system

Abstract

We provide the system. [Solution] In order to integrate the functions of multiple artificial intelligence models, a means for analyzing the technical documentation and output examples of the artificial intelligence models, Based on the analysis results, a means to infer and integrate the functions of each artificial intelligence model, A means of generating a new artificial intelligence model based on integrated functions and deploying it to the user's terminal, A system that includes this.

Description

Technical Field

[0004] , , , ,

[0005] , , , ,

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] When multiple artificial intelligence models operate independently, there is a problem that the user has to share context and intention with each individual model. Also, due to the lack of interoperability between different artificial intelligence models, it is difficult to efficiently utilize functions according to the purpose, and there is a problem that there is a limit to the overall productivity improvement.

Means for Solving the Problems

[0005] This invention provides a means for analyzing the technical documentation and output examples of multiple artificial intelligence models, and for inferring and integrating the functions of each model based on the analysis results. This rearranges the functions of different artificial intelligence models into a single integrated artificial intelligence model, which is then deployed to the user's terminal. Through this integration process, users can efficiently utilize the functions of multiple artificial intelligence models while eliminating the need for context sharing. Furthermore, the invention provides a mechanism for continuously improving the accuracy and performance of the models by collecting feedback from users.

[0006] An "artificial intelligence model" is an information processing system that possesses data processing capabilities tailored to specific tasks and purposes, and performs information analysis and generation through learning.

[0007] A "technical document" is a document that provides detailed explanations of the functions, usage, and output formats of an artificial intelligence model.

[0008] An "output example" is a sample that shows specific data or results generated by an artificial intelligence model in response to a given input.

[0009] "Analysis" is the process of thoroughly examining technical documents and output examples to understand the functions and characteristics of an artificial intelligence model.

[0010] "Functional integration" refers to combining the individual functions provided by multiple artificial intelligence models and reconfiguring them into a single, seamlessly functioning system.

[0011] A "user terminal" refers to a device, such as a computer or mobile device, that a user uses to operate an artificial intelligence model.

[0012] "Feedback" refers to evaluations and opinions provided by users to improve and modify the performance of artificial intelligence models. [Brief explanation of the drawing]

[0013] [Figure 1]This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

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

[0016] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

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

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

[0019] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and 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), or Bluetooth (registered trademark), etc.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

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

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] This invention aims to realize a system that integrates multiple artificial intelligence models, allowing users to efficiently utilize their functions. This system primarily involves a server analyzing the technical documentation and output examples of each artificial intelligence model, and then integrating their functions based on the analysis results.

[0035] When a user accesses the platform and selects multiple artificial intelligence models, the server collects technical documentation and output examples related to these models from a database. Based on the collected data, the server performs analysis to gain a detailed understanding of the characteristics and operating patterns of each model. Based on the information obtained from this analysis, the server integrates the functions of multiple models and designs a new integrated model.

[0036] The server generates a newly integrated artificial intelligence model and deploys it to the user's terminal. This allows the user to conveniently utilize the functions of multiple artificial intelligence models through a single interface on their terminal.

[0037] As a concrete example, consider the case where the user selects an AI model for automatic article generation and image generation. In this case, the server analyzes the technical documentation and past output examples of both models and integrates the functionality to simultaneously generate images based on the article's theme. This allows the user to input the article's theme and structure once, and related images will be generated at the same time, enabling consistent project progress.

[0038] Furthermore, the server acquires user feedback, which is then used as data to improve the model's accuracy and performance. This feedback cycle provides a mechanism for continuously improving the performance of the artificial intelligence model.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The user accesses the platform and selects the artificial intelligence model they wish to use. Once the selection is complete, the user enters information about the task they intend to perform and the expected output.

[0042] Step 2:

[0043] The server automatically collects technical documentation and existing output examples related to the selected artificial intelligence model from the database. This information collection is a preliminary step to accurately understanding the model's capabilities.

[0044] Step 3:

[0045] The server analyzes the collected technical documents and output examples. Using natural language processing techniques, it identifies what inputs each model requires and what results it outputs. This analysis provides a detailed understanding of the model's characteristics and operation.

[0046] Step 4:

[0047] The server infers the functions of each artificial intelligence model based on the analysis results and integrates those functions. In doing so, it establishes common operating parameters and data formats to build a seamless interface between the artificial intelligence models.

[0048] Step 5:

[0049] The server generates new artificial intelligence models based on integrated functionality. The generation process includes steps that combine training data from different models as needed.

[0050] Step 6:

[0051] The server deploys the newly generated artificial intelligence model to the user's terminal. This allows the user to use the AI ​​model in the configured environment.

[0052] Step 7:

[0053] Users interact with the deployed artificial intelligence model to perform tasks. They can also review the generated output and provide additional instructions.

[0054] Step 8:

[0055] User feedback is sent to the server. The server analyzes this feedback and uses it to improve the artificial intelligence model. Through this feedback loop, the model's performance and accuracy are improved.

[0056] (Example 1)

[0057] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0058] With the advancement of information processing technology, there is a growing need to efficiently utilize and integrate multiple information processing models with different characteristics. However, due to differences in the technical characteristics and outputs of each model, users cannot easily integrate them, and the integration process is time-consuming and laborious. Furthermore, there is a lack of mechanisms to effectively utilize post-use feedback and improve model performance. Therefore, to solve these problems, a means of efficiently analyzing and integrating the characteristics of multiple models is necessary, and it is also required to continuously improve performance by utilizing feedback.

[0059] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0060] In this invention, the server includes means for an information processing device to analyze technical descriptions and generated output examples of multiple information processing models, means for identifying and integrating the functions of each information processing model based on the analysis results, and means for generating a new integrated information processing model and providing it to the user's input device. This enables the efficient integration of information processing models with different characteristics, allowing users to conveniently utilize them through a consistent interface. Furthermore, performance improvements are continuously made based on user feedback, improving the accuracy and responsiveness of the model.

[0061] An "information processing device" is a general term for a device that receives data, processes and analyzes that data, and generates intended output.

[0062] An "information processing model" is a set of calculations and logic used to generate a desired output for a given input.

[0063] "Technical descriptions" refer to documents and materials that describe the design, operation, and characteristics of an information processing model.

[0064] "Analysis" is the process of understanding the structure of information and extracting the necessary information.

[0065] "Identifying functions" means clarifying the specific capabilities and roles that each information processing model provides.

[0066] "Integration" refers to combining the functions of multiple information processing models to operate as a single system.

[0067] "User input device" refers to an electronic device used by a user to input information and interact with a system.

[0068] "Generation" refers to creating a working version of the designed information processing model.

[0069] "Feedback" refers to opinions and reports about the performance and usability that users provide after using a system.

[0070] This invention includes embodiments of a system that integrates multiple information processing models and allows users to utilize them efficiently. Essentially, it provides a platform that integrates the capabilities of multiple information processing models, based on an information processing device (server) and a user input device (terminal).

[0071] The server first collects descriptions of relevant technologies and past output examples from a database, based on the information processing model selected by the user through an input device. This utilizes software libraries for natural language processing and data mining. Specific examples of useful software include Python's Pandas library and Tensorflow®. The server then analyzes this data to understand the characteristics of each model.

[0072] Subsequently, the server designs an integrated model and actually generates it. The generated integrated model is provided to the user's terminal, enabling operation on the terminal. The user can obtain systematic data output by entering specific prompt statements through the integrated interface. In this process, the integration function of the information processing model is utilized in generating the output, thus providing consistent results.

[0073] As a concrete example, a user can input a prompt to generate information on a theme such as "articles about environmental protection." Upon inputting this prompt, the system automatically creates related visual materials along with the article, providing consistent content. This significantly improves user efficiency and allows them to leverage the strengths of multiple information processing models.

[0074] Furthermore, the server continuously collects user feedback and uses it as data to improve the model's performance. This allows the information processing system to continuously evolve and provide users with the optimal interface and functionality.

[0075] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0076] Step 1:

[0077] The user accesses the platform and selects the information processing model they wish to use. Information about the selected model is entered and sent to the server. This selection prompts the server to begin the process of collecting technical descriptions and output examples of the selected model from its database.

[0078] Step 2:

[0079] The server collects technical documentation and output examples related to the information processing model selected by the user from a database. It uses the identification information of the selected model as input and retrieves relevant data based on this. The server uses Python or SQL to search the database and extract the necessary data. The output is a dataset of technical specifications and historical model outputs.

[0080] Step 3:

[0081] The server analyzes the collected technical descriptions and output examples to understand the characteristics of each model. The collected dataset is used as input, and the output provides characteristic information about the model. Specifically, the server uses natural language processing algorithms to extract features and identify the operating patterns of the models.

[0082] Step 4:

[0083] The server designs a new model that integrates the functions of each information processing model based on the analysis results. The input is characteristic information obtained from each information processing model. The server uses this information to design a model that enables seamless integration of functions between the models. The output is the design specification for the new integrated model.

[0084] Step 5:

[0085] The server actually generates the designed integrated model. In this step, the structure of the information processing model is built based on the design specifications, and the generated model is ready to go. The input is the design specifications, and the output is the actually working integrated model.

[0086] Step 6:

[0087] The generated integrated model is provided to the user's terminal, and the user can use its interface. The user enters prompts from the terminal and requests the generation of output based on them. In this step, the integrated model performs data processing and calculations based on the input prompts and generates the specified output. The output is information requested by the user.

[0088] Step 7:

[0089] The server collects feedback from users and uses it to improve the model's performance. User feedback after use is collected as input, and the model is improved based on this feedback. The output is performance data of the improved model. This allows the system to continuously evolve and improve the user experience.

[0090] (Application Example 1)

[0091] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0092] There is a need for methods that efficiently integrate multiple intelligent systems, enabling not only convenient user access but also real-time delivery of product information based on voice input. Such technologies are essential for providing a more interactive and intuitive user experience.

[0093] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0094] In this invention, the server includes means for analyzing technical information and output examples of intelligent systems; means for inferring and integrating the functions of each intelligent system based on the analysis results; means for generating a new intelligent system based on the integrated functions and deploying it to the user terminal; and means for analyzing the user's voice input using the intelligent system and displaying product information and related images in real time. This enables the user to efficiently utilize multiple intelligent systems from a single interface and to interactively acquire product information.

[0095] An "intelligent system" refers to a collection of artificial intelligence designed to perform specific tasks or functions.

[0096] "Technical information" refers to information including documentation concerning the design, operation, and performance necessary for an intelligent system to function.

[0097] "Output examples" refer to specific examples that show the deliverables or results produced by an intelligent system.

[0098] "Analysis" refers to the process of thoroughly examining the technical information and output examples of intelligent systems to understand their characteristics and operating patterns.

[0099] "Integration" refers to combining the functions of multiple intelligence systems to create a single, unified system.

[0100] A "user terminal" refers to a device on which an intelligent system is deployed and used to utilize its functions.

[0101] "Voice input" refers to a method of converting spoken words by a user into digital signals to provide instructions and information to a system.

[0102] "Real-time" refers to the ability of a system to process information with minimal delay and provide results immediately.

[0103] This invention is a system that enables users to efficiently utilize the functions of multiple intelligent systems by integrating them. The server collects and analyzes technical information and output examples of the intelligent systems. Specifically, it uses the Google® Speech-to-Text API to convert speech input into text data, which is then processed on the server side. Based on this text data, the server uses the OpenAI® GPT model to generate product information and recommendations. It also uses a generative AI model, such as an image generation system (e.g., DALL-E), to generate product-related images in real time, which are then displayed on the user's device (e.g., smart glasses or a head-mounted display).

[0104] This system is designed to allow users to intuitively obtain product information using voice commands. For example, if a user gives the voice command "I'm looking for a leather jacket," the server will start analyzing the data and quickly generate and display relevant product information and images. An example of a prompt could be, "Please generate detailed information and design samples for leather jackets." This provides users with an intuitive and efficient search experience.

