system

Abstract

We provide the system. [Solution] A means that enables multiple information processing modules to cooperate with each other on a distributed communication structure, A means for securely sharing data between these information processing modules using encryption technology, Each information processing module has a means to individually perform a specific analysis task, A means of integrating environmental data in real time and providing decision support information, A means of displaying results on the user's terminal and dynamically updating the information, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] When processing large-scale data efficiently and making decisions, a centralized system has limitations in processing capacity and scalability. Furthermore, problems also arise in ensuring security and reliability, and particularly when processing a large amount of data in real time, delays and bottlenecks are likely to occur. In such a situation, a method for efficiently and securely processing data in a distributed system is required.

Means for Solving the Problems

[0005] To solve this problem, the present invention provides a system that enables multiple artificial intelligence modules to collaborate with each other on a distributed data communication structure. This system has means for securely sharing data among artificial intelligence modules using encryption technology and is designed so that each artificial intelligence module individually performs a specific processing task. It also incorporates distributed ledger technology to record data transactions within the distributed data communication structure and prevent unauthorized modification, enabling collaborative decision-making by sharing insights generated by each artificial intelligence module with other modules in real time.

[0006] An "artificial intelligence module" is a digital system that uses algorithms and machine learning models designed to perform specific processing tasks.

[0007] A "distributed data communication structure" is a system configuration in which multiple nodes exchange data with each other via a network.

[0008] "Encryption technology" is a method of transforming information using a specific algorithm in order to ensure the confidentiality and security of data.

[0009] "Distributed ledger technology" is a technology for recording and managing the history of digital transactions in a distributed manner, without relying on a central authority.

[0010] "Real-time sharing" refers to a process where information is immediately transmitted to other system components as soon as it is generated.

[0011] "Collaboration" refers to multiple entities working together towards a common goal. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2]This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] 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]

[0013] 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.

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

[0015] In the following embodiments, a 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.

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

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

[0018] In the following embodiments, a labeled communication I / F (Interface) is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

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

[0020] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0033] The system of the present invention enables multiple artificial intelligence modules to collaborate on a distributed data communication structure, thereby achieving efficient processing of large-scale data and secure decision-making. Each module implements an algorithm specialized for a specific task and performs optimal processing according to a pre-defined objective.

[0034] The server is responsible for building the distributed network and providing the infrastructure for each terminal to connect. This allows the artificial intelligence modules on the terminals to seamlessly participate in the network and creates an environment where data can be easily shared with each other. Furthermore, the server plays a role in improving the overall security of the system by recording transactions through distributed ledger technology.

[0035] The terminal uses a connected artificial intelligence module to process data acquired from external sources. This processing includes data preprocessing, model application, and result analysis. The processed results are securely shared with the artificial intelligence modules of other terminals using encryption technology. This enables scalable operation while maintaining high overall system reliability.

[0036] Users receive insights from multiple artificial intelligence modules via their devices in real time and use them to make decisions. A specific example of this system is market forecasting in the financial sector. The AI ​​modules on the device collect and analyze vast amounts of market data and share the results with other devices via the blockchain. Users can then make investment decisions based on the analysis results from each module.

[0037] In this way, the system of the present invention overcomes the limitations of known technologies and realizes a more efficient and secure data processing environment. By using a distributed architecture and reliable ledger technology, it promotes collaboration among artificial intelligence modules and delivers superior performance in a wide range of applications.

[0038] The following describes the processing flow.

[0039] Step 1:

[0040] The terminal starts up the artificial intelligence module and loads a model suited to the specific task. Once initialization is complete, the module connects to the network and prepares to communicate with other modules.

[0041] Step 2:

[0042] The server initiates the construction of a distributed network. It manages the connections of each terminal, records transactions using distributed ledger technology, and maintains overall security.

[0043] Step 3:

[0044] The device collects data from external data sources (e.g., sensors, databases). The collected data is preprocessed, including noise reduction and conversion to the required format.

[0045] Step 4:

[0046] The device's artificial intelligence module analyzes pre-processed data. This analysis includes applying machine learning models and executing algorithms, generating results tailored to the specific task.

[0047] Step 5:

[0048] The terminal shares analysis results with other artificial intelligence modules. Data is securely transmitted using encryption technology, and the information shared via the server is recorded on the blockchain.

[0049] Step 6:

[0050] The terminal receives data shared from other modules and adjusts its own task processing based on that data. Real-time information exchange enables efficient collaboration.

[0051] Step 7:

[0052] Users receive analysis results from their devices and make decisions based on them. Generative AI models provide additional insights and future predictions, which are then used as a basis for their decisions.

