system

Abstract

We provide the system. [Solution] A device that receives user requests and target information, A device for selecting an appropriate generative model based on the target information, A device that automatically generates information using the generation model, A device that adjusts the generated information according to the user's request, A device for optimizing the performance of the adjusted information, A device that automatically creates a distribution plan to support the generation and management of content, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In content production, it is required to create various forms of content efficiently and quickly. However, the conventional methods have problems such as requiring a great deal of time and resources and being unable to flexibly meet various user requirements. Therefore, there is a need for a technology that automates content generation according to user instructions and goals and improves its efficiency.

Means for Solving the Problems

[0005] The present invention provides a system that receives user instructions and goal information, selects an appropriate generative model based on the goal information, and further provides a means for automatically generating diverse content using the generative model. The generated content is customized according to user requests, and its performance is optimized through search engine optimization and data analysis, thereby realizing an efficient content creation system.

[0006] A "user" is an individual or legal entity that uses the system for the purpose of generating content.

[0007] "Instructions and goal information" refers to information about the requirements and desired outcomes that users provide regarding the content they generate.

[0008] A "generative model" is an algorithm or machine learning model used to generate content.

[0009] "Content" refers to digital information such as text, images, audio, and video created by generative models.

[0010] "Customization" is the process of making changes and adjustments to generated content in response to user requests.

[0011] "Performance optimization" refers to adjustments and improvement activities carried out through search engine optimization and data analysis to enhance the effectiveness of content. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4]It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0013] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0018] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. 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), or Bluetooth (registered trademark).

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] This invention is a system that automates content generation, in which the server utilizes various generation models to generate content based on user-specified instructions and target information. This system enables flexible and rapid content creation to meet diverse user needs.

[0034] The program will operate as follows:

[0035] The user inputs instructions and target information for the content they want to generate using their device and sends this information to the server. The server analyzes the received information and dynamically selects the appropriate generation model. This selection is based on the user's target content and format. For example, a text generation model is selected for generating blog posts, and an image generation model is selected for creating images.

[0036] After the content is generated, the server presents it to the user and customizes it based on user feedback. For example, if a user requests a "blog post about environmental issues," the server selects an appropriate text generation model and generates an article containing comprehensive information, from an introduction to specific examples. The article can then be customized to the user's preference, with adjustments to tone and the inclusion of additional statistical data.

[0037] Furthermore, the server optimizes the performance of the generated content by improving its display ranking through search engine optimization (SEO) and data analysis. In this way, the present invention realizes highly efficient content creation that meets the diverse needs of users and enables its use in various fields.

[0038] The following describes the processing flow.

[0039] Step 1:

[0040] The user uses the device interface to input detailed instructions and goal information for the content they want to generate. This input includes information such as the content type, theme, and style.

[0041] Step 2:

[0042] The terminal sends user input information to the server. The transmitted information is formatted appropriately for use in subsequent processes.

[0043] Step 3:

[0044] The server analyzes the received instructions and target information and selects an appropriate generative model based on this analysis. For example, a text generation model or an image generation model might be selected.

[0045] Step 4:

[0046] The server activates the selected generative model and generates content based on the user's input. During this generation process, content aligned with the objective is created based on an algorithm.

[0047] Step 5:

[0048] The server temporarily stores the generated content and presents it to the user as an initial output. At this stage, the user is asked to review the content and quality.

[0049] Step 6:

[0050] Users can provide additional feedback and request revisions to the presented content through their devices. This includes adjustments to tone and style.

[0051] Step 7:

[0052] The device sends user feedback to the server. The server receives this feedback and customizes it as needed.

[0053] Step 8:

[0054] The server optimizes content performance using SEO measures and data analysis as needed. This helps improve search engine rankings.

[0055] Step 9:

[0056] Once the final content is ready, the server will deliver it to the user. The user will receive and use the content in a format appropriate to their purpose.

[0057] (Example 1)

[0058] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0059] In today's world, generating content that meets the diverse needs of information processing device users requires speed and flexibility. However, conventional technologies struggle to effectively meet these demands, particularly in the complex and inefficient processes of adjusting generated data and improving its visibility.

[0060] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0061] In this invention, the server includes means for a user to input instructions and target information using an information processing device, means for analyzing the instructions and target information and dynamically selecting an appropriate generation algorithm, means for generating data using the generation algorithm, and means for using information retrieval technology to improve the visibility of the adjusted data. This enables efficient content generation and improved visibility while responding to the diverse needs of users of the information processing device.

[0062] An "information processing device" is a device used by users to input instructions and target information, and includes computers, smartphones, and other similar devices.

[0063] "Means for inputting instructions and target information" refers to interfaces or methods for users to input specific requirements and conditions for the content they wish to generate into an information processing device.

[0064] "Methods for dynamically selecting a generation algorithm" refer to the process of analyzing instructions and target information received from the user and selecting the most suitable generation model in real time based on that analysis.

[0065] "Means of generating data" refers to a function that automatically generates content according to instructions and target information using a selected generation algorithm.

[0066] "Means of using information retrieval technology to improve the visibility of adjusted data" refers to methods of using search engine algorithms and data analysis techniques to optimize the display order of generated data and deliver it to a wider audience.

[0067] This invention is an automated system for efficiently generating content that meets the diverse needs of users. Upon receiving user instructions, the server dynamically selects an appropriate generation model according to those instructions and generates the content. Specifically, users input instructions and target information regarding the content they wish to generate using a terminal. For example, a wide range of inputs are possible, such as creating blog posts, producing images, or generating audio content.

[0068] The server analyzes these inputs and selects the appropriate generative AI model. Natural language processing techniques are used for text generation, and image synthesis algorithms are employed for image generation. During this process, the server uses appropriate software to process and calculate data, achieving efficient content generation. Specifically, well-known natural language processing tools are used for text generation, and specialized image algorithms are utilized for image generation.

[0069] The generated content is temporarily stored on the server and presented to the user. User feedback is sent back to the server, which then adjusts the content based on that feedback. This ensures that the user receives the adjusted content they desired.

[0070] As a concrete example, suppose a user enters a prompt such as, "Please generate a beginner's guide to spring gardening, including detailed instructions and recommended plant species, in an easy-to-understand style." In this case, the server selects an appropriate generation model based on the prompt and generates a guide summarizing beginner-friendly gardening information. The characteristic of this invention is that it enables content generation that flexibly responds to the diverse needs of users in this way.

[0071] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0072] Step 1:

[0073] The user uses their device to input instructions and target information for the content they want to generate. Specifically, the user describes their requests regarding the generation of text and images in natural language. For example, they might input a prompt such as, "Please generate a blog post about environmental issues." This prompt is sent to the server via the device. The input data is then used for subsequent processing in response to the user's request.

[0074] Step 2:

[0075] The server analyzes the prompt message received from the user. Using natural language processing techniques, the server performs data analysis to understand the intent and content of the input instructions. Based on this analysis, it selects an appropriate generative AI model. For example, if the requirement is text generation, it selects a text generation model; if the requirement is image generation, it selects an image generation model. The output is information about the selected model, which forms the basis for content generation in the next stage.

[0076] Step 3:

[0077] The server generates content using a selected generative AI model. At this stage, prompt sentences are input to the generative model, and data processing and calculations are performed to generate content in the specified format. For example, a text generation model sequentially generates relevant sentences based on the prompt sentences. This generated content is stored on the server and presented to the user in the next step.

[0078] Step 4:

[0079] The server presents the generated content to the user and receives feedback. The user reviews the output and provides specific feedback as needed, such as "Please adjust the tone" or "Please add more details." This feedback is sent to the server and used for further customization.

[0080] Step 5:

[0081] The server customizes the content based on feedback received from the user. Specifically, it uses a regenerative model to incorporate additional information and adjust styles. The newly processed data is then generated as the final version of the content that meets the user's requirements. This final version is then finalized on the server and proceeds to the optimization step.

[0082] Step 6:

[0083] The server uses information retrieval techniques to improve the visibility of the completed content. It employs search engine optimization (SEO) and data analysis techniques to improve the content's ranking. Specific actions include keyword optimization and metadata adjustment. The output of this step is optimized content, ready to be delivered more efficiently to a wider audience.

[0084] (Application Example 1)

[0085] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0086] In recent years, content distribution services have been required to quickly and efficiently generate and deliver content that meets diverse demands. However, traditional methods have problems in that it is difficult to generate content that aligns with the specific needs of users, and furthermore, optimizing the distribution plan requires a great deal of effort.

[0087] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0088] In this invention, the server includes a device for receiving user requests and target information, a device for selecting an appropriate generation model based on the target information, a device for automatically generating information using the generation model, a device for adjusting the generated information according to user requests, a device for optimizing the performance of the adjusted information, and a device for automatically creating a delivery plan to support content generation and management. This makes it possible to efficiently generate content that meets diverse requests and to deliver it optimally.

[0089] A "device for receiving user requests and goal information" is a device that has the function of receiving and accurately receiving specific requests and goals regarding the content that a user wants to create.

[0090] A "generative model selection device" is a device that selects the most suitable generative AI model based on the received requests and objectives.

[0091] A "device that automatically generates information" is a device that uses a selected generation AI model to automatically create the information and content that users need.

[0092] A "device for adjusting generated information according to user requests" is a device that further modifies and adapts generated content according to the user's specific preferences and feedback.

[0093] A "device for optimizing the performance of adjusted information" is a device that optimizes adjusted content to enhance its performance so that it functions to its fullest potential.

[0094] A "device that automatically creates distribution plans" is a device that has the function of automatically determining and creating schedules and methods for optimally distributing generated and adjusted content.

[0095] The system for implementing this invention uses a server, a user terminal, and a generative AI model as its main components. The user inputs instructions and target information necessary for content generation through the terminal. This information is sent to the server, which analyzes the received information to select an appropriate generative model. Examples of generative models used include GPT (Generative Pretrained Transformer), a model for text generation, and DALL-E, a generative AI for image generation.

[0096] The server automatically generates content using the selected generative model. The generated content is further refined based on detailed user requests and feedback. This refinement allows for customization to include the writing style and detailed information requested by the user.

[0097] Subsequently, the server optimizes the performance of the adjusted content. SEO (Search Engine Optimization) and data analysis tools are utilized for this purpose. Furthermore, the server automatically creates a delivery plan to enable efficient distribution of the generated content.

[0098] For example, if a user wants to generate a blog post about summer activities, they would use the following prompt on their device:

[0099] "Create a blog post detailing fun summer activities for the whole family. The post should include tips for safety and ways to save money."

[0100] Based on this prompt, the server can select the appropriate generative model and generate and adjust the necessary content. This allows users to obtain high-quality content in a short amount of time.

[0101] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0102] Step 1:

[0103] The user inputs instructions and goal information for the content they want to generate using their device. This input includes specific prompts, such as, "Create a blog post detailing fun summer activities for the whole family." This clarifies the theme and focus of the content to be generated.

[0104] Step 2:

[0105] The terminal sends the input instructions and target information to the server. The server uses machine learning models to analyze this information and understand the user's requests. This analysis determines which generative model should be adopted.

[0106] Step 3:

[0107] The server selects an appropriate generation AI model based on the analysis results. Specifically, it chooses a model such as GPT or DALL-E that is suitable for the given theme. With this selected model, the server is ready for efficient content generation.