[0105] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0106] Step 1:

[0107] The user enters a voice command into the user's device. The device receives this voice data and uses the Google Speech-to-Text API to convert the voice into text data. This converted text is then output.

[0108] Step 2:

[0109] Text data is sent to the server. The server analyzes the received text data and uses OpenAI's GPT model to generate product information and recommendation data. Here, it generates the best response to the query based on the input text and outputs it.

[0110] Step 3:

[0111] Based on the generated product information, the server uses an image generation system to generate images related to the product. In this step, prompt text is input to the generation AI model, and images corresponding to that text are output. As a specific example, the prompt "Generate detailed information and design samples for a leather jacket" is used.

[0112] Step 4:

[0113] The server sends the generated product information and related images to the user's terminal. The terminal receives this information and displays it to the user in an intuitive interface. This allows the user to visually confirm the information obtained from voice input.

[0114] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0115] This invention relates to a system that integrates multiple artificial intelligence models and combines them with an emotion engine that recognizes user emotions. In addition to the technology of integrating the functions of multiple models, this system aims to provide a more personalized experience by recognizing user emotions in real time and adjusting responses accordingly.

[0116] Users access the platform through their terminals and select the artificial intelligence model they wish to use. Based on this selection, the server collects technical documentation and output examples for each model and analyzes them in detail. Through this analysis, the server extracts the operational parameters for each model and integrates their functions while ensuring compatibility between models.

[0117] Next, the server generates an integrated model and deploys it to the user terminal. In addition, it integrates an emotion engine and configures it to analyze the user's emotions. The terminal uses the emotion engine to process the user's speech, facial expressions, input data, etc., in real time during user interaction and infer the user's emotional state.

[0118] A concrete example is a customer support scenario. When a user accesses technical support and requests assistance, the server-integrated artificial intelligence model provides problem-solving steps. The emotion engine recognizes whether the user is frustrated or anxious and adjusts the tone and content of the response accordingly. For example, an frustrated user would receive a more sympathetic and prompt response, while an anxious user would be provided with additional reassuring information.

[0119] Furthermore, feedback information collected from users is statistically analyzed by the server and used to improve the model. In this way, the system is designed to continuously learn and improve the user experience.

[0120] The following describes the processing flow.

[0121] Step 1:

[0122] Users access the platform through their device and select from several artificial intelligence models they wish to use. They also input detailed information about their objectives and expected output.

[0123] Step 2:

[0124] The server collects technical documentation and output examples related to the selected artificial intelligence model from the database. This information serves as foundational data for understanding the model's functions and characteristics.

[0125] Step 3:

[0126] The server analyzes technical documents and output examples to extract the operating parameters and characteristics of each artificial intelligence model. Through this analysis, it gains a detailed understanding of the conditions and settings required for each model's operation.

[0127] Step 4:

[0128] The server integrates the functions of multiple artificial intelligence models based on the analysis results. This process involves establishing common interfaces and data formats to ensure compatibility between the models.

[0129] Step 5:

[0130] The server integrates an emotion engine to recognize user emotions and generates a new, integrated artificial intelligence model. The emotion engine has the capability to analyze user emotions in real time in order to personalize the user experience.

[0131] Step 6:

[0132] Once a new artificial intelligence model is generated, the server deploys it to the user's terminal. This makes the terminal ready to use the integrated model.

[0133] Step 7:

[0134] The device uses an emotion engine to analyze the user's speech and behavioral data in real time and infer their emotional state. A function is then activated that adjusts the response according to the user's emotions.

[0135] Step 8:

[0136] Users utilize artificial intelligence models and verify the results. Furthermore, the emotion engine optimizes the user experience.

[0137] Step 9:

[0138] User feedback is sent from the device to the server, where the server statistically analyzes the information. The analysis results are then used to improve the accuracy and performance of the artificial intelligence model.

[0139] (Example 2)

[0140] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0141] Current intelligent processing models struggle with integrating functions across different models, and their generative models lack the ability to respond to users' real-time emotions. This limits the provision of more sophisticated and personalized user experiences. Furthermore, there is a need to effectively incorporate user feedback to improve the entire intelligent processing model.

[0142] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0143] In this invention, the server includes means for analyzing technical information and output data of multiple intelligent processing models, means for inferring and aggregating the operational characteristics of each intelligent processing model based on the analysis results, and means for generating a new intelligent processing model based on the aggregated operational characteristics and deploying it to the user's device. This enables the effective integration of the functions of different intelligent processing models and allows for responses that take into account the user's emotions.

[0144] An "intelligent processing model" is an information processing system that uses artificial intelligence technology to perform data processing and analysis in order to solve specific problems.

[0145] "Technical information" refers to documents and data that contain specialized knowledge and specifications related to intelligent processing models.

[0146] "Output data" refers to the data that an intelligent processing model generates as a result or response in response to an input.

[0147] "Operational characteristics" refer to the traits or attributes that describe how an intelligent processing model behaves under specific conditions.

[0148] "Aggregation" is the process of combining multiple elements into one.

[0149] "User-facing devices" refer to devices or interfaces that users directly operate and use to utilize the functions of intelligent processing models.

[0150] An "emotional processing mechanism" is a technical configuration for detecting, analyzing, and reflecting the user's emotions in the response.

[0151] "Cooperation" is the ability for different intellectual processing models to work together and function without interfering with each other.

[0152] This invention provides a system for integrating intelligent processing models and generating responses that respond to the user's emotions.

[0153] The server first collects and analyzes technical information and output data from multiple intelligent processing models. For example, it analyzes documents related to specific machine learning algorithms and natural language processing engines, and uses this to infer the operational characteristics of each model. Based on these characteristics, the server integrates the functions of different models to generate a new intelligent processing model.

[0154] Next, the generated model is deployed to the user's device. Specifically, a server unit with a high-performance processor and sufficient memory is crucial hardware. Furthermore, efficient data processing is possible through the use of data analysis libraries and APIs.

[0155] The device uses a pre-installed emotion processing mechanism to process the user's speech and facial expression data in real time. Based on this, the device infers the user's emotional state and transmits that information to the server.

[0156] Consider a scenario where a user accesses customer support, for example, a rapid problem-solving procedure can be presented based on an integrated intelligent processing model. The emotion processing mechanism generates a more empathetic and responsive response when the user is frustrated.

[0157] Furthermore, to optimize responses based on the user's emotions, a generative AI model can be used to generate prompts. An example of a prompt is, "Generate a response that takes the user's emotions into consideration. The user is feeling anxious about the current situation."

[0158] In this way, the present invention realizes a system that can integrate different intelligent processing models and provide flexible responses that respond to the user's emotions.

[0159] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0160] Step 1:

[0161] The user selects their desired intelligent processing model through the terminal. The user's input is sent to the server as model selection information. The server receives this information and begins collecting technical information and output data for the corresponding intelligent processing model.

[0162] Step 2:

[0163] The server analyzes the collected technical information and output data. Technical documentation and output examples related to intelligent processing models are provided as input. The server uses natural language processing and data mining techniques to extract the model's operational characteristics from this data. This analysis clarifies what data processing is required and generates inferred operational characteristics.

[0164] Step 3:

[0165] The server aggregates the functions of different models based on their operational characteristics. The operational characteristics extracted in the previous step are used as input. The server uses integration technology to generate a single compatible intelligent processing model. As a result, a new intelligent processing model integrating the characteristics of multiple models is output.

[0166] Step 4:

[0167] The server deploys the generated intelligent processing model to the user's terminal. Deployment to the terminal is automatic, and the terminal sets the deployed model to a usable state. This process includes software updates and the installation of necessary libraries.

[0168] Step 5:

[0169] The device processes the user's emotions in real time using an emotion processing mechanism. Input data includes the user's voice and facial expressions. The device performs voice and facial analysis to infer the user's emotional state. This output data indicates the user's current emotional state.

[0170] Step 6:

[0171] The server adjusts its response based on the inferred emotional state. The server receives the user's emotional state and request as input. The generative AI model uses prompts such as, "Generate a response that takes the user's emotions into consideration," to generate an appropriate response. This response data is the final output.

[0172] (Application Example 2)

[0173] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0174] Modern information processing systems suffer from a lack of personalized service delivery that responds to users' emotional states. Furthermore, the effective integration of multiple machine learning engines is challenging, resulting in low system compatibility and inefficient functional integration. Solving these problems is essential.

[0175] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0176] In this invention, the server includes means for analyzing the technical documentation and output results of multiple machine learning engines in order to integrate the functions of multiple machine learning engines; means for inferring and integrating the functions of each machine learning engine based on the analysis results; and means for constructing a new machine learning engine based on the integrated functions and deploying it to an information processing device. This enables the provision of personalized information display content based on the user's emotional state and the efficient integration of multiple machine learning engines.

[0177] A "machine learning engine" is a system that analyzes data and builds learning models to achieve pattern recognition and prediction.

[0178] A "technical document" is a document that describes in detail the design, specifications, and operating principles of a machine learning engine.

[0179] "Output results" refer to the data and information generated as a result of a machine learning engine processing input data.

[0180] "Analysis" is the process of examining technical documents and output results in detail to clarify their structure and function.

[0181] "Integration" is the process of combining the functions of multiple machine learning engines to make them function as a single, integrated system.

[0182] An "information processing device" is a device that has the function of processing data and generating or managing information.

[0183] "Emotional state" refers to the user's current psychological state and mood, which can be inferred from their facial expressions, words, and other cues.

[0184] "Personalized information display content" refers to information and content that is customized according to the individual user's preferences and emotional state.

[0185] This invention is a system that provides personalized content based on the user's emotional state via an application installed on the user's terminal. The server integrates the functions of multiple machine learning engines and analyzes them from technical documents and output results. This allows it to infer the functions of each machine learning engine, build a new engine based on the integrated functions, and deploy it to the information processing device.

[0186] This system uses facial recognition and speech analysis algorithms to identify the user's emotional state in real time. Hardware includes smartphones and smart glasses, which capture facial expressions and speech via cameras and microphones. Software includes Google's Face API and Microsoft's Emotion API for facial recognition, and TensorFlow and PyTorch for emotion analysis. The server processes this data and recommends content that reflects the user's emotional state.

[0187] As a concrete example, when a user is watching a movie, if the application detects from their facial expression that they are "bored," it will automatically suggest an exciting action movie from its content library. This can improve the satisfaction of the viewing experience. The following prompt message is used: "Input the user's viewing history data and real-time sentiment analysis results to recommend the next content to watch. Select the optimal content type based on their emotional state, such as a gentle movie, an action-packed show, or a moving documentary."

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

[0189] Step 1:

[0190] The server retrieves technical documentation and output results from multiple machine learning engines. It analyzes the retrieved data to identify the functions of each engine. The input data consists of technical documentation and output results, with the output being information about the functions of each engine. The analysis involves classifying the document content using natural language processing techniques and identifying the functions.

[0191] Step 2:

[0192] The server integrates the functions of the machine learning engines based on the analysis results. The input is the output information from step 1, and the output is the integrated engine model. This integration involves using algorithms that combine the strengths of each engine while ensuring compatibility.

[0193] Step 3:

[0194] The device uses its camera and microphone to capture the user's emotional state in real time from their face and voice. Input is facial recognition and voice data, and output is the estimated emotional state. This includes specific actions for performing real-time emotion analysis using Google's Face API and Emotion API.

[0195] Step 4:

[0196] The server selects the most suitable content for the user based on the captured emotional state. The input for this step is the emotional state and the user's viewing history data, and the output is recommended content. A recommendation algorithm is used for selection, extracting content that matches the user's interests and emotions.

[0197] Step 5:

[0198] Users view content provided on their devices and receive a personalized experience tailored to their emotions. The content provided is selected by the server and matches the emotional data at the time of viewing. After viewing, users have the opportunity to provide feedback, which is sent to the server and used in the next step.