[0053] (Example 1)

[0054] 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."

[0055] The challenge lies in building a reliable system that efficiently and securely processes data from multiple information processing devices in a distributed environment, thereby supporting real-time decision-making. In particular, ensuring the security of data sharing, the reliability of analysis results, and real-time capabilities to enable users to make rapid decisions are crucial.

[0056] 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.

[0057] In this invention, the server includes means for constructing a distributed network infrastructure, means for preprocessing and analyzing data, and means for securely sharing data using encryption technology. This enables the information processing device to efficiently process data and facilitates data sharing and analysis in a distributed environment. Users are supported in real-time decision-making, and the system as a whole becomes highly reliable.

[0058] An "information processing device" is a computer system that has the functions of collecting, processing, and analyzing data.

[0059] A "distributed network infrastructure" refers to a network structure that serves as the foundation for multiple information processing devices to connect with each other and communicate data.

[0060] A "machine learning algorithm" is a data analysis technique used to analyze large amounts of data and discover specific patterns or rules.

[0061] "Encryption technology" refers to the technology used to prevent unauthorized access and tampering by third parties by encrypting data.

[0062] "Distributed recording technology" refers to a technology that prevents tampering by recording data transactions and change histories in a distributed manner across multiple information processing devices.

[0063] A "user" is an individual or organization that makes decisions using data and analysis results provided through an information processing device.

[0064] "Receiving in real time" refers to the format and timing of receiving information provided by an information processing device immediately.

[0065] "Feedback" refers to opinions and improvement suggestions provided by users based on the results obtained from the system, which the system then incorporates into future data processing and analysis.

[0066] This system achieves an efficient and reliable data processing environment by enabling multiple information processing devices to collaborate on a distributed network infrastructure.

[0067] The server is responsible for building the distributed network infrastructure and providing the foundation for each terminal to connect. Specifically, this involves configuring communication protocols and using routing technologies to optimize data flow. The server also implements processes to ensure data confidentiality and integrity using encryption technologies.

[0068] Each terminal is an information processing device equipped with artificial intelligence. The terminals collect external data and clean it through preprocessing. This includes normalizing the dataset and extracting features using software frameworks (e.g., Python, Tensorflow®). The data is then analyzed using applicable machine learning algorithms, and the insights gained are shared with other terminals. Throughout this process, secure data transmission is ensured using AES encryption technology.

[0069] Users receive analysis results in real time via their devices and make decisions based on them. For example, regarding market forecasts based on financial market data, users decide on an investment strategy based on the analyzed results. The feedback obtained at this time is reflected in the next analysis model by the information processing device, further improving accuracy.

[0070] A concrete example is collecting market data and using machine learning models to predict stock price fluctuations. These predictions are encrypted and transmitted to other participating nodes via a decentralized network. Users can then make investment decisions based on these results.

[0071] An example of a prompt to input into the generated AI model is, "How does this system enable collaboration between AI modules in a distributed environment?"

[0072] In this way, the system enables efficient and secure data processing that was difficult with existing technologies, and supports user decision-making.

[0073] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0074] Step 1:

[0075] The server establishes a distributed network. First, it configures the network protocol and provides an environment where terminals can connect securely. As input, the server receives authentication information and network configuration data from terminals, and as output, it grants connection permission to terminals. This allows each terminal to participate stably within the distributed network.

[0076] Step 2:

[0077] The terminal collects data from external sources. For example, it obtains real-time market data from a financial market API. This collected data is the input, and the terminal performs preprocessing such as data formatting and noise reduction, outputting a cleaned dataset. This processing ensures that the less noisy data is passed on to the next analysis step.

[0078] Step 3:

[0079] The device uses a pre-trained machine learning model to analyze pre-processed data. This involves applying deep learning algorithms to learn market trend patterns as a model. The input is processed data, and the output is a prediction result as the analysis result. The data obtained here is specific data, such as future stock price predictions.

[0080] Step 4:

[0081] The terminal shares the obtained analysis results with other terminals using encryption technology. Here, AES encryption technology is used to protect the prediction results, and the results are transmitted using distributed recording technologies such as blockchain. The input is the analysis results, and the output is encrypted data sent over the network. This process ensures the security and confidentiality of the data.

[0082] Step 5:

[0083] Users receive analysis results from their devices and make decisions based on them. Recommended actions based on the analysis results are provided as user input, which they then use to make decisions such as investment decisions. The output is returned to the device as feedback for improvement and used to refine subsequent data analyses. Users can make quick decisions by reviewing this data in real time.