[0108] Step 4:

[0109] The server automatically generates content according to the instructions using a selected generative model. During the generation process, text and images are generated based on the input information. For example, based on prompts, the text of a blog post is output.

[0110] Step 5:

[0111] The generated content is customized on the server to meet user requests. Based on user feedback, the writing style is adjusted and additional information is incorporated. As a result, content that more closely matches the user's expectations is obtained.

[0112] Step 6:

[0113] The server further optimizes the customized content. In this process, search engine optimization (SEO) techniques and data analysis are used to improve the content's online performance.

[0114] Step 7:

[0115] After optimization, the server automatically creates a content delivery plan and prepares the content for delivery at the optimal time and in the best way. This allows users to make more effective use of the content they generate.

[0116] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0117] This invention is a content generation system that takes user emotions into consideration. It selects the optimal generation model based on user instructions and goal information, and adjusts the content using an emotion engine, thereby achieving a high level of customization.

[0118] The program will operate as follows:

[0119] The user inputs instructions and goal information about the content they want to generate through their device. This information is sent to the server, which uses an emotion engine to analyze the user's emotions. Based on the analysis, the server selects an appropriate generative model and uses that model to generate the content. In this generation process, the user's emotional information is applied to the tone and style of the content.

[0120] The generated content is temporarily stored on the server and then presented to the user. At this stage, the user can provide further feedback on the content provided. If the user requests emotional adjustments, the server uses the sentiment engine again to analyze and optimize the style and tone of the content.

[0121] For example, if a user wants to create a friendly-toned social media post about a gift, the server analyzes the user's mood using an emotion engine and selects a text generation model with a positive and casual tone. The generated post content is then adjusted according to the user's preferences. Finally, the server optimizes the content's performance through search engine optimization and data analysis before delivering it to the user in its final form.

[0122] In this way, by recognizing user emotions and reflecting them in the content, a system can be realized that quickly delivers high-quality content that better aligns with the user's intentions.

[0123] The following describes the processing flow.

[0124] Step 1:

[0125] The user inputs instructions regarding the theme, purpose, desired style, and tone of the content to be generated via the device.

[0126] Step 2:

[0127] The terminal sends the user's input information to the server, including the type of content and detailed instructions.

[0128] Step 3:

[0129] The server analyzes the received information and uses an emotion engine to identify the emotions contained in the user's instructions. This allows it to understand the user's intended emotions.

[0130] Step 4:

[0131] The server selects the optimal generative model based on the identified sentiment information. For example, if the sentiment is recognized as "friendly," it will choose a text generation model that matches that tone.

[0132] Step 5:

[0133] The server automatically generates content using a selected generative model. The generated content has a style that reflects the user's intended emotions.

[0134] Step 6:

[0135] The server temporarily stores the generated content and presents it to the user for review. The user reviews this content and provides feedback if any changes are needed.

[0136] Step 7:

[0137] Users may request content adjustments based on the feedback they provide. This may include further emotional adjustments or changes in tone.

[0138] Step 8:

[0139] The server uses the sentiment engine again to adjust the content based on user feedback. The adjusted content is then presented to the user again.

[0140] Step 9:

[0141] The server performs search engine optimization (SEO) and data analysis to enhance the final content quality and optimize the content's online performance.

[0142] Step 10:

[0143] Once the final version of the content is ready, the server will provide it to the user. The user can then use this content as needed.

[0144] (Example 2)

[0145] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0146] In recent years, there has been a growing demand for content that aligns with users' emotions and preferences, but conventional systems have struggled to adequately reflect user intent. Furthermore, the optimization processes required to maximize the performance of the generated content have been insufficient, making it difficult to increase user satisfaction.

[0147] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0148] In this invention, the server includes means for receiving user input information and having an information processing device for analyzing said input information, means for selecting a location information generation device based on the analysis results, and means for generating information using the location information generation device. This makes it possible to generate high-quality content that reflects the user's emotions and intentions. Furthermore, user satisfaction can be increased by adjusting the generated content with an emotion analysis device and optimizing the display performance with an evaluation device.

[0149] A "user" is the entity that inputs instructions and target information into an information system and receives the generated content.

[0150] "Input information" refers to the instructions and goal information that users provide to the system for content generation.

[0151] An "information processing device" is a device that analyzes input information received from a user and creates basic data for selecting an appropriate generative model.

[0152] A "location information generation device" refers to a generation model selected to generate optimal content based on user input information and analysis results.

[0153] An "emotion analysis device" is a device that adjusts generated content according to the user's emotions and instructions, thereby achieving an expression that aligns with the user's intentions.

[0154] An "evaluation device" is a device used to analyze and improve the performance of generated content in order to optimize its display performance.

[0155] In the embodiment of the invention, this system uses a combination of various information processing devices and software to generate content that reflects the user's intent. The specific implementation method is described below.

[0156] The user uses a terminal to input specific instructions and goal information about the content they want to generate. This information includes what they want to express and the desired style and tone. For example, they might give the instruction, "Write a fun post introducing birthday presents in a friendly tone." This input information is sent to the server as a prompt.

[0157] The server passes the received prompt message to the information processing unit, which then analyzes the input information. This analysis uses natural language processing techniques to understand the content and extract the user's emotional state and the intent behind the instructions. Based on these analysis results, the server selects the most appropriate generative AI model. This selection uses a generative model that excels at generating textual information.

[0158] The selected generative AI model generates content using user prompts and analysis results as input. This generation process utilizes an emotion analyzer to adjust the content according to the user's emotions and instructions. Specifically, it is configured to generate content with a casual and approachable writing style.

[0159] The generated content is temporarily stored on the server and presented to the user as it is received. The user reviews this content and provides feedback via their device as needed. If the user requests further adjustments at this stage, the server again uses sentiment analysis to refine the content.

[0160] In the final stage, the server uses evaluation equipment to optimize the performance of the generated content. This optimization utilizes search engine optimization techniques and data analysis tools to maximize content exposure and effectiveness.

[0161] Thus, this system can quickly deliver high-quality content that prioritizes and appropriately reflects the user's emotions and intentions.

[0162] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0163] Step 1:

[0164] The user enters instructions and goal information about the content they want to generate using their device. This input is in text format and includes details such as the content's subject, tone, and style. An example of input data might be, "I want to create a social media post about birthday presents in a friendly tone." This information is sent to the server as a prompt.

[0165] Step 2:

[0166] The server forwards the received prompt message to the information processing unit, where the data is analyzed. Using natural language processing techniques, the system analyzes keywords and context contained in the user's instructions to infer the user's emotions and intentions. The analysis results are temporarily stored in a database for use in the next step.

[0167] Step 3:

[0168] The server selects the most suitable generative AI model based on the analysis results. Here, a selection algorithm is used to choose a model that matches the tone and style desired by the user. The selected generative AI model might, for example, excel at producing casual writing styles. The selection results are output as metadata and used in the content generation process.

[0169] Step 4:

[0170] The server generates content using the selected generative AI model and prompt text as input. The generative AI model automatically generates content based on the specified tone and style using the input information. The generated content is text data that faithfully reflects the user's instructions. This is output as generated data, and the process proceeds to the next adjustment step.

[0171] Step 5:

[0172] The server re-evaluates the content generated using the sentiment analyzer and adjusts the tone and style as needed. The sentiment analyzer receives user feedback and performs additional data processing to adjust the tone of the content. This process adjusts the tone based on feedback such as "make it brighter." The adjusted content is output as updated data.

[0173] Step 6:

[0174] Ultimately, the server optimizes content performance using evaluation equipment. Search engine optimization and data analysis tools are used to optimize the generated content's online visibility and user engagement. This typically involves adjusting keyword density and optimizing meta information. The optimized content is then delivered to the user as the final output.

[0175] (Application Example 2)

[0176] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0177] Traditional content generation tools have a weakness: they lack sufficient customization to accommodate individual user emotions and styles, making it difficult to quickly deliver personalized content that meets user expectations. Furthermore, they lack mechanisms to properly incorporate feedback to optimize the performance of the generated content.

[0178] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0179] In this invention, the server includes means for receiving user instructions and goal information, means for selecting an appropriate machine learning model based on the goal information, means for automatically generating content using the machine learning model, means for customizing the style and tone of the generated content based on the user's emotional information, and means for optimizing the performance of the customized content through data analysis. This enables the rapid generation of personalized content that responds to the individual emotions of the user and the optimization of its performance.

[0180] "Means for receiving user instructions and goal information" refers to a system for users to input specific requests or desired outcomes regarding content creation.

[0181] "Means for selecting an appropriate machine learning model" refers to algorithms and processes for selecting the most suitable machine learning model based on user instructions and target information.

[0182] "Methods for automatically generating content using machine learning models" refers to methods for automatically creating content based on input information by utilizing selected machine learning models.

[0183] "Means of customizing the style and tone of generated content based on user emotional information" refers to technologies that reflect user emotional data in generated content and adjust its expression and tone.

[0184] "Methods for optimizing the performance of customized content through data analysis" refers to methods of evaluating and analyzing the effectiveness and impact of content, and improving the quality and effectiveness of the content based on the results.

[0185] This invention is a system that generates personalized content while taking user emotions into consideration. First, the user inputs instructions and goal information regarding the content through a terminal. This information is sent to a server, which uses an emotion engine to analyze the user's emotions based on this information. The emotion engine analyzes the user's emotional state from the input information and selects the optimal machine learning model based on the results. Using the selected model, the server automatically generates content in an appropriate style and tone.

[0186] The generated content is customized according to the user's emotions and ultimately presented to the user. Users can provide feedback on the content provided. Based on this feedback, the server uses the emotion engine again to make necessary adjustments and optimize the style and tone of the content. In addition, the performance of the content is evaluated through data analysis, and as a result, the content provided is best suited to the user's needs and objectives.

[0187] As a concrete example, suppose a user wants to create a message for a celebratory event. In this case, the user enters a prompt such as, "I want to create a message in a bright and friendly tone." The emotion engine analyzes this input, selects a text generation model that reflects positive emotions, and generates content that aligns with the user's intentions.

[0188] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0189] Step 1:

[0190] The user uses a device to input instructions and goal information regarding the content they want to generate. This input is structured as prompts. The entered prompts serve to concretize the user's intentions and desired emotions.

[0191] Step 2:

[0192] The terminal sends the prompt text entered by the user to the server. The server receives this prompt text and analyzes the user's emotional state using an emotion engine. Data processing takes place here, and the prompt text is converted into emotional features. The user's emotional information is obtained as output.

[0193] Step 3:

[0194] The server selects the most suitable machine learning model based on the analysis results. This process takes emotional information as input and identifies the appropriate generative AI model. The selected generative model is obtained as output.

[0195] Step 4:

[0196] Using the selected machine learning model, the server automatically generates content. Here, the style and tone of the content are determined based on the user's sentiment information. The input is the selected model and sentiment information, and the output is the generated content.

[0197] Step 5:

[0198] The generated content is further customized based on the user's sentiment information. If the server receives feedback from the user, it uses the sentiment engine again to make adjustments. The input is the generated content and user feedback, and the output is the customized content.

[0199] Step 6:

[0200] The server analyzes and optimizes the performance of customized content. Data analysis evaluates content views and engagement, providing metrics for optimization. The output is performance-optimized content.