[0199] Step 6:

[0200] The server analyzes feedback collected from users and uses it to improve the new integrated model. The input is feedback information, and the output is the improved engine model. The analysis includes evaluating the feedback information using statistical methods and specific actions for training the model.

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

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

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

[0204] [Second Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0217] This invention aims to realize a system that integrates multiple artificial intelligence models, allowing users to efficiently utilize their functions. This system primarily involves a server analyzing the technical documentation and output examples of each artificial intelligence model, and then integrating their functions based on the analysis results.

[0218] When a user accesses the platform and selects multiple artificial intelligence models, the server collects technical documentation and output examples related to these models from a database. Based on the collected data, the server performs analysis to gain a detailed understanding of the characteristics and operating patterns of each model. Based on the information obtained from this analysis, the server integrates the functions of multiple models and designs a new integrated model.

[0219] The server generates a newly integrated artificial intelligence model and deploys it to the user's terminal. This allows the user to conveniently utilize the functions of multiple artificial intelligence models through a single interface on their terminal.

[0220] As a concrete example, consider the case where the user selects an AI model for automatic article generation and image generation. In this case, the server analyzes the technical documentation and past output examples of both models and integrates the functionality to simultaneously generate images based on the article's theme. This allows the user to input the article's theme and structure once, and related images will be generated at the same time, enabling consistent project progress.

[0221] Furthermore, the server acquires user feedback, which is then used as data to improve the model's accuracy and performance. This feedback cycle provides a mechanism for continuously improving the performance of the artificial intelligence model.

[0222] The following describes the processing flow.

[0223] Step 1:

[0224] The user accesses the platform and selects the artificial intelligence model they wish to use. Once the selection is complete, the user enters information about the task they intend to perform and the expected output.

[0225] Step 2:

[0226] The server automatically collects technical documentation and existing output examples related to the selected artificial intelligence model from the database. This information collection is a preliminary step to accurately understanding the model's capabilities.

[0227] Step 3:

[0228] The server analyzes the collected technical documents and output examples. Using natural language processing techniques, it identifies what inputs each model requires and what results it outputs. This analysis provides a detailed understanding of the model's characteristics and operation.

[0229] Step 4:

[0230] The server infers the functions of each artificial intelligence model based on the analysis results and integrates those functions. In doing so, it establishes common operating parameters and data formats to build a seamless interface between the artificial intelligence models.

[0231] Step 5:

[0232] The server generates new artificial intelligence models based on integrated functionality. The generation process includes steps that combine training data from different models as needed.

[0233] Step 6:

[0234] The server deploys the newly generated artificial intelligence model to the user's terminal. This allows the user to use the AI ​​model in the configured environment.

[0235] Step 7:

[0236] Users interact with the deployed artificial intelligence model to perform tasks. They can also review the generated output and provide additional instructions.

[0237] Step 8:

[0238] User feedback is sent to the server. The server analyzes this feedback and uses it to improve the artificial intelligence model. Through this feedback loop, the model's performance and accuracy are improved.

[0239] (Example 1)

[0240] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0241] With the advancement of information processing technology, there is a growing need to efficiently utilize and integrate multiple information processing models with different characteristics. However, due to differences in the technical characteristics and outputs of each model, users cannot easily integrate them, and the integration process is time-consuming and laborious. Furthermore, there is a lack of mechanisms to effectively utilize post-use feedback and improve model performance. Therefore, to solve these problems, a means of efficiently analyzing and integrating the characteristics of multiple models is necessary, and it is also required to continuously improve performance by utilizing feedback.

[0242] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0243] In this invention, the server includes means for an information processing device to analyze technical descriptions and generated output examples of multiple information processing models, means for identifying and integrating the functions of each information processing model based on the analysis results, and means for generating a new integrated information processing model and providing it to the user's input device. This enables the efficient integration of information processing models with different characteristics, allowing users to conveniently utilize them through a consistent interface. Furthermore, performance improvements are continuously made based on user feedback, improving the accuracy and responsiveness of the model.

[0244] An "information processing device" is a general term for a device that receives data, processes and analyzes that data, and generates intended output.

[0245] An "information processing model" is a set of calculations and logic used to generate a desired output for a given input.

[0246] "Technical descriptions" refer to documents and materials that describe the design, operation, and characteristics of an information processing model.

[0247] "Analysis" is the process of understanding the structure of information and extracting the necessary information.

[0248] "Identifying functions" means clarifying the specific capabilities and roles that each information processing model provides.

[0249] "Integration" refers to combining the functions of multiple information processing models to operate as a single system.

[0250] "User input device" refers to an electronic device used by a user to input information and interact with a system.

[0251] "Generation" refers to creating a working version of the designed information processing model.

[0252] "Feedback" refers to opinions and reports about the performance and usability that users provide after using a system.

[0253] This invention includes embodiments of a system that integrates multiple information processing models and allows users to utilize them efficiently. Essentially, it provides a platform that integrates the capabilities of multiple information processing models, based on an information processing device (server) and a user input device (terminal).

[0254] The server first collects descriptions of relevant technologies and past output examples from a database, based on the information processing model selected by the user through an input device. This utilizes software libraries for natural language processing and data mining. Specific examples of useful software include Python's Pandas library and TensorFlow. The server then analyzes this data to understand the characteristics of each model.

[0255] Subsequently, the server designs an integrated model and actually generates it. The generated integrated model is provided to the user's terminal, enabling operation on the terminal. The user can obtain systematic data output by entering specific prompt statements through the integrated interface. In this process, the integration function of the information processing model is utilized in generating the output, thus providing consistent results.

[0256] As a concrete example, a user can input a prompt to generate information on a theme such as "articles about environmental protection." Upon inputting this prompt, the system automatically creates related visual materials along with the article, providing consistent content. This significantly improves user efficiency and allows them to leverage the strengths of multiple information processing models.

[0257] Furthermore, the server continuously collects user feedback and uses it as data to improve the model's performance. This allows the information processing system to continuously evolve and provide users with the optimal interface and functionality.

[0258] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0259] Step 1:

[0260] The user accesses the platform and selects the information processing model they wish to use. Information about the selected model is entered and sent to the server. This selection prompts the server to begin the process of collecting technical descriptions and output examples of the selected model from its database.

[0261] Step 2:

[0262] The server collects technical documentation and output examples related to the information processing model selected by the user from a database. It uses the identification information of the selected model as input and retrieves relevant data based on this. The server uses Python or SQL to search the database and extract the necessary data. The output is a dataset of technical specifications and historical model outputs.

[0263] Step 3:

[0264] The server analyzes the collected technical descriptions and output examples to understand the characteristics of each model. The collected dataset is used as input, and the output provides characteristic information about the model. Specifically, the server uses natural language processing algorithms to extract features and identify the operating patterns of the models.

[0265] Step 4:

[0266] The server designs a new model that integrates the functions of each information processing model based on the analysis results. The input is characteristic information obtained from each information processing model. The server uses this information to design a model that enables seamless integration of functions between the models. The output is the design specification for the new integrated model.

[0267] Step 5:

[0268] The server actually generates the designed integrated model. In this step, the structure of the information processing model is built based on the design specifications, and the generated model is ready to go. The input is the design specifications, and the output is the actually working integrated model.

[0269] Step 6:

[0270] The generated integrated model is provided to the user's terminal, and the user can use its interface. The user enters prompts from the terminal and requests the generation of output based on them. In this step, the integrated model performs data processing and calculations based on the input prompts and generates the specified output. The output is information requested by the user.

[0271] Step 7:

[0272] The server collects feedback from users and uses it to improve the model's performance. User feedback after use is collected as input, and the model is improved based on this feedback. The output is performance data of the improved model. This allows the system to continuously evolve and improve the user experience.

[0273] (Application Example 1)

[0274] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0275] There is a need for methods that efficiently integrate multiple intelligent systems, enabling not only convenient user access but also real-time delivery of product information based on voice input. Such technologies are essential for providing a more interactive and intuitive user experience.

[0276] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0277] In this invention, the server includes means for analyzing the technical information and output examples of intelligent systems, means for inferring and integrating the functions of each intelligent system based on the analysis results, means for generating a new intelligent system based on the integrated functions and deploying it to the user terminal, and means for analyzing the voice input of the user using the intelligent system and displaying information related to the product and related images in real time. Thereby, the user can efficiently utilize a plurality of intelligent systems from one interface and interactively obtain product information.

[0278] "Intelligent system" refers to an aggregate of artificial intelligence designed to execute specific tasks or functions.

[0279] "Technical information" refers to information including documents related to the design, operation, and performance necessary for the intelligent system to operate.

[0280] "Output example" refers to a specific example indicating the artifacts or results executed by the intelligent system.

[0281] "Analysis" refers to the process of investigating in detail the technical information and output examples of the intelligent system and understanding its characteristics and operation patterns. <000089!>

[0282] "Integration" means connecting the functions of multiple intelligent systems to form one unified system.

[0283] "User terminal" refers to a device for deploying the intelligent system and utilizing its functions.

[0284] "Voice input" refers to a method of converting the words spoken by the user into digital signals to give instructions and information to the system.

[0285] "Real time" refers to the ability of the system to provide results immediately with minimal delay when processing information.

[0286] The present invention is a system that enables users to efficiently use the functions of multiple intelligent systems by integrating them. The server collects and analyzes the technical information and output examples of the intelligent systems. Specifically, it uses the Google Speech-to-Text API to convert voice input into text data and processes this on the server side. Based on this text data, the server uses OpenAI's GPT model to generate information and recommendations regarding products. Additionally, it uses an image generation system (e.g., DALL-E), which is a generative AI model, to generate images related to the products in real time and display these on the user's client terminal (e.g., smart glasses or head-mounted displays).

[0287] This system is designed to allow users to intuitively obtain product information using voice commands. For example, when a user issues a voice command such as "looking for a leather jacket", the server starts the analysis and quickly generates and displays relevant product information and images. As an example of the prompt text, a format like "Please generate detailed information and design samples of a leather jacket." can be used. This enables the user to obtain an intuitive and efficient search experience.

[0288] The flow of specific processing in Application Example 1 will be described using FIG. 12.

[0289] Step 1:

[0290] The user inputs a voice command into the client terminal. The terminal receives this voice data and uses the Google Speech-to-Text API to convert the voice into text data. This converted text is output.

[0291] Step 2:

[0292] Text data is sent to the server. The server analyzes the received text data and uses OpenAI's GPT model to generate product information and recommendation data. Here, it generates the best response to the query based on the input text and outputs it.

[0293] Step 3:

[0294] Based on the generated product information, the server uses an image generation system to generate images related to the product. In this step, prompt text is input to the generation AI model, and images corresponding to that text are output. As a specific example, the prompt "Generate detailed information and design samples for a leather jacket" is used.

[0295] Step 4:

[0296] The server sends the generated product information and related images to the user's terminal. The terminal receives this information and displays it to the user in an intuitive interface. This allows the user to visually confirm the information obtained from voice input.

[0297] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0298] This invention relates to a system that integrates multiple artificial intelligence models and combines them with an emotion engine that recognizes user emotions. In addition to the technology of integrating the functions of multiple models, this system aims to provide a more personalized experience by recognizing user emotions in real time and adjusting responses accordingly.

[0299] Users access the platform through their terminals and select the artificial intelligence model they wish to use. Based on this selection, the server collects technical documentation and output examples for each model and analyzes them in detail. Through this analysis, the server extracts the operational parameters for each model and integrates their functions while ensuring compatibility between models.

[0300] Next, the server generates an integrated model and deploys it to the user terminal. In addition, it integrates an emotion engine and configures it to analyze the user's emotions. The terminal uses the emotion engine to process the user's speech, facial expressions, input data, etc., in real time during user interaction and infer the user's emotional state.

