedback, preventing an efficient animation production process.

[0839] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0840] In this invention, the server includes a means for receiving natural language instructions from a user, a means for analyzing the natural language instructions and converting them into animation requirements, and a generation AI means for generating animations based on the converted requirements. This allows even general users to easily create high-quality animated advertisements in natural language. Furthermore, by including a means for providing a preview of the generated animation and a means for receiving and incorporating user feedback, an efficient animation production process can be realized, allowing animations for advertising campaigns to be quickly provided.

[0841] The "means for receiving instructions in natural language from the user" refers to an interface and function that allows the user to input instructions for animation production in natural language and for the system to receive them.

[0842] "Means for analyzing natural language instructions and converting them into animation requirements" refers to the function and process of converting natural language instructions received from a user into a format that a machine can understand and extracting specific production requirements for the animation.

[0843] The "generative AI means for generating animations based on converted requirements" refers to an artificial intelligence engine and related technologies that automatically generate animations based on analyzed requirements.

[0844] The "means for providing a user with a preview of the generated animation" refers to a function and interface that displays the initially generated animation so that the user can check it.

[0845] "Means for receiving feedback from users and reflecting it in the generating AI means" is a function that receives correction requests provided by the user after checking the preview, and sends them back to the generating AI engine to be reflected in the animation.

[0846] The "means for generating a final animation that reflects feedback" refers to the process and technique for generating a final animation after reflecting user feedback.

[0847] The "means for providing the final animation to the user" refers to the functionality and interface that provides the completed animation so that the user can download or view it.

[0848] "Means for creating high-quality animated advertisements for advertising campaigns in natural language on a user terminal" refers to a process and technology that allows a user to input instructions for creating advertising animations in natural language using a terminal, and the system generates high-quality advertising animations based on those instructions.

[0849] The "means for transmitting advertisement production instructions in natural language from the user to the server" refers to a function and interface for transmitting advertisement production instructions entered by the user to the server via the network.

[0850] The "means for the server to analyze instructions and extract requirements for advertising animation" refers to the functions and processes for analyzing received natural language advertising production instructions and extracting specific requirements for advertising animation.

[0851] "Generative AI means for generating animations suitable for advertising purposes based on requirements" refers to an artificial intelligence engine and related technologies that automatically generate animations that meet advertising purposes based on extracted requirements.

[0852] "Means for sending a preview link of the generated animation to a user terminal and receiving user confirmation and feedback" refers to a function and interface for displaying a preview of the generated animation on a user terminal and receiving confirmation and feedback.

[0853] The "means for providing a download link for the final animation to a user terminal" refers to a function and interface that provides the completed final animation to a user terminal as a download link.

[0854] DETAILED DESCRIPTION OF THE INVENTION In the preferred embodiment of the present invention, a system is described that allows for easy generation of high quality animated advertisements in natural language for advertising campaigns.

[0855] First, a user uses a device such as a smartphone or tablet to input instructions for animation production in natural language. For example, they might input instructions like, "I want to create a 30-second animated commercial that conveys the features and appeal of a newly released smartphone. It should include a scene in which a character uses the smartphone to explain its convenient functions."

[0856] The input natural language instructions are sent from the device to the server. At this time, data is sent as an HTTP request using API communication. The server analyzes the received instructions using a natural language processing (NLP) engine and extracts the requirements for animation production. For natural language processing, a Python NLP library (such as NLTK or spaCy) is used, for example.

[0857] Next, the server optimizes the extracted requirements and converts them into a format suitable for the generative AI engine. During this process, the requirements are converted and optimized using a data processing script. The converted requirements are then sent to the generative AI engine, which generates the initial animation. The generative AI means used for this is, for example, OpenAI's API or DALL-E.

[0858] The generated initial animation is sent from the server to the user's device as a preview link. The user can check the animation through this preview link and provide feedback. For example, the user can input a command such as "I want the character's clothes to look more business-like."

[0859] The server again uses a natural language processing engine to analyze the user's feedback and convert it into specific revision requirements, which are then sent to a generative AI engine to revise the animation. This process is repeated until the user is satisfied.

[0860] Once the final animation is generated, the server generates a download link to provide the completed animation to the user's device, where the user can download the final animation and use it in their advertising campaign.

[0861] For example, when introducing a new smartwatch, a user can enter a specific prompt such as, "I want to create an animation that introduces the smartwatch and highlights its features," and the system will generate a high-quality animation based on this instruction.

[0862] The system allows users to easily generate high-quality animations that can be used in advertising campaigns using natural language, without requiring specialized skills.

[0863] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0864] Step 1:

[0865] The user uses a terminal to input instructions for animation production in natural language. For example, they might input, "I want to create a 30-second animated commercial that conveys the features and appeal of a newly released smartphone. It should include a scene in which a character uses the smartphone to explain its convenient functions." This input is received by the system and sent to the next step.

[0866] Step 2:

[0867] The device sends input instructions in natural language to the server. The input data is natural language text and is sent to the server as an HTTP request. The server receives the request and converts it into a usable format for analysis.

[0868] Step 3:

[0869] The server parses the received natural language instructions using a natural language processing (NLP) engine. The input data is natural language text, which is parsed using an NLP engine (e.g., spaCy or NLTK) to extract the information needed for animation production requirements. The output is a list of requirements.

[0870] Step 4:

[0871] The server optimizes the extracted requirements list and converts it into a format suitable for the generative AI engine. The input data is the extracted requirements list, which is converted into the optimal format using a data processing script (e.g., Python). The output is formatted data to be sent to the generative AI engine.

[0872] Step 5:

[0873] The server sends the optimized requirement list to the generative AI engine to generate the initial animation. The input data is formatted data, and the generative AI engine (e.g., OpenAI API or DALL-E) generates the animation. The output is the initial generated animation data.

[0874] Step 6:

[0875] The server sends the generated initial animation to the user's device as a preview link. The input data is the initially generated animation data, which is sent to the user's device as an HTTP request. The user can check the animation using the preview link.

[0876] Step 7:

[0877] The user checks the preview and provides feedback. The input is natural language text, which is sent from the device to the server. For example, the user might input a command such as, "I want the character's clothing to look more business-like."

[0878] Step 8:

[0879] The server again uses a natural language processing engine to analyze the user's feedback and convert it into specific correction requirements. The input data is the natural language text of the feedback, and the NLP engine extracts the correction requirements. The output is a list of correction requirements.

[0880] Step 9:

[0881] The server sends modification requirements to the generative AI engine to modify the animation. The input data is a list of modification requirements, and the generative AI engine is used to regenerate the animation. The output is the modified animation data.

[0882] Step 10:

[0883] Once the final animation is generated, the server generates a download link to provide the completed animation to the user and sends it to the user's device. The input data is the final animation data, which is sent to the user's device as an HTTP request. The user can download the final animation via this link and use it in their advertising campaign.

[0884] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0885] This invention is a system that automatically generates high-quality and diverse animations using natural language instructions from the user and an emotion engine that analyzes the user's emotions. In particular, it recognizes the user's emotions and adjusts the animation requirements based on them to provide more personalized animations.

[0886] User instruction input

[0887] The user uses the device to input instructions for animation production in natural language. For example, they might input, "I want to create a 30-second animation introducing our new smartwatch product. I want to create a scene with characters in motion." The input instructions are sent from the device to the server.

[0888] Receiving and parsing instructions

[0889] The server receives the instruction data sent by the user and analyzes it using a natural language processing (NLP) engine. The NLP engine extracts animation requirements from the instructions and generates a list of specific requirements. For example, requirements such as "introduce the smartwatch," "use of characters," "moving scenes," and "30 seconds" are extracted.

[0890] Applying the Emotion Engine

[0891] The server also passes the received instruction data to the emotion engine, which analyzes the user's emotions. The emotion engine recognizes emotions (e.g., joy, excitement, tension, etc.) from the user's language and context, and reflects the extracted emotional information in the animation requirements. For example, if the user is excited, it can add more dynamic movements and vivid colors to the requirements.

[0892] Transforming and optimizing animation requirements

[0893] The server integrates the extracted requirements and emotion information and converts it into a format suitable for the generative AI, thereby providing all the information necessary for the generative AI and optimizing the requirements list.

[0894] Generate initial animation

[0895] The server then sends the optimized requirement list to the generative AI engine, which generates initial animations based on the given requirements and emotion information. This stage includes character modeling, basic scene setup, and actions. The generated initial animations are returned to the server.

[0896] Identification of intermediate products

[0897] The generated initial animation is provided as a preview from the server to the user's device. The user can check this preview and provide feedback. For example, the user can send correction instructions such as "I want the character's clothing to look more business-like" to the server via their device.

[0898] Receiving and incorporating feedback

[0899] The server receives the user's feedback and analyzes it again using the NLP engine and emotion engine. Taking into account the content of the feedback as well as the user's emotions, it generates specific correction requirements and sends them to the generation AI.

[0900] Generating the final animation

[0901] The generation AI regenerates the animation based on the modification requirements and emotion information, and returns the modified animation data to the server, which then retrieves this data and prepares it as the final animation.

[0902] Providing the final animation

[0903] The server generates a download link to provide the completed final animation to the user, and the download link is sent to the user's device, allowing the user to obtain the final animation through the link.