[0201] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0202] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0203] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0204] [Second Embodiment]

[0205] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0206] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0207] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0208] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0209] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0210] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0211] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0212] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0213] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0214] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0215] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0216] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0217] This invention is a system that automates content generation, in which the server utilizes various generation models to generate content based on user-specified instructions and target information. This system enables flexible and rapid content creation to meet diverse user needs.

[0218] The program will operate as follows:

[0219] The user inputs instructions and target information for the content they want to generate using their device and sends this information to the server. The server analyzes the received information and dynamically selects the appropriate generation model. This selection is based on the user's target content and format. For example, a text generation model is selected for generating blog posts, and an image generation model is selected for creating images.

[0220] After the content is generated, the server presents it to the user and customizes it based on user feedback. For example, if a user requests a "blog post about environmental issues," the server selects an appropriate text generation model and generates an article containing comprehensive information, from an introduction to specific examples. The article can then be customized to the user's preference, with adjustments to tone and the inclusion of additional statistical data.

[0221] Furthermore, the server optimizes the performance of the generated content by improving its display ranking through search engine optimization (SEO) and data analysis. In this way, the present invention realizes highly efficient content creation that meets the diverse needs of users and enables its use in various fields.

[0222] The following describes the processing flow.

[0223] Step 1:

[0224] The user uses the device interface to input detailed instructions and goal information for the content they want to generate. This input includes information such as the content type, theme, and style.

[0225] Step 2:

[0226] The terminal sends user input information to the server. The transmitted information is formatted appropriately for use in subsequent processes.

[0227] Step 3:

[0228] The server analyzes the received instructions and target information and selects an appropriate generative model based on this analysis. For example, a text generation model or an image generation model might be selected.

[0229] Step 4:

[0230] The server activates the selected generative model and generates content based on the user's input. During this generation process, content aligned with the objective is created based on an algorithm.

[0231] Step 5:

[0232] The server temporarily stores the generated content and presents it to the user as an initial output. At this stage, the user is asked to review the content and quality.

[0233] Step 6:

[0234] Users can provide additional feedback and request revisions to the presented content through their devices. This includes adjustments to tone and style.

[0235] Step 7:

[0236] The device sends user feedback to the server. The server receives this feedback and customizes it as needed.

[0237] Step 8:

[0238] The server optimizes content performance using SEO measures and data analysis as needed. This helps improve search engine rankings.

[0239] Step 9:

[0240] Once the final content is ready, the server will deliver it to the user. The user will receive and use the content in a format appropriate to their purpose.

[0241] (Example 1)

[0242] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0243] In today's world, generating content that meets the diverse needs of information processing device users requires speed and flexibility. However, conventional technologies struggle to effectively meet these demands, particularly in the complex and inefficient processes of adjusting generated data and improving its visibility.

[0244] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0245] In this invention, the server includes means for a user to input instructions and target information using an information processing device, means for analyzing the instructions and target information and dynamically selecting an appropriate generation algorithm, means for generating data using the generation algorithm, and means for using information retrieval technology to improve the visibility of the adjusted data. This enables efficient content generation and improved visibility while responding to the diverse needs of users of the information processing device.

[0246] An "information processing device" is a device used by users to input instructions and target information, and includes computers, smartphones, and other similar devices.

[0247] "Means for inputting instructions and target information" refers to interfaces or methods for users to input specific requirements and conditions for the content they wish to generate into an information processing device.

[0248] "Methods for dynamically selecting a generation algorithm" refer to the process of analyzing instructions and target information received from the user and selecting the most suitable generation model in real time based on that analysis.

[0249] "Means of generating data" refers to a function that automatically generates content according to instructions and target information using a selected generation algorithm.

[0250] "Means of using information retrieval technology to improve the visibility of adjusted data" refers to methods of using search engine algorithms and data analysis techniques to optimize the display order of generated data and deliver it to a wider audience.

[0251] This invention is an automated system for efficiently generating content that meets the diverse needs of users. Upon receiving user instructions, the server dynamically selects an appropriate generation model according to those instructions and generates the content. Specifically, users input instructions and target information regarding the content they wish to generate using a terminal. For example, a wide range of inputs are possible, such as creating blog posts, producing images, or generating audio content.

[0252] The server analyzes these inputs and selects the appropriate generative AI model. Natural language processing techniques are used for text generation, and image synthesis algorithms are employed for image generation. During this process, the server uses appropriate software to process and calculate data, achieving efficient content generation. Specifically, well-known natural language processing tools are used for text generation, and specialized image algorithms are utilized for image generation.

[0253] The generated content is temporarily stored on the server and presented to the user. User feedback is sent back to the server, which then adjusts the content based on that feedback. This ensures that the user receives the adjusted content they desired.

[0254] As a concrete example, suppose a user enters a prompt such as, "Please generate a beginner's guide to spring gardening, including detailed instructions and recommended plant species, in an easy-to-understand style." In this case, the server selects an appropriate generation model based on the prompt and generates a guide summarizing beginner-friendly gardening information. The characteristic of this invention is that it enables content generation that flexibly responds to the diverse needs of users in this way.

[0255] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0256] Step 1:

[0257] The user uses their device to input instructions and target information for the content they want to generate. Specifically, the user describes their requests regarding the generation of text and images in natural language. For example, they might input a prompt such as, "Please generate a blog post about environmental issues." This prompt is sent to the server via the device. The input data is then used for subsequent processing in response to the user's request.

[0258] Step 2:

[0259] The server analyzes the prompt message received from the user. Using natural language processing techniques, the server performs data analysis to understand the intent and content of the input instructions. Based on this analysis, it selects an appropriate generative AI model. For example, if the requirement is text generation, it selects a text generation model; if the requirement is image generation, it selects an image generation model. The output is information about the selected model, which forms the basis for content generation in the next stage.

[0260] Step 3:

[0261] The server generates content using a selected generative AI model. At this stage, prompt sentences are input to the generative model, and data processing and calculations are performed to generate content in the specified format. For example, a text generation model sequentially generates relevant sentences based on the prompt sentences. This generated content is stored on the server and presented to the user in the next step.

[0262] Step 4:

[0263] The server presents the generated content to the user and receives feedback. The user reviews the output and provides specific feedback as needed, such as "Please adjust the tone" or "Please add more details." This feedback is sent to the server and used for further customization.

[0264] Step 5:

[0265] The server customizes the content based on feedback received from the user. Specifically, it uses a regenerative model to incorporate additional information and adjust styles. The newly processed data is then generated as the final version of the content that meets the user's requirements. This final version is then finalized on the server and proceeds to the optimization step.

[0266] Step 6:

[0267] The server uses information retrieval techniques to improve the visibility of the completed content. It employs search engine optimization (SEO) and data analysis techniques to improve the content's ranking. Specific actions include keyword optimization and metadata adjustment. The output of this step is optimized content, ready to be delivered more efficiently to a wider audience.

[0268] (Application Example 1)

[0269] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0270] In recent years, content distribution services have been required to quickly and efficiently generate and deliver content that meets diverse demands. However, traditional methods have problems in that it is difficult to generate content that aligns with the specific needs of users, and furthermore, optimizing the distribution plan requires a great deal of effort.

[0271] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0272] In this invention, the server includes a device for receiving user requests and target information, a device for selecting an appropriate generation model based on the target information, a device for automatically generating information using the generation model, a device for adjusting the generated information according to user requests, a device for optimizing the performance of the adjusted information, and a device for automatically creating a delivery plan to support content generation and management. This makes it possible to efficiently generate content that meets diverse requests and to deliver it optimally.

[0273] A "device for receiving user requests and goal information" is a device that has the function of receiving and accurately receiving specific requests and goals regarding the content that a user wants to create.

[0274] A "generative model selection device" is a device that selects the most suitable generative AI model based on the received requests and objectives.

[0275] A "device that automatically generates information" is a device that uses a selected generation AI model to automatically create the information and content that users need.

[0276] A "device for adjusting generated information according to user requests" is a device that further modifies and adapts generated content according to the user's specific preferences and feedback.

[0277] A "device for optimizing the performance of adjusted information" is a device that optimizes adjusted content to enhance its performance so that it functions to its fullest potential.

[0278] A "device that automatically creates distribution plans" is a device that has the function of automatically determining and creating schedules and methods for optimally distributing generated and adjusted content.

[0279] The system for implementing this invention uses a server, a user terminal, and a generative AI model as its main components. The user inputs instructions and target information necessary for content generation through the terminal. This information is sent to the server, which analyzes the received information to select an appropriate generative model. Examples of generative models used include GPT (Generative Pretrained Transformer), a model for text generation, and DALL-E, a generative AI for image generation.

[0280] The server automatically generates content using the selected generative model. The generated content is further refined based on detailed user requests and feedback. This refinement allows for customization to include the writing style and detailed information requested by the user.

[0281] Subsequently, the server optimizes the performance of the adjusted content. SEO (Search Engine Optimization) and data analysis tools are utilized for this purpose. Furthermore, the server automatically creates a delivery plan to enable efficient distribution of the generated content.

[0282] For example, if a user wants to generate a blog post about summer activities, they would use the following prompt on their device:

[0283] "Please create a blog post that details activities that can be enjoyed with family in the summer. Include tips for enjoying them safely and ways to keep costs down."

[0284] Based on this prompt sentence, the server can select a relevant generation model and perform the generation and adjustment of the necessary content. As a result, the user can obtain high-quality content in a short time.

[0285] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0286] Step 1:

[0287] The user inputs instructions or target information for the content to be generated using the terminal. This input includes a specific prompt sentence. For example, it could be something like "Please create a blog post that details activities that can be enjoyed with family in the summer." This clarifies the theme and argument of the content to be generated.

[0288] Step 2:

[0289] The terminal sends the input instructions and target information to the server. The server utilizes a machine learning model to analyze this information and understand the user's request. Based on this analysis, a determination is made as to which generation model should be adopted.

[0290] Step 3:

[0291] The server selects an appropriate generation AI model based on the analysis results. Specifically, it selects models such as GPT or DALL-E that are suitable for the given theme. With this selected model, preparations for efficient content generation are completed.

[0292] Step 4:

[0293] The server automatically generates content according to the instructions using a selected generative model. During the generation process, text and images are generated based on the input information. For example, based on prompts, the text of a blog post is output.

[0294] Step 5:

[0295] The generated content is customized on the server to meet user requests. Based on user feedback, the writing style is adjusted and additional information is incorporated. As a result, content that more closely matches the user's expectations is obtained.

[0296] Step 6:

[0297] The server further optimizes the customized content. In this process, search engine optimization (SEO) techniques and data analysis are used to improve the content's online performance.

[0298] Step 7:

[0299] After optimization, the server automatically creates a content delivery plan and prepares the content for delivery at the optimal time and in the best way. This allows users to make more effective use of the content they generate.

[0300] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0301] This invention is a content generation system that takes user emotions into consideration. It selects the optimal generation model based on user instructions and goal information, and adjusts the content using an emotion engine, thereby achieving a high level of customization.

[0302] The program will operate as follows:

[0303] The user inputs instructions and target information regarding the content to be generated through the terminal. This information is sent to the server, and the server analyzes the user's emotions using an emotion engine. Based on the analysis results, the server selects an appropriate generation model and uses that model to generate the content. In this generation process, the user's emotion information is applied to the tone and style of the content.