[0301] A concrete example is a customer support scenario. When a user accesses technical support and requests assistance, the server-integrated artificial intelligence model provides problem-solving steps. The emotion engine recognizes whether the user is frustrated or anxious and adjusts the tone and content of the response accordingly. For example, an frustrated user would receive a more sympathetic and prompt response, while an anxious user would be provided with additional reassuring information.

[0302] Furthermore, feedback information collected from users is statistically analyzed by the server and used to improve the model. In this way, the system is designed to continuously learn and improve the user experience.

[0303] The following describes the processing flow.

[0304] Step 1:

[0305] Users access the platform through their device and select from several artificial intelligence models they wish to use. They also input detailed information about their objectives and expected output.

[0306] Step 2:

[0307] The server collects technical documents and output examples related to the selected artificial intelligence model from the database. This information serves as the basic data for understanding the functions and characteristics of the model.

[0308] Step 3:

[0309] The server analyzes the technical documents and output examples and extracts the operation parameters and characteristics of each artificial intelligence model. Through the analysis, the conditions and settings required for the operation of each model are grasped in detail.

[0310] Step 4:

[0311] Based on the analysis results, the server integrates the functions of multiple artificial intelligence models. In this process, common interfaces and data formats are set to ensure compatibility between models.

[0312] Step 5: [[ID=2​​​​​​​​​​​​​​​​​​​​​​​​​Users utilize artificial intelligence models and verify the results. Furthermore, the emotion engine optimizes the user experience.

[0320] Step 9:

[0321] User feedback is sent from the device to the server, where the server statistically analyzes the information. The analysis results are then used to improve the accuracy and performance of the artificial intelligence model.

[0322] (Example 2)

[0323] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0324] Current intelligent processing models struggle with integrating functions across different models, and their generative models lack the ability to respond to users' real-time emotions. This limits the provision of more sophisticated and personalized user experiences. Furthermore, there is a need to effectively incorporate user feedback to improve the entire intelligent processing model.

[0325] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0326] In this invention, the server includes means for analyzing technical information and output data of multiple intelligent processing models, means for inferring and aggregating the operational characteristics of each intelligent processing model based on the analysis results, and means for generating a new intelligent processing model based on the aggregated operational characteristics and deploying it to the user's device. This enables the effective integration of the functions of different intelligent processing models and allows for responses that take into account the user's emotions.

[0327] An "intelligent processing model" is an information processing system that uses artificial intelligence technology to perform data processing and analysis in order to solve specific problems.

[0328] "Technical information" refers to documents and data that contain specialized knowledge and specifications related to intelligent processing models.

[0329] "Output data" refers to the data that an intelligent processing model generates as a result or response in response to an input.

[0330] "Operational characteristics" refer to the traits or attributes that describe how an intelligent processing model behaves under specific conditions.

[0331] "Aggregation" is the process of combining multiple elements into one.

[0332] "User-facing devices" refer to devices or interfaces that users directly operate and use to utilize the functions of intelligent processing models.

[0333] An "emotional processing mechanism" is a technical configuration for detecting, analyzing, and reflecting the user's emotions in the response.

[0334] "Cooperation" is the ability for different intellectual processing models to work together and function without interfering with each other.

[0335] This invention provides a system for integrating intelligent processing models and generating responses that respond to the user's emotions.

[0336] The server first collects and analyzes technical information and output data from multiple intelligent processing models. For example, it analyzes documents related to specific machine learning algorithms and natural language processing engines, and uses this to infer the operational characteristics of each model. Based on these characteristics, the server integrates the functions of different models to generate a new intelligent processing model.

[0337] Next, the generated model is deployed to the user's device. Specifically, a server unit with a high-performance processor and sufficient memory is crucial hardware. Furthermore, efficient data processing is possible through the use of data analysis libraries and APIs.

[0338] The device uses a pre-installed emotion processing mechanism to process the user's speech and facial expression data in real time. Based on this, the device infers the user's emotional state and transmits that information to the server.

[0339] Consider a scenario where a user accesses customer support, for example, a rapid problem-solving procedure can be presented based on an integrated intelligent processing model. The emotion processing mechanism generates a more empathetic and responsive response when the user is frustrated.

[0340] Furthermore, to optimize responses based on the user's emotions, a generative AI model can be used to generate prompts. An example of a prompt is, "Generate a response that takes the user's emotions into consideration. The user is feeling anxious about the current situation."

[0341] In this way, the present invention realizes a system that can integrate different intelligent processing models and provide flexible responses that respond to the user's emotions.

[0342] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0343] Step 1:

[0344] The user selects their desired intelligent processing model through the terminal. The user's input is sent to the server as model selection information. The server receives this information and begins collecting technical information and output data for the corresponding intelligent processing model.

[0345] Step 2:

[0346] The server analyzes the collected technical information and output data. Technical documentation and output examples related to intelligent processing models are provided as input. The server uses natural language processing and data mining techniques to extract the model's operational characteristics from this data. This analysis clarifies what data processing is required and generates inferred operational characteristics.

[0347] Step 3:

[0348] The server aggregates the functions of different models based on their operational characteristics. The operational characteristics extracted in the previous step are used as input. The server uses integration technology to generate a single compatible intelligent processing model. As a result, a new intelligent processing model integrating the characteristics of multiple models is output.

[0349] Step 4:

[0350] The server deploys the generated intelligent processing model to the user's terminal. Deployment to the terminal is automatic, and the terminal sets the deployed model to a usable state. This process includes software updates and the installation of necessary libraries.

[0351] Step 5:

[0352] The device processes the user's emotions in real time using an emotion processing mechanism. Input data includes the user's voice and facial expressions. The device performs voice and facial analysis to infer the user's emotional state. This output data indicates the user's current emotional state.

[0353] Step 6:

[0354] The server adjusts its response based on the inferred emotional state. The server receives the user's emotional state and request as input. The generative AI model uses prompts such as, "Generate a response that takes the user's emotions into consideration," to generate an appropriate response. This response data is the final output.

[0355] (Application Example 2)

[0356] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0357] Modern information processing systems suffer from a lack of personalized service delivery that responds to users' emotional states. Furthermore, the effective integration of multiple machine learning engines is challenging, resulting in low system compatibility and inefficient functional integration. Solving these problems is essential.

[0358] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0359] In this invention, the server includes means for analyzing the technical documentation and output results of multiple machine learning engines in order to integrate the functions of multiple machine learning engines; means for inferring and integrating the functions of each machine learning engine based on the analysis results; and means for constructing a new machine learning engine based on the integrated functions and deploying it to an information processing device. This enables the provision of personalized information display content based on the user's emotional state and the efficient integration of multiple machine learning engines.

[0360] A "machine learning engine" is a system that analyzes data and builds learning models to achieve pattern recognition and prediction.

[0361] A "technical document" is a document that describes in detail the design, specifications, and operating principles of a machine learning engine.

[0362] "Output results" refer to the data and information generated as a result of a machine learning engine processing input data.

[0363] "Analysis" is the process of examining technical documents and output results in detail to clarify their structure and function.

[0364] "Integration" is the process of combining the functions of multiple machine learning engines to make them function as a single, integrated system.

[0365] An "information processing device" is a device that has the function of processing data and generating or managing information.

[0366] "Emotional state" refers to the user's current psychological state and mood, which can be inferred from their facial expressions, words, and other cues.

[0367] "Personalized information display content" refers to information and content that is customized according to the individual user's preferences and emotional state.

[0368] This invention is a system that provides personalized content based on the user's emotional state via an application installed on the user's terminal. The server integrates the functions of multiple machine learning engines and analyzes them from technical documents and output results. This allows it to infer the functions of each machine learning engine, build a new engine based on the integrated functions, and deploy it to the information processing device.

[0369] This system uses facial recognition and speech analysis algorithms to identify the user's emotional state in real time. Hardware includes smartphones and smart glasses, which capture facial expressions and speech via cameras and microphones. Software includes Google's Face API and Microsoft's Emotion API for facial recognition, and TensorFlow and PyTorch for emotion analysis. A server processes this data and recommends content that reflects the user's emotional state.

[0370] As a concrete example, when a user is watching a movie, if the application detects from their facial expression that they are "bored," it will automatically suggest an exciting action movie from its content library. This can improve the satisfaction of the viewing experience. The following prompt message is used: "Input the user's viewing history data and real-time sentiment analysis results to recommend the next content to watch. Select the optimal content type based on their emotional state, such as a gentle movie, an action-packed show, or a moving documentary."

[0371] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0372] Step 1:

[0373] The server retrieves technical documentation and output results from multiple machine learning engines. It analyzes the retrieved data to identify the functions of each engine. The input data consists of technical documentation and output results, with the output being information about the functions of each engine. The analysis involves classifying the document content using natural language processing techniques and identifying the functions.

[0374] Step 2:

[0375] The server integrates the functions of the machine learning engines based on the analysis results. The input is the output information from step 1, and the output is the integrated engine model. This integration involves using algorithms that combine the strengths of each engine while ensuring compatibility.

[0376] Step 3:

[0377] The device uses its camera and microphone to capture the user's emotional state in real time from their face and voice. Input is facial recognition and voice data, and output is the estimated emotional state. This includes specific actions for performing real-time emotion analysis using Google's Face API and Emotion API.

[0378] Step 4:

[0379] The server selects the most suitable content for the user based on the captured emotional state. The input for this step is the emotional state and the user's viewing history data, and the output is recommended content. A recommendation algorithm is used for selection, extracting content that matches the user's interests and emotions.

[0380] Step 5:

[0381] Users view content provided on their devices and receive a personalized experience tailored to their emotions. The content provided is selected by the server and matches the emotional data at the time of viewing. After viewing, users have the opportunity to provide feedback, which is sent to the server and used in the next step.

[0382] Step 6:

[0383] The server analyzes feedback collected from users and uses it to improve the new integrated model. The input is feedback information, and the output is the improved engine model. The analysis includes evaluating the feedback information using statistical methods and specific actions for training the model.

[0384] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0385] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0386] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0387] [Third Embodiment]

[0388] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0389] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0390] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0391] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0392] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0393] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0394] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0395] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0396] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0397] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0398] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0399] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0400] This invention aims to realize a system that integrates multiple artificial intelligence models, allowing users to efficiently utilize their functions. This system primarily involves a server analyzing the technical documentation and output examples of each artificial intelligence model, and then integrating their functions based on the analysis results.

[0401] When a user accesses the platform and selects multiple artificial intelligence models, the server collects technical documentation and output examples related to these models from a database. Based on the collected data, the server performs analysis to gain a detailed understanding of the characteristics and operating patterns of each model. Based on the information obtained from this analysis, the server integrates the functions of multiple models and designs a new integrated model.

[0402] The server generates a newly integrated artificial intelligence model and deploys it to the user's terminal. This allows the user to conveniently utilize the functions of multiple artificial intelligence models through a single interface on their terminal.

[0403] As a concrete example, consider the case where the user selects an AI model for automatic article generation and image generation. In this case, the server analyzes the technical documentation and past output examples of both models and integrates the functionality to simultaneously generate images based on the article's theme. This allows the user to input the article's theme and structure once, and related images will be generated at the same time, enabling consistent project progress.

[0404] Furthermore, the server acquires user feedback, which is then used as data to improve the model's accuracy and performance. This feedback cycle provides a mechanism for continuously improving the performance of the artificial intelligence model.

[0405] The following describes the processing flow.

[0406] Step 1:

[0407] The user accesses the platform and selects the artificial intelligence model they wish to use. Once the selection is complete, the user enters information about the task they intend to perform and the expected output.

[0408] Step 2:

[0409] The server automatically collects technical documentation and existing output examples related to the selected artificial intelligence model from the database. This information collection is a preliminary step to accurately understanding the model's capabilities.

[0410] Step 3:

[0411] The server analyzes the collected technical documents and output examples. Using natural language processing techniques, it identifies what inputs each model requires and what results it outputs. This analysis provides a detailed understanding of the model's characteristics and operation.