[0904] As a concrete example, when generating a 30-second animation introducing a new smartwatch product, the user inputs instructions such as, "I want to create an animation that introduces the smartwatch and highlights its features." The server analyzes these instructions, uses an emotion engine to recognize the user's emotions (e.g., excitement), and generates a list of requirements based on these. The generation AI generates an initial animation and then reflects the user's feedback and emotional information to create the final animation. This series of processes allows users to easily and efficiently create personalized, high-quality animations.

[0905] The processing flow will be explained below.

[0906] Step 1:

[0907] The user uses the device to input instructions for animation production in natural language. For example, they might input, "I want to create a 30-second animation introducing our new smartwatch product. I want to create a scene with characters and movement." The device then sends the input instructions to the server.

[0908] Step 2:

[0909] The server receives the instruction data sent by the user and passes it to a natural language processing (NLP) engine for analysis. The NLP engine extracts animation requirements from the instructions. The extracted requirements include "introduce the smartwatch," "use of characters," "moving scenes," and "30 seconds."

[0910] Step 3:

[0911] The server passes the received instruction data to the emotion engine, which analyzes the user's emotions. For example, if the user is excited, the emotion engine recognizes this and extracts emotion information such as "excited" or "positive."

[0912] Step 4:

[0913] The server integrates the extracted requirement list and emotion information and converts it into a format suitable for generative AI, including adjusting the animation style based on the emotion (e.g., color usage and movement emphasis).

[0914] Step 5:

[0915] The server sends the optimized requirement list to the generation AI engine, which generates an initial animation based on the requirement list and emotion information. This initial animation includes basic character modeling, scene setup, and basic movements. The generated initial animation is returned to the server.

[0916] Step 6:

[0917] The server sends a preview of the generated initial animation to the user's device, where the user can view the preview and provide feedback, such as "I'd like the character's clothing to look more business-like."

[0918] Step 7:

[0919] The device sends the user's feedback data to the server, which then receives the feedback data and analyzes it again using the NLP engine and emotion engine. Specific correction requirements are generated based on the feedback content.

[0920] Step 8:

[0921] The server reflects the feedback requirements and emotional information and sends it to the generation AI means. The generation AI regenerates the animation based on this. This regeneration process includes corrections specified in the feedback and style adjustments based on the emotional information. The corrected animation data is returned to the server.

[0922] Step 9:

[0923] The server prepares the final version of the modified animation and generates a download link for the user, which is then sent to the user's device.

[0924] Step 10:

[0925] The user can then use the provided download link to download the final animation from their device, allowing them to receive the final product introduction animation.

[0926] By following the above steps, the user can easily create a variety of high-quality animations based on the user's emotions, simply by issuing instructions without moving their hands.

[0927] Example 2

[0928] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0929] Current animation generation systems struggle to efficiently generate personalized, high-quality animations that meet user needs. In particular, they lack a process for generating animations that takes user emotions into account, resulting in generated animations that do not adequately reflect user expectations and emotions. Furthermore, the process of making corrections based on user feedback is cumbersome and time-consuming, and improvements are needed to increase user satisfaction.

[0930] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0931] In this invention, the server includes means for receiving natural language instructions from a user, means for analyzing the natural language instructions and converting them into animation requirements, means for analyzing the user's emotions from the natural language instructions, generation AI means for generating animation based on the converted requirements and the analyzed emotional information, means for providing a preview of the generated animation to the user, means for receiving feedback from the user and reflecting it in the generation AI means, means for generating a final animation that reflects the feedback and emotional information, and means for providing the final animation to the user. This enables the generation of personalized, high-quality animation that takes user instructions and emotions into consideration.

[0932] A "user" is a person who operates the system to input animation instructions and checks and provides feedback on the generated animation.

[0933] "Natural language instructions" refer to instructions written in sentence format that are input by a user through a terminal.

[0934] "Analysis" is the process of using a natural language processing engine and an emotion engine to understand the user's instructions and emotions from the context and convert them into specific data.

[0935] "Animation requirements" are specific conditions and elements for generating animations, extracted from the analyzed natural language instructions and emotional information.

[0936] "Emotion information" is data about the user's emotions (e.g., joy, excitement, tension) extracted from the user's natural language instructions.

[0937] The "generative AI means" is an artificial intelligence system that automatically generates animations based on the extracted animation requirements and emotional information.

[0938] A "preview" is a short video that allows the user to see an early version of the generated animation.

[0939] "Feedback" refers to correction instructions and evaluations provided by the user after checking the preview.

[0940] The "final animation" refers to the final animation that reflects the user's feedback and emotional information.

[0941] The "server" is a computer system that executes various processing means, manages and analyzes instructions and feedback from users, and generates and provides the final animation.

[0942] A "terminal" is a device that a user uses to input natural language instructions, see a preview of the generated animation, and provide feedback.

[0943] The present invention is a system that automatically generates high-quality, personalized animations by utilizing natural language instructions from a user and a generative AI model with an emotion engine. The following describes an embodiment of the system.

[0944] User instruction input

[0945] A user uses a device (e.g., a PC or smartphone) to access a dedicated application or website and input instructions for animation production in natural language. For example, they might input instructions such as, "I want to create a 30-second animation introducing our new smartwatch product. I want to create a scene with characters in motion." These input instructions are then sent from the device to the server.

[0946] Receiving and parsing instructions

[0947] The server receives instruction data sent by the user. This data is automatically passed to a natural language processing (NLP) engine for analysis. The NLP engine extracts animation requirements from the user's instructions and generates a list of specific requirements. For example, requirements such as "introduce the smartwatch," "use of characters," "moving scenes," and "30 seconds" are extracted from the instructions.

[0948] Applying the Emotion Engine

[0949] At the same time, the server passes the received instruction data to the emotion engine, which analyzes the user's emotions. The emotion engine recognizes emotions (e.g., joy, excitement, tension) from the user's context and vocabulary, and reflects this emotional information in the animation requirements. For example, if the user is excited, more dynamic movements and vivid colors are added to the requirements.

[0950] Transforming and optimizing animation requirements

[0951] The server then integrates the extracted requirements list with the emotion information and converts it into a format suitable for the generative AI model. This process ensures that all the information required by the generative AI is gathered and the requirements list is optimized. Specifically, the requirements list is converted into a data structure such as JSON format.

[0952] Generate initial animation

[0953] The server sends the optimized requirement list to the generative AI engine, which then models the character, sets up the basic scene, plans the action, and generates the initial animation based on the requirements and emotion information. Once this series of processes is complete, the generated initial animation data is sent back to the server.

[0954] Identification of intermediate products

[0955] The generated initial animation is provided as a preview from the server to the user's device. The user can check the preview on their device and provide feedback on any points of concern or changes they would like to make. For example, they can send detailed correction instructions, such as "I would like the character's clothing to be more business-like," to the server from their device.

[0956] Receiving and incorporating feedback

[0957] The server receives feedback from the user. The received feedback is analyzed again by the NLP engine and emotion engine to generate specific correction requirements. In addition, the user's latest emotional information is also reflected. This information is then sent again to the generative AI engine.

[0958] Generating the final animation

[0959] The generative AI engine regenerates the animation based on the user's modification requirements and emotional information. The final animation data reflecting the modification requests is sent back to the server, which then retrieves this data and prepares the final animation.

[0960] Providing the final animation

[0961] The server generates a download link for providing the completed final animation to the user, and the download link is sent to the user's device, allowing the user to download and obtain the final animation through the link.

[0962] Specific examples

[0963] For example, when generating a 30-second animation introducing a new smartwatch product, the user inputs instructions such as, "I want to create an animation that introduces the smartwatch and highlights its features." The server analyzes these instructions, uses an emotion engine to recognize the user's emotions (e.g., excitement), and generates a list of requirements based on those emotions. The generative AI generates an initial animation and then reflects the user's feedback and emotional information to create the final animation. This series of processes allows users to easily and efficiently create personalized, high-quality animations.

[0964] Prompt Sentence Examples

[0965] "Create a 30-second animation showcasing a new smartwatch. I'd like it to be animated with characters and incorporate emotions that excite the user."

[0966] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0967] Step 1:

[0968] User instruction input

[0969] The user uses a device to access a dedicated application or website and inputs instructions for animation production in natural language. For example, they might input, "I want to create a 30-second animation introducing our new smartwatch. I want to create a scene with characters in motion." This input is then sent from the device to the server.

[0970] Input: Natural language animation instructions

[0971] Output: Instruction data sent from the terminal to the server

[0972] Step 2:

[0973] Receiving and parsing instructions

[0974] The server receives instruction data sent by the user. This data is automatically passed to a natural language processing (NLP) engine for analysis. The NLP engine extracts animation requirements from the user's instructions and generates a list of specific requirements. For example, it extracts requirements such as "introduce a smartwatch," "use of characters," "scenes with movement," and "30 seconds."

[0975] Input: Instruction data sent by the user

[0976] Data processing: Analysis using a natural language processing engine

[0977] Output: Extracted animation requirements list

[0978] Step 3:

[0979] Applying the Emotion Engine

[0980] At the same time, the server passes the received instruction data to the emotion engine, which analyzes the user's emotions. The emotion engine recognizes emotions (e.g., joy, excitement, tension) from the user's context and vocabulary, and reflects this emotional information in the animation requirements. For example, if the user is excited, more dynamic movements and vivid colors are added to the requirements.