[0304] The generated content is temporarily stored on the server and presented to the user. At this stage, the user can provide further feedback on the provided content. If there is a request for adjustment in terms of emotions from the user, the server performs analysis again using the emotion engine and optimizes the style and tone of the content.

[0305] As a specific example, when the user wishes to create a "user - friendly tone SNS post about a present", the server analyzes the user's mood with the emotion engine and selects a text generation model with a positive and casual tone. The generated post content is adjusted according to the user's wishes. Finally, the server optimizes the performance of the content through search engine optimization and data analysis and provides it to the user in its final form.

[0306] In this way, by recognizing the user's emotions and reflecting them in the content, a system that can quickly provide high - quality content more in line with the user's intentions is realized.

[0307] The following describes the processing flow.

[0308] Step 1:

[0309] The user inputs instructions such as the theme, purpose, desired style and tone of the content to be generated via the terminal.

[0310] Step 2:

[0311] The terminal sends the user's input information to the server, including the type of content and detailed instructions.

[0312] Step 3:

[0313] The server analyzes the received information and uses an emotion engine to identify the emotions contained in the user's instructions. This allows it to understand the user's intended emotions.

[0314] Step 4:

[0315] The server selects the optimal generative model based on the identified sentiment information. For example, if the sentiment is recognized as "friendly," it will choose a text generation model that matches that tone.

[0316] Step 5:

[0317] The server automatically generates content using a selected generative model. The generated content has a style that reflects the user's intended emotions.

[0318] Step 6:

[0319] The server temporarily stores the generated content and presents it to the user for review. The user reviews this content and provides feedback if any changes are needed.

[0320] Step 7:

[0321] Users may request content adjustments based on the feedback they provide. This may include further emotional adjustments or changes in tone.

[0322] Step 8:

[0323] The server uses the sentiment engine again to adjust the content based on user feedback. The adjusted content is then presented to the user again.

[0324] Step 9:

[0325] The server performs search engine optimization (SEO) and data analysis to enhance the final content quality and optimize the content's online performance.

[0326] Step 10:

[0327] Once the final version of the content is ready, the server will provide it to the user. The user can then use this content as needed.

[0328] (Example 2)

[0329] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0330] In recent years, there has been a growing demand for content that aligns with users' emotions and preferences, but conventional systems have struggled to adequately reflect user intent. Furthermore, the optimization processes required to maximize the performance of the generated content have been insufficient, making it difficult to increase user satisfaction.

[0331] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0332] In this invention, the server includes means for receiving user input information and having an information processing device for analyzing said input information, means for selecting a location information generation device based on the analysis results, and means for generating information using the location information generation device. This makes it possible to generate high-quality content that reflects the user's emotions and intentions. Furthermore, user satisfaction can be increased by adjusting the generated content with an emotion analysis device and optimizing the display performance with an evaluation device.

[0333] A "user" is the entity that inputs instructions and target information into an information system and receives the generated content.

[0334] "Input information" refers to the instructions and goal information that users provide to the system for content generation.

[0335] An "information processing device" is a device that analyzes input information received from a user and creates basic data for selecting an appropriate generative model.

[0336] A "location information generation device" refers to a generation model selected to generate optimal content based on user input information and analysis results.

[0337] An "emotion analysis device" is a device that adjusts generated content according to the user's emotions and instructions, thereby achieving an expression that aligns with the user's intentions.

[0338] An "evaluation device" is a device used to analyze and improve the performance of generated content in order to optimize its display performance.

[0339] In the embodiment of the invention, this system uses a combination of various information processing devices and software to generate content that reflects the user's intent. The specific implementation method is described below.

[0340] The user uses a terminal to input specific instructions and goal information about the content they want to generate. This information includes what they want to express and the desired style and tone. For example, they might give the instruction, "Write a fun post introducing birthday presents in a friendly tone." This input information is sent to the server as a prompt.

[0341] The server passes the received prompt message to the information processing unit, which then analyzes the input information. This analysis uses natural language processing techniques to understand the content and extract the user's emotional state and the intent behind the instructions. Based on these analysis results, the server selects the most appropriate generative AI model. This selection uses a generative model that excels at generating textual information.

[0342] The selected generative AI model generates content using user prompts and analysis results as input. This generation process utilizes an emotion analyzer to adjust the content according to the user's emotions and instructions. Specifically, it is configured to generate content with a casual and approachable writing style.

[0343] The generated content is temporarily stored on the server and presented to the user as it is received. The user reviews this content and provides feedback via their device as needed. If the user requests further adjustments at this stage, the server again uses sentiment analysis to refine the content.

[0344] In the final stage, the server uses evaluation equipment to optimize the performance of the generated content. This optimization utilizes search engine optimization techniques and data analysis tools to maximize content exposure and effectiveness.

[0345] Thus, this system can quickly deliver high-quality content that prioritizes and appropriately reflects the user's emotions and intentions.

[0346] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0347] Step 1:

[0348] The user enters instructions and goal information about the content they want to generate using their device. This input is in text format and includes details such as the content's subject, tone, and style. An example of input data might be, "I want to create a social media post about birthday presents in a friendly tone." This information is sent to the server as a prompt.

[0349] Step 2:

[0350] The server forwards the received prompt message to the information processing unit, where the data is analyzed. Using natural language processing techniques, the system analyzes keywords and context contained in the user's instructions to infer the user's emotions and intentions. The analysis results are temporarily stored in a database for use in the next step.

[0351] Step 3:

[0352] The server selects the most suitable generative AI model based on the analysis results. Here, a selection algorithm is used to choose a model that matches the tone and style desired by the user. The selected generative AI model might, for example, excel at producing casual writing styles. The selection results are output as metadata and used in the content generation process.

[0353] Step 4:

[0354] The server generates content using the selected generative AI model and prompt text as input. The generative AI model automatically generates content based on the specified tone and style using the input information. The generated content is text data that faithfully reflects the user's instructions. This is output as generated data, and the process proceeds to the next adjustment step.

[0355] Step 5:

[0356] The server re-evaluates the content generated using the sentiment analyzer and adjusts the tone and style as needed. The sentiment analyzer receives user feedback and performs additional data processing to adjust the tone of the content. This process adjusts the tone based on feedback such as "make it brighter." The adjusted content is output as updated data.

[0357] Step 6:

[0358] Ultimately, the server optimizes content performance using evaluation equipment. Search engine optimization and data analysis tools are used to optimize the generated content's online visibility and user engagement. This typically involves adjusting keyword density and optimizing meta information. The optimized content is then delivered to the user as the final output.

[0359] (Application Example 2)

[0360] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0361] Traditional content generation tools have a weakness: they lack sufficient customization to accommodate individual user emotions and styles, making it difficult to quickly deliver personalized content that meets user expectations. Furthermore, they lack mechanisms to properly incorporate feedback to optimize the performance of the generated content.

[0362] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0363] In this invention, the server includes means for receiving user instructions and goal information, means for selecting an appropriate machine learning model based on the goal information, means for automatically generating content using the machine learning model, means for customizing the style and tone of the generated content based on the user's emotional information, and means for optimizing the performance of the customized content through data analysis. This enables the rapid generation of personalized content that responds to the individual emotions of the user and the optimization of its performance.

[0364] "Means for receiving user instructions and goal information" refers to a system for users to input specific requests or desired outcomes regarding content creation.

[0365] "Means for selecting an appropriate machine learning model" refers to algorithms and processes for selecting the most suitable machine learning model based on user instructions and target information.

[0366] "Methods for automatically generating content using machine learning models" refers to methods for automatically creating content based on input information by utilizing selected machine learning models.

[0367] "Means of customizing the style and tone of generated content based on user emotional information" refers to technologies that reflect user emotional data in generated content and adjust its expression and tone.

[0368] "Methods for optimizing the performance of customized content through data analysis" refers to methods of evaluating and analyzing the effectiveness and impact of content, and improving the quality and effectiveness of the content based on the results.

[0369] This invention is a system that generates personalized content while taking user emotions into consideration. First, the user inputs instructions and goal information regarding the content through a terminal. This information is sent to a server, which uses an emotion engine to analyze the user's emotions based on this information. The emotion engine analyzes the user's emotional state from the input information and selects the optimal machine learning model based on the results. Using the selected model, the server automatically generates content in an appropriate style and tone.

[0370] The generated content is customized according to the user's emotions and ultimately presented to the user. Users can provide feedback on the content provided. Based on this feedback, the server uses the emotion engine again to make necessary adjustments and optimize the style and tone of the content. In addition, the performance of the content is evaluated through data analysis, and as a result, the content provided is best suited to the user's needs and objectives.

[0371] As a concrete example, suppose a user wants to create a message for a celebratory event. In this case, the user enters a prompt such as, "I want to create a message in a bright and friendly tone." The emotion engine analyzes this input, selects a text generation model that reflects positive emotions, and generates content that aligns with the user's intentions.

[0372] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0373] Step 1:

[0374] The user uses a device to input instructions and goal information regarding the content they want to generate. This input is structured as prompts. The entered prompts serve to concretize the user's intentions and desired emotions.

[0375] Step 2:

[0376] The terminal sends the prompt text entered by the user to the server. The server receives this prompt text and analyzes the user's emotional state using an emotion engine. Data processing takes place here, and the prompt text is converted into emotional features. The user's emotional information is obtained as output.

[0377] Step 3:

[0378] The server selects the most suitable machine learning model based on the analysis results. This process takes emotional information as input and identifies the appropriate generative AI model. The selected generative model is obtained as output.

[0379] Step 4:

[0380] Using the selected machine learning model, the server automatically generates content. Here, the style and tone of the content are determined based on the user's sentiment information. The input is the selected model and sentiment information, and the output is the generated content.

[0381] Step 5:

[0382] The generated content is further customized based on the user's sentiment information. If the server receives feedback from the user, it uses the sentiment engine again to make adjustments. The input is the generated content and user feedback, and the output is the customized content.

[0383] Step 6:

[0384] The server analyzes and optimizes the performance of customized content. Data analysis evaluates content views and engagement, providing metrics for optimization. The output is performance-optimized content.

[0385] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0386] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0387] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0388] [Third Embodiment]

[0389] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0390] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0391] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0392] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0393] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0394] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0395] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0396] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0397] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0398] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0399] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0400] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0401] This invention is a system that automates content generation, in which the server utilizes various generation models to generate content based on user-specified instructions and target information. This system enables flexible and rapid content creation to meet diverse user needs.

[0402] The program will operate as follows:

[0403] The user inputs instructions and target information for the content they want to generate using their device and sends this information to the server. The server analyzes the received information and dynamically selects the appropriate generation model. This selection is based on the user's target content and format. For example, a text generation model is selected for generating blog posts, and an image generation model is selected for creating images.

[0404] After the content is generated, the server presents it to the user and customizes it based on user feedback. For example, if a user requests a "blog post about environmental issues," the server selects an appropriate text generation model and generates an article containing comprehensive information, from an introduction to specific examples. The article can then be customized to the user's preference, with adjustments to tone and the inclusion of additional statistical data.

[0405] Furthermore, the server optimizes the performance of the generated content by improving its display ranking through search engine optimization (SEO) and data analysis. In this way, the present invention realizes highly efficient content creation that meets the diverse needs of users and enables its use in various fields.

[0406] The following describes the processing flow.

[0407] Step 1:

[0408] The user uses the device interface to input detailed instructions and goal information for the content they want to generate. This input includes information such as the content type, theme, and style.

