system

Abstract

To easily introduce a generation AI in a company and to perform optimum prompt engineering and filtering of illegal contents.SOLUTION: The system includes a user interface, a content filter, a prompt engineering infrastructure, an LLM engine, and a ConfigCenter. The user interface receives a user operation. The content filter filters content generated based on an operation received by the user interface. The prompt engineering infrastructure optimizes the prompts based on the content filtered by the content filter. The LLM engine generates an output based on the optimized prompt. ConfigCenter manages the configuration of the user interface, content filters, prompt engineering infrastructure, and LLM engine elements.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, it was difficult to easily introduce generative AI in-house and perform optimal prompt engineering and filtering of fraudulent content.

[0005] The system of the embodiment aims to easily introduce generative AI within a company and perform optimal prompt engineering and filtering of fraudulent content. [Means for solving the problem]

[0006] A system according to an embodiment includes a user interface, a content filter, a prompt engineering platform, an LLM engine, and a ConfigCenter. The user interface accepts user operations. The content filter filters content generated based on the operations accepted by the user interface. The prompt engineering platform optimizes prompts based on the content filtered by the content filter. The LLM engine generates output based on the prompts optimized by the prompt engineering platform. The ConfigCenter manages the configuration of each element of the user interface, the content filter, the prompt engineering platform, and the LLM engine. [Effects of the Invention]

[0007] The system according to the embodiment allows for easy in-house implementation of generative AI, enabling optimal prompt engineering and filtering of fraudulent content. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7]FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The generative AI platform according to an embodiment of the present invention is a system that can be easily implemented and utilized within a company. This system has the ability to freely select any LLM (large-scale language model) available within the company as its engine. Furthermore, it provides APIs, SDKs, and UIs that allow for easy adoption of various industry-known prompt engineering best practices. It also provides APIs, SDKs, and UIs that allow for easy integration of functions that expand the capabilities of LLMs, such as Retrieval-Augmented Generation (RAG). It also has a malicious content filtering function, and each component provides a platform that allows users to customize and expand it. This allows the generative AI platform to be easily implemented and utilized within a company. For example, it can be used for a variety of purposes, such as automating and streamlining business processes and enhancing data analysis. Furthermore, each component can be customized and expanded, allowing for flexible adaptation to specific business needs.

[0029] A generative AI platform according to an embodiment includes a user interface, a content filter, a prompt engineering platform, an LLM engine, and a ConfigCenter. The user interface accepts user operations. For example, the user interface allows various settings and trials to be performed from a browser screen. The user interface also allows actual model usage and settings to be changed through an SDK. The content filter filters the generated content based on the operations accepted by the user interface. For example, the content filter checks whether the text generated by the generative AI contains inappropriate content and filters it as necessary. The prompt engineering platform optimizes prompts based on the content filtered by the content filter. For example, the prompt engineering platform provides functionality that allows techniques commonly used in prompt utilization, such as conversation history, future learning, and thought chaining, to be easily incorporated into existing business processes simply by configuring the platform and calling an API. The LLM engine generates output based on prompts optimized by the prompt engineering platform. For example, the LLM engine provides various LLM models that can be used in-house and provides a freely interchangeable middle layer according to demand. ConfigCenter manages the configuration of each element of the user interface, content filter, prompt engineering platform, and LLM engine. For example, ConfigCenter is a storage location for the settings and customizations of various components. Users can centrally manage the settings of each component through ConfigCenter and make changes or customizations as needed. This allows the generative AI platform to be easily implemented and utilized within a company. It can be used for a variety of purposes, such as automating and streamlining business processes and enhancing data analysis. Furthermore, each component can be customized and expanded, allowing for flexible adaptation to specific business needs.

[0030] The user interface integrates a voice recognition function, which enables operations to be performed by voice commands. The user interface integrates the voice recognition function. For example, the user interface uses a microphone to analyze the user's voice in real time and recognizes voice commands. The voice recognition function enables operations to be performed by voice commands. For example, the user can open a menu or change settings by voice. The voice recognition function also supports multiple languages ​​and can recognize voice commands in the language selected by the user. This enables operations to be performed by voice commands.

[0031] The user interface incorporates AR technology, which enables operations that combine the physical environment with digital information. The user interface incorporates AR technology. For example, the user interface overlays digital objects onto the real world through a camera. AR technology enables operations that combine the physical environment with digital information. For example, digital information is overlaid on the real world that the user sees through a camera. AR technology also recognizes the user's gestures and movements, enabling interactive operations. This enables operations that combine the physical environment with digital information.

[0032] The user interface is provided as a mobile app, which can be accessible from smartphones and tablets. The user interface is provided as a mobile app. For example, the user interface is developed as an app for iOS or Android, and can be accessed from smartphones and tablets. The mobile app can also be accessed from smartphones and tablets. For example, a user can use a smartphone or tablet to access the generative AI platform and perform various settings and trials. The mobile app also has a push notification function, which can notify the user of important information in real time. This makes it accessible from smartphones and tablets.

[0033] The user interface incorporates gamification elements, which can increase user engagement. The user interface incorporates gamification elements. For example, the user interface introduces a point system or badges, allowing users to earn points or badges by performing specific actions. The gamification elements increase user engagement. For example, users can collect points to participate in rankings or collect badges, making using the platform more fun. Furthermore, the gamification elements increase user motivation and encourage continued use. This makes it possible to increase user engagement.