[0981] Input: Instruction data to be analyzed

[0982] Data processing: Emotion analysis using an emotion engine

[0983] Output: Parsed emotion information

[0984] Step 4:

[0985] Transforming and optimizing animation requirements

[0986] The server then integrates the extracted requirements list with the emotion information and converts it into a format suitable for the generative AI model. This process ensures that all the information required by the generative AI is gathered and the requirements list is optimized. Specifically, the requirements list is converted into a data structure such as JSON format.

[0987] Input: Requirement list and sentiment information

[0988] Data processing: requirements optimization and format conversion

[0989] Output: An optimized requirements list for a generative AI model

[0990] Step 5:

[0991] Generate initial animation

[0992] The server sends the optimized requirement list to the generative AI engine, which then models the character, sets up the basic scene, and plans the movement based on the requirements and emotion information, generating the initial animation. Once this series of processes is complete, the generated initial animation data is sent back to the server.

[0993] Input: Optimized requirements list

[0994] Data processing: Generative AI animation generation

[0995] Output: Initial animation data

[0996] Step 6:

[0997] Identification of intermediate products

[0998] The generated initial animation is sent as a preview from the server to the user's device. The user can check the preview on their device and provide feedback on any areas of concern or changes they would like to see. For example, they can send detailed correction instructions, such as "I would like the character's clothing to look more business-like," to the server.

[0999] Input: Initial animation preview

[1000] Data processing: User feedback

[1001] Output: List of modified requirements

[1002] Step 7:

[1003] Receiving and incorporating feedback

[1004] The server receives feedback from the user. The received feedback is analyzed again by the NLP engine and emotion engine. Specific correction requirements are generated, and the user's latest emotional information is also reflected. This information is then sent back to the generative AI engine.

[1005] Input: User feedback

[1006] Data processing: Analysis of feedback and generation of revised requirements

[1007] Output: Modified requirement list and sentiment information

[1008] Step 8:

[1009] Generating the final animation

[1010] The generative AI engine regenerates the animation based on the user's modification requirements and emotional information. The final animation data reflecting the modification requests is sent back to the server. The server receives this data and prepares the final animation.

[1011] Input: Modified requirement list and sentiment information

[1012] Data processing: Regenerating animations using generative AI

[1013] Output: Final animation data

[1014] Step 9:

[1015] Providing the final animation

[1016] The server generates a download link for the completed final animation to provide the user with the animation, and the download link is sent to the user's device, allowing the user to download and obtain the final animation through the link.

[1017] Input: Final animation data

[1018] Data processing: Generate download links

[1019] Output: Send a download link to the user's device

[1020] (Application example 2)

[1021] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1022] Conventional animation production systems make it difficult for users to easily reflect individual emotions and specific instructions, resulting in a cumbersome process for creating personalized, high-quality animations. Furthermore, there is a lack of effective means for quickly and intuitively generating animations in specific fields such as advertising. There is a need for a system that can solve these problems and automatically generate high-quality animations that reflect individual emotions based on natural language instructions from users.

[1023] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving natural language instructions from a user; means for analyzing the natural language instructions and converting them into animation requirements; means for reading the user's emotions from the analyzed natural language instructions and generating animation requirements that reflect the emotions; generation AI means for generating animation based on the converted requirements; means for providing a preview of the generated animation to the user; means for receiving feedback from the user and reflecting it in the generation AI means; means for generating a final animation that reflects the feedback and the read emotions; and means for providing the final animation to the user. This makes it possible to quickly generate personalized, high-quality animation that reflects the user's emotions.

[1024] The "means for receiving instructions in natural language from a user" refers to a device or interface for recognizing instructions input in natural language by a user and transmitting the instructions to a server.

[1025] The "means for parsing natural language instructions and converting them into animation requirements" refers to software or algorithms that parse natural language instructions entered by a user and convert those instructions into specific animation requirements.

[1026] "Means for reading the user's emotions from the analyzed natural language instructions and generating animation requirements that reflect those emotions" is an algorithm that extracts the user's emotions from the analyzed instructions and generates animation requirements taking those emotions into consideration.

[1027] "Generative AI means" refers to an artificial intelligence system that automatically generates initial and final animations based on the requirements of the converted animation.

[1028] The "means for providing a preview to the user" refers to a system or interface for visually displaying to the user intermediate and final results of the generated animation.

[1029] The "means for receiving feedback and reflecting it in the generating AI means" is an algorithm for receiving feedback provided by the user, analyzing that feedback, and reflecting it in the generating AI.

[1030] The "means for generating final animation" is an AI system that generates the final animation based on user feedback and emotional information.

[1031] The "means for providing the final animation to the user" refers to a system or interface that allows the user to download or view the completed final animation.

[1032] This invention is a system for quickly and effectively generating animations for advertising. This system includes a series of processes that receive natural language instructions from a user, analyze them, and generate animations that reflect the user's emotions.

[1033] First, the user inputs instructions for animation production in natural language via a device such as a smartphone. These instructions are then sent from the device to the server. For example, a user might say, "I want to create a 30-second animated advertisement introducing our new lunch menu. I want to give it a seasonal feel."

[1034] The server receives the instruction data sent by the user and analyzes it using a natural language processing engine (e.g., Google Cloud Natural Language API). During this analysis, animation requirements are extracted from the instructions. For example, from the above instructions, requirements such as "new lunch menu," "seasonal feel," and "30-second animation" are extracted.

[1035] Next, the server uses an emotion analysis engine (e.g., IBM Watson Tone Analyzer) to analyze the user's emotions. In this process, emotions (e.g., excitement, joy, etc.) are recognized from the user's vocabulary and context, and the extracted emotional information is reflected in the animation requirements. For example, if the user excitedly inputs a command such as "I want to create a sense of the season," animation requirements with more dynamic color usage and movement are added.

[1036] The server integrates these animation requirements and emotion information and converts them into a format suitable for a generative AI model (e.g., DALL-E or GPT-4). This production AI model generates an initial animation based on the given requirements. The generated initial animation is then provided as a preview from the server to the user's device.

[1037] The user checks the preview and provides feedback for corrections, such as "I'd like the background of the scene to be a warmer color." This feedback is sent from the device to the server, where it is again subjected to natural language processing and sentiment analysis to generate specific correction requirements.

[1038] The generative AI model regenerates the animation based on the modified requirements to create the final animation, which is then provided as a download link from the server to the user's device, allowing the user to download the animation through this link.

[1039] As a concrete example, the prompt text for "If you want to create an advertising animation for the new menu item 'Special Japanese-style Hamburger Steak'" is as follows:

[1040] "We'd like to create a 30-second animated ad to promote our new special Japanese-style hamburger lunch. Emphasize the autumn feel with warm colors and dynamic movements."

[1041] The present invention allows users to quickly generate personalized, emotionally-driven, and high-quality advertising animations.

[1042] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1043] Step 1:

[1044] The user uses a terminal to input instructions for animation production in natural language. For example, the instructions might be, "I want to create a 30-second animated advertisement introducing our new special Japanese-style hamburger steak lunch. Please emphasize the autumnal feeling with warm colors and dynamic movements." After input, this data is sent from the terminal to the server.

[1045] Step 2:

[1046] The server sends the received instruction data to a natural language processing engine (e.g., Google Cloud Natural Language API) for analysis. The input for the analysis is the user's natural language instruction, and the output is a list of requirements such as "new special Japanese-style hamburger lunch," "warm colors," "dynamic movements," "autumn seasonal feel," and "30-second animation."

[1047] Step 3:

[1048] The server sends the acquired requirement list and instruction data to an emotion analysis engine (e.g., IBM Watson Tone Analyzer) to extract the user's emotion. The input is the instruction data, and the output is the recognized emotion information (e.g., joy, excitement). This adds the emotion information to the requirement list.

[1049] Step 4:

[1050] The server integrates and optimizes the converted requirement list and emotion information into a format suitable for the generative AI model (e.g., DALL-E or GPT-4). The input of this process is the requirement list and emotion information, and the output is data in a format that can be interpreted by the generative AI model.

[1051] Step 5:

[1052] The server sends the optimized data to the generative AI model to generate the initial animation. The input is the optimized data, and the output is the initial animation. The generated initial animation is returned to the server.

[1053] Step 6:

[1054] The server provides a preview of the initial animation to the user's device, and the user can view the preview and provide feedback in natural language, such as "I'd like the background color to be warmer."

[1055] Step 7:

[1056] The server receives feedback from the user and passes it back to the natural language processing engine and sentiment analysis engine for analysis. The input is the feedback, and the output is the correction requirements and sentiment information.

[1057] Step 8:

[1058] The server issues regeneration instructions to the generative AI model based on the modification requirements, generating the final animation. The input is the modification requirements and emotion information, and the output is the final animation.

[1059] Step 9:

[1060] The final animation is provided to the user's device as a download link from the server, and the user can obtain the final animation through the link.