[0084] (Application Example 1)

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

[0086] Modern cities face challenges such as traffic congestion and inefficient road use due to rapid population growth and increasing traffic volume. Traditional transportation systems are unable to effectively utilize distributed data, making it difficult to provide citizens with comfortable and efficient means of transportation. To solve this problem, an advanced system is needed that processes diverse data in real time and provides users with optimal routes and traffic information.

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

[0088] In this invention, the server includes means for enabling multiple information processing modules to cooperate with each other on a distributed communication structure, means for securely sharing data among these information processing modules using encryption technology, means for each information processing module to individually perform a specific analysis task, means for integrating environmental data in real time and providing decision support information, and means for presenting results to a user terminal and dynamically updating the information. This enables an efficient traffic information provision system in urban environments.

[0089] An "information processing module" is a separate processor that analyzes data and generates results according to a specific task.

[0090] A "distributed communication structure" is a structure in which different network nodes cooperate independently with each other and exchange data, without requiring centralized management.

[0091] "Encryption technology" is a technique that transforms data and communication content in a way that prevents others from deciphering it, and is a means of ensuring security.

[0092] "Environmental data integration" is the process of centrally collecting and analyzing data acquired from different sensors and devices.

[0093] "Decision support information" refers to information that serves as a guide for users to choose appropriate actions, based on data analysis results.

[0094] A "user terminal" is a device used by the end user to receive information and perform operations.

[0095] "Dynamic information updating" is a process in which information is revised in a timely manner based on data that changes in real time.

[0096] The system that realizes this application example includes a server with a distributed communication structure, multiple information processing modules, encryption technology, secure data sharing, real-time data integration, decision support information provision, and dynamic information updates on user terminals.

[0097] The server utilizes Apache® Kafka or similar data streaming platforms to deliver real-time data collected from various sensors and devices to information processing modules. These information processing modules use machine learning frameworks such as TensorFlow and PyTorch to perform data analysis and pattern detection. The results are managed on a blockchain using encryption technology to ensure security.

[0098] The terminal provides information to user devices, including smartphones and tablets, and presents optimized routes and modes of transport in real time. Users receive information through the application and are requested to recalculate the route as needed. For example, when a user launches the application to travel within the city, environmental data is analyzed in real time, and the optimal route is recommended.

[0099] An example of a prompt message is: "Analyze current traffic data within the city and recommend the smoothest commute route. Also, suggest ways to notify users, including real-time traffic disruption information."

[0100] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0101] Step 1:

[0102] The server collects traffic data from various sensors and devices installed throughout the city and uses Apache Kafka to transfer this data to a stream processing system. The input is real-time traffic data from the sensors, and the output is a data stream delivered to the information processing module. At this stage, the sensor information is formatted and the data format is standardized.

[0103] Step 2:

[0104] The information processing module receives a data stream from the server and performs real-time analysis of the data using TensorFlow or PyTorch. The input is formatted traffic data, and the output is analyzed traffic patterns and future congestion predictions. This process applies traffic pattern recognition algorithms to extract specific patterns (e.g., congestion predictions).

[0105] Step 3:

[0106] The server encrypts the analysis results from the information processing module and securely records them in a database using blockchain technology. The input is the analyzed traffic data, and the output is encrypted data entries. This prevents data tampering and ensures reliability.

[0107] Step 4:

[0108] The terminal receives a request from the user and sends a prompt message to the generating AI model that generates real-time travel route information. The input is the user's current location and destination, and the output is an optimized route suggestion. In this step, the generating AI model dynamically generates the route based on traffic information.

[0109] Step 5:

[0110] The user receives decision-making support information regarding optimal travel routes and traffic conditions through their device. The input is optimized route information, and the output is navigation information displayed on the user interface. Based on this information, the user selects actions to travel efficiently.

[0111] 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.

[0112] The system of the present invention enables more sophisticated data processing and decision-making by having multiple artificial intelligence modules collaborate on a distributed data communication structure and by combining them with an emotion engine that recognizes the user's emotions. Each module has an algorithm specialized for a specific task, and the emotion engine analyzes data from the user to identify the emotional state.

[0113] The server provides the infrastructure for the distributed network, creating an environment where terminals can connect and share data and sentiment information with each other over the network. The server also plays a role in ensuring system security by recording all data transactions and sentiment data transactions through distributed ledger technology.

[0114] The device processes external data through an artificial intelligence module and generates information in real time based on it. Furthermore, by utilizing an emotion engine, it can analyze the user's emotions and dynamically adjust the operation of each module based on that information. For example, if a positive emotional state is recognized, the system will make proactive decisions, while if it is negative, it will focus on risk management.