[0034] Content filters integrate image recognition technology, which can detect inappropriate content not only in text but also in images and videos. Content filters integrate image recognition technology. For example, content filters analyze the content of generated images and videos to detect inappropriate content. Image recognition technology detects inappropriate content not only in text but also in images and videos. For example, content filters automatically detect and filter inappropriate images and videos. In addition, image recognition technology supports multiple image and video formats and can analyze a variety of media content. This makes it possible to detect inappropriate content not only in text but also in images and videos.

[0035] Content filters reflect user feedback, which allows them to continuously improve their filtering accuracy. Content filters reflect user feedback. For example, content filters provide a function that allows users to report content that they find inappropriate. Feedback allows them to continuously improve their filtering accuracy. For example, content filters improve their filtering algorithms based on user feedback, thereby increasing accuracy. Feedback can also be used to collect user usage data and review the evaluation criteria for filtering accuracy. This allows them to continuously improve their filtering accuracy.

[0036] Content filters are applied to other internal systems, including email and chat tools, and can achieve company-wide content management. Content filters are applied to other internal systems. For example, a content filter is integrated into an email system or chat tool to filter the content of messages sent and received. Internal systems include email and chat tools. For example, a content filter is integrated into an email system to automatically block emails containing inappropriate content. It is also integrated into chat tools to filter the content of messages sent and received in real time. Content filters achieve company-wide content management. For example, uniform filtering standards can be applied company-wide to ensure consistent content management across all communication channels within the company. This enables company-wide content management.

[0037] The content filter has a multilingual capability, which allows it to filter inappropriate content in different languages. The content filter has a multilingual capability. For example, the content filter supports multiple languages, such as English, French, and Chinese, and can analyze text in different languages. The multilingual capability also filters inappropriate content in different languages. For example, the content filter applies a filtering algorithm based on the definition of inappropriate content in each language to detect inappropriate content. The multilingual capability can also use a translation algorithm to uniformly analyze text in different languages, which enables it to filter inappropriate content in different languages.

[0038] The prompt engineering platform has an automatic learning function, which can improve the accuracy of prompts based on usage history. The prompt engineering platform has an automatic learning function. For example, the prompt engineering platform collects user usage history and uses it as learning data. The automatic learning function improves the accuracy of prompts based on usage history. For example, the prompt engineering platform analyzes past prompts and their results, and improves the algorithm that generates optimal prompts. The automatic learning function can also reflect user feedback and continuously improve the accuracy of prompts. This makes it possible to improve the accuracy of prompts based on usage history.

[0039] The prompt engineering platform reflects user feedback, and this feedback can improve the customizability of prompts. The prompt engineering platform reflects user feedback. For example, the prompt engineering platform provides a function that allows users to evaluate the content of prompts and report areas for improvement. The feedback improves the customizability of prompts. For example, the prompt engineering platform customizes the content and format of prompts based on user feedback. The feedback also makes it possible to provide prompts that meet the user's needs, improving user satisfaction. This makes it possible to improve the customizability of prompts.

[0040] The prompt engineering platform can also be applied to other AI models, including image generation models, and can realize multimodal prompt engineering. The prompt engineering platform can also be applied to other AI models. For example, the prompt engineering platform can be applied to image generation models to realize prompt engineering using both text and images. The AI ​​model includes an image generation model. For example, the prompt engineering platform supports models that generate images based on text prompts. The prompt engineering platform realizes multimodal prompt engineering. For example, the prompt engineering platform generates prompts that combine multiple modalities, such as text, image, and audio, and inputs them into an AI model. This enables multimodal prompt engineering.

[0041] The prompt engineering platform integrates cloud services, and the cloud services can enable remote access and management. The prompt engineering platform integrates cloud services. For example, the prompt engineering platform can configure and manage prompts on the cloud. The cloud services enable remote access and management. For example, a user can remotely access the prompt engineering platform to configure and manage prompts. The cloud services can also allow multiple users to simultaneously access and collaboratively configure and manage prompts. This enables remote access and management.

[0042] The LLM engine has an automatic tuning function, which can maintain optimal performance according to usage conditions. The LLM engine has an automatic tuning function. For example, the LLM engine has an algorithm that adjusts performance according to usage frequency and load. The automatic tuning function maintains optimal performance according to usage conditions. For example, the LLM engine monitors usage conditions in real time and adjusts resource allocation as needed. The automatic tuning function can also optimize performance based on past usage data. This makes it possible to maintain optimal performance according to usage conditions.

[0043] The LLM engine incorporates user feedback, which allows it to continuously improve the accuracy and quality of the output. The LLM engine incorporates user feedback. For example, the LLM engine provides a function that allows users to evaluate the output content and report areas for improvement. Feedback allows it to continuously improve the accuracy and quality of the output. For example, the LLM engine improves the output algorithm based on user feedback, improving accuracy and quality. Feedback can also be used to collect user usage data and review the output evaluation criteria. This allows it to continuously improve the accuracy and quality of the output.

[0044] The LLM engine works with other internal systems, which include data analysis tools, enabling the LLM engine to achieve integrated data processing. The LLM engine works with other internal systems. For example, the LLM engine works with data analysis tools to generate output based on the results of data analysis. Internal systems include data analysis tools. For example, the LLM engine generates more accurate output based on data obtained from the data analysis tools. The LLM engine achieves integrated data processing. For example, the LLM engine collects data from multiple data sources and performs integrated analysis to perform comprehensive data processing. The LLM engine can also work with data analysis tools to update and analyze data in real time. This enables integrated data processing.