[1061] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1062] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1063] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1064] [Fourth embodiment]

[1065] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1066] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1067] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1068] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1069] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1070] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1071] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1072] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1073] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1074] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1075] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1076] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1077] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1078] This invention is a system that generates animations by analyzing and converting instructions entered by the user in natural language. This system enables the creation of high-quality and diverse animations without forcing the user to perform specific operations.

[1079] User instruction input

[1080] First, the user uses the device to send instructions in natural language to the system. For example, the user might enter the following instruction: "I want to create a 30-second animation showcasing our new smartwatch. I want to create a moving scene with characters." Once this instruction is entered, the device sends it to the server.

[1081] Receiving and parsing instructions

[1082] The server receives instructions sent by the user and analyzes them using a natural language processing (NLP) engine. The NLP engine extracts animation requirements from the instructions and generates a list of requirements. This list of requirements includes specific conditions such as "introduce the smartwatch," "use of characters," "scenes with movement," and "30 seconds."

[1083] Transforming and optimizing animation requirements

[1084] The server converts the generated requirements list into a format suitable for the generating AI and optimizes it, so that all the information the generating AI needs is prepared.

[1085] Generate initial animation

[1086] The server then sends the optimized requirements list to the generative AI engine, which generates initial animations based on the given requirements, including character modeling, basic scene setup, and dynamic actions.

[1087] Identification of intermediate products

[1088] The generated initial animation is provided as a preview to the user's device from the server. The user can check this preview and provide feedback. For example, the user can send correction instructions such as "I want the character's clothing to look more business-like" to the server via their device.

[1089] Receiving and incorporating feedback

[1090] The server receives user feedback, analyzes it again using NLP, and converts it into specific modification requirements, which are then sent back to the generation AI, which then modifies the animation based on this.

[1091] Generating the final animation

[1092] Once the final animation is generated, the server retrieves the completed animation data and generates a download link for the user, who can then download and use the final animation.

[1093] As a concrete example, when generating a 30-second animation introducing a new smartwatch, the user first inputs instructions such as, "I want to create an animation that introduces the smartwatch and highlights its features." The server analyzes these instructions, sends the necessary requirements to the generation AI, provides the generated preview to the user, makes corrections based on feedback, and finally provides the user with a download link. This series of processes allows users to easily and efficiently create high-quality animations.

[1094] The processing flow will be explained below.

[1095] Step 1:

[1096] The user uses the device to input instructions for animation production in natural language. For example, they might input, "I want to create a 30-second animation introducing our new smartwatch." The device then sends the input instructions to the server as text data.

[1097] Step 2:

[1098] The server receives the instruction data sent by the user and passes it to a natural language processing (NLP) engine for analysis. This analysis extracts animation requirements from the user's instructions. For example, the instructions may be analyzed to identify the requirements: "Introduce the smartwatch," "Use a character," "Movement scene," and "30 seconds."

[1099] Step 3:

[1100] The server converts the extracted requirements into a format suitable for generative AI, generates a requirements list, and then sends the optimized requirements list to the generative AI engine.

[1101] Step 4:

[1102] The generation AI generates initial animations based on a list of requirements sent from the server, which includes character modeling, basic scene setup, and actions. The generated initial animations are returned to the server.

[1103] Step 5:

[1104] The server provides a preview of the generated initial animation to the user's device, allowing the user to view the intermediate animation results and provide feedback.

[1105] Step 6:

[1106] The user can use the device to input feedback on the previewed animation, such as "I'd like the character's clothing to look more business-like," and the device will then send this feedback to the server.

[1107] Step 7:

[1108] The server receives the feedback from the user, analyzes it again using the NLP engine, generates specific correction requirements based on the feedback, and sends them to the generation AI.

[1109] Step 8:

[1110] The generation AI regenerates the animation based on the modified requirements and returns the modified animation data to the server, which then retrieves this data and prepares it as the final animation.

[1111] Step 9:

[1112] The server generates a download link to provide the completed final animation to the user, and the download link is sent to the user's device, allowing the user to obtain the final animation through the link.

[1113] By following the above steps, users can easily create high-quality animations with a variety of graphic styles by simply issuing instructions without moving their hands.

[1114] Example 1

[1115] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1116] Conventional animation production systems require users to have detailed operations and technical knowledge, making it difficult to efficiently create high-quality animations. It is also difficult to quickly and reliably incorporate feedback into the process of understanding user instructions and generating animations that reflect those instructions. To solve these problems, a system is needed that can accurately analyze users' natural language instructions and efficiently embody them as animations.

[1117] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1118] In this invention, the server includes means for receiving natural language instructions from a user, means for analyzing the natural language instructions and converting them into animation requirements, means for converting the converted requirements into a format understandable by a generation AI engine and optimizing them, generation AI means for generating an animation based on the optimized requirements, means for providing a preview of the generated animation to the user, means for receiving feedback from the user and reflecting it in the generation AI means, means for generating a final animation that reflects the feedback, and means for generating a download link for providing the final animation to the user. This enables users to create high-quality animations with simple instructions in natural language and to quickly and reliably modify and complete animations that reflect feedback.

[1119] A "user" is an entity that inputs instructions to the system in natural language and generates animations.

[1120] A "natural language instruction" is a request or command entered by a user in a natural language, such as text or voice.

[1121] The "analysis means" is a means having a function for analyzing instructions in natural language and converting them into animation requirements.

[1122] "Animation requirements" refers to the conditions and components necessary for generating animation extracted by the analysis means.

[1123] A "generative AI engine" is an artificial intelligence engine that generates animations based on the animation requirements.

[1124] "Generative AI means" refers to means including functions and processes for generating animations using a generative AI engine.

[1125] An "optimization means" is a means that has the function of converting the converted requirements into a format that can be understood by the generative AI engine and optimizing them.

[1126] The "preview providing means" is a means having a function for providing a preview of the generated animation to the user.

[1127] "Feedback" refers to opinions and instructions that a user submits to the system after checking the preview and inputting any necessary corrections or improvements.

[1128] The "feedback receiving means" is a means that has the function of receiving feedback from the user and reflecting it in the generating AI means.

[1129] "Final animation" refers to the animation that has been revised and completed based on user feedback.

[1130] The "download link generating means" is a means having a function for generating a download link for providing the final animation to the user.

[1131] System Configuration

[1132] This invention is a system that generates animations by analyzing and converting instructions entered by the user in natural language. This system enables the creation of high-quality, diverse animations without forcing the user to perform specific operations.

[1133] Hardware and Software

[1134] This system uses the following hardware and software:

[1135] 1. Hardware:

[1136] Device: A computer, smartphone, tablet, etc., through which a user inputs instructions.

[1137] Server: A high-performance server that performs instruction analysis and animation generation processing.

[1138] 2. Software:

[1139] Natural language processing engine (NLP engine): Analyzes the user's natural language instructions and extracts animation requirements. As a concrete example, we use the Google Cloud Natural Language API.

[1140] Generative AI engine: An artificial intelligence engine for generating animations. As a specific example, we will use OpenAI's DALL-E.

[1141] Program processing description

[1142] 1. User input

[1143] The user uses the device to send instructions in natural language to the system. For example, the user might enter the following instruction: "I want to create a 30-second animation showcasing a new smartwatch. I want to create a moving scene with characters." Once this instruction is entered, the device sends it to the server.

[1144] 2. Receiving and analyzing instructions

[1145] The server receives instructions sent by the user and analyzes them using a natural language processing engine. The NLP engine extracts animation requirements from the instructions and generates a list of requirements. This list of requirements includes specific conditions such as "introduce the smartwatch," "use of characters," "scenes with movement," and "30 seconds."

[1146] 3. Transforming and optimizing animation requirements

[1147] The server converts the generated requirements list into a format that the generative AI engine can understand and optimizes it, ensuring that all the information the generative AI engine needs is prepared.

[1148] 4. Generating the initial animation

[1149] The server then sends the optimized requirements list to the generative AI engine, which generates initial animations based on the given requirements, including character modeling, basic scene settings, and dynamic actions.

[1150] 5. Identification of intermediate products

[1151] The generated initial animation is provided as a preview from the server to the user's device. The user can check this preview and provide feedback. For example, the user can send correction instructions such as "I want the character's clothing to look more business-like" to the server via their device.

[1152] 6. Receiving and implementing feedback

[1153] The server receives user feedback, analyzes it again using a natural language processing engine, and converts it into specific modification requirements, which are then sent back to the generative AI engine, which then modifies the animation based on the results.

[1154] 7. Generating the final animation

[1155] Once the final animation is generated, the server retrieves the completed animation data and generates a download link for the user, who can then download and use the final animation.

[1156] Specific examples

[1157] For example, to generate a 30-second animation introducing a new smartwatch, a user first inputs instructions such as, "I want to create an animation that introduces the smartwatch and highlights its features." The server analyzes these instructions, sends the necessary requirements to the generation AI engine, and provides the generated preview to the user. The user then checks the preview, makes any necessary corrections, and finally receives a download link. This process allows users to create high-quality animations easily and efficiently.

[1158] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1159] Step 1: User input

[1160] The user uses the device to input instructions for animation production in natural language. This input is done using the text box or voice input function of a dedicated application. Specifically, the user enters instructions such as, "I want to create a 30-second animation introducing our new smartwatch product. I want to create a scene with moving characters." The input data is sent in text format.