[0412] Step 4:

[0413] The server infers the functions of each artificial intelligence model based on the analysis results and integrates those functions. In doing so, it establishes common operating parameters and data formats to build a seamless interface between the artificial intelligence models.

[0414] Step 5:

[0415] The server generates new artificial intelligence models based on integrated functionality. The generation process includes steps that combine training data from different models as needed.

[0416] Step 6:

[0417] The server deploys the newly generated artificial intelligence model to the user's terminal. This allows the user to use the AI ​​model in the configured environment.

[0418] Step 7:

[0419] Users interact with the deployed artificial intelligence model to perform tasks. They can also review the generated output and provide additional instructions.

[0420] Step 8:

[0421] User feedback is sent to the server. The server analyzes this feedback and uses it to improve the artificial intelligence model. Through this feedback loop, the model's performance and accuracy are improved.

[0422] (Example 1)

[0423] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0424] With the advancement of information processing technology, there is a growing need to efficiently utilize and integrate multiple information processing models with different characteristics. However, due to differences in the technical characteristics and outputs of each model, users cannot easily integrate them, and the integration process is time-consuming and laborious. Furthermore, there is a lack of mechanisms to effectively utilize post-use feedback and improve model performance. Therefore, to solve these problems, a means of efficiently analyzing and integrating the characteristics of multiple models is necessary, and it is also required to continuously improve performance by utilizing feedback.

[0425] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0426] In this invention, the server includes means for an information processing device to analyze technical descriptions and generated output examples of multiple information processing models, means for identifying and integrating the functions of each information processing model based on the analysis results, and means for generating a new integrated information processing model and providing it to the user's input device. This enables the efficient integration of information processing models with different characteristics, allowing users to conveniently utilize them through a consistent interface. Furthermore, performance improvements are continuously made based on user feedback, improving the accuracy and responsiveness of the model.

[0427] An "information processing device" is a general term for a device that receives data, processes and analyzes that data, and generates intended output.

[0428] An "information processing model" is a set of calculations and logic used to generate a desired output for a given input.

[0429] "Technical descriptions" refer to documents and materials that describe the design, operation, and characteristics of an information processing model.

[0430] "Analysis" is the process of understanding the structure of information and extracting the necessary information.

[0431] "Identifying functions" means clarifying the specific capabilities and roles that each information processing model provides.

[0432] "Integration" refers to combining the functions of multiple information processing models to operate as a single system.

[0433] "User input device" refers to an electronic device used by a user to input information and interact with a system.

[0434] "Generation" refers to creating a working version of the designed information processing model.

[0435] "Feedback" refers to opinions and reports about the performance and usability that users provide after using a system.

[0436] This invention includes embodiments of a system that integrates multiple information processing models and allows users to utilize them efficiently. Essentially, it provides a platform that integrates the capabilities of multiple information processing models, based on an information processing device (server) and a user input device (terminal).

[0437] The server first collects descriptions of relevant technologies and past output examples from a database, based on the information processing model selected by the user through an input device. This utilizes software libraries for natural language processing and data mining. Specific examples of useful software include Python's Pandas library and TensorFlow. The server then analyzes this data to understand the characteristics of each model.

[0438] Subsequently, the server designs an integrated model and actually generates it. The generated integrated model is provided to the user's terminal, enabling operation on the terminal. The user can obtain systematic data output by entering specific prompt statements through the integrated interface. In this process, the integration function of the information processing model is utilized in generating the output, thus providing consistent results.

[0439] As a concrete example, a user can input a prompt to generate information on a theme such as "articles about environmental protection." Upon inputting this prompt, the system automatically creates related visual materials along with the article, providing consistent content. This significantly improves user efficiency and allows them to leverage the strengths of multiple information processing models.

[0440] Furthermore, the server continuously collects user feedback and uses it as data to improve the model's performance. This allows the information processing system to continuously evolve and provide users with the optimal interface and functionality.

[0441] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0442] Step 1:

[0443] The user accesses the platform and selects the information processing model they wish to use. Information about the selected model is entered and sent to the server. This selection prompts the server to begin the process of collecting technical descriptions and output examples of the selected model from its database.

[0444] Step 2:

[0445] The server collects technical documentation and output examples related to the information processing model selected by the user from a database. It uses the identification information of the selected model as input and retrieves relevant data based on this. The server uses Python or SQL to search the database and extract the necessary data. The output is a dataset of technical specifications and historical model outputs.

[0446] Step 3:

[0447] The server analyzes the collected technical descriptions and output examples to understand the characteristics of each model. The collected dataset is used as input, and the output provides characteristic information about the model. Specifically, the server uses natural language processing algorithms to extract features and identify the operating patterns of the models.

[0448] Step 4:

[0449] The server designs a new model that integrates the functions of each information processing model based on the analysis results. The input is characteristic information obtained from each information processing model. The server uses this information to design a model that enables seamless integration of functions between the models. The output is the design specification for the new integrated model.

[0450] Step 5:

[0451] The server actually generates the designed integrated model. In this step, the structure of the information processing model is built based on the design specifications, and the generated model is ready to go. The input is the design specifications, and the output is the actually working integrated model.

[0452] Step 6:

[0453] The generated integrated model is provided to the user's terminal, and the user can use its interface. The user enters prompts from the terminal and requests the generation of output based on them. In this step, the integrated model performs data processing and calculations based on the input prompts and generates the specified output. The output is information requested by the user.

[0454] Step 7:

[0455] The server collects feedback from users and uses it to improve the model's performance. User feedback after use is collected as input, and the model is improved based on this feedback. The output is performance data of the improved model. This allows the system to continuously evolve and improve the user experience.

[0456] (Application Example 1)

[0457] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0458] There is a need for methods that efficiently integrate multiple intelligent systems, enabling not only convenient user access but also real-time delivery of product information based on voice input. Such technologies are essential for providing a more interactive and intuitive user experience.

[0459] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0460] In this invention, the server includes means for analyzing technical information and output examples of intelligent systems; means for inferring and integrating the functions of each intelligent system based on the analysis results; means for generating a new intelligent system based on the integrated functions and deploying it to the user terminal; and means for analyzing the user's voice input using the intelligent system and displaying product information and related images in real time. This enables the user to efficiently utilize multiple intelligent systems from a single interface and to interactively acquire product information.

[0461] An "intelligent system" refers to a collection of artificial intelligence designed to perform specific tasks or functions.

[0462] "Technical information" refers to information including documentation concerning the design, operation, and performance necessary for an intelligent system to function.

[0463] "Output examples" refer to specific examples that show the deliverables or results produced by an intelligent system.

[0464] "Analysis" refers to the process of thoroughly examining the technical information and output examples of intelligent systems to understand their characteristics and operating patterns.

[0465] "Integration" refers to combining the functions of multiple intelligence systems to create a single, unified system.

[0466] A "user terminal" refers to a device on which an intelligent system is deployed and used to utilize its functions.

[0467] "Voice input" refers to a method of converting spoken words by a user into digital signals to provide instructions and information to a system.

[0468] "Real-time" refers to the ability of a system to process information with minimal delay and provide results immediately.

[0469] This invention is a system that enables users to efficiently utilize the functions of multiple intelligent systems by integrating them. The server collects and analyzes technical information and output examples of the intelligent systems. Specifically, it uses the Google Speech-to-Text API to convert speech input into text data, which is then processed on the server side. Based on this text data, the server uses OpenAI's GPT model to generate information and recommendations about products. It also uses a generative AI model, such as an image generation system (e.g., DALL-E), to generate images related to products in real time, which are then displayed on the user's device (e.g., smart glasses or a head-mounted display).

[0470] This system is designed to allow users to intuitively obtain product information using voice commands. For example, if a user gives the voice command "I'm looking for a leather jacket," the server will start analyzing the data and quickly generate and display relevant product information and images. An example of a prompt could be, "Please generate detailed information and design samples for leather jackets." This provides users with an intuitive and efficient search experience.

[0471] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0472] Step 1:

[0473] The user enters a voice command into the user's device. The device receives this voice data and uses the Google Speech-to-Text API to convert the voice into text data. This converted text is then output.

[0474] Step 2:

[0475] Text data is sent to the server. The server analyzes the received text data and uses OpenAI's GPT model to generate product information and recommendation data. Here, it generates the best response to the query based on the input text and outputs it.

[0476] Step 3:

[0477] Based on the generated product information, the server uses an image generation system to generate images related to the product. In this step, prompt text is input to the generation AI model, and images corresponding to that text are output. As a specific example, the prompt "Generate detailed information and design samples for a leather jacket" is used.

[0478] Step 4:

[0479] The server sends the generated product information and related images to the user's terminal. The terminal receives this information and displays it to the user in an intuitive interface. This allows the user to visually confirm the information obtained from voice input.

[0480] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0481] This invention relates to a system that integrates multiple artificial intelligence models and combines them with an emotion engine that recognizes user emotions. In addition to the technology of integrating the functions of multiple models, this system aims to provide a more personalized experience by recognizing user emotions in real time and adjusting responses accordingly.

[0482] Users access the platform through their terminals and select the artificial intelligence model they wish to use. Based on this selection, the server collects technical documentation and output examples for each model and analyzes them in detail. Through this analysis, the server extracts the operational parameters for each model and integrates their functions while ensuring compatibility between models.

[0483] Next, the server generates an integrated model and deploys it to the user terminal. In addition, it integrates an emotion engine and configures it to analyze the user's emotions. The terminal uses the emotion engine to process the user's speech, facial expressions, input data, etc., in real time during user interaction and infer the user's emotional state.

[0484] A concrete example is a customer support scenario. When a user accesses technical support and requests assistance, the server-integrated artificial intelligence model provides problem-solving steps. The emotion engine recognizes whether the user is frustrated or anxious and adjusts the tone and content of the response accordingly. For example, an frustrated user would receive a more sympathetic and prompt response, while an anxious user would be provided with additional reassuring information.

[0485] Furthermore, feedback information collected from users is statistically analyzed by the server and used to improve the model. In this way, the system is designed to continuously learn and improve the user experience.

[0486] The following describes the processing flow.

[0487] Step 1:

[0488] Users access the platform through their device and select from several artificial intelligence models they wish to use. They also input detailed information about their objectives and expected output.

[0489] Step 2:

[0490] The server collects technical documentation and output examples related to the selected artificial intelligence model from the database. This information serves as foundational data for understanding the model's functions and characteristics.

[0491] Step 3:

[0492] The server analyzes technical documents and output examples to extract the operating parameters and characteristics of each artificial intelligence model. Through this analysis, it gains a detailed understanding of the conditions and settings required for each model's operation.

[0493] Step 4:

[0494] The server integrates the functions of multiple artificial intelligence models based on the analysis results. This process involves establishing common interfaces and data formats to ensure compatibility between the models.

[0495] Step 5:

[0496] The server integrates an emotion engine to recognize user emotions and generates a new, integrated artificial intelligence model. The emotion engine has the capability to analyze user emotions in real time in order to personalize the user experience.

[0497] Step 6:

[0498] Once a new artificial intelligence model is generated, the server deploys it to the user's terminal. This makes the terminal ready to use the integrated model.

[0499] Step 7:

[0500] The device uses an emotion engine to analyze the user's speech and behavioral data in real time and infer their emotional state. A function is then activated that adjusts the response according to the user's emotions.

[0501] Step 8:

[0502] Users utilize artificial intelligence models and verify the results. Furthermore, the emotion engine optimizes the user experience.

[0503] Step 9:

[0504] User feedback is sent from the device to the server, where the server statistically analyzes the information. The analysis results are then used to improve the accuracy and performance of the artificial intelligence model.