[0045] The LLM engine has a multilingual support function, which can enable the generation of text in different languages. The LLM engine has a multilingual support function. For example, the LLM engine supports multiple languages, such as English, French, and Chinese, and can generate text in different languages. The multilingual support function enables the generation of text in different languages. For example, the LLM engine generates text based on the grammar and vocabulary of each language, achieving natural linguistic expression. The multilingual support function can also use a translation algorithm to convert text between different languages. This makes it possible to generate text in different languages.

[0046] ConfigCenter has an automatic backup function that can securely store the history of configuration changes. ConfigCenter has an automatic backup function. For example, ConfigCenter automatically creates a backup every time a configuration change is made and stores the change history. The automatic backup function securely stores the history of configuration changes. For example, ConfigCenter encrypts and stores backup data to protect it from unauthorized access. The automatic backup function can also create backups periodically to maintain the latest configuration state. This makes it possible to securely store the history of configuration changes.

[0047] ConfigCenter reflects user feedback, and this feedback can improve the customizability of settings. ConfigCenter reflects user feedback. For example, ConfigCenter provides a function that allows users to evaluate the content of settings and report areas for improvement. Feedback improves the customizability of settings. For example, ConfigCenter adds setting items or improves existing setting items based on user feedback. Feedback also makes it possible to provide settings that meet user needs, improving user satisfaction. This makes it possible to improve the customizability of settings.

[0048] ConfigCenter works with other internal systems, including project management tools, and can achieve integrated configuration management. ConfigCenter works with other internal systems. For example, ConfigCenter works with a project management tool to automatically adjust settings according to the progress of a project. The internal system includes a project management tool. For example, ConfigCenter provides settings according to the progress of a project based on data obtained from the project management tool. ConfigCenter achieves integrated configuration management. For example, ConfigCenter collects configuration data from multiple internal systems and manages it centrally, thereby achieving integrated configuration management. ConfigCenter can also change and update settings in real time. This enables integrated configuration management.

[0049] ConfigCenter has a multilingual support function, which allows configuration management in different languages. ConfigCenter supports multiple languages, such as English, French, and Chinese, and allows configuration management in different languages. ConfigCenter's multilingual support function allows configuration management in different languages. For example, ConfigCenter manages configuration items in each language in a unified manner and displays the settings in the language selected by the user. The multilingual support function can also use a translation algorithm to convert settings between different languages, allowing configuration management in different languages.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The generative AI platform can further include a behavioral analysis unit that analyzes a user's behavioral history. The behavioral analysis unit collects and analyzes a user's operation history and usage patterns. For example, it can analyze which functions a user frequently uses and what time of day they access them. Based on the analysis results, the behavioral analysis unit can suggest optimal functions and settings to the user. For example, if a user frequently uses a particular function, it can suggest placing that function on the home screen. The behavioral analysis unit can also optimize system performance based on the user's usage patterns. This enables optimal suggestions and performance improvements based on user behavior.

[0052] The generative AI platform can further include a learning management unit that manages the user's learning progress. The learning management unit collects and analyzes the user's learning history and progress. For example, it can analyze which learning materials the user is using and how much progress they have made. The learning management unit can propose an optimal learning plan for the user based on the analysis results. For example, if the user is behind in a particular area, it can propose a learning plan that focuses on that area. The learning management unit can also optimize system settings according to the user's learning progress. This makes it possible to make optimal suggestions and optimize settings based on the user's learning progress.

[0053] The generative AI platform can further include a schedule management unit that manages the user's schedule. The schedule management unit collects and manages the user's plans and tasks. For example, it can analyze the plans and tasks entered by the user in their calendar and propose an optimal schedule. The schedule management unit can send reminders to the user based on the analysis results. For example, if an important meeting or deadline is approaching, it can send a reminder to notify the user. The schedule management unit can also optimize system settings according to the user's schedule. This enables optimal suggestions and optimization of settings based on the user's schedule.

[0054] The generative AI platform can further include a purchasing analysis unit that analyzes a user's purchasing history. The purchasing analysis unit collects and analyzes the user's purchasing history and preferences. For example, it can analyze which products the user frequently purchases and which brands the user prefers. Based on the analysis results, the purchasing analysis unit can suggest optimal products and services to the user. For example, if the user prefers a particular brand, it can suggest new products from that brand. The purchasing analysis unit can also optimize system settings based on the user's purchasing patterns. This enables optimal suggestions and optimization of settings based on the user's purchasing history.

[0055] The generative AI platform can further include an exercise management unit that manages the user's exercise history. The exercise management unit collects and analyzes the user's exercise history and health data. For example, it can analyze how much exercise the user does and which exercises are effective. The exercise management unit can propose an optimal exercise plan for the user based on the analysis results. For example, if the user prefers a particular exercise, it can propose a plan centered around that exercise. The exercise management unit can also optimize system settings according to the user's exercise history. This enables optimal suggestions and settings to be optimized based on the user's exercise history.

[0056] The processing flow of the first embodiment will be briefly explained below.