[1161] Step 2: Sending instruction data

[1162] The terminal sends the natural language instructions entered by the user to the server using an HTTP POST request, with the data packaged in JSON format. The input data is the user's instruction text, and the output data is the JSON data sent to the server.

[1163] Step 3: Analyze the instruction data

[1164] The server analyzes the received instruction data. Specifically, it uses a natural language processing engine (e.g., Google Cloud Natural Language API) to extract animation requirements from the instruction text. The input data is the user's instruction text, and the output data is a list of requirements. This list of requirements includes specific conditions such as "introduce the smartwatch," "use of a character," "scene with movement," and "30 seconds."

[1165] Step 4: Generate a requirements list

[1166] The server generates a requirements list based on the analysis results obtained from the NLP engine. Here, the extracted requirements are organized into a list format and converted into a format that can be understood by the generation AI engine. The input data is the analysis results, and the output data is the requirements list.

[1167] Step 5: Transform and optimize your requirements list

[1168] The server converts the generated requirement list into a prompt that can be referenced by the generation AI engine and performs optimization. Specifically, it formats the requirement list into something like "introduce a smartwatch, use a character, include a scene with movement, 30 seconds." The input data is the requirement list, and the output data is a prompt for the generation AI.

[1169] Step 6: Generate the initial animation

[1170] The server sends the optimized prompt to the AI ​​engine, which then generates the initial animation based on the prompt. The initial creation includes character modeling and basic scene settings. The input data is the prompt, and the output data is the initial animation file.

[1171] Step 7: Check the intermediate products

[1172] The server provides the generated initial animation as a preview to the user's device. The device displays this animation in a playable format. The user visually checks the preview and provides feedback as needed. The input data is the initial animation file, and the output data is the user's feedback.

[1173] Step 8: Getting user feedback

[1174] After checking the preview, the user can submit feedback for corrections and improvements. Specifically, the user can enter feedback such as "I would like the character's clothing to be more business-like." The device then sends this feedback to the server. The input data is the user's feedback, and the output data is the feedback's JSON data.

[1175] Step 9: Analyze and transform feedback

[1176] The server analyzes the feedback received from the user again using a natural language processing engine and converts it into specific revision requirements. The input data is the user feedback, and the output data is a list of revision requirements.

[1177] Step 10: Modifying the animation

[1178] Based on the feedback, the server sends modification requirements to the generative AI engine to modify the animation. The generative AI engine regenerates the animation based on the new requirements. The input data is the list of modification requirements, and the output data is the modified animation file.

[1179] Step 11: Generate the final animation

[1180] Once the final animation is generated, the server retrieves the completed animation data and generates a download link to provide to the user. The input data is the modified animation file, and the output data is the download link.

[1181] Step 12: Provide a download link

[1182] The server sends the generated download link to the user's device. The user can use this link to download and use the final animation. The input data is the download link, and the output data is the user's download action.

[1183] (Application example 1)

[1184] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1185] Conventional animation generation systems require specialized knowledge and skills, making it difficult for average users to easily generate high-quality animations. Furthermore, in order to respond quickly to advertising campaigns, a means for easily creating high-quality animated advertisements is required. Furthermore, there is a lack of a means for smoothly previewing generated animations and incorporating feedback, preventing an efficient animation production process.

[1186] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1187] In this invention, the server includes a means for receiving natural language instructions from a user, a means for analyzing the natural language instructions and converting them into animation requirements, and a generation AI means for generating animations based on the converted requirements. This allows even general users to easily create high-quality animated advertisements in natural language. Furthermore, by including a means for providing a preview of the generated animation and a means for receiving and incorporating user feedback, an efficient animation production process can be realized, allowing animations for advertising campaigns to be quickly provided.

[1188] The "means for receiving instructions in natural language from the user" refers to an interface and function that allows the user to input instructions for animation production in natural language and for the system to receive them.

[1189] "Means for analyzing natural language instructions and converting them into animation requirements" refers to the function and process of converting natural language instructions received from a user into a format that a machine can understand and extracting specific production requirements for the animation.

[1190] The "generative AI means for generating animations based on converted requirements" refers to an artificial intelligence engine and related technologies that automatically generate animations based on analyzed requirements.

[1191] The "means for providing a user with a preview of the generated animation" refers to a function and interface that displays the initially generated animation so that the user can check it.

[1192] "Means for receiving feedback from users and reflecting it in the generating AI means" is a function that receives correction requests provided by the user after checking the preview, and sends them back to the generating AI engine to be reflected in the animation.

[1193] The "means for generating a final animation that reflects feedback" refers to the process and technique for generating a final animation after reflecting user feedback.

[1194] The "means for providing the final animation to the user" refers to the functionality and interface that provides the completed animation so that the user can download or view it.

[1195] "Means for creating high-quality animated advertisements for advertising campaigns in natural language on a user terminal" refers to a process and technology that allows a user to input instructions for creating advertising animations in natural language using a terminal, and the system generates high-quality advertising animations based on those instructions.

[1196] The "means for transmitting advertisement production instructions in natural language from the user to the server" refers to a function and interface for transmitting advertisement production instructions entered by the user to the server via the network.

[1197] The "means for the server to analyze instructions and extract requirements for advertising animation" refers to the functions and processes for analyzing received natural language advertising production instructions and extracting specific requirements for advertising animation.

[1198] "Generative AI means for generating animations suitable for advertising purposes based on requirements" refers to an artificial intelligence engine and related technologies that automatically generate animations that meet advertising purposes based on extracted requirements.

[1199] "Means for sending a preview link of the generated animation to a user terminal and receiving user confirmation and feedback" refers to a function and interface for displaying a preview of the generated animation on a user terminal and receiving confirmation and feedback.

[1200] The "means for providing a download link for the final animation to a user terminal" refers to a function and interface that provides the completed final animation to a user terminal as a download link.

[1201] DETAILED DESCRIPTION OF THE INVENTION In the preferred embodiment of the present invention, a system is described that allows for easy generation of high quality animated advertisements in natural language for advertising campaigns.

[1202] First, a user uses a device such as a smartphone or tablet to input instructions for animation production in natural language. For example, they might input instructions like, "I want to create a 30-second animated commercial that conveys the features and appeal of a newly released smartphone. It should include a scene in which a character uses the smartphone to explain its convenient functions."

[1203] The input natural language instructions are sent from the device to the server. At this time, data is sent as an HTTP request using API communication. The server analyzes the received instructions using a natural language processing (NLP) engine and extracts the requirements for animation production. For natural language processing, a Python NLP library (such as NLTK or spaCy) is used, for example.

[1204] Next, the server optimizes the extracted requirements and converts them into a format suitable for the generative AI engine. During this process, the requirements are converted and optimized using a data processing script. The converted requirements are then sent to the generative AI engine, which generates the initial animation. The generative AI means used for this is, for example, OpenAI's API or DALL-E.

[1205] The generated initial animation is sent from the server to the user's device as a preview link. The user can check the animation through this preview link and provide feedback. For example, the user can input a command such as "I want the character's clothes to look more business-like."

[1206] The server again uses a natural language processing engine to analyze the user's feedback and convert it into specific revision requirements, which are then sent to a generative AI engine to revise the animation. This process is repeated until the user is satisfied.

[1207] Once the final animation is generated, the server generates a download link to provide the completed animation to the user's device, where the user can download the final animation and use it in their advertising campaign.

[1208] For example, when introducing a new smartwatch, a user can enter a specific prompt such as, "I want to create an animation that introduces the smartwatch and highlights its features," and the system will generate a high-quality animation based on this instruction.

[1209] The system allows users to easily generate high-quality animations that can be used in advertising campaigns using natural language, without requiring specialized skills.

[1210] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1211] Step 1:

[1212] The user uses a terminal to input instructions for animation production in natural language. For example, they might input, "I want to create a 30-second animated commercial that conveys the features and appeal of a newly released smartphone. It should include a scene in which a character uses the smartphone to explain its convenient functions." This input is received by the system and sent to the next step.

[1213] Step 2:

[1214] The device sends input instructions in natural language to the server. The input data is natural language text and is sent to the server as an HTTP request. The server receives the request and converts it into a usable format for analysis.

[1215] Step 3:

[1216] The server parses the received natural language instructions using a natural language processing (NLP) engine. The input data is natural language text, which is parsed using an NLP engine (e.g., spaCy or NLTK) to extract the information needed for animation production requirements. The output is a list of requirements.

[1217] Step 4:

[1218] The server optimizes the extracted requirements list and converts it into a format suitable for the generative AI engine. The input data is the extracted requirements list, which is converted into the optimal format using a data processing script (e.g., Python). The output is formatted data to be sent to the generative AI engine.

[1219] Step 5:

[1220] The server sends the optimized requirement list to the generative AI engine to generate the initial animation. The input data is formatted data, and the generative AI engine (e.g., OpenAI API or DALL-E) generates the animation. The output is the initial generated animation data.

[1221] Step 6:

[1222] The server sends the generated initial animation to the user's device as a preview link. The input data is the initially generated animation data, which is sent to the user's device as an HTTP request. The user can check the animation using the preview link.