[0409] Step 2:

[0410] The terminal sends user input information to the server. The transmitted information is formatted appropriately for use in subsequent processes.

[0411] Step 3:

[0412] The server analyzes the received instructions and target information and selects an appropriate generative model based on this analysis. For example, a text generation model or an image generation model might be selected.

[0413] Step 4:

[0414] The server activates the selected generative model and generates content based on the user's input. During this generation process, content aligned with the objective is created based on an algorithm.

[0415] Step 5:

[0416] The server temporarily stores the generated content and presents it to the user as an initial output. At this stage, the user is asked to review the content and quality.

[0417] Step 6:

[0418] Users can provide additional feedback and request revisions to the presented content through their devices. This includes adjustments to tone and style.

[0419] Step 7:

[0420] The device sends user feedback to the server. The server receives this feedback and customizes it as needed.

[0421] Step 8:

[0422] The server optimizes content performance using SEO measures and data analysis as needed. This helps improve search engine rankings.

[0423] Step 9:

[0424] Once the final content is ready, the server will deliver it to the user. The user will receive and use the content in a format appropriate to their purpose.

[0425] (Example 1)

[0426] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0427] In today's world, generating content that meets the diverse needs of information processing device users requires speed and flexibility. However, conventional technologies struggle to effectively meet these demands, particularly in the complex and inefficient processes of adjusting generated data and improving its visibility.

[0428] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0429] In this invention, the server includes means for a user to input instructions and target information using an information processing device, means for analyzing the instructions and target information and dynamically selecting an appropriate generation algorithm, means for generating data using the generation algorithm, and means for using information retrieval technology to improve the visibility of the adjusted data. This enables efficient content generation and improved visibility while responding to the diverse needs of users of the information processing device.

[0430] An "information processing device" is a device used by users to input instructions and target information, and includes computers, smartphones, and other similar devices.

[0431] "Means for inputting instructions and target information" refers to interfaces or methods for users to input specific requirements and conditions for the content they wish to generate into an information processing device.

[0432] "Methods for dynamically selecting a generation algorithm" refer to the process of analyzing instructions and target information received from the user and selecting the most suitable generation model in real time based on that analysis.

[0433] "Means of generating data" refers to a function that automatically generates content according to instructions and target information using a selected generation algorithm.

[0434] "Means of using information retrieval technology to improve the visibility of adjusted data" refers to methods of using search engine algorithms and data analysis techniques to optimize the display order of generated data and deliver it to a wider audience.

[0435] This invention is an automated system for efficiently generating content that meets the diverse needs of users. Upon receiving user instructions, the server dynamically selects an appropriate generation model according to those instructions and generates the content. Specifically, users input instructions and target information regarding the content they wish to generate using a terminal. For example, a wide range of inputs are possible, such as creating blog posts, producing images, or generating audio content.

[0436] The server analyzes these inputs and selects the appropriate generative AI model. Natural language processing techniques are used for text generation, and image synthesis algorithms are employed for image generation. During this process, the server uses appropriate software to process and calculate data, achieving efficient content generation. Specifically, well-known natural language processing tools are used for text generation, and specialized image algorithms are utilized for image generation.

[0437] The generated content is temporarily stored on the server and presented to the user. User feedback is sent back to the server, which then adjusts the content based on that feedback. This ensures that the user receives the adjusted content they desired.

[0438] As a concrete example, suppose a user enters a prompt such as, "Please generate a beginner's guide to spring gardening, including detailed instructions and recommended plant species, in an easy-to-understand style." In this case, the server selects an appropriate generation model based on the prompt and generates a guide summarizing beginner-friendly gardening information. The characteristic of this invention is that it enables content generation that flexibly responds to the diverse needs of users in this way.

[0439] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0440] Step 1:

[0441] The user uses their device to input instructions and target information for the content they want to generate. Specifically, the user describes their requests regarding the generation of text and images in natural language. For example, they might input a prompt such as, "Please generate a blog post about environmental issues." This prompt is sent to the server via the device. The input data is then used for subsequent processing in response to the user's request.

[0442] Step 2:

[0443] The server analyzes the prompt message received from the user. Using natural language processing techniques, the server performs data analysis to understand the intent and content of the input instructions. Based on this analysis, it selects an appropriate generative AI model. For example, if the requirement is text generation, it selects a text generation model; if the requirement is image generation, it selects an image generation model. The output is information about the selected model, which forms the basis for content generation in the next stage.

[0444] Step 3:

[0445] The server generates content using a selected generative AI model. At this stage, prompt sentences are input to the generative model, and data processing and calculations are performed to generate content in the specified format. For example, a text generation model sequentially generates relevant sentences based on the prompt sentences. This generated content is stored on the server and presented to the user in the next step.

[0446] Step 4:

[0447] The server presents the generated content to the user and receives feedback. The user reviews the output and provides specific feedback as needed, such as "Please adjust the tone" or "Please add more details." This feedback is sent to the server and used for further customization.

[0448] Step 5:

[0449] The server customizes the content based on feedback received from the user. Specifically, it uses a regenerative model to incorporate additional information and adjust styles. The newly processed data is then generated as the final version of the content that meets the user's requirements. This final version is then finalized on the server and proceeds to the optimization step.

[0450] Step 6:

[0451] The server uses information retrieval techniques to improve the visibility of the completed content. It employs search engine optimization (SEO) and data analysis techniques to improve the content's ranking. Specific actions include keyword optimization and metadata adjustment. The output of this step is optimized content, ready to be delivered more efficiently to a wider audience.

[0452] (Application Example 1)

[0453] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0454] In recent years, content distribution services have been required to quickly and efficiently generate and deliver content that meets diverse demands. However, traditional methods have problems in that it is difficult to generate content that aligns with the specific needs of users, and furthermore, optimizing the distribution plan requires a great deal of effort.

[0455] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0456] In this invention, the server includes a device for receiving user requests and target information, a device for selecting an appropriate generation model based on the target information, a device for automatically generating information using the generation model, a device for adjusting the generated information according to user requests, a device for optimizing the performance of the adjusted information, and a device for automatically creating a delivery plan to support content generation and management. This makes it possible to efficiently generate content that meets diverse requests and to deliver it optimally.

[0457] A "device for receiving user requests and goal information" is a device that has the function of receiving and accurately receiving specific requests and goals regarding the content that a user wants to create.

[0458] A "generative model selection device" is a device that selects the most suitable generative AI model based on the received requests and objectives.

[0459] A "device that automatically generates information" is a device that uses a selected generation AI model to automatically create the information and content that users need.

[0460] A "device for adjusting generated information according to user requests" is a device that further modifies and adapts generated content according to the user's specific preferences and feedback.

[0461] A "device for optimizing the performance of adjusted information" is a device that optimizes adjusted content to enhance its performance so that it functions to its fullest potential.

[0462] A "device that automatically creates distribution plans" is a device that has the function of automatically determining and creating schedules and methods for optimally distributing generated and adjusted content.

[0463] The system for implementing this invention uses a server, a user terminal, and a generative AI model as its main components. The user inputs instructions and target information necessary for content generation through the terminal. This information is sent to the server, which analyzes the received information to select an appropriate generative model. Examples of generative models used include GPT (Generative Pretrained Transformer), a model for text generation, and DALL-E, a generative AI for image generation.

[0464] The server automatically generates content using the selected generative model. The generated content is further refined based on detailed user requests and feedback. This refinement allows for customization to include the writing style and detailed information requested by the user.

[0465] Subsequently, the server optimizes the performance of the adjusted content. SEO (Search Engine Optimization) and data analysis tools are utilized for this purpose. Furthermore, the server automatically creates a delivery plan to enable efficient distribution of the generated content.

[0466] For example, if a user wants to generate a blog post about summer activities, they would use the following prompt on their device:

[0467] "Create a blog post detailing fun summer activities for the whole family. The post should include tips for safety and ways to save money."

[0468] Based on this prompt, the server can select the appropriate generative model and generate and adjust the necessary content. This allows users to obtain high-quality content in a short amount of time.

[0469] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0470] Step 1:

[0471] The user inputs instructions and goal information for the content they want to generate using their device. This input includes specific prompts, such as, "Create a blog post detailing fun summer activities for the whole family." This clarifies the theme and focus of the content to be generated.

[0472] Step 2:

[0473] The terminal sends the input instructions and target information to the server. The server uses machine learning models to analyze this information and understand the user's requests. This analysis determines which generative model should be adopted.

[0474] Step 3:

[0475] The server selects an appropriate generation AI model based on the analysis results. Specifically, it chooses a model such as GPT or DALL-E that is suitable for the given theme. With this selected model, the server is ready for efficient content generation.

[0476] Step 4:

[0477] The server automatically generates content according to the instructions using a selected generative model. During the generation process, text and images are generated based on the input information. For example, based on prompts, the text of a blog post is output.

[0478] Step 5:

[0479] The generated content is customized on the server to meet user requests. Based on user feedback, the writing style is adjusted and additional information is incorporated. As a result, content that more closely matches the user's expectations is obtained.

[0480] Step 6:

[0481] The server further optimizes the customized content. In this process, search engine optimization (SEO) techniques and data analysis are used to improve the content's online performance.

[0482] Step 7:

[0483] After optimization, the server automatically creates a content delivery plan and prepares the content for delivery at the optimal time and in the best way. This allows users to make more effective use of the content they generate.

[0484] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0485] This invention is a content generation system that takes user emotions into consideration. It selects the optimal generation model based on user instructions and goal information, and adjusts the content using an emotion engine, thereby achieving a high level of customization.

[0486] The program will operate as follows:

[0487] The user inputs instructions and goal information about the content they want to generate through their device. This information is sent to the server, which uses an emotion engine to analyze the user's emotions. Based on the analysis, the server selects an appropriate generative model and uses that model to generate the content. In this generation process, the user's emotional information is applied to the tone and style of the content.

[0488] The generated content is temporarily stored on the server and then presented to the user. At this stage, the user can provide further feedback on the content provided. If the user requests emotional adjustments, the server uses the sentiment engine again to analyze and optimize the style and tone of the content.

[0489] For example, if a user wants to create a friendly-toned social media post about a gift, the server analyzes the user's mood using an emotion engine and selects a text generation model with a positive and casual tone. The generated post content is then adjusted according to the user's preferences. Finally, the server optimizes the content's performance through search engine optimization and data analysis before delivering it to the user in its final form.

[0490] In this way, by recognizing user emotions and reflecting them in the content, a system can be realized that quickly delivers high-quality content that better aligns with the user's intentions.

[0491] The following describes the processing flow.

[0492] Step 1:

[0493] The user inputs instructions regarding the theme, purpose, desired style, and tone of the content to be generated via the device.

[0494] Step 2:

[0495] The terminal sends the user's input information to the server, including the type of content and detailed instructions.

[0496] Step 3:

[0497] The server analyzes the received information and uses an emotion engine to identify the emotions contained in the user's instructions. This allows it to understand the user's intended emotions.

[0498] Step 4:

[0499] The server selects the optimal generative model based on the identified sentiment information. For example, if the sentiment is recognized as "friendly," it will choose a text generation model that matches that tone.

[0500] Step 5:

[0501] The server automatically generates content using a selected generative model. The generated content has a style that reflects the user's intended emotions.

[0502] Step 6:

[0503] The server temporarily stores the generated content and presents it to the user for review. The user reviews this content and provides feedback if any changes are needed.