[0057] Step 1: The user interface accepts user operations. For example, the user interface allows various settings and trials to be performed from a browser screen. The user interface also allows actual model use and setting changes to be made via the SDK. Step 2: The content filter filters the generated content based on the operations received by the user interface. For example, the content filter checks whether the text generated by the generation AI contains inappropriate content and filters it as necessary. Step 3: The prompt engineering platform optimizes prompts based on the content filtered by the content filter. For example, the prompt engineering platform provides functionality that makes it easy to incorporate common prompt utilization techniques, such as conversation history, short-shot learning, and thought chaining, into existing business processes simply by configuring settings and calling an API. Step 4: The LLM engine generates output based on the prompts optimized by the prompt engineering platform. For example, the LLM engine provides various LLM models that can be used in-house, providing a freely interchangeable middle layer according to demand. Step 5: ConfigCenter manages the configuration of each element of the user interface, content filter, prompt engineering platform, and LLM engine. For example, ConfigCenter is a place to store the configuration and customization of various components, and users can centrally manage the configuration of each component through ConfigCenter and change or customize it as needed.

[0058] (Example 2) The generative AI platform according to an embodiment of the present invention is a system that can be easily implemented and utilized within a company. This system has the ability to freely select any LLM (large-scale language model) available within the company as its engine. Furthermore, it provides APIs, SDKs, and UIs that allow for easy adoption of various industry-known prompt engineering best practices. It also provides APIs, SDKs, and UIs that allow for easy integration of functions that expand the capabilities of LLMs, such as Retrieval-Augmented Generation (RAG). It also has a malicious content filtering function, and each component provides a platform that allows users to customize and expand it. This allows the generative AI platform to be easily implemented and utilized within a company. For example, it can be used for a variety of purposes, such as automating and streamlining business processes and enhancing data analysis. Furthermore, each component can be customized and expanded, allowing for flexible adaptation to specific business needs.

[0059] A generative AI platform according to an embodiment includes a user interface, a content filter, a prompt engineering platform, an LLM engine, and a ConfigCenter. The user interface accepts user operations. For example, the user interface allows various settings and trials to be performed from a browser screen. The user interface also allows actual model usage and settings to be changed through an SDK. The content filter filters the generated content based on the operations accepted by the user interface. For example, the content filter checks whether the text generated by the generative AI contains inappropriate content and filters it as necessary. The prompt engineering platform optimizes prompts based on the content filtered by the content filter. For example, the prompt engineering platform provides functionality that allows techniques commonly used in prompt utilization, such as conversation history, future learning, and thought chaining, to be easily incorporated into existing business processes simply by configuring the platform and calling an API. The LLM engine generates output based on prompts optimized by the prompt engineering platform. For example, the LLM engine provides various LLM models that can be used in-house and provides a freely interchangeable middle layer according to demand. ConfigCenter manages the configuration of each element of the user interface, content filter, prompt engineering platform, and LLM engine. For example, ConfigCenter is a storage location for the settings and customizations of various components. Users can centrally manage the settings of each component through ConfigCenter and make changes or customizations as needed. This allows the generative AI platform to be easily implemented and utilized within a company. It can be used for a variety of purposes, such as automating and streamlining business processes and enhancing data analysis. Furthermore, each component can be customized and expanded, allowing for flexible adaptation to specific business needs.

[0060] The user interface is equipped with a real-time emotion analysis function using generative AI, and the emotion analysis function can customize the interface according to the user's emotions. The user interface is equipped with a real-time emotion analysis function using generative AI. For example, the user interface uses a camera and microphone to analyze the user's facial expressions and voice in real time to detect emotions. The emotion analysis function customizes the interface according to the user's emotions. For example, if the user is relaxed, the theme can be changed to a calm color scheme. Alternatively, if the user is concentrating, the layout can be changed to a simple one that makes it easier to concentrate. This makes it possible to customize the interface according to the user's emotions.

[0061] The user interface integrates a voice recognition function, which enables operations to be performed by voice commands. The user interface integrates the voice recognition function. For example, the user interface uses a microphone to analyze the user's voice in real time and recognizes voice commands. The voice recognition function enables operations to be performed by voice commands. For example, the user can open a menu or change settings by voice. The voice recognition function also supports multiple languages ​​and can recognize voice commands in the language selected by the user. This enables operations to be performed by voice commands.

[0062] The user interface incorporates AR technology, which enables operations that combine the physical environment with digital information. The user interface incorporates AR technology. For example, the user interface overlays digital objects onto the real world through a camera. AR technology enables operations that combine the physical environment with digital information. For example, digital information is overlaid on the real world that the user sees through a camera. AR technology also recognizes the user's gestures and movements, enabling interactive operations. This enables operations that combine the physical environment with digital information.

[0063] The user interface is provided as a mobile app, which can be accessible from smartphones and tablets. The user interface is provided as a mobile app. For example, the user interface is developed as an app for iOS or Android, and can be accessed from smartphones and tablets. The mobile app can also be accessed from smartphones and tablets. For example, a user can use a smartphone or tablet to access the generative AI platform and perform various settings and trials. The mobile app also has a push notification function, which can notify the user of important information in real time. This makes it accessible from smartphones and tablets.

[0064] The user interface incorporates gamification elements, which can increase user engagement. The user interface incorporates gamification elements. For example, the user interface introduces a point system or badges, allowing users to earn points or badges by performing specific actions. The gamification elements increase user engagement. For example, users can collect points to participate in rankings or collect badges, making using the platform more fun. Furthermore, the gamification elements increase user motivation and encourage continued use. This makes it possible to increase user engagement.