[0505] (Example 2)

[0506] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0507] Current intelligent processing models struggle with integrating functions across different models, and their generative models lack the ability to respond to users' real-time emotions. This limits the provision of more sophisticated and personalized user experiences. Furthermore, there is a need to effectively incorporate user feedback to improve the entire intelligent processing model.

[0508] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0509] In this invention, the server includes means for analyzing technical information and output data of multiple intelligent processing models, means for inferring and aggregating the operational characteristics of each intelligent processing model based on the analysis results, and means for generating a new intelligent processing model based on the aggregated operational characteristics and deploying it to the user's device. This enables the effective integration of the functions of different intelligent processing models and allows for responses that take into account the user's emotions.

[0510] An "intelligent processing model" is an information processing system that uses artificial intelligence technology to perform data processing and analysis in order to solve specific problems.

[0511] "Technical information" refers to documents and data that contain specialized knowledge and specifications related to intelligent processing models.

[0512] "Output data" refers to the data that an intelligent processing model generates as a result or response in response to an input.

[0513] "Operational characteristics" refer to the traits or attributes that describe how an intelligent processing model behaves under specific conditions.

[0514] "Aggregation" is the process of combining multiple elements into one.

[0515] "User-facing devices" refer to devices or interfaces that users directly operate and use to utilize the functions of intelligent processing models.

[0516] An "emotional processing mechanism" is a technical configuration for detecting, analyzing, and reflecting the user's emotions in the response.

[0517] "Cooperation" is the ability for different intellectual processing models to work together and function without interfering with each other.

[0518] This invention provides a system for integrating intelligent processing models and generating responses that respond to the user's emotions.

[0519] The server first collects and analyzes technical information and output data from multiple intelligent processing models. For example, it analyzes documents related to specific machine learning algorithms and natural language processing engines, and uses this to infer the operational characteristics of each model. Based on these characteristics, the server integrates the functions of different models to generate a new intelligent processing model.

[0520] Next, the generated model is deployed to the user's device. Specifically, a server unit with a high-performance processor and sufficient memory is crucial hardware. Furthermore, efficient data processing is possible through the use of data analysis libraries and APIs.

[0521] The device uses a pre-installed emotion processing mechanism to process the user's speech and facial expression data in real time. Based on this, the device infers the user's emotional state and transmits that information to the server.

[0522] Consider a scenario where a user accesses customer support, for example, a rapid problem-solving procedure can be presented based on an integrated intelligent processing model. The emotion processing mechanism generates a more empathetic and responsive response when the user is frustrated.

[0523] Furthermore, to optimize responses based on the user's emotions, a generative AI model can be used to generate prompts. An example of a prompt is, "Generate a response that takes the user's emotions into consideration. The user is feeling anxious about the current situation."

[0524] In this way, the present invention realizes a system that can integrate different intelligent processing models and provide flexible responses that respond to the user's emotions.

[0525] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0526] Step 1:

[0527] The user selects their desired intelligent processing model through the terminal. The user's input is sent to the server as model selection information. The server receives this information and begins collecting technical information and output data for the corresponding intelligent processing model.

[0528] Step 2:

[0529] The server analyzes the collected technical information and output data. Technical documentation and output examples related to intelligent processing models are provided as input. The server uses natural language processing and data mining techniques to extract the model's operational characteristics from this data. This analysis clarifies what data processing is required and generates inferred operational characteristics.

[0530] Step 3:

[0531] The server aggregates the functions of different models based on their operational characteristics. The operational characteristics extracted in the previous step are used as input. The server uses integration technology to generate a single compatible intelligent processing model. As a result, a new intelligent processing model integrating the characteristics of multiple models is output.

[0532] Step 4:

[0533] The server deploys the generated intelligent processing model to the user's terminal. Deployment to the terminal is automatic, and the terminal sets the deployed model to a usable state. This process includes software updates and the installation of necessary libraries.

[0534] Step 5:

[0535] The device processes the user's emotions in real time using an emotion processing mechanism. Input data includes the user's voice and facial expressions. The device performs voice and facial analysis to infer the user's emotional state. This output data indicates the user's current emotional state.

[0536] Step 6:

[0537] The server adjusts its response based on the inferred emotional state. The server receives the user's emotional state and request as input. The generative AI model uses prompts such as, "Generate a response that takes the user's emotions into consideration," to generate an appropriate response. This response data is the final output.

[0538] (Application Example 2)

[0539] Next, we will explain Application Example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0540] Modern information processing systems suffer from a lack of personalized service delivery that responds to users' emotional states. Furthermore, the effective integration of multiple machine learning engines is challenging, resulting in low system compatibility and inefficient functional integration. Solving these problems is essential.

[0541] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0542] In this invention, the server includes means for analyzing the technical documentation and output results of multiple machine learning engines in order to integrate the functions of multiple machine learning engines; means for inferring and integrating the functions of each machine learning engine based on the analysis results; and means for constructing a new machine learning engine based on the integrated functions and deploying it to an information processing device. This enables the provision of personalized information display content based on the user's emotional state and the efficient integration of multiple machine learning engines.

[0543] A "machine learning engine" is a system that analyzes data and builds learning models to achieve pattern recognition and prediction.

[0544] A "technical document" is a document that describes in detail the design, specifications, and operating principles of a machine learning engine.

[0545] "Output results" refer to the data and information generated as a result of a machine learning engine processing input data.

[0546] "Analysis" is the process of examining technical documents and output results in detail to clarify their structure and function.

[0547] "Integration" is the process of combining the functions of multiple machine learning engines to make them function as a single, integrated system.

[0548] An "information processing device" is a device that has the function of processing data and generating or managing information.

[0549] "Emotional state" refers to the user's current psychological state and mood, which can be inferred from their facial expressions, words, and other cues.

[0550] "Personalized information display content" refers to information and content that is customized according to the individual user's preferences and emotional state.

[0551] This invention is a system that provides personalized content based on the user's emotional state via an application installed on the user's terminal. The server integrates the functions of multiple machine learning engines and analyzes them from technical documents and output results. This allows it to infer the functions of each machine learning engine, build a new engine based on the integrated functions, and deploy it to the information processing device.

[0552] This system uses facial recognition and speech analysis algorithms to identify the user's emotional state in real time. Hardware includes smartphones and smart glasses, which capture facial expressions and speech via cameras and microphones. Software includes Google's Face API and Microsoft's Emotion API for facial recognition, and TensorFlow and PyTorch for emotion analysis. A server processes this data and recommends content that reflects the user's emotional state.

[0553] As a concrete example, when a user is watching a movie, if the application detects from their facial expression that they are "bored," it will automatically suggest an exciting action movie from its content library. This can improve the satisfaction of the viewing experience. The following prompt message is used: "Input the user's viewing history data and real-time sentiment analysis results to recommend the next content to watch. Select the optimal content type based on their emotional state, such as a gentle movie, an action-packed show, or a moving documentary."

[0554] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0555] Step 1:

[0556] The server retrieves technical documentation and output results from multiple machine learning engines. It analyzes the retrieved data to identify the functions of each engine. The input data consists of technical documentation and output results, with the output being information about the functions of each engine. The analysis involves classifying the document content using natural language processing techniques and identifying the functions.

[0557] Step 2:

[0558] The server integrates the functions of the machine learning engines based on the analysis results. The input is the output information from step 1, and the output is the integrated engine model. This integration involves using algorithms that combine the strengths of each engine while ensuring compatibility.

[0559] Step 3:

[0560] The device uses its camera and microphone to capture the user's emotional state in real time from their face and voice. Input is facial recognition and voice data, and output is the estimated emotional state. This includes specific actions for performing real-time emotion analysis using Google's Face API and Emotion API.

[0561] Step 4:

[0562] The server selects the most suitable content for the user based on the captured emotional state. The input for this step is the emotional state and the user's viewing history data, and the output is recommended content. A recommendation algorithm is used for selection, extracting content that matches the user's interests and emotions.

[0563] Step 5:

[0564] Users view content provided on their devices and receive a personalized experience tailored to their emotions. The content provided is selected by the server and matches the emotional data at the time of viewing. After viewing, users have the opportunity to provide feedback, which is sent to the server and used in the next step.

[0565] Step 6:

[0566] The server analyzes feedback collected from users and uses it to improve the new integrated model. The input is feedback information, and the output is the improved engine model. The analysis includes evaluating the feedback information using statistical methods and specific actions for training the model.

[0567] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0568] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0569] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0570] [Fourth Embodiment]

[0571] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0572] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0573] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0574] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0575] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0576] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0577] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0578] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0579] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0580] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0581] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0582] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0583] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0584] This invention aims to realize a system that integrates multiple artificial intelligence models, allowing users to efficiently utilize their functions. This system primarily involves a server analyzing the technical documentation and output examples of each artificial intelligence model, and then integrating their functions based on the analysis results.

[0585] When a user accesses the platform and selects multiple artificial intelligence models, the server collects technical documentation and output examples related to these models from a database. Based on the collected data, the server performs analysis to gain a detailed understanding of the characteristics and operating patterns of each model. Based on the information obtained from this analysis, the server integrates the functions of multiple models and designs a new integrated model.

[0586] The server generates a newly integrated artificial intelligence model and deploys it to the user's terminal. This allows the user to conveniently utilize the functions of multiple artificial intelligence models through a single interface on their terminal.

[0587] As a concrete example, consider the case where the user selects an AI model for automatic article generation and image generation. In this case, the server analyzes the technical documentation and past output examples of both models and integrates the functionality to simultaneously generate images based on the article's theme. This allows the user to input the article's theme and structure once, and related images will be generated at the same time, enabling consistent project progress.

[0588] Furthermore, the server acquires user feedback, which is then used as data to improve the model's accuracy and performance. This feedback cycle provides a mechanism for continuously improving the performance of the artificial intelligence model.

[0589] The following describes the processing flow.

[0590] Step 1:

[0591] The user accesses the platform and selects the artificial intelligence model they wish to use. Once the selection is complete, the user enters information about the task they intend to perform and the expected output.

[0592] Step 2:

[0593] The server automatically collects technical documentation and existing output examples related to the selected artificial intelligence model from the database. This information collection is a preliminary step to accurately understanding the model's capabilities.

[0594] Step 3:

[0595] The server analyzes the collected technical documents and output examples. Using natural language processing techniques, it identifies what inputs each model requires and what results it outputs. This analysis provides a detailed understanding of the model's characteristics and operation.

[0596] Step 4:

[0597] The server infers the functions of each artificial intelligence model based on the analysis results and integrates those functions. In doing so, it establishes common operating parameters and data formats to build a seamless interface between the artificial intelligence models.

[0598] Step 5:

[0599] The server generates new artificial intelligence models based on integrated functionality. The generation process includes steps that combine training data from different models as needed.

[0600] Step 6:

[0601] The server deploys the newly generated artificial intelligence model to the user's terminal. This allows the user to use the AI ​​model in the configured environment.

[0602] Step 7:

[0603] Users interact with the deployed artificial intelligence model to perform tasks. They can also review the generated output and provide additional instructions.

[0604] Step 8:

[0605] User feedback is sent to the server. The server analyzes this feedback and uses it to improve the artificial intelligence model. Through this feedback loop, the model's performance and accuracy are improved.

[0606] (Example 1)

[0607] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0608] With the advancement of information processing technology, there is a growing need to efficiently utilize and integrate multiple information processing models with different characteristics. However, due to differences in the technical characteristics and outputs of each model, users cannot easily integrate them, and the integration process is time-consuming and laborious. Furthermore, there is a lack of mechanisms to effectively utilize post-use feedback and improve model performance. Therefore, to solve these problems, a means of efficiently analyzing and integrating the characteristics of multiple models is necessary, and it is also required to continuously improve performance by utilizing feedback.

[0609] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0610] In this invention, the server includes means for an information processing device to analyze technical descriptions and generated output examples of multiple information processing models, means for identifying and integrating the functions of each information processing model based on the analysis results, and means for generating a new integrated information processing model and providing it to the user's input device. This enables the efficient integration of information processing models with different characteristics, allowing users to conveniently utilize them through a consistent interface. Furthermore, performance improvements are continuously made based on user feedback, improving the accuracy and responsiveness of the model.