[0504] Step 7:

[0505] Users may request content adjustments based on the feedback they provide. This may include further emotional adjustments or changes in tone.

[0506] Step 8:

[0507] The server uses the sentiment engine again to adjust the content based on user feedback. The adjusted content is then presented to the user again.

[0508] Step 9:

[0509] The server performs search engine optimization (SEO) and data analysis to enhance the final content quality and optimize the content's online performance.

[0510] Step 10:

[0511] Once the final version of the content is ready, the server will provide it to the user. The user can then use this content as needed.

[0512] (Example 2)

[0513] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0514] In recent years, there has been a growing demand for content that aligns with users' emotions and preferences, but conventional systems have struggled to adequately reflect user intent. Furthermore, the optimization processes required to maximize the performance of the generated content have been insufficient, making it difficult to increase user satisfaction.

[0515] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0516] In this invention, the server includes means for receiving user input information and having an information processing device for analyzing said input information, means for selecting a location information generation device based on the analysis results, and means for generating information using the location information generation device. This makes it possible to generate high-quality content that reflects the user's emotions and intentions. Furthermore, user satisfaction can be increased by adjusting the generated content with an emotion analysis device and optimizing the display performance with an evaluation device.

[0517] A "user" is the entity that inputs instructions and target information into an information system and receives the generated content.

[0518] "Input information" refers to the instructions and goal information that users provide to the system for content generation.

[0519] An "information processing device" is a device that analyzes input information received from a user and creates basic data for selecting an appropriate generative model.

[0520] A "location information generation device" refers to a generation model selected to generate optimal content based on user input information and analysis results.

[0521] An "emotion analysis device" is a device that adjusts generated content according to the user's emotions and instructions, thereby achieving an expression that aligns with the user's intentions.

[0522] An "evaluation device" is a device used to analyze and improve the performance of generated content in order to optimize its display performance.

[0523] In the embodiment of the invention, this system uses a combination of various information processing devices and software to generate content that reflects the user's intent. The specific implementation method is described below.

[0524] The user uses a terminal to input specific instructions and goal information about the content they want to generate. This information includes what they want to express and the desired style and tone. For example, they might give the instruction, "Write a fun post introducing birthday presents in a friendly tone." This input information is sent to the server as a prompt.

[0525] The server passes the received prompt message to the information processing unit, which then analyzes the input information. This analysis uses natural language processing techniques to understand the content and extract the user's emotional state and the intent behind the instructions. Based on these analysis results, the server selects the most appropriate generative AI model. This selection uses a generative model that excels at generating textual information.

[0526] The selected generative AI model generates content using user prompts and analysis results as input. This generation process utilizes an emotion analyzer to adjust the content according to the user's emotions and instructions. Specifically, it is configured to generate content with a casual and approachable writing style.

[0527] The generated content is temporarily stored on the server and presented to the user as it is received. The user reviews this content and provides feedback via their device as needed. If the user requests further adjustments at this stage, the server again uses sentiment analysis to refine the content.

[0528] In the final stage, the server uses evaluation equipment to optimize the performance of the generated content. This optimization utilizes search engine optimization techniques and data analysis tools to maximize content exposure and effectiveness.

[0529] Thus, this system can quickly deliver high-quality content that prioritizes and appropriately reflects the user's emotions and intentions.

[0530] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0531] Step 1:

[0532] The user enters instructions and goal information about the content they want to generate using their device. This input is in text format and includes details such as the content's subject, tone, and style. An example of input data might be, "I want to create a social media post about birthday presents in a friendly tone." This information is sent to the server as a prompt.

[0533] Step 2:

[0534] The server forwards the received prompt message to the information processing unit, where the data is analyzed. Using natural language processing techniques, the system analyzes keywords and context contained in the user's instructions to infer the user's emotions and intentions. The analysis results are temporarily stored in a database for use in the next step.

[0535] Step 3:

[0536] The server selects the most suitable generative AI model based on the analysis results. Here, a selection algorithm is used to choose a model that matches the tone and style desired by the user. The selected generative AI model might, for example, excel at producing casual writing styles. The selection results are output as metadata and used in the content generation process.

[0537] Step 4:

[0538] The server generates content using the selected generative AI model and prompt text as input. The generative AI model automatically generates content based on the specified tone and style using the input information. The generated content is text data that faithfully reflects the user's instructions. This is output as generated data, and the process proceeds to the next adjustment step.

[0539] Step 5:

[0540] The server re-evaluates the content generated using the sentiment analyzer and adjusts the tone and style as needed. The sentiment analyzer receives user feedback and performs additional data processing to adjust the tone of the content. This process adjusts the tone based on feedback such as "make it brighter." The adjusted content is output as updated data.

[0541] Step 6:

[0542] Ultimately, the server optimizes content performance using evaluation equipment. Search engine optimization and data analysis tools are used to optimize the generated content's online visibility and user engagement. This typically involves adjusting keyword density and optimizing meta information. The optimized content is then delivered to the user as the final output.

[0543] (Application Example 2)

[0544] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0545] Traditional content generation tools have a weakness: they lack sufficient customization to accommodate individual user emotions and styles, making it difficult to quickly deliver personalized content that meets user expectations. Furthermore, they lack mechanisms to properly incorporate feedback to optimize the performance of the generated content.

[0546] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0547] In this invention, the server includes means for receiving user instructions and goal information, means for selecting an appropriate machine learning model based on the goal information, means for automatically generating content using the machine learning model, means for customizing the style and tone of the generated content based on the user's emotional information, and means for optimizing the performance of the customized content through data analysis. This enables the rapid generation of personalized content that responds to the individual emotions of the user and the optimization of its performance.

[0548] "Means for receiving user instructions and goal information" refers to a system for users to input specific requests or desired outcomes regarding content creation.

[0549] "Means for selecting an appropriate machine learning model" refers to algorithms and processes for selecting the most suitable machine learning model based on user instructions and target information.

[0550] "Methods for automatically generating content using machine learning models" refers to methods for automatically creating content based on input information by utilizing selected machine learning models.

[0551] "Means of customizing the style and tone of generated content based on user emotional information" refers to technologies that reflect user emotional data in generated content and adjust its expression and tone.

[0552] "Methods for optimizing the performance of customized content through data analysis" refers to methods of evaluating and analyzing the effectiveness and impact of content, and improving the quality and effectiveness of the content based on the results.

[0553] This invention is a system that generates personalized content while taking user emotions into consideration. First, the user inputs instructions and goal information regarding the content through a terminal. This information is sent to a server, which uses an emotion engine to analyze the user's emotions based on this information. The emotion engine analyzes the user's emotional state from the input information and selects the optimal machine learning model based on the results. Using the selected model, the server automatically generates content in an appropriate style and tone.

[0554] The generated content is customized according to the user's emotions and ultimately presented to the user. Users can provide feedback on the content provided. Based on this feedback, the server uses the emotion engine again to make necessary adjustments and optimize the style and tone of the content. In addition, the performance of the content is evaluated through data analysis, and as a result, the content provided is best suited to the user's needs and objectives.

[0555] As a concrete example, suppose a user wants to create a message for a celebratory event. In this case, the user enters a prompt such as, "I want to create a message in a bright and friendly tone." The emotion engine analyzes this input, selects a text generation model that reflects positive emotions, and generates content that aligns with the user's intentions.

[0556] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0557] Step 1:

[0558] The user uses a device to input instructions and goal information regarding the content they want to generate. This input is structured as prompts. The entered prompts serve to concretize the user's intentions and desired emotions.

[0559] Step 2:

[0560] The terminal sends the prompt text entered by the user to the server. The server receives this prompt text and analyzes the user's emotional state using an emotion engine. Data processing takes place here, and the prompt text is converted into emotional features. The user's emotional information is obtained as output.

[0561] Step 3:

[0562] The server selects the most suitable machine learning model based on the analysis results. This process takes emotional information as input and identifies the appropriate generative AI model. The selected generative model is obtained as output.

[0563] Step 4:

[0564] Using the selected machine learning model, the server automatically generates content. Here, the style and tone of the content are determined based on the user's sentiment information. The input is the selected model and sentiment information, and the output is the generated content.

[0565] Step 5:

[0566] The generated content is further customized based on the user's sentiment information. If the server receives feedback from the user, it uses the sentiment engine again to make adjustments. The input is the generated content and user feedback, and the output is the customized content.

[0567] Step 6:

[0568] The server analyzes and optimizes the performance of customized content. Data analysis evaluates content views and engagement, providing metrics for optimization. The output is performance-optimized content.

[0569] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0570] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0571] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0572] [Fourth Embodiment]

[0573] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0574] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0575] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0576] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0577] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0578] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0579] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0580] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0581] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0582] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0583] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0584] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0585] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0586] This invention is a system that automates content generation, in which the server utilizes various generation models to generate content based on user-specified instructions and target information. This system enables flexible and rapid content creation to meet diverse user needs.

[0587] The program will operate as follows:

[0588] The user inputs instructions and target information for the content they want to generate using their device and sends this information to the server. The server analyzes the received information and dynamically selects the appropriate generation model. This selection is based on the user's target content and format. For example, a text generation model is selected for generating blog posts, and an image generation model is selected for creating images.

[0589] After the content is generated, the server presents it to the user and customizes it based on user feedback. For example, if a user requests a "blog post about environmental issues," the server selects an appropriate text generation model and generates an article containing comprehensive information, from an introduction to specific examples. The article can then be customized to the user's preference, with adjustments to tone and the inclusion of additional statistical data.

[0590] Furthermore, the server optimizes the performance of the generated content by improving its display ranking through search engine optimization (SEO) and data analysis. In this way, the present invention realizes highly efficient content creation that meets the diverse needs of users and enables its use in various fields.

[0591] The following describes the processing flow.

[0592] Step 1:

[0593] The user uses the device interface to input detailed instructions and goal information for the content they want to generate. This input includes information such as the content type, theme, and style.

[0594] Step 2:

[0595] The terminal sends user input information to the server. The transmitted information is formatted appropriately for use in subsequent processes.

[0596] Step 3:

[0597] The server analyzes the received instructions and target information and selects an appropriate generative model based on this analysis. For example, a text generation model or an image generation model might be selected.

[0598] Step 4:

[0599] The server activates the selected generative model and generates content based on the user's input. During this generation process, content aligned with the objective is created based on an algorithm.

[0600] Step 5:

[0601] The server temporarily stores the generated content and presents it to the user as an initial output. At this stage, the user is asked to review the content and quality.

[0602] Step 6:

[0603] Users can provide additional feedback and request revisions to the presented content through their devices. This includes adjustments to tone and style.

[0604] Step 7:

[0605] The device sends user feedback to the server. The server receives this feedback and customizes it as needed.

[0606] Step 8:

[0607] The server optimizes content performance using SEO measures and data analysis as needed. This helps improve search engine rankings.

[0608] Step 9:

[0609] Once the final content is ready, the server will deliver it to the user. The user will receive and use the content in a format appropriate to their purpose.

[0610] (Example 1)

[0611] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0612] In today's world, generating content that meets the diverse needs of information processing device users requires speed and flexibility. However, conventional technologies struggle to effectively meet these demands, particularly in the complex and inefficient processes of adjusting generated data and improving its visibility.