[0065] The user interface uses an emotion estimation function, which can automatically change the theme and color scheme of the interface based on the user's emotions. The user interface uses the emotion estimation function. For example, the user interface uses a camera or microphone to analyze the user's facial expressions and voice in real time to detect emotions. The emotion estimation function automatically changes the theme and color scheme of the interface based on the user's emotions. For example, if the user is relaxed, the theme is changed to a calm color scheme. Also, if the user is concentrating, the layout is changed to a simple one that makes it easier to concentrate. This makes it possible to automatically change the theme and color scheme of the interface based on the user's emotions.

[0066] The content filter is equipped with a sentiment analysis function using generative AI, and the sentiment analysis function can filter emotionally inappropriate content. The content filter is equipped with a sentiment analysis function using generative AI. For example, the content filter analyzes the sentiment score of text generated by the generative AI to detect emotionally inappropriate content. The sentiment analysis function filters out emotionally inappropriate content. For example, the content filter automatically filters text with strong emotions of anger or sadness so that it is not displayed to the user. The sentiment analysis function can also warn users in advance of content that they may find offensive. This makes it possible to filter emotionally inappropriate content.

[0067] Content filters integrate image recognition technology, which can detect inappropriate content not only in text but also in images and videos. Content filters integrate image recognition technology. For example, content filters analyze the content of generated images and videos to detect inappropriate content. Image recognition technology detects inappropriate content not only in text but also in images and videos. For example, content filters automatically detect and filter inappropriate images and videos. In addition, image recognition technology supports multiple image and video formats and can analyze a variety of media content. This makes it possible to detect inappropriate content not only in text but also in images and videos.

[0068] Content filters reflect user feedback, which allows them to continuously improve their filtering accuracy. Content filters reflect user feedback. For example, content filters provide a function that allows users to report content that they find inappropriate. Feedback allows them to continuously improve their filtering accuracy. For example, content filters improve their filtering algorithms based on user feedback, thereby increasing accuracy. Feedback can also be used to collect user usage data and review the evaluation criteria for filtering accuracy. This allows them to continuously improve their filtering accuracy.

[0069] Content filters are applied to other internal systems, including email and chat tools, and can achieve company-wide content management. Content filters are applied to other internal systems. For example, a content filter is integrated into an email system or chat tool to filter the content of messages sent and received. Internal systems include email and chat tools. For example, a content filter is integrated into an email system to automatically block emails containing inappropriate content. It is also integrated into chat tools to filter the content of messages sent and received in real time. Content filters achieve company-wide content management. For example, uniform filtering standards can be applied company-wide to ensure consistent content management across all communication channels within the company. This enables company-wide content management.

[0070] The content filter has a multilingual capability, which allows it to filter inappropriate content in different languages. The content filter has a multilingual capability. For example, the content filter supports multiple languages, such as English, French, and Chinese, and can analyze text in different languages. The multilingual capability also filters inappropriate content in different languages. For example, the content filter applies a filtering algorithm based on the definition of inappropriate content in each language to detect inappropriate content. The multilingual capability can also use a translation algorithm to uniformly analyze text in different languages, which enables it to filter inappropriate content in different languages.

[0071] The content filter uses an emotion estimation function to provide advance warning of content that users may find offensive. For example, the content filter analyzes the emotion score of text generated by the generative AI to detect content that users may find offensive. The emotion estimation function provides advance warning of content that users may find offensive. For example, the content filter displays a warning message on text with a high emotion score to alert the user. The emotion estimation function can also adjust the strength of the warning according to the user's emotional state. This enables advance warning of content that users may find offensive.

[0072] The prompt engineering platform is equipped with an emotion analysis function that uses generative AI, and the emotion analysis function can optimize prompts according to the user's emotions. The prompt engineering platform is equipped with an emotion analysis function that uses generative AI. For example, in the prompt engineering platform, the generative AI analyzes the user's emotional state and calculates an emotion score. The emotion analysis function optimizes prompts according to the user's emotions. For example, if the user is relaxed, it provides a gentle prompt, and if the user is concentrating, it provides a simple prompt that makes it easier to concentrate. The emotion analysis function can also dynamically change the content and format of the prompt according to the user's emotional state. This makes it possible to optimize prompts according to the user's emotions.

[0073] The prompt engineering platform has an automatic learning function, which can improve the accuracy of prompts based on usage history. The prompt engineering platform has an automatic learning function. For example, the prompt engineering platform collects user usage history and uses it as learning data. The automatic learning function improves the accuracy of prompts based on usage history. For example, the prompt engineering platform analyzes past prompts and their results, and improves the algorithm that generates optimal prompts. The automatic learning function can also reflect user feedback and continuously improve the accuracy of prompts. This makes it possible to improve the accuracy of prompts based on usage history.

[0074] The prompt engineering platform reflects user feedback, and this feedback can improve the customizability of prompts. The prompt engineering platform reflects user feedback. For example, the prompt engineering platform provides a function that allows users to evaluate the content of prompts and report areas for improvement. The feedback improves the customizability of prompts. For example, the prompt engineering platform customizes the content and format of prompts based on user feedback. The feedback also makes it possible to provide prompts that meet the user's needs, improving user satisfaction. This makes it possible to improve the customizability of prompts.