[1223] Step 7:

[1224] The user checks the preview and provides feedback. The input is natural language text, which is sent from the device to the server. For example, the user might input a command such as, "I want the character's clothing to look more business-like."

[1225] Step 8:

[1226] The server again uses a natural language processing engine to analyze the user's feedback and convert it into specific correction requirements. The input data is the natural language text of the feedback, and the NLP engine extracts the correction requirements. The output is a list of correction requirements.

[1227] Step 9:

[1228] The server sends modification requirements to the generative AI engine to modify the animation. The input data is a list of modification requirements, and the generative AI engine is used to regenerate the animation. The output is the modified animation data.

[1229] Step 10:

[1230] Once the final animation is generated, the server generates a download link to provide the completed animation to the user and sends it to the user's device. The input data is the final animation data, which is sent to the user's device as an HTTP request. The user can download the final animation via this link and use it in their advertising campaign.

[1231] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1232] This invention is a system that automatically generates high-quality and diverse animations using natural language instructions from the user and an emotion engine that analyzes the user's emotions. In particular, it recognizes the user's emotions and adjusts the animation requirements based on them to provide more personalized animations.

[1233] User instruction input

[1234] The user uses the device to input instructions for animation production in natural language. For example, they might input, "I want to create a 30-second animation introducing our new smartwatch product. I want to create a scene with characters in motion." The input instructions are sent from the device to the server.

[1235] Receiving and parsing instructions

[1236] The server receives the instruction data sent by the user and analyzes it using a natural language processing (NLP) engine. The NLP engine extracts animation requirements from the instructions and generates a list of specific requirements. For example, requirements such as "introduce the smartwatch," "use of characters," "moving scenes," and "30 seconds" are extracted.

[1237] Applying the Emotion Engine

[1238] The server also passes the received instruction data to the emotion engine, which analyzes the user's emotions. The emotion engine recognizes emotions (e.g., joy, excitement, tension, etc.) from the user's language and context, and reflects the extracted emotional information in the animation requirements. For example, if the user is excited, it can add more dynamic movements and vivid colors to the requirements.

[1239] Transforming and optimizing animation requirements

[1240] The server integrates the extracted requirements and emotion information and converts it into a format suitable for the generative AI, thereby providing all the information necessary for the generative AI and optimizing the requirements list.

[1241] Generate initial animation

[1242] The server then sends the optimized requirement list to the generative AI engine, which generates initial animations based on the given requirements and emotion information. This stage includes character modeling, basic scene setup, and actions. The generated initial animations are returned to the server.

[1243] Identification of intermediate products

[1244] The generated initial animation is provided as a preview from the server to the user's device. The user can check this preview and provide feedback. For example, the user can send correction instructions such as "I want the character's clothing to look more business-like" to the server via their device.

[1245] Receiving and incorporating feedback

[1246] The server receives the user's feedback and analyzes it again using the NLP engine and emotion engine. Taking into account the content of the feedback as well as the user's emotions, it generates specific correction requirements and sends them to the generation AI.

[1247] Generating the final animation

[1248] The generation AI regenerates the animation based on the modification requirements and emotion information, and returns the modified animation data to the server, which then retrieves this data and prepares it as the final animation.

[1249] Providing the final animation

[1250] The server generates a download link to provide the completed final animation to the user, and the download link is sent to the user's device, allowing the user to obtain the final animation through the link.

[1251] As a concrete example, when generating a 30-second animation introducing a new smartwatch product, the user inputs instructions such as, "I want to create an animation that introduces the smartwatch and highlights its features." The server analyzes these instructions, uses an emotion engine to recognize the user's emotions (e.g., excitement), and generates a list of requirements based on these. The generation AI generates an initial animation and then reflects the user's feedback and emotional information to create the final animation. This series of processes allows users to easily and efficiently create personalized, high-quality animations.

[1252] The processing flow will be explained below.

[1253] Step 1:

[1254] The user uses the device to input instructions for animation production in natural language. For example, they might input, "I want to create a 30-second animation introducing our new smartwatch product. I want to create a scene with characters and movement." The device then sends the input instructions to the server.

[1255] Step 2:

[1256] The server receives the instruction data sent by the user and passes it to a natural language processing (NLP) engine for analysis. The NLP engine extracts animation requirements from the instructions. The extracted requirements include "introduce the smartwatch," "use of characters," "moving scenes," and "30 seconds."

[1257] Step 3:

[1258] The server passes the received instruction data to the emotion engine, which analyzes the user's emotions. For example, if the user is excited, the emotion engine recognizes this and extracts emotion information such as "excited" or "positive."

[1259] Step 4:

[1260] The server integrates the extracted requirement list and emotion information and converts it into a format suitable for generative AI, including adjusting the animation style based on the emotion (e.g., color usage and movement emphasis).

[1261] Step 5:

[1262] The server sends the optimized requirement list to the generation AI engine, which generates an initial animation based on the requirement list and emotion information. This initial animation includes basic character modeling, scene setup, and basic movements. The generated initial animation is returned to the server.

[1263] Step 6:

[1264] The server sends a preview of the generated initial animation to the user's device, where the user can view the preview and provide feedback, such as "I'd like the character's clothing to look more business-like."

[1265] Step 7:

[1266] The device sends the user's feedback data to the server, which then receives the feedback data and analyzes it again using the NLP engine and emotion engine. Specific correction requirements are generated based on the feedback content.

[1267] Step 8:

[1268] The server reflects the feedback requirements and emotional information and sends it to the generation AI means. The generation AI regenerates the animation based on this. This regeneration process includes corrections specified in the feedback and style adjustments based on the emotional information. The corrected animation data is returned to the server.

[1269] Step 9:

[1270] The server prepares the final version of the modified animation and generates a download link for the user, which is then sent to the user's device.

[1271] Step 10:

[1272] The user can then use the provided download link to download the final animation from their device, allowing them to receive the final product introduction animation.

[1273] By following the above steps, the user can easily create a variety of high-quality animations based on the user's emotions, simply by issuing instructions without moving their hands.

[1274] Example 2

[1275] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1276] Current animation generation systems struggle to efficiently generate personalized, high-quality animations that meet user needs. In particular, they lack a process for generating animations that takes user emotions into account, resulting in generated animations that do not adequately reflect user expectations and emotions. Furthermore, the process of making corrections based on user feedback is cumbersome and time-consuming, and improvements are needed to increase user satisfaction.

[1277] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1278] In this invention, the server includes means for receiving natural language instructions from a user, means for analyzing the natural language instructions and converting them into animation requirements, means for analyzing the user's emotions from the natural language instructions, generation AI means for generating animation based on the converted requirements and the analyzed emotional information, means for providing a preview of the generated animation to the user, means for receiving feedback from the user and reflecting it in the generation AI means, means for generating a final animation that reflects the feedback and emotional information, and means for providing the final animation to the user. This enables the generation of personalized, high-quality animation that takes user instructions and emotions into consideration.

[1279] A "user" is a person who operates the system to input animation instructions and checks and provides feedback on the generated animation.

[1280] "Natural language instructions" refer to instructions written in sentence format that are input by a user through a terminal.

[1281] "Analysis" is the process of using a natural language processing engine and an emotion engine to understand the user's instructions and emotions from the context and convert them into specific data.

[1282] "Animation requirements" are specific conditions and elements for generating animations, extracted from the analyzed natural language instructions and emotional information.

[1283] "Emotion information" is data about the user's emotions (e.g., joy, excitement, tension) extracted from the user's natural language instructions.

[1284] The "generative AI means" is an artificial intelligence system that automatically generates animations based on the extracted animation requirements and emotional information.

[1285] A "preview" is a short video that allows the user to see an early version of the generated animation.

[1286] "Feedback" refers to correction instructions and evaluations provided by the user after checking the preview.

[1287] The "final animation" refers to the final animation that reflects the user's feedback and emotional information.

[1288] The "server" is a computer system that executes various processing means, manages and analyzes instructions and feedback from users, and generates and provides the final animation.

[1289] A "terminal" is a device that a user uses to input natural language instructions, see a preview of the generated animation, and provide feedback.

[1290] The present invention is a system that automatically generates high-quality, personalized animations by utilizing natural language instructions from a user and a generative AI model with an emotion engine. The following describes an embodiment of the system.

[1291] User instruction input

[1292] A user uses a device (e.g., a PC or smartphone) to access a dedicated application or website and input instructions for animation production in natural language. For example, they might input instructions such as, "I want to create a 30-second animation introducing our new smartwatch product. I want to create a scene with characters in motion." These input instructions are then sent from the device to the server.

[1293] Receiving and parsing instructions

[1294] The server receives instruction data sent by the user. This data is automatically passed to a natural language processing (NLP) engine for analysis. The NLP engine extracts animation requirements from the user's instructions and generates a list of specific requirements. For example, requirements such as "introduce the smartwatch," "use of characters," "moving scenes," and "30 seconds" are extracted from the instructions.

[1295] Applying the Emotion Engine

[1296] At the same time, the server passes the received instruction data to the emotion engine, which analyzes the user's emotions. The emotion engine recognizes emotions (e.g., joy, excitement, tension) from the user's context and vocabulary, and reflects this emotional information in the animation requirements. For example, if the user is excited, more dynamic movements and vivid colors are added to the requirements.