[0613] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0614] In this invention, the server includes means for a user to input instructions and target information using an information processing device, means for analyzing the instructions and target information and dynamically selecting an appropriate generation algorithm, means for generating data using the generation algorithm, and means for using information retrieval technology to improve the visibility of the adjusted data. This enables efficient content generation and improved visibility while responding to the diverse needs of users of the information processing device.

[0615] An "information processing device" is a device used by users to input instructions and target information, and includes computers, smartphones, and other similar devices.

[0616] "Means for inputting instructions and target information" refers to interfaces or methods for users to input specific requirements and conditions for the content they wish to generate into an information processing device.

[0617] "Methods for dynamically selecting a generation algorithm" refer to the process of analyzing instructions and target information received from the user and selecting the most suitable generation model in real time based on that analysis.

[0618] "Means of generating data" refers to a function that automatically generates content according to instructions and target information using a selected generation algorithm.

[0619] "Means of using information retrieval technology to improve the visibility of adjusted data" refers to methods of using search engine algorithms and data analysis techniques to optimize the display order of generated data and deliver it to a wider audience.

[0620] This invention is an automated system for efficiently generating content that meets the diverse needs of users. Upon receiving user instructions, the server dynamically selects an appropriate generation model according to those instructions and generates the content. Specifically, users input instructions and target information regarding the content they wish to generate using a terminal. For example, a wide range of inputs are possible, such as creating blog posts, producing images, or generating audio content.

[0621] The server analyzes these inputs and selects the appropriate generative AI model. Natural language processing techniques are used for text generation, and image synthesis algorithms are employed for image generation. During this process, the server uses appropriate software to process and calculate data, achieving efficient content generation. Specifically, well-known natural language processing tools are used for text generation, and specialized image algorithms are utilized for image generation.

[0622] The generated content is temporarily stored on the server and presented to the user. User feedback is sent back to the server, which then adjusts the content based on that feedback. This ensures that the user receives the adjusted content they desired.

[0623] As a concrete example, suppose a user enters a prompt such as, "Please generate a beginner's guide to spring gardening, including detailed instructions and recommended plant species, in an easy-to-understand style." In this case, the server selects an appropriate generation model based on the prompt and generates a guide summarizing beginner-friendly gardening information. The characteristic of this invention is that it enables content generation that flexibly responds to the diverse needs of users in this way.

[0624] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0625] Step 1:

[0626] The user uses their device to input instructions and target information for the content they want to generate. Specifically, the user describes their requests regarding the generation of text and images in natural language. For example, they might input a prompt such as, "Please generate a blog post about environmental issues." This prompt is sent to the server via the device. The input data is then used for subsequent processing in response to the user's request.

[0627] Step 2:

[0628] The server analyzes the prompt message received from the user. Using natural language processing techniques, the server performs data analysis to understand the intent and content of the input instructions. Based on this analysis, it selects an appropriate generative AI model. For example, if the requirement is text generation, it selects a text generation model; if the requirement is image generation, it selects an image generation model. The output is information about the selected model, which forms the basis for content generation in the next stage.

[0629] Step 3:

[0630] The server generates content using a selected generative AI model. At this stage, prompt sentences are input to the generative model, and data processing and calculations are performed to generate content in the specified format. For example, a text generation model sequentially generates relevant sentences based on the prompt sentences. This generated content is stored on the server and presented to the user in the next step.

[0631] Step 4:

[0632] The server presents the generated content to the user and receives feedback. The user reviews the output and provides specific feedback as needed, such as "Please adjust the tone" or "Please add more details." This feedback is sent to the server and used for further customization.

[0633] Step 5:

[0634] The server customizes the content based on feedback received from the user. Specifically, it uses a regenerative model to incorporate additional information and adjust styles. The newly processed data is then generated as the final version of the content that meets the user's requirements. This final version is then finalized on the server and proceeds to the optimization step.

[0635] Step 6:

[0636] The server uses information retrieval techniques to improve the visibility of the completed content. It employs search engine optimization (SEO) and data analysis techniques to improve the content's ranking. Specific actions include keyword optimization and metadata adjustment. The output of this step is optimized content, ready to be delivered more efficiently to a wider audience.

[0637] (Application Example 1)

[0638] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0639] In recent years, content distribution services have been required to quickly and efficiently generate and deliver content that meets diverse demands. However, traditional methods have problems in that it is difficult to generate content that aligns with the specific needs of users, and furthermore, optimizing the distribution plan requires a great deal of effort.

[0640] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0641] In this invention, the server includes a device for receiving user requests and target information, a device for selecting an appropriate generation model based on the target information, a device for automatically generating information using the generation model, a device for adjusting the generated information according to user requests, a device for optimizing the performance of the adjusted information, and a device for automatically creating a delivery plan to support content generation and management. This makes it possible to efficiently generate content that meets diverse requests and to deliver it optimally.

[0642] A "device for receiving user requests and goal information" is a device that has the function of receiving and accurately receiving specific requests and goals regarding the content that a user wants to create.

[0643] A "generative model selection device" is a device that selects the most suitable generative AI model based on the received requests and objectives.

[0644] A "device that automatically generates information" is a device that uses a selected generation AI model to automatically create the information and content that users need.

[0645] A "device for adjusting generated information according to user requests" is a device that further modifies and adapts generated content according to the user's specific preferences and feedback.

[0646] A "device for optimizing the performance of adjusted information" is a device that optimizes adjusted content to enhance its performance so that it functions to its fullest potential.

[0647] A "device that automatically creates distribution plans" is a device that has the function of automatically determining and creating schedules and methods for optimally distributing generated and adjusted content.

[0648] The system for implementing this invention uses a server, a user terminal, and a generative AI model as its main components. The user inputs instructions and target information necessary for content generation through the terminal. This information is sent to the server, which analyzes the received information to select an appropriate generative model. Examples of generative models used include GPT (Generative Pretrained Transformer), a model for text generation, and DALL-E, a generative AI for image generation.

[0649] The server automatically generates content using the selected generative model. The generated content is further refined based on detailed user requests and feedback. This refinement allows for customization to include the writing style and detailed information requested by the user.

[0650] Subsequently, the server optimizes the performance of the adjusted content. SEO (Search Engine Optimization) and data analysis tools are utilized for this purpose. Furthermore, the server automatically creates a delivery plan to enable efficient distribution of the generated content.

[0651] For example, if a user wants to generate a blog post about summer activities, they would use the following prompt on their device:

[0652] "Create a blog post detailing fun summer activities for the whole family. The post should include tips for safety and ways to save money."

[0653] Based on this prompt, the server can select the appropriate generative model and generate and adjust the necessary content. This allows users to obtain high-quality content in a short amount of time.

[0654] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0655] Step 1:

[0656] The user inputs instructions and goal information for the content they want to generate using their device. This input includes specific prompts, such as, "Create a blog post detailing fun summer activities for the whole family." This clarifies the theme and focus of the content to be generated.

[0657] Step 2:

[0658] The terminal sends the input instructions and target information to the server. The server uses machine learning models to analyze this information and understand the user's requests. This analysis determines which generative model should be adopted.

[0659] Step 3:

[0660] The server selects an appropriate generation AI model based on the analysis results. Specifically, it chooses a model such as GPT or DALL-E that is suitable for the given theme. With this selected model, the server is ready for efficient content generation.

[0661] Step 4:

[0662] The server automatically generates content according to the instructions using a selected generative model. During the generation process, text and images are generated based on the input information. For example, based on prompts, the text of a blog post is output.

[0663] Step 5:

[0664] The generated content is customized on the server to meet user requests. Based on user feedback, the writing style is adjusted and additional information is incorporated. As a result, content that more closely matches the user's expectations is obtained.

[0665] Step 6:

[0666] The server further optimizes the customized content. In this process, search engine optimization (SEO) techniques and data analysis are used to improve the content's online performance.

[0667] Step 7:

[0668] After optimization, the server automatically creates a content delivery plan and prepares the content for delivery at the optimal time and in the best way. This allows users to make more effective use of the content they generate.

[0669] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0670] This invention is a content generation system that takes user emotions into consideration. It selects the optimal generation model based on user instructions and goal information, and adjusts the content using an emotion engine, thereby achieving a high level of customization.

[0671] The program will operate as follows:

[0672] The user inputs instructions and goal information about the content they want to generate through their device. This information is sent to the server, which uses an emotion engine to analyze the user's emotions. Based on the analysis, the server selects an appropriate generative model and uses that model to generate the content. In this generation process, the user's emotional information is applied to the tone and style of the content.

[0673] The generated content is temporarily stored on the server and then presented to the user. At this stage, the user can provide further feedback on the content provided. If the user requests emotional adjustments, the server uses the sentiment engine again to analyze and optimize the style and tone of the content.

[0674] For example, if a user wants to create a friendly-toned social media post about a gift, the server analyzes the user's mood using an emotion engine and selects a text generation model with a positive and casual tone. The generated post content is then adjusted according to the user's preferences. Finally, the server optimizes the content's performance through search engine optimization and data analysis before delivering it to the user in its final form.

[0675] In this way, by recognizing user emotions and reflecting them in the content, a system can be realized that quickly delivers high-quality content that better aligns with the user's intentions.

[0676] The following describes the processing flow.

[0677] Step 1:

[0678] The user inputs instructions regarding the theme, purpose, desired style, and tone of the content to be generated via the device.

[0679] Step 2:

[0680] The terminal sends the user's input information to the server, including the type of content and detailed instructions.

[0681] Step 3:

[0682] The server analyzes the received information and uses an emotion engine to identify the emotions contained in the user's instructions. This allows it to understand the user's intended emotions.

[0683] Step 4:

[0684] The server selects the optimal generative model based on the identified sentiment information. For example, if the sentiment is recognized as "friendly," it will choose a text generation model that matches that tone.

[0685] Step 5:

[0686] The server automatically generates content using a selected generative model. The generated content has a style that reflects the user's intended emotions.

[0687] Step 6:

[0688] The server temporarily stores the generated content and presents it to the user for review. The user reviews this content and provides feedback if any changes are needed.

[0689] Step 7:

[0690] Users may request content adjustments based on the feedback they provide. This may include further emotional adjustments or changes in tone.

[0691] Step 8:

[0692] The server uses the sentiment engine again to adjust the content based on user feedback. The adjusted content is then presented to the user again.

[0693] Step 9:

[0694] The server performs search engine optimization (SEO) and data analysis to enhance the final content quality and optimize the content's online performance.

[0695] Step 10:

[0696] Once the final version of the content is ready, the server will provide it to the user. The user can then use this content as needed.

[0697] (Example 2)

[0698] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0699] In recent years, there has been a growing demand for content that aligns with users' emotions and preferences, but conventional systems have struggled to adequately reflect user intent. Furthermore, the optimization processes required to maximize the performance of the generated content have been insufficient, making it difficult to increase user satisfaction.

[0700] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0701] In this invention, the server includes means for receiving user input information and having an information processing device for analyzing said input information, means for selecting a location information generation device based on the analysis results, and means for generating information using the location information generation device. This makes it possible to generate high-quality content that reflects the user's emotions and intentions. Furthermore, user satisfaction can be increased by adjusting the generated content with an emotion analysis device and optimizing the display performance with an evaluation device.

[0702] A "user" is the entity that inputs instructions and target information into an information system and receives the generated content.

[0703] "Input information" refers to the instructions and goal information that users provide to the system for content generation.