[0075] The prompt engineering platform can also be applied to other AI models, including image generation models, and can realize multimodal prompt engineering. The prompt engineering platform can also be applied to other AI models. For example, the prompt engineering platform can be applied to image generation models to realize prompt engineering using both text and images. The AI ​​model includes an image generation model. For example, the prompt engineering platform supports models that generate images based on text prompts. The prompt engineering platform realizes multimodal prompt engineering. For example, the prompt engineering platform generates prompts that combine multiple modalities, such as text, image, and audio, and inputs them into an AI model. This enables multimodal prompt engineering.

[0076] The prompt engineering platform integrates cloud services, and the cloud services can enable remote access and management. The prompt engineering platform integrates cloud services. For example, the prompt engineering platform can configure and manage prompts on the cloud. The cloud services enable remote access and management. For example, a user can remotely access the prompt engineering platform to configure and manage prompts. The cloud services can also allow multiple users to simultaneously access and collaboratively configure and manage prompts. This enables remote access and management.

[0077] The prompt engineering platform uses an emotion estimation function to suggest prompts based on the user's emotions. For example, in the prompt engineering platform, a generation AI analyzes the user's emotional state and calculates an emotion score. The emotion estimation function suggests prompts based on the user's emotions. For example, if the user is relaxed, it suggests a gentle prompt, and if the user is concentrating, it suggests a simple prompt that helps them concentrate. The emotion estimation function can also dynamically change the content and format of the prompt depending on the user's emotional state. This makes it possible to suggest prompts based on the user's emotions.

[0078] The LLM engine is equipped with a sentiment analysis function using generative AI, which can generate output according to the user's emotions. The LLM engine is equipped with a sentiment analysis function using generative AI. For example, in the LLM engine, generative AI analyzes the user's emotional state and calculates an emotion score. The sentiment analysis function generates output according to the user's emotions. For example, if the user is relaxed, it provides output in a calm tone, and if the user is concentrating, it provides output in a simple tone that helps with concentration. The sentiment analysis function can also dynamically change the content and format of the output according to the user's emotional state. This makes it possible to generate output according to the user's emotions.

[0079] The LLM engine has an automatic tuning function, which can maintain optimal performance according to usage conditions. The LLM engine has an automatic tuning function. For example, the LLM engine has an algorithm that adjusts performance according to usage frequency and load. The automatic tuning function maintains optimal performance according to usage conditions. For example, the LLM engine monitors usage conditions in real time and adjusts resource allocation as needed. The automatic tuning function can also optimize performance based on past usage data. This makes it possible to maintain optimal performance according to usage conditions.

[0080] The LLM engine incorporates user feedback, which allows it to continuously improve the accuracy and quality of the output. The LLM engine incorporates user feedback. For example, the LLM engine provides a function that allows users to evaluate the output content and report areas for improvement. Feedback allows it to continuously improve the accuracy and quality of the output. For example, the LLM engine improves the output algorithm based on user feedback, improving accuracy and quality. Feedback can also be used to collect user usage data and review the output evaluation criteria. This allows it to continuously improve the accuracy and quality of the output.

[0081] The LLM engine works with other internal systems, which include data analysis tools, enabling the LLM engine to achieve integrated data processing. The LLM engine works with other internal systems. For example, the LLM engine works with data analysis tools to generate output based on the results of data analysis. Internal systems include data analysis tools. For example, the LLM engine generates more accurate output based on data obtained from the data analysis tools. The LLM engine achieves integrated data processing. For example, the LLM engine collects data from multiple data sources and performs integrated analysis to perform comprehensive data processing. The LLM engine can also work with data analysis tools to update and analyze data in real time. This enables integrated data processing.

[0082] The LLM engine has a multilingual support function, which can enable the generation of text in different languages. The LLM engine has a multilingual support function. For example, the LLM engine supports multiple languages, such as English, French, and Chinese, and can generate text in different languages. The multilingual support function enables the generation of text in different languages. For example, the LLM engine generates text based on the grammar and vocabulary of each language, achieving natural linguistic expression. The multilingual support function can also use a translation algorithm to convert text between different languages. This makes it possible to generate text in different languages.

[0083] The LLM engine uses an emotion estimation function to adjust output based on the user's emotions. For example, in the LLM engine, the generation AI analyzes the user's emotional state and calculates an emotion score. The emotion estimation function adjusts output based on the user's emotions. For example, if the user is relaxed, it provides a calm tone output, and if the user is concentrating, it provides a simple tone output that helps with concentration. The emotion estimation function can also dynamically change the content and format of the output depending on the user's emotional state. This makes it possible to adjust output based on the user's emotions.

[0084] ConfigCenter is equipped with an emotion analysis function that uses generative AI, which can suggest settings based on the user's emotions. ConfigCenter is equipped with an emotion analysis function that uses generative AI. For example, ConfigCenter's generative AI analyzes the user's emotional state and calculates an emotion score. The emotion analysis function suggests settings based on the user's emotions. For example, if the user is relaxed, it suggests calm settings, and if the user is concentrating, it suggests simple settings that help them concentrate. The emotion analysis function can also dynamically change the content and format of settings based on the user's emotional state. This makes it possible to suggest settings based on the user's emotions.