[1297] Transforming and optimizing animation requirements

[1298] The server then integrates the extracted requirements list with the emotion information and converts it into a format suitable for the generative AI model. This process ensures that all the information required by the generative AI is gathered and the requirements list is optimized. Specifically, the requirements list is converted into a data structure such as JSON format.

[1299] Generate initial animation

[1300] The server sends the optimized requirement list to the generative AI engine, which then models the character, sets up the basic scene, plans the action, and generates the initial animation based on the requirements and emotion information. Once this series of processes is complete, the generated initial animation data is sent back to the server.

[1301] Identification of intermediate products

[1302] The generated initial animation is provided as a preview from the server to the user's device. The user can check the preview on their device and provide feedback on any points of concern or changes they would like to make. For example, they can send detailed correction instructions, such as "I would like the character's clothing to be more business-like," to the server from their device.

[1303] Receiving and incorporating feedback

[1304] The server receives feedback from the user. The received feedback is analyzed again by the NLP engine and emotion engine to generate specific correction requirements. In addition, the user's latest emotional information is also reflected. This information is then sent again to the generative AI engine.

[1305] Generating the final animation

[1306] The generative AI engine regenerates the animation based on the user's modification requirements and emotional information. The final animation data reflecting the modification requests is sent back to the server, which then retrieves this data and prepares the final animation.

[1307] Providing the final animation

[1308] The server generates a download link for providing the completed final animation to the user, and the download link is sent to the user's device, allowing the user to download and obtain the final animation through the link.

[1309] Specific examples

[1310] For example, when generating a 30-second animation introducing a new smartwatch product, the user inputs instructions such as, "I want to create an animation that introduces the smartwatch and highlights its features." The server analyzes these instructions, uses an emotion engine to recognize the user's emotions (e.g., excitement), and generates a list of requirements based on those emotions. The generative AI generates an initial animation and then reflects the user's feedback and emotional information to create the final animation. This series of processes allows users to easily and efficiently create personalized, high-quality animations.

[1311] Prompt Sentence Examples

[1312] "Create a 30-second animation showcasing a new smartwatch. I'd like it to be animated with characters and incorporate emotions that excite the user."

[1313] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1314] Step 1:

[1315] User instruction input

[1316] The user uses a device to access a dedicated application or website and inputs instructions for animation production in natural language. For example, they might input, "I want to create a 30-second animation introducing our new smartwatch. I want to create a scene with characters in motion." This input is then sent from the device to the server.

[1317] Input: Natural language animation instructions

[1318] Output: Instruction data sent from the terminal to the server

[1319] Step 2:

[1320] Receiving and parsing instructions

[1321] The server receives instruction data sent by the user. This data is automatically passed to a natural language processing (NLP) engine for analysis. The NLP engine extracts animation requirements from the user's instructions and generates a list of specific requirements. For example, it extracts requirements such as "introduce a smartwatch," "use of characters," "scenes with movement," and "30 seconds."

[1322] Input: Instruction data sent by the user

[1323] Data processing: Analysis using a natural language processing engine

[1324] Output: Extracted animation requirements list

[1325] Step 3:

[1326] Applying the Emotion Engine

[1327] At the same time, the server passes the received instruction data to the emotion engine, which analyzes the user's emotions. The emotion engine recognizes emotions (e.g., joy, excitement, tension) from the user's context and vocabulary, and reflects this emotional information in the animation requirements. For example, if the user is excited, more dynamic movements and vivid colors are added to the requirements.

[1328] Input: Instruction data to be analyzed

[1329] Data processing: Emotion analysis using an emotion engine

[1330] Output: Parsed emotion information

[1331] Step 4:

[1332] Transforming and optimizing animation requirements

[1333] The server then integrates the extracted requirements list with the emotion information and converts it into a format suitable for the generative AI model. This process ensures that all the information required by the generative AI is gathered and the requirements list is optimized. Specifically, the requirements list is converted into a data structure such as JSON format.

[1334] Input: Requirement list and sentiment information

[1335] Data processing: requirements optimization and format conversion

[1336] Output: An optimized requirements list for a generative AI model

[1337] Step 5:

[1338] Generate initial animation

[1339] The server sends the optimized requirement list to the generative AI engine, which then models the character, sets up the basic scene, and plans the movement based on the requirements and emotion information, generating the initial animation. Once this series of processes is complete, the generated initial animation data is sent back to the server.

[1340] Input: Optimized requirements list

[1341] Data processing: Generative AI animation generation

[1342] Output: Initial animation data

[1343] Step 6:

[1344] Identification of intermediate products

[1345] The generated initial animation is sent as a preview from the server to the user's device. The user can check the preview on their device and provide feedback on any areas of concern or changes they would like to see. For example, they can send detailed correction instructions, such as "I would like the character's clothing to look more business-like," to the server.

[1346] Input: Initial animation preview

[1347] Data processing: User feedback

[1348] Output: List of modified requirements

[1349] Step 7:

[1350] Receiving and incorporating feedback

[1351] The server receives feedback from the user. The received feedback is analyzed again by the NLP engine and emotion engine. Specific correction requirements are generated, and the user's latest emotional information is also reflected. This information is then sent back to the generative AI engine.

[1352] Input: User feedback

[1353] Data processing: Analysis of feedback and generation of revised requirements

[1354] Output: Modified requirement list and sentiment information

[1355] Step 8:

[1356] Generating the final animation

[1357] The generative AI engine regenerates the animation based on the user's modification requirements and emotional information. The final animation data reflecting the modification requests is sent back to the server. The server receives this data and prepares the final animation.

[1358] Input: Modified requirement list and sentiment information

[1359] Data processing: Regenerating animations using generative AI

[1360] Output: Final animation data

[1361] Step 9:

[1362] Providing the final animation

[1363] The server generates a download link for the completed final animation to provide the user with the animation, and the download link is sent to the user's device, allowing the user to download and obtain the final animation through the link.

[1364] Input: Final animation data

[1365] Data processing: Generate download links

[1366] Output: Send a download link to the user's device

[1367] (Application example 2)

[1368] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1369] Conventional animation production systems make it difficult for users to easily reflect individual emotions and specific instructions, resulting in a cumbersome process for creating personalized, high-quality animations. Furthermore, there is a lack of effective means for quickly and intuitively generating animations in specific fields such as advertising. There is a need for a system that can solve these problems and automatically generate high-quality animations that reflect individual emotions based on natural language instructions from users.

[1370] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving natural language instructions from a user; means for analyzing the natural language instructions and converting them into animation requirements; means for reading the user's emotions from the analyzed natural language instructions and generating animation requirements that reflect the emotions; generation AI means for generating animation based on the converted requirements; means for providing a preview of the generated animation to the user; means for receiving feedback from the user and reflecting it in the generation AI means; means for generating a final animation that reflects the feedback and the read emotions; and means for providing the final animation to the user. This makes it possible to quickly generate personalized, high-quality animation that reflects the user's emotions.

[1371] The "means for receiving instructions in natural language from a user" refers to a device or interface for recognizing instructions input in natural language by a user and transmitting the instructions to a server.

[1372] The "means for parsing natural language instructions and converting them into animation requirements" refers to software or algorithms that parse natural language instructions entered by a user and convert those instructions into specific animation requirements.

[1373] "Means for reading the user's emotions from the analyzed natural language instructions and generating animation requirements that reflect those emotions" is an algorithm that extracts the user's emotions from the analyzed instructions and generates animation requirements taking those emotions into consideration.

[1374] "Generative AI means" refers to an artificial intelligence system that automatically generates initial and final animations based on the requirements of the converted animation.

[1375] The "means for providing a preview to the user" refers to a system or interface for visually displaying to the user intermediate and final results of the generated animation.

[1376] The "means for receiving feedback and reflecting it in the generating AI means" is an algorithm for receiving feedback provided by the user, analyzing that feedback, and reflecting it in the generating AI.

[1377] The "means for generating final animation" is an AI system that generates the final animation based on user feedback and emotional information.

[1378] The "means for providing the final animation to the user" refers to a system or interface that allows the user to download or view the completed final animation.

[1379] This invention is a system for quickly and effectively generating animations for advertising. This system includes a series of processes that receive natural language instructions from a user, analyze them, and generate animations that reflect the user's emotions.

[1380] First, the user inputs instructions for animation production in natural language via a device such as a smartphone. These instructions are then sent from the device to the server. For example, a user might say, "I want to create a 30-second animated advertisement introducing our new lunch menu. I want to give it a seasonal feel."

[1381] The server receives the instruction data sent by the user and analyzes it using a natural language processing engine (e.g., Google Cloud Natural Language API). During this analysis, animation requirements are extracted from the instructions. For example, from the above instructions, requirements such as "new lunch menu," "seasonal feel," and "30-second animation" are extracted.

[1382] Next, the server uses an emotion analysis engine (e.g., IBM Watson Tone Analyzer) to analyze the user's emotions. In this process, emotions (e.g., excitement, joy, etc.) are recognized from the user's vocabulary and context, and the extracted emotional information is reflected in the animation requirements. For example, if the user excitedly inputs a command such as "I want to create a sense of the season," animation requirements with more dynamic color usage and movement are added.