[0115] Users access insights gathered from various modules via their devices and make decisions based on emotional feedback provided by the emotion engine. A concrete example is improving the customer experience on e-commerce platforms. The device can read emotions from the user's eye movements and tone of voice, and the system can use this information to improve product recommendations.

[0116] Thus, the system of the present invention utilizes a combination of an emotion engine and an artificial intelligence module to implement an advanced interactive system, thereby achieving a new level of data processing efficiency and decision support.

[0117] The following describes the processing flow.

[0118] Step 1:

[0119] The device activates its emotion engine and acquires input data from the user. It analyzes data sources such as voice, images, and text to prepare for identifying the user's emotional state.

[0120] Step 2:

[0121] The device's artificial intelligence module receives emotional data from the emotion engine and uses it to perform specific tasks. Based on emotions, it dynamically adjusts the algorithm's parameters to perform processing appropriate for the user.

[0122] Step 3:

[0123] The server receives data and sentiment data sent from the terminal and records them within a distributed data communication structure. All information is stored securely using distributed ledger technology.

[0124] Step 4:

[0125] The device shares emotional data with other artificial intelligence modules in real time. Based on this data, the other modules adjust their collaborative actions and work together to complete tasks.

[0126] Step 5:

[0127] Users review the sentiment analysis results provided by their device and the resulting changes in task execution to make decisions. They receive feedback based on sentiment data and use it to make better decisions.

[0128] Step 6:

[0129] The device receives user feedback, readjusts its emotion engine and artificial intelligence module, and incorporates this feedback into subsequent data processing. The learning function is used to improve the overall accuracy of the system.

[0130] (Example 2)

[0131] 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."

[0132] Modern information systems require real-time decision support that reflects user emotions. However, conventional technologies have struggled to appropriately analyze user emotions and reflect them in the overall system decision-making process. As a result, providing information and decision support that meets user needs has been difficult.

[0133] 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.

[0134] In this invention, the server includes means for multiple intelligent modules to cooperate on a distributed information communication structure, means for securely sharing information among these intelligent modules using encryption technology, and means for analyzing the user's emotional state using an emotion recognition engine and dynamically adjusting the operation of each intelligent module. This enables appropriate decision-making support that takes the user's emotions into consideration.

[0135] An "intelligent module" is a program based on artificial intelligence technology that can autonomously perform specific processing tasks.

[0136] "Information and communication structure" refers to a network structure that designs the paths and protocols through which data flows within a system.

[0137] "Encryption technology" is a method for securely protecting data and is a technology used to ensure the confidentiality and integrity of information.

[0138] An "emotion recognition engine" is a system component that includes algorithms that process voice, biometric information, and other data in order to analyze the user's emotional state.

[0139] A "generative AI model" is a form of artificial intelligence technology that generates new information and recommendations based on given data and prompts.

[0140] "Distributed ledger technology" is a technology for recording data securely and transparently, and is a form of distributed database that prevents information tampering.

[0141] In one embodiment of the present invention, a system combining multiple intelligent modules and an emotion recognition engine is used on a distributed network. A server builds the network infrastructure and provides an environment where terminals can connect and securely share information and emotional information. Encryption technology is utilized in this system, and each information communication is conducted in a secure state.

[0142] The device processes data through an intelligent module and uses a generative AI model to generate appropriate information and recommendations. The emotion recognition engine built into the device uses hardware such as microphones and cameras to analyze the user's emotional state. Based on this analysis, the intelligent module dynamically adjusts its operation to provide services tailored to the user's needs.

[0143] Users make decisions based on information provided by their devices. For example, on e-commerce sites, product recommendations are made based on the user's purchase history and current emotional state. In this case, the generative AI model constructs an optimal product list based on prompts such as, "Please suggest products that match my current emotional state."

[0144] This system integrates emotion recognition and artificial intelligence technology to create an interactive system that is more attuned to human emotions. This improves the user experience and enables efficient information provision and decision-making support.

[0145] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0146] Step 1:

[0147] The server receives user data and emotional information transmitted from terminals via the network. Input data includes biometric information and behavioral logs. The server analyzes this data and categorizes it appropriately. The output is a well-organized dataset, which serves as the foundational information for each intelligent module to begin processing.

[0148] Step 2:

[0149] The terminal utilizes an intelligent module to process datasets received from the server and analyze the user's emotional state using an emotion recognition engine. The input is organized data provided by the server. The terminal analyzes voice and facial expression data to identify the emotional state and plans real-time system actions to respond. The output is the analyzed emotional data and recommended actions based on it.