[0611] An "information processing device" is a general term for a device that receives data, processes and analyzes that data, and generates intended output.

[0612] An "information processing model" is a set of calculations and logic used to generate a desired output for a given input.

[0613] "Technical descriptions" refer to documents and materials that describe the design, operation, and characteristics of an information processing model.

[0614] "Analysis" is the process of understanding the structure of information and extracting the necessary information.

[0615] "Identifying functions" means clarifying the specific capabilities and roles that each information processing model provides.

[0616] "Integration" refers to combining the functions of multiple information processing models to operate as a single system.

[0617] "User input device" refers to an electronic device used by a user to input information and interact with a system.

[0618] "Generation" refers to creating a working version of the designed information processing model.

[0619] "Feedback" refers to opinions and reports about the performance and usability that users provide after using a system.

[0620] This invention includes embodiments of a system that integrates multiple information processing models and allows users to utilize them efficiently. Essentially, it provides a platform that integrates the capabilities of multiple information processing models, based on an information processing device (server) and a user input device (terminal).

[0621] The server first collects descriptions of relevant technologies and past output examples from a database, based on the information processing model selected by the user through an input device. This utilizes software libraries for natural language processing and data mining. Specific examples of useful software include Python's Pandas library and TensorFlow. The server then analyzes this data to understand the characteristics of each model.

[0622] Subsequently, the server designs an integrated model and actually generates it. The generated integrated model is provided to the user's terminal, enabling operation on the terminal. The user can obtain systematic data output by entering specific prompt statements through the integrated interface. In this process, the integration function of the information processing model is utilized in generating the output, thus providing consistent results.

[0623] As a concrete example, a user can input a prompt to generate information on a theme such as "articles about environmental protection." Upon inputting this prompt, the system automatically creates related visual materials along with the article, providing consistent content. This significantly improves user efficiency and allows them to leverage the strengths of multiple information processing models.

[0624] Furthermore, the server continuously collects user feedback and uses it as data to improve the model's performance. This allows the information processing system to continuously evolve and provide users with the optimal interface and functionality.

[0625] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0626] Step 1:

[0627] The user accesses the platform and selects the information processing model they wish to use. Information about the selected model is entered and sent to the server. This selection prompts the server to begin the process of collecting technical descriptions and output examples of the selected model from its database.

[0628] Step 2:

[0629] The server collects technical documentation and output examples related to the information processing model selected by the user from a database. It uses the identification information of the selected model as input and retrieves relevant data based on this. The server uses Python or SQL to search the database and extract the necessary data. The output is a dataset of technical specifications and historical model outputs.

[0630] Step 3:

[0631] The server analyzes the collected technical descriptions and output examples to understand the characteristics of each model. The collected dataset is used as input, and the output provides characteristic information about the model. Specifically, the server uses natural language processing algorithms to extract features and identify the operating patterns of the models.

[0632] Step 4:

[0633] The server designs a new model that integrates the functions of each information processing model based on the analysis results. The input is characteristic information obtained from each information processing model. The server uses this information to design a model that enables seamless integration of functions between the models. The output is the design specification for the new integrated model.

[0634] Step 5:

[0635] The server actually generates the designed integrated model. In this step, the structure of the information processing model is built based on the design specifications, and the generated model is ready to go. The input is the design specifications, and the output is the actually working integrated model.

[0636] Step 6:

[0637] The generated integrated model is provided to the user's terminal, and the user can use its interface. The user enters prompts from the terminal and requests the generation of output based on them. In this step, the integrated model performs data processing and calculations based on the input prompts and generates the specified output. The output is information requested by the user.

[0638] Step 7:

[0639] The server collects feedback from users and uses it to improve the model's performance. User feedback after use is collected as input, and the model is improved based on this feedback. The output is performance data of the improved model. This allows the system to continuously evolve and improve the user experience.

[0640] (Application Example 1)

[0641] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0642] There is a need for methods that efficiently integrate multiple intelligent systems, enabling not only convenient user access but also real-time delivery of product information based on voice input. Such technologies are essential for providing a more interactive and intuitive user experience.

[0643] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0644] In this invention, the server includes means for analyzing technical information and output examples of intelligent systems; means for inferring and integrating the functions of each intelligent system based on the analysis results; means for generating a new intelligent system based on the integrated functions and deploying it to the user terminal; and means for analyzing the user's voice input using the intelligent system and displaying product information and related images in real time. This enables the user to efficiently utilize multiple intelligent systems from a single interface and to interactively acquire product information.

[0645] An "intelligent system" refers to a collection of artificial intelligence designed to perform specific tasks or functions.

[0646] "Technical information" refers to information including documentation concerning the design, operation, and performance necessary for an intelligent system to function.

[0647] "Output examples" refer to specific examples that show the deliverables or results produced by an intelligent system.

[0648] "Analysis" refers to the process of thoroughly examining the technical information and output examples of intelligent systems to understand their characteristics and operating patterns.

[0649] "Integration" refers to combining the functions of multiple intelligence systems to create a single, unified system.

[0650] A "user terminal" refers to a device on which an intelligent system is deployed and used to utilize its functions.

[0651] "Voice input" refers to a method of converting spoken words by a user into digital signals to provide instructions and information to a system.

[0652] "Real-time" refers to the ability of a system to process information with minimal delay and provide results immediately.

[0653] This invention is a system that enables users to efficiently utilize the functions of multiple intelligent systems by integrating them. The server collects and analyzes technical information and output examples of the intelligent systems. Specifically, it uses the Google Speech-to-Text API to convert speech input into text data, which is then processed on the server side. Based on this text data, the server uses OpenAI's GPT model to generate information and recommendations about products. It also uses a generative AI model, such as an image generation system (e.g., DALL-E), to generate images related to products in real time, which are then displayed on the user's device (e.g., smart glasses or a head-mounted display).

[0654] This system is designed to allow users to intuitively obtain product information using voice commands. For example, if a user gives the voice command "I'm looking for a leather jacket," the server will start analyzing the data and quickly generate and display relevant product information and images. An example of a prompt could be, "Please generate detailed information and design samples for leather jackets." This provides users with an intuitive and efficient search experience.

[0655] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0656] Step 1:

[0657] The user enters a voice command into the user's device. The device receives this voice data and uses the Google Speech-to-Text API to convert the voice into text data. This converted text is then output.

[0658] Step 2:

[0659] Text data is sent to the server. The server analyzes the received text data and uses OpenAI's GPT model to generate product information and recommendation data. Here, it generates the best response to the query based on the input text and outputs it.

[0660] Step 3:

[0661] Based on the generated product information, the server uses an image generation system to generate images related to the product. In this step, prompt text is input to the generation AI model, and images corresponding to that text are output. As a specific example, the prompt "Generate detailed information and design samples for a leather jacket" is used.

[0662] Step 4:

[0663] The server sends the generated product information and related images to the user's terminal. The terminal receives this information and displays it to the user in an intuitive interface. This allows the user to visually confirm the information obtained from voice input.

[0664] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0665] This invention relates to a system that integrates multiple artificial intelligence models and combines them with an emotion engine that recognizes user emotions. In addition to the technology of integrating the functions of multiple models, this system aims to provide a more personalized experience by recognizing user emotions in real time and adjusting responses accordingly.

[0666] Users access the platform through their terminals and select the artificial intelligence model they wish to use. Based on this selection, the server collects technical documentation and output examples for each model and analyzes them in detail. Through this analysis, the server extracts the operational parameters for each model and integrates their functions while ensuring compatibility between models.

[0667] Next, the server generates an integrated model and deploys it to the user terminal. In addition, it integrates an emotion engine and configures it to analyze the user's emotions. The terminal uses the emotion engine to process the user's speech, facial expressions, input data, etc., in real time during user interaction and infer the user's emotional state.

[0668] A concrete example is a customer support scenario. When a user accesses technical support and requests assistance, the server-integrated artificial intelligence model provides problem-solving steps. The emotion engine recognizes whether the user is frustrated or anxious and adjusts the tone and content of the response accordingly. For example, an frustrated user would receive a more sympathetic and prompt response, while an anxious user would be provided with additional reassuring information.

[0669] Furthermore, feedback information collected from users is statistically analyzed by the server and used to improve the model. In this way, the system is designed to continuously learn and improve the user experience.

[0670] The following describes the processing flow.

[0671] Step 1:

[0672] Users access the platform through their device and select from several artificial intelligence models they wish to use. They also input detailed information about their objectives and expected output.

[0673] Step 2:

[0674] The server collects technical documentation and output examples related to the selected artificial intelligence model from the database. This information serves as foundational data for understanding the model's functions and characteristics.

[0675] Step 3:

[0676] The server analyzes technical documents and output examples to extract the operating parameters and characteristics of each artificial intelligence model. Through this analysis, it gains a detailed understanding of the conditions and settings required for each model's operation.

[0677] Step 4:

[0678] The server integrates the functions of multiple artificial intelligence models based on the analysis results. This process involves establishing common interfaces and data formats to ensure compatibility between the models.

[0679] Step 5:

[0680] The server integrates an emotion engine to recognize user emotions and generates a new, integrated artificial intelligence model. The emotion engine has the capability to analyze user emotions in real time in order to personalize the user experience.

[0681] Step 6:

[0682] Once a new artificial intelligence model is generated, the server deploys it to the user's terminal. This makes the terminal ready to use the integrated model.

[0683] Step 7:

[0684] The device uses an emotion engine to analyze the user's speech and behavioral data in real time and infer their emotional state. A function is then activated that adjusts the response according to the user's emotions.

[0685] Step 8:

[0686] Users utilize artificial intelligence models and verify the results. Furthermore, the emotion engine optimizes the user experience.

[0687] Step 9:

[0688] User feedback is sent from the device to the server, where the server statistically analyzes the information. The analysis results are then used to improve the accuracy and performance of the artificial intelligence model.

[0689] (Example 2)

[0690] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0691] Current intelligent processing models struggle with integrating functions across different models, and their generative models lack the ability to respond to users' real-time emotions. This limits the provision of more sophisticated and personalized user experiences. Furthermore, there is a need to effectively incorporate user feedback to improve the entire intelligent processing model.

[0692] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0693] In this invention, the server includes means for analyzing technical information and output data of multiple intelligent processing models, means for inferring and aggregating the operational characteristics of each intelligent processing model based on the analysis results, and means for generating a new intelligent processing model based on the aggregated operational characteristics and deploying it to the user's device. This enables the effective integration of the functions of different intelligent processing models and allows for responses that take into account the user's emotions.

[0694] An "intelligent processing model" is an information processing system that uses artificial intelligence technology to perform data processing and analysis in order to solve specific problems.

[0695] "Technical information" refers to documents and data that contain specialized knowledge and specifications related to intelligent processing models.

[0696] "Output data" refers to the data that an intelligent processing model generates as a result or response in response to an input.

[0697] "Operational characteristics" refer to the traits or attributes that describe how an intelligent processing model behaves under specific conditions.

[0698] "Aggregation" is the process of combining multiple elements into one.

[0699] "User-facing devices" refer to devices or interfaces that users directly operate and use to utilize the functions of intelligent processing models.

[0700] An "emotional processing mechanism" is a technical configuration for detecting, analyzing, and reflecting the user's emotions in the response.

[0701] "Cooperation" is the ability for different intellectual processing models to work together and function without interfering with each other.

[0702] This invention provides a system for integrating intelligent processing models and generating responses that respond to the user's emotions.

[0703] The server first collects and analyzes technical information and output data from multiple intelligent processing models. For example, it analyzes documents related to specific machine learning algorithms and natural language processing engines, and uses this to infer the operational characteristics of each model. Based on these characteristics, the server integrates the functions of different models to generate a new intelligent processing model.