[1383] The server integrates these animation requirements and emotion information and converts them into a format suitable for a generative AI model (e.g., DALL-E or GPT-4). This production AI model generates an initial animation based on the given requirements. The generated initial animation is then provided as a preview from the server to the user's device.

[1384] The user checks the preview and provides feedback for corrections, such as "I'd like the background of the scene to be a warmer color." This feedback is sent from the device to the server, where it is again subjected to natural language processing and sentiment analysis to generate specific correction requirements.

[1385] The generative AI model regenerates the animation based on the modified requirements to create the final animation, which is then provided as a download link from the server to the user's device, allowing the user to download the animation through this link.

[1386] As a concrete example, the prompt text for "If you want to create an advertising animation for the new menu item 'Special Japanese-style Hamburger Steak'" is as follows:

[1387] "We'd like to create a 30-second animated ad to promote our new special Japanese-style hamburger lunch. Emphasize the autumn feel with warm colors and dynamic movements."

[1388] The present invention allows users to quickly generate personalized, emotionally-driven, and high-quality advertising animations.

[1389] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1390] Step 1:

[1391] The user uses a terminal to input instructions for animation production in natural language. For example, the instructions might be, "I want to create a 30-second animated advertisement introducing our new special Japanese-style hamburger steak lunch. Please emphasize the autumnal feeling with warm colors and dynamic movements." After input, this data is sent from the terminal to the server.

[1392] Step 2:

[1393] The server sends the received instruction data to a natural language processing engine (e.g., Google Cloud Natural Language API) for analysis. The input for the analysis is the user's natural language instruction, and the output is a list of requirements such as "new special Japanese-style hamburger lunch," "warm colors," "dynamic movements," "autumn seasonal feel," and "30-second animation."

[1394] Step 3:

[1395] The server sends the acquired requirement list and instruction data to an emotion analysis engine (e.g., IBM Watson Tone Analyzer) to extract the user's emotion. The input is the instruction data, and the output is the recognized emotion information (e.g., joy, excitement). This adds the emotion information to the requirement list.

[1396] Step 4:

[1397] The server integrates and optimizes the converted requirement list and emotion information into a format suitable for the generative AI model (e.g., DALL-E or GPT-4). The input of this process is the requirement list and emotion information, and the output is data in a format that can be interpreted by the generative AI model.

[1398] Step 5:

[1399] The server sends the optimized data to the generative AI model to generate the initial animation. The input is the optimized data, and the output is the initial animation. The generated initial animation is returned to the server.

[1400] Step 6:

[1401] The server provides a preview of the initial animation to the user's device, and the user can view the preview and provide feedback in natural language, such as "I'd like the background color to be warmer."

[1402] Step 7:

[1403] The server receives feedback from the user and passes it back to the natural language processing engine and sentiment analysis engine for analysis. The input is the feedback, and the output is the correction requirements and sentiment information.

[1404] Step 8:

[1405] The server issues regeneration instructions to the generative AI model based on the modification requirements, generating the final animation. The input is the modification requirements and emotion information, and the output is the final animation.

[1406] Step 9:

[1407] The final animation is provided to the user's device as a download link from the server, and the user can obtain the final animation through the link.

[1408] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1409] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1410] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1411] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1412] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1413] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1414] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1415] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1416] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1417] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1418] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1419] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1420] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1421] 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.

[1422] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1423] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1424] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1425] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1426] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1427] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1428] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1429] The following is further disclosed regarding the above embodiment.

[1430] (Claim 1)

[1431] means for receiving natural language instructions from a user;

[1432] means for parsing and converting the natural language instructions into animation requirements;

[1433] A generating AI means for generating an animation based on the converted requirements;

[1434] means for providing a user with a preview of the generated animation;

[1435] A means for receiving feedback from the user and reflecting it in the generating AI means;

[1436] means for generating a final animation that reflects the feedback;

[1437] means for providing said final animation to a user;

[1438] A system including:

[1439] (Claim 2)

[1440] 2. The system of claim 1, wherein the means for providing a preview of the generated animation is used for checking intermediate products.

[1441] (Claim 3)

[1442] 10. The system of claim 1, wherein the analyzing means includes a natural language processing engine.

[1443] (Claim 4)

[1444] 10. The system of claim 1, wherein said generating AI means is capable of generating a plurality of graphic styles.

[1445] (Claim 5)

[1446] 10. The system of claim 1, wherein the means for providing the final animation to the user generates a download link.

[1447] "Example 1"

[1448] (Claim 1)

[1449] means for receiving natural language instructions from a user;

[1450] means for parsing and converting the natural language instructions into animation requirements;

[1451] A means for converting the converted requirements into a format understandable by a generative AI engine and optimizing the requirements;

[1452] A generating AI means for generating animations based on the optimized requirements;

[1453] means for providing a user with a preview of the generated animation;

[1454] A means for receiving feedback from the user and reflecting it in the generating AI means;

[1455] means for generating a final animation that reflects the feedback;

[1456] means for generating a download link for providing the final animation to a user;

[1457] A system including:

[1458] (Claim 2)

[1459] 2. The system of claim 1, wherein the means for providing a preview of the generated animation is used for checking intermediate products.

[1460] (Claim 3)

[1461] 2. The system of claim 1, wherein the analysis means includes a natural language processing engine used to analyze and convert feedback into specific revision requirements.

[1462] "Application Example 1"

[1463] (Claim 1)

[1464] means for receiving natural language instructions from a user;

[1465] means for parsing and converting the natural language instructions into animation requirements;

[1466] A generating AI means for generating an animation based on the converted requirements;

[1467] means for providing a user with a preview of the generated animation;

[1468] A means for receiving feedback from the user and reflecting it in the generating AI means;

[1469] means for generating a final animation that reflects the feedback;

[1470] means for providing said final animation to a user;

[1471] A means for creating high-quality animated ads for advertising campaigns in natural language on a user device;

[1472] means for transmitting advertisement production instructions in natural language from a user to a server;

[1473] means for the server to analyze the instructions and extract requirements for advertisement animation;

[1474] A generating AI means for generating animation suitable for advertising purposes based on the requirements;

[1475] means for transmitting a preview link of the generated animation to a user terminal and receiving user confirmation and feedback;

[1476] means for providing a download link for the final animation to a user terminal;

[1477] A system including:

[1478] (Claim 2)

[1479] 10. The system of claim 1, wherein the means for providing a preview of the generated animation is used to verify the intermediate product and receive user feedback for modifying the animation.

[1480] (Claim 3)

[1481] 2. The system according to claim 1, wherein the analyzing means includes a natural language processing engine for analyzing a user's natural language instructions to extract requirements for the advertising animation.

[1482] "Example 2: Combining Emotion Engines"

[1483] (Claim 1)

[1484] means for receiving natural language instructions from a user;

[1485] means for parsing and converting the natural language instructions into animation requirements;

[1486] means for analyzing a user's emotion from the natural language instruction;

[1487] A generating AI means for generating an animation based on the converted requirements and the analyzed emotion information;

[1488] means for providing a user with a preview of the generated animation;

[1489] A means for receiving feedback from the user and reflecting it in the generating AI means;

[1490] means for generating a final animation that reflects the feedback and emotional information;

[1491] means for providing said final animation to a user;

[1492] A system including:

[1493] (Claim 2)

[1494] 2. The system of claim 1, wherein the means for providing a preview of the generated animation is used for checking intermediate products.

[1495] (Claim 3)

[1496] 10. The system of claim 1, wherein the analysis means includes a natural language processing engine and a sentiment analysis engine.

[1497] "Application example 2 when combining emotion engines"

[1498] (Claim 1)

[1499] means for receiving natural language instructions from a user;

[1500] means for parsing and converting the natural language instructions into animation requirements;

[1501] a means for reading a user's emotion from the analyzed natural language instructions and generating animation requirements that reflect the emotion;

[1502] A generating AI means for generating an animation based on the converted requirements;

[1503] means for providing a user with a preview of the generated animation;

[1504] A means for receiving feedback from the user and reflecting it in the generating AI means;

[1505] means for generating a final animation that reflects the feedback and the sensed emotions;

[1506] means for providing said final animation to a user;

[1507] A system including:

[1508] (Claim 2)

[1509] 2. The system of claim 1, wherein the means for providing a preview of the generated animation is used for checking intermediate products.

[1510] (Claim 3)

[1511] 10. The system of claim 1, wherein the analysis means includes a natural language processing engine and a sentiment analysis engine. [Explanation of symbols]

[1512] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving natural language instructions from a user; means for parsing and converting the natural language instructions into animation requirements; A generating AI means for generating an animation based on the converted requirements; means for providing a user with a preview of the generated animation; A means for receiving feedback from the user and reflecting it in the generating AI means; means for generating a final animation that reflects the feedback; means for providing said final animation to a user; A system including:

2. 2. The system of claim 1, wherein the means for providing a preview of the generated animation is used for checking intermediate products.

3. 2. The system of claim 1, wherein said analyzing means includes a natural language processing engine.

4. 2. The system of claim 1, wherein said generating AI means is capable of generating a plurality of graphic styles.

5. 2. The system of claim 1, wherein the means for providing the final animation to the user generates a download link.

Images