[0704] An "information processing device" is a device that analyzes input information received from a user and creates basic data for selecting an appropriate generative model.

[0705] A "location information generation device" refers to a generation model selected to generate optimal content based on user input information and analysis results.

[0706] An "emotion analysis device" is a device that adjusts generated content according to the user's emotions and instructions, thereby achieving an expression that aligns with the user's intentions.

[0707] An "evaluation device" is a device used to analyze and improve the performance of generated content in order to optimize its display performance.

[0708] In the embodiment of the invention, this system uses a combination of various information processing devices and software to generate content that reflects the user's intent. The specific implementation method is described below.

[0709] The user uses a terminal to input specific instructions and goal information about the content they want to generate. This information includes what they want to express and the desired style and tone. For example, they might give the instruction, "Write a fun post introducing birthday presents in a friendly tone." This input information is sent to the server as a prompt.

[0710] The server passes the received prompt message to the information processing unit, which then analyzes the input information. This analysis uses natural language processing techniques to understand the content and extract the user's emotional state and the intent behind the instructions. Based on these analysis results, the server selects the most appropriate generative AI model. This selection uses a generative model that excels at generating textual information.

[0711] The selected generative AI model generates content using user prompts and analysis results as input. This generation process utilizes an emotion analyzer to adjust the content according to the user's emotions and instructions. Specifically, it is configured to generate content with a casual and approachable writing style.

[0712] The generated content is temporarily stored on the server and presented to the user as it is received. The user reviews this content and provides feedback via their device as needed. If the user requests further adjustments at this stage, the server again uses sentiment analysis to refine the content.

[0713] In the final stage, the server uses evaluation equipment to optimize the performance of the generated content. This optimization utilizes search engine optimization techniques and data analysis tools to maximize content exposure and effectiveness.

[0714] Thus, this system can quickly deliver high-quality content that prioritizes and appropriately reflects the user's emotions and intentions.

[0715] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0716] Step 1:

[0717] The user enters instructions and goal information about the content they want to generate using their device. This input is in text format and includes details such as the content's subject, tone, and style. An example of input data might be, "I want to create a social media post about birthday presents in a friendly tone." This information is sent to the server as a prompt.

[0718] Step 2:

[0719] The server forwards the received prompt message to the information processing unit, where the data is analyzed. Using natural language processing techniques, the system analyzes keywords and context contained in the user's instructions to infer the user's emotions and intentions. The analysis results are temporarily stored in a database for use in the next step.

[0720] Step 3:

[0721] The server selects the most suitable generative AI model based on the analysis results. Here, a selection algorithm is used to choose a model that matches the tone and style desired by the user. The selected generative AI model might, for example, excel at producing casual writing styles. The selection results are output as metadata and used in the content generation process.

[0722] Step 4:

[0723] The server generates content using the selected generative AI model and prompt text as input. The generative AI model automatically generates content based on the specified tone and style using the input information. The generated content is text data that faithfully reflects the user's instructions. This is output as generated data, and the process proceeds to the next adjustment step.

[0724] Step 5:

[0725] The server re-evaluates the content generated using the sentiment analyzer and adjusts the tone and style as needed. The sentiment analyzer receives user feedback and performs additional data processing to adjust the tone of the content. This process adjusts the tone based on feedback such as "make it brighter." The adjusted content is output as updated data.

[0726] Step 6:

[0727] Ultimately, the server optimizes content performance using evaluation equipment. Search engine optimization and data analysis tools are used to optimize the generated content's online visibility and user engagement. This typically involves adjusting keyword density and optimizing meta information. The optimized content is then delivered to the user as the final output.

[0728] (Application Example 2)

[0729] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0730] Traditional content generation tools have a weakness: they lack sufficient customization to accommodate individual user emotions and styles, making it difficult to quickly deliver personalized content that meets user expectations. Furthermore, they lack mechanisms to properly incorporate feedback to optimize the performance of the generated content.

[0731] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0732] In this invention, the server includes means for receiving user instructions and goal information, means for selecting an appropriate machine learning model based on the goal information, means for automatically generating content using the machine learning model, means for customizing the style and tone of the generated content based on the user's emotional information, and means for optimizing the performance of the customized content through data analysis. This enables the rapid generation of personalized content that responds to the individual emotions of the user and the optimization of its performance.

[0733] "Means for receiving user instructions and goal information" refers to a system for users to input specific requests or desired outcomes regarding content creation.

[0734] "Means for selecting an appropriate machine learning model" refers to algorithms and processes for selecting the most suitable machine learning model based on user instructions and target information.

[0735] "Methods for automatically generating content using machine learning models" refers to methods for automatically creating content based on input information by utilizing selected machine learning models.

[0736] "Means of customizing the style and tone of generated content based on user emotional information" refers to technologies that reflect user emotional data in generated content and adjust its expression and tone.

[0737] "Methods for optimizing the performance of customized content through data analysis" refers to methods of evaluating and analyzing the effectiveness and impact of content, and improving the quality and effectiveness of the content based on the results.

[0738] This invention is a system that generates personalized content while taking user emotions into consideration. First, the user inputs instructions and goal information regarding the content through a terminal. This information is sent to a server, which uses an emotion engine to analyze the user's emotions based on this information. The emotion engine analyzes the user's emotional state from the input information and selects the optimal machine learning model based on the results. Using the selected model, the server automatically generates content in an appropriate style and tone.

[0739] The generated content is customized according to the user's emotions and ultimately presented to the user. Users can provide feedback on the content provided. Based on this feedback, the server uses the emotion engine again to make necessary adjustments and optimize the style and tone of the content. In addition, the performance of the content is evaluated through data analysis, and as a result, the content provided is best suited to the user's needs and objectives.

[0740] As a concrete example, suppose a user wants to create a message for a celebratory event. In this case, the user enters a prompt such as, "I want to create a message in a bright and friendly tone." The emotion engine analyzes this input, selects a text generation model that reflects positive emotions, and generates content that aligns with the user's intentions.

[0741] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0742] Step 1:

[0743] The user uses a device to input instructions and goal information regarding the content they want to generate. This input is structured as prompts. The entered prompts serve to concretize the user's intentions and desired emotions.

[0744] Step 2:

[0745] The terminal sends the prompt text entered by the user to the server. The server receives this prompt text and analyzes the user's emotional state using an emotion engine. Data processing takes place here, and the prompt text is converted into emotional features. The user's emotional information is obtained as output.

[0746] Step 3:

[0747] The server selects the most suitable machine learning model based on the analysis results. This process takes emotional information as input and identifies the appropriate generative AI model. The selected generative model is obtained as output.

[0748] Step 4:

[0749] Using the selected machine learning model, the server automatically generates content. Here, the style and tone of the content are determined based on the user's sentiment information. The input is the selected model and sentiment information, and the output is the generated content.

[0750] Step 5:

[0751] The generated content is further customized based on the user's sentiment information. If the server receives feedback from the user, it uses the sentiment engine again to make adjustments. The input is the generated content and user feedback, and the output is the customized content.

[0752] Step 6:

[0753] The server analyzes and optimizes the performance of customized content. Data analysis evaluates content views and engagement, providing metrics for optimization. The output is performance-optimized content.

[0754] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0755] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0756] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0757] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0758] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0759] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0760] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0761] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0762] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0763] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0764] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0765] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0766] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0767] 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.

[0768] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0769] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0770] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0771] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0772] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0773] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0774] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0775] The following is further disclosed regarding the embodiments described above.

[0776] (Claim 1)

[0777] A means of receiving user instructions and target information,

[0778] A means for selecting an appropriate generative model based on the target information,

[0779] A means for automatically generating content using the generation model,

[0780] A means of customizing the generated content according to user requests,

[0781] Means for optimizing the performance of the customized content,

[0782] A system that includes this.

[0783] (Claim 2)

[0784] The system according to claim 1, wherein the generation model generates a variety of content including text, images, audio, and video.

[0785] (Claim 3)

[0786] The system according to claim 1, wherein the performance optimization is performed by search engine optimization and data analysis.

[0787] "Example 1"

[0788] (Claim 1)

[0789] A means by which the user inputs instructions and target information using an information processing device,

[0790] A means for analyzing the aforementioned instructions and target information and dynamically selecting an appropriate generation algorithm,

[0791] Means for generating data using the aforementioned generation algorithm,

[0792] A means of adjusting the generated data based on user feedback,

[0793] A means of using information retrieval techniques to improve the visibility of adjusted data,

[0794] A system that includes this.

[0795] (Claim 2)

[0796] The system according to claim 1, wherein the generation algorithm generates data in different formats, including documents, images, audio, and video.

[0797] (Claim 3)

[0798] The system according to claim 1, wherein the improvement of the visibility of the aforementioned data is carried out by information retrieval technology and analysis technology.

[0799] "Application Example 1"

[0800] (Claim 1)

[0801] A device that receives user requests and target information,

[0802] A device for selecting an appropriate generative model based on the target information,

[0803] A device that automatically generates information using the generation model,

[0804] A device that adjusts the generated information according to the user's request,

[0805] A device for optimizing the performance of the adjusted information,

[0806] A device that automatically creates a distribution plan to support the generation and management of content,

[0807] A system that includes this.

[0808] (Claim 2)

[0809] The system according to claim 1, wherein the generation model generates a variety of media including text, images, audio, and video.

[0810] (Claim 3)

[0811] The system according to claim 1, wherein the optimization of the performance is performed by search engine optimization and data evaluation.

[0812] "Example 2 of combining an emotion engine"

[0813] (Claim 1)

[0814] A means having an information processing device for receiving user input information and analyzing said input information,

[0815] A means for selecting a location information generation device based on the analysis results,

[0816] Means for generating information using the location information generation device,

[0817] A means for adjusting the generated information according to the user's instructions using an emotion analysis device,

[0818] A means for optimizing the display performance of the adjusted information using an evaluation device,

[0819] A system that includes this.

[0820] (Claim 2)

[0821] The system according to claim 1, wherein the location information generating device generates text, visual information, sound, and moving images.

[0822] (Claim 3)

[0823] The system according to claim 1, wherein the optimization of the display performance is performed by an understanding assistance device and a data analysis device.

[0824] "Application example 2 when combining with an emotional engine"

[0825] (Claim 1)

[0826] A means of receiving user instructions and target information,

[0827] A means for selecting an appropriate machine learning model based on the target information,

[0828] A means for automatically generating content using the machine learning model,

[0829] A means of customizing the style and tone of generated content based on user sentiment information,

[0830] A means for optimizing the performance of the customized content through data analysis,

[0831] A system that includes this.

[0832] (Claim 2)

[0833] The system according to claim 1, wherein the machine learning model generates diverse content including text, images, audio, and video.

[0834] (Claim 3)

[0835] The system according to claim 1, wherein the performance optimization is performed by search algorithm optimization and data statistics. [Explanation of Symbols]

[0836] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A device that receives user requests and target information, A device for selecting an appropriate generative model based on the target information, A device that automatically generates information using the generation model, A device that adjusts the generated information according to the user's request, A device for optimizing the performance of the adjusted information, A device that automatically creates a distribution plan to support the generation and management of content, A system that includes this.

2. The system according to claim 1, wherein the generation model generates a variety of media including text, images, audio, and video.

3. The system according to claim 1, wherein the optimization of the performance is performed by search engine optimization and data evaluation.

Images