[0704] Next, the generated model is deployed to the user's device. Specifically, a server unit with a high-performance processor and sufficient memory is crucial hardware. Furthermore, efficient data processing is possible through the use of data analysis libraries and APIs.

[0705] The device uses a pre-installed emotion processing mechanism to process the user's speech and facial expression data in real time. Based on this, the device infers the user's emotional state and transmits that information to the server.

[0706] Consider a scenario where a user accesses customer support, for example, a rapid problem-solving procedure can be presented based on an integrated intelligent processing model. The emotion processing mechanism generates a more empathetic and responsive response when the user is frustrated.

[0707] Furthermore, to optimize responses based on the user's emotions, a generative AI model can be used to generate prompts. An example of a prompt is, "Generate a response that takes the user's emotions into consideration. The user is feeling anxious about the current situation."

[0708] In this way, the present invention realizes a system that can integrate different intelligent processing models and provide flexible responses that respond to the user's emotions.

[0709] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0710] Step 1:

[0711] The user selects their desired intelligent processing model through the terminal. The user's input is sent to the server as model selection information. The server receives this information and begins collecting technical information and output data for the corresponding intelligent processing model.

[0712] Step 2:

[0713] The server analyzes the collected technical information and output data. Technical documentation and output examples related to intelligent processing models are provided as input. The server uses natural language processing and data mining techniques to extract the model's operational characteristics from this data. This analysis clarifies what data processing is required and generates inferred operational characteristics.

[0714] Step 3:

[0715] The server aggregates the functions of different models based on their operational characteristics. The operational characteristics extracted in the previous step are used as input. The server uses integration technology to generate a single compatible intelligent processing model. As a result, a new intelligent processing model integrating the characteristics of multiple models is output.

[0716] Step 4:

[0717] The server deploys the generated intelligent processing model to the user's terminal. Deployment to the terminal is automatic, and the terminal sets the deployed model to a usable state. This process includes software updates and the installation of necessary libraries.

[0718] Step 5:

[0719] The device processes the user's emotions in real time using an emotion processing mechanism. Input data includes the user's voice and facial expressions. The device performs voice and facial analysis to infer the user's emotional state. This output data indicates the user's current emotional state.

[0720] Step 6:

[0721] The server adjusts its response based on the inferred emotional state. The server receives the user's emotional state and request as input. The generative AI model uses prompts such as, "Generate a response that takes the user's emotions into consideration," to generate an appropriate response. This response data is the final output.

[0722] (Application Example 2)

[0723] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0724] Modern information processing systems suffer from a lack of personalized service delivery that responds to users' emotional states. Furthermore, the effective integration of multiple machine learning engines is challenging, resulting in low system compatibility and inefficient functional integration. Solving these problems is essential.

[0725] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0726] In this invention, the server includes means for analyzing the technical documentation and output results of multiple machine learning engines in order to integrate the functions of multiple machine learning engines; means for inferring and integrating the functions of each machine learning engine based on the analysis results; and means for constructing a new machine learning engine based on the integrated functions and deploying it to an information processing device. This enables the provision of personalized information display content based on the user's emotional state and the efficient integration of multiple machine learning engines.

[0727] A "machine learning engine" is a system that analyzes data and builds learning models to achieve pattern recognition and prediction.

[0728] A "technical document" is a document that describes in detail the design, specifications, and operating principles of a machine learning engine.

[0729] "Output results" refer to the data and information generated as a result of a machine learning engine processing input data.

[0730] "Analysis" is the process of examining technical documents and output results in detail to clarify their structure and function.

[0731] "Integration" is the process of combining the functions of multiple machine learning engines to make them function as a single, integrated system.

[0732] An "information processing device" is a device that has the function of processing data and generating or managing information.

[0733] "Emotional state" refers to the user's current psychological state and mood, which can be inferred from their facial expressions, words, and other cues.

[0734] "Personalized information display content" refers to information and content that is customized according to the individual user's preferences and emotional state.

[0735] This invention is a system that provides personalized content based on the user's emotional state via an application installed on the user's terminal. The server integrates the functions of multiple machine learning engines and analyzes them from technical documents and output results. This allows it to infer the functions of each machine learning engine, build a new engine based on the integrated functions, and deploy it to the information processing device.

[0736] This system uses facial recognition and speech analysis algorithms to identify the user's emotional state in real time. Hardware includes smartphones and smart glasses, which capture facial expressions and speech via cameras and microphones. Software includes Google's Face API and Microsoft's Emotion API for facial recognition, and TensorFlow and PyTorch for emotion analysis. A server processes this data and recommends content that reflects the user's emotional state.

[0737] As a concrete example, when a user is watching a movie, if the application detects from their facial expression that they are "bored," it will automatically suggest an exciting action movie from its content library. This can improve the satisfaction of the viewing experience. The following prompt message is used: "Input the user's viewing history data and real-time sentiment analysis results to recommend the next content to watch. Select the optimal content type based on their emotional state, such as a gentle movie, an action-packed show, or a moving documentary."

[0738] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0739] Step 1:

[0740] The server retrieves technical documentation and output results from multiple machine learning engines. It analyzes the retrieved data to identify the functions of each engine. The input data consists of technical documentation and output results, with the output being information about the functions of each engine. The analysis involves classifying the document content using natural language processing techniques and identifying the functions.

[0741] Step 2:

[0742] The server integrates the functions of the machine learning engines based on the analysis results. The input is the output information from step 1, and the output is the integrated engine model. This integration involves using algorithms that combine the strengths of each engine while ensuring compatibility.

[0743] Step 3:

[0744] The device uses its camera and microphone to capture the user's emotional state in real time from their face and voice. Input is facial recognition and voice data, and output is the estimated emotional state. This includes specific actions for performing real-time emotion analysis using Google's Face API and Emotion API.

[0745] Step 4:

[0746] The server selects the most suitable content for the user based on the captured emotional state. The input for this step is the emotional state and the user's viewing history data, and the output is recommended content. A recommendation algorithm is used for selection, extracting content that matches the user's interests and emotions.

[0747] Step 5:

[0748] Users view content provided on their devices and receive a personalized experience tailored to their emotions. The content provided is selected by the server and matches the emotional data at the time of viewing. After viewing, users have the opportunity to provide feedback, which is sent to the server and used in the next step.

[0749] Step 6:

[0750] The server analyzes feedback collected from users and uses it to improve the new integrated model. The input is feedback information, and the output is the improved engine model. The analysis includes evaluating the feedback information using statistical methods and specific actions for training the model.

[0751] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0752] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0753] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0754] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0755] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0756] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0757] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0758] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0759] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0760] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0761] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0762] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0763] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0764] 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.

[0765] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0766] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0767] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0768] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0769] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0770] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0771] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0772] The following is further disclosed regarding the embodiments described above.

[0773] (Claim 1)

[0774] In order to integrate the functions of multiple artificial intelligence models, a means for analyzing the technical documentation and output examples of the artificial intelligence models,

[0775] Based on the analysis results, a means to infer and integrate the functions of each artificial intelligence model,

[0776] A means of generating a new artificial intelligence model based on integrated functions and deploying it to the user's terminal,

[0777] A system that includes this.

[0778] (Claim 2)

[0779] The system according to claim 1, comprising means for collecting user feedback and using it to improve the accuracy and performance of the generated artificial intelligence model.

[0780] (Claim 3)

[0781] The system according to claim 1, comprising means for automatically extracting operating parameters of an artificial intelligence model from the technical document and output examples to be analyzed, thereby ensuring compatibility between artificial intelligence models.

[0782] "Example 1"

[0783] (Claim 1)

[0784] In order for the information processing device to integrate the functions of multiple information processing models, it provides means for analyzing the technical description and generated output examples of each information processing model,

[0785] Based on the analysis results, a means for identifying the functions of each information processing model and integrating those functions,

[0786] A means for generating a new information processing model based on integrated functions and providing it to the user's input device,

[0787] A means of collecting descriptions of relevant information processing model technologies and past output examples based on user selection,

[0788] A means for receiving user input and consistently generating corresponding output through multiple integrated functions,

[0789] A system that includes this.

[0790] (Claim 2)

[0791] The system according to claim 1, comprising means for collecting user feedback on usage and for using to improve the accuracy and performance of the generated information processing model.

[0792] (Claim 3)

[0793] The system according to claim 1, comprising means for automatically extracting numerical values ​​relating to the operation of an information processing model from a description of the analysis technique and an example of the generated output, thereby maintaining compatibility between information processing models.

[0794] "Application Example 1"

[0795] (Claim 1)

[0796] In order to integrate the functions of multiple intelligent systems, a means for analyzing the technical information and output examples of intelligent systems,

[0797] Based on the analysis results, a means to infer and integrate the functions of each intelligent system,

[0798] A means of generating a new intelligent system based on integrated functions and deploying it to the user's terminal,

[0799] A means of using an intelligent system to analyze the user's voice input and display product information and related images in real time,

[0800] A system that includes this.

[0801] (Claim 2)

[0802] The system according to claim 1, comprising means for collecting user feedback and using it to improve the accuracy and performance of the generated intelligent system.

[0803] (Claim 3)

[0804] The system according to claim 1, comprising means for automatically extracting operational variables of an intelligent system from the technical information to be analyzed and the output examples, thereby ensuring compatibility between intelligent systems.

[0805] "Example 2 of combining an emotion engine"

[0806] (Claim 1)

[0807] A means for analyzing the technical information and output data of multiple intelligent processing models,

[0808] A means for inferring and aggregating the operational characteristics of each intelligent processing model based on the analysis results,

[0809] A means of generating a new intelligent processing model based on aggregated operational characteristics and deploying it to user-facing devices,

[0810] A means of integrating an emotion processing mechanism that predicts the user's emotions in real time and reflects them in the response,

[0811] A means of adjusting responses based on the results of user emotion analysis,

[0812] A system that includes this.

[0813] (Claim 2)

[0814] The system according to claim 1, which collects evaluation information from users and uses it to improve the accuracy and performance of the generated intelligent processing model.

[0815] (Claim 3)

[0816] The system according to claim 1, which automatically extracts operating parameters of an intelligent processing model from the technical information to be analyzed and the output data, thereby ensuring cooperation between intelligent processing models.

[0817] "Application example 2 when combining with an emotional engine"

[0818] (Claim 1)

[0819] To integrate the functions of multiple machine learning engines, a means of analyzing the technical documentation and output results of machine learning engines,

[0820] Based on the analysis results, a means to infer and integrate the functions of each machine learning engine,

[0821] A means of building a new machine learning engine based on integrated functions and deploying it to an information processing device,

[0822] A means for processing input data and making inferences according to the emotional state in order to identify a person's emotional state,

[0823] A means for optimizing information display content based on emotional state,

[0824] A system that includes this.

[0825] (Claim 2)

[0826] The system according to claim 1, comprising means for collecting user response information and using it to improve the accuracy and performance of a generated machine learning engine.

[0827] (Claim 3)

[0828] The system according to claim 1, comprising means for automatically extracting operational variables for a machine learning engine from the technical document to be analyzed and the output results, thereby ensuring compatibility between machine learning engines. [Explanation of symbols]

[0829] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. In order to integrate the functions of multiple artificial intelligence models, a means for analyzing the technical documentation and output examples of the artificial intelligence models, Based on the analysis results, a means to infer and integrate the functions of each artificial intelligence model, A means of generating a new artificial intelligence model based on integrated functions and deploying it to the user's terminal, A system that includes this.

2. The system according to claim 1, comprising means for collecting user feedback and using it to improve the accuracy and performance of the generated artificial intelligence model.

3. The system according to claim 1, comprising means for automatically extracting operating parameters of an artificial intelligence model from the technical document and output examples to be analyzed, thereby ensuring compatibility between artificial intelligence models.

Images