[0085] ConfigCenter has an automatic backup function that can securely store the history of configuration changes. ConfigCenter has an automatic backup function. For example, ConfigCenter automatically creates a backup every time a configuration change is made and stores the change history. The automatic backup function securely stores the history of configuration changes. For example, ConfigCenter encrypts and stores backup data to protect it from unauthorized access. The automatic backup function can also create backups periodically to maintain the latest configuration state. This makes it possible to securely store the history of configuration changes.

[0086] ConfigCenter reflects user feedback, and this feedback can improve the customizability of settings. ConfigCenter reflects user feedback. For example, ConfigCenter provides a function that allows users to evaluate the content of settings and report areas for improvement. Feedback improves the customizability of settings. For example, ConfigCenter adds setting items or improves existing setting items based on user feedback. Feedback also makes it possible to provide settings that meet user needs, improving user satisfaction. This makes it possible to improve the customizability of settings.

[0087] ConfigCenter works with other internal systems, including project management tools, and can achieve integrated configuration management. ConfigCenter works with other internal systems. For example, ConfigCenter works with a project management tool to automatically adjust settings according to the progress of a project. The internal system includes a project management tool. For example, ConfigCenter provides settings according to the progress of a project based on data obtained from the project management tool. ConfigCenter achieves integrated configuration management. For example, ConfigCenter collects configuration data from multiple internal systems and manages it centrally, thereby achieving integrated configuration management. ConfigCenter can also change and update settings in real time. This enables integrated configuration management.

[0088] ConfigCenter has a multilingual support function, which allows configuration management in different languages. ConfigCenter supports multiple languages, such as English, French, and Chinese, and allows configuration management in different languages. ConfigCenter's multilingual support function allows configuration management in different languages. For example, ConfigCenter manages configuration items in each language in a unified manner and displays the settings in the language selected by the user. The multilingual support function can also use a translation algorithm to convert settings between different languages, allowing configuration management in different languages.

[0089] ConfigCenter uses an emotion estimation function to optimize settings based on the user's emotions. For example, ConfigCenter's generative AI analyzes the user's emotional state and calculates an emotion score. The emotion estimation function optimizes settings based on the user's emotions. For example, if the user is relaxed, it suggests gentle settings, and if the user is concentrating, it suggests simple settings that facilitate concentration. The emotion estimation function can also dynamically change the content and format of settings depending on the user's emotional state. This makes it possible to optimize settings based on the user's emotions.

[0090] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0091] The generative AI platform can further include a behavioral analysis unit that analyzes a user's behavioral history. The behavioral analysis unit collects and analyzes a user's operation history and usage patterns. For example, it can analyze which functions a user frequently uses and what time of day they access them. Based on the analysis results, the behavioral analysis unit can suggest optimal functions and settings to the user. For example, if a user frequently uses a particular function, it can suggest placing that function on the home screen. The behavioral analysis unit can also optimize system performance based on the user's usage patterns. This enables optimal suggestions and performance improvements based on user behavior.

[0092] The generative AI platform can further include a health management unit that monitors the user's health status. The health management unit monitors and analyzes the user's heart rate and stress level. For example, it can obtain the user's heart rate in real time through a wearable device and estimate the stress level. Based on the analysis results, the health management unit can make suggestions to the user to help them relax. For example, if the user shows a high stress level, it can suggest relaxing music or meditation. The health management unit can also limit system use depending on the user's health status. This enables optimal suggestions and usage restrictions based on the user's health status.

[0093] The generative AI platform can further include a learning management unit that manages the user's learning progress. The learning management unit collects and analyzes the user's learning history and progress. For example, it can analyze which learning materials the user is using and how much progress they have made. The learning management unit can propose an optimal learning plan for the user based on the analysis results. For example, if the user is behind in a particular area, it can propose a learning plan that focuses on that area. The learning management unit can also optimize system settings according to the user's learning progress. This makes it possible to make optimal suggestions and optimize settings based on the user's learning progress.

[0094] The generative AI platform can further include a music suggestion unit that estimates the user's emotions and suggests music based on those emotions. The music suggestion unit analyzes the user's facial expressions and voice to estimate emotions. For example, if the user is relaxed, it suggests calm music, and if the user is concentrating, it suggests music that helps them concentrate. The music suggestion unit can also dynamically change the genre and tempo of music depending on the user's emotional state. This makes it possible to suggest optimal music based on the user's emotions.

[0095] The generative AI platform can further include a schedule management unit that manages the user's schedule. The schedule management unit collects and manages the user's plans and tasks. For example, it can analyze the plans and tasks entered by the user in their calendar and propose an optimal schedule. The schedule management unit can send reminders to the user based on the analysis results. For example, if an important meeting or deadline is approaching, it can send a reminder to notify the user. The schedule management unit can also optimize system settings according to the user's schedule. This enables optimal suggestions and optimization of settings based on the user's schedule.

[0096] The generative AI platform can further include a reminder unit that estimates the user's emotions and sends reminders based on those emotions. The reminder unit analyzes the user's facial expressions and voice to estimate emotions. For example, if the user is feeling stressed, it can send a reminder to relax, and if the user is concentrating, it can send a reminder for an important task. The reminder unit can also dynamically change the content and timing of reminders depending on the user's emotional state. This makes it possible to send optimal reminders based on the user's emotions.

[0097] The generative AI platform can further include a purchasing analysis unit that analyzes a user's purchasing history. The purchasing analysis unit collects and analyzes the user's purchasing history and preferences. For example, it can analyze which products the user frequently purchases and which brands the user prefers. Based on the analysis results, the purchasing analysis unit can suggest optimal products and services to the user. For example, if the user prefers a particular brand, it can suggest new products from that brand. The purchasing analysis unit can also optimize system settings based on the user's purchasing patterns. This enables optimal suggestions and optimization of settings based on the user's purchasing history.

[0098] The generative AI platform can further include a news suggestion unit that estimates the user's emotions and suggests news based on those emotions. The news suggestion unit analyzes the user's facial expressions and voice to estimate emotions. For example, if the user is relaxed, it suggests calm news, and if the user is focused, it suggests important news. The news suggestion unit can also dynamically change the genre and content of news depending on the user's emotional state. This makes it possible to suggest optimal news based on the user's emotions.

[0099] The generative AI platform can further include an exercise management unit that manages the user's exercise history. The exercise management unit collects and analyzes the user's exercise history and health data. For example, it can analyze how much exercise the user does and which exercises are effective. The exercise management unit can propose an optimal exercise plan for the user based on the analysis results. For example, if the user prefers a particular exercise, it can propose a plan centered around that exercise. The exercise management unit can also optimize system settings according to the user's exercise history. This enables optimal suggestions and settings to be optimized based on the user's exercise history.

[0100] The generative AI platform can further include an ad suggestion unit that estimates a user's emotions and suggests advertisements based on those emotions. The ad suggestion unit analyzes the user's facial expressions and voice to estimate emotions. For example, if the user is relaxed, it suggests an advertisement with a calm tone, and if the user is concentrating, it suggests an advertisement with a simple tone that helps the user to concentrate. The ad suggestion unit can also dynamically change the content and format of advertisements depending on the user's emotional state. This makes it possible to suggest optimal advertisements based on the user's emotions.

[0101] The processing flow of the second embodiment will be briefly explained below.

[0102] Step 1: The user interface accepts user operations. For example, the user interface allows various settings and trials to be performed from a browser screen. The user interface also allows actual model use and setting changes to be made via the SDK. Step 2: The content filter filters the generated content based on the operations received by the user interface. For example, the content filter checks whether the text generated by the generation AI contains inappropriate content and filters it as necessary. Step 3: The prompt engineering platform optimizes prompts based on the content filtered by the content filter. For example, the prompt engineering platform provides functionality that makes it easy to incorporate common prompt utilization techniques, such as conversation history, short-shot learning, and thought chaining, into existing business processes simply by configuring settings and calling an API. Step 4: The LLM engine generates output based on the prompts optimized by the prompt engineering platform. For example, the LLM engine provides various LLM models that can be used in-house, providing a freely interchangeable middle layer according to demand. Step 5: ConfigCenter manages the configuration of each element of the user interface, content filter, prompt engineering platform, and LLM engine. For example, ConfigCenter is a place to store the configuration and customization of various components, and users can centrally manage the configuration of each component through ConfigCenter and change or customize it as needed.

[0103] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0104] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0105] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0106] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0107] 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.

[0108] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0109] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0110] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0111] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0112] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0113] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0114] 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.

[0115] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0116] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0117] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0118] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0119] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0120] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0121] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0122] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0123] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0124] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0125] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0126] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0127] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0128] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0129] 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.

[0130] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0131] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0132] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0133] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0134] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0135] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0136] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0137] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0138] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0139] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0140] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0141] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0142] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0143] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0144] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0145] 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.

[0146] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0147] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0148] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0149] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0150] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0151] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0152] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0153] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0154] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0155] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0156] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0157] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0158] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0159] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0160] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0161] 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.

[0162] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0163] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0164] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0165] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0166] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0167] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0168] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0169] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0170] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A user interface; Content filters and Prompt Engineering Foundation and LLM engine and ConfigCenter and The user interface includes: Accepts user operations, The content filter filtering the generated content based on operations received by the user interface; The prompt engineering platform includes: optimizing the prompt based on the content filtered by the content filter; The LLM engine is generating an output based on the prompts optimized by the prompt engineering infrastructure; The ConfigCenter Manages the configuration of the user interface, the content filter, the prompt engineering infrastructure, and the LLM engine elements A system characterized by:

2. The user interface includes: Equipped with real-time sentiment analysis function using the generative AI, The sentiment analysis function Customize the interface according to the user's emotions 2. The system of claim 1.

3. The content filter Equipped with emotion analysis function using the generative AI, The sentiment analysis function Filtering emotionally inappropriate content 2. The system of claim 1.

4. The prompt engineering platform includes: Equipped with emotion analysis function using the generative AI, The sentiment analysis function Optimize prompts based on user emotions 2. The system of claim 1.

5. The LLM engine is Equipped with emotion analysis function using the generative AI, The sentiment analysis function Generate output according to user emotions 2. The system of claim 1.

6. The ConfigCenter Equipped with emotion analysis function using the generative AI, The sentiment analysis function Suggest settings based on user emotions 2. The system of claim 1.

7. The user interface includes: Integrated voice recognition function, The voice recognition function Enable voice command operation 2. The system of claim 1.

8. The content filter Reflecting user feedback, The feedback may be Continually improve filtering accuracy 2. The system of claim 1.

Images