[0150] Step 3:

[0151] The device uses a generative AI model to generate appropriate information and recommendations based on the user's emotional state and past data. The input consists of emotional data and insights generated by the intelligent module. The device interprets this information based on the prompt, "Please suggest products that match my current emotional state," and provides the user with the most suitable suggestions. The output is a list of products and information recommendations provided to the user.

[0152] Step 4:

[0153] The user receives information from the device and makes a decision. Inputs include information recommendations and product lists from the device. The user evaluates this information and takes action to make a choice. The output is the user's choice and is recorded as data for the next processing cycle.

[0154] Step 5:

[0155] The server records data obtained from all processes in a distributed ledger and generates feedback to improve system performance. Inputs are data transactions and emotional data generated at every step. The server analyzes this data and delivers feedback to terminals to inform subsequent interactions. Outputs are feedback information for system improvement.

[0156] (Application Example 2)

[0157] 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".

[0158] In modern electronic payment services, personalizing the purchasing experience by considering user emotions is a challenging task. Traditional systems struggle to appropriately adjust services based on the user's emotional state, and there is a need for optimal methods to maximize user satisfaction and purchasing intent.

[0159] 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.

[0160] In this invention, the server includes means for enabling multiple information processing modules to cooperate with each other on a distributed information transmission structure, means for securely sharing data among these information processing modules using encryption technology, and means for an emotion analysis device to analyze the user's emotional state and dynamically adjust the operation of the information processing modules based on the emotional information. This enables the personalization of the purchasing experience based on the user's emotions.

[0161] An "information processing module" is an element that individually performs specific information processing tasks and works in cooperation with other modules to realize the overall system function.

[0162] A "distributed information transmission structure" is a structure in which information is distributed and held across multiple nodes on a network, rather than on a centralized server.

[0163] "Encryption technology" is a technique that uses specific algorithms to convert information into an unreadable format in order to protect data from unauthorized access.

[0164] An "emotion analysis device" is a device that identifies a user's emotional state based on data such as their facial expressions and voice.

[0165] "Distributed ledger technology" is a technology that manages and operates ledgers, such as blockchains, on a decentralized network in order to record data transactions and prevent unauthorized alteration.

[0166] "Inference" refers to the process of drawing conclusions or insights based on multiple data and pieces of information.

[0167] "Emotional information" refers to data that indicates a user's emotional state, or information based on that data.

[0168] The system implementing this invention provides an innovative method for personalizing the user's purchasing experience in electronic payment services. The server can have multiple information processing modules collaborate on a distributed information transmission structure, thereby processing large amounts of data rapidly. Each information processing module is responsible for a specific information processing task, such as natural language processing or inference, and data sharing between modules is securely performed using encryption technology.

[0169] The terminal uses an emotion analysis device to acquire real-time emotional information from the user and transmit it to a central server. For example, by using the terminal's camera and microphone, it analyzes the user's facial expressions and tone of voice to identify the user's current emotional state. This emotional information is used to dynamically adjust the operation of the information processing module, optimizing the entire system so that the user can complete the payment process comfortably and without stress.

[0170] Through this system, users can receive emotion-based services. For example, if emotion analysis detects excitement when a user is hesitant about purchasing a new product, the system will immediately present relevant product reviews and tutorials to support their purchase decision. Additionally, the prompt used for the generative AI model is, "When a user is undecided about a product, show how to provide additional information and options to help them make a decision."

[0171] Such a system will enable personalized payment services based on user emotions, which is expected to improve purchasing intent and enhance customer satisfaction.

[0172] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0173] Step 1:

[0174] The device uses a camera and microphone to capture the user's facial expressions and voice tone. This input data is sent to an emotion analysis device, where it is processed in real time to identify the user's emotional state. The output is an analysis result indicating which emotional state the user is currently experiencing, such as excitement, relief, or confusion.

[0175] Step 2:

[0176] The server receives emotion information sent from the terminal and distributes it to the information processing module. Here, the emotion information received as input is encrypted to share the infrastructure with other modules and transmitted securely. The output at this stage is encrypted emotion information.

[0177] Step 3:

[0178] The information processing module dynamically adjusts product recommendations to the user based on received sentiment information. Using a generative AI model, it generates prompts based on the user's emotional state and selects highly relevant product reviews and tutorials. The input to this process is encrypted sentiment information, and the output is personalized product recommendations for the user.

[0179] Step 4:

[0180] The user receives product information suggested through the terminal and makes a purchase decision based on that information. The terminal displays details of products the user is interested in and provides a user interface for entering payment information. The input consists of product suggestions and the user's selection, and the output is the final purchase decision.

[0181] Step 5:

[0182] Once the purchase is complete, the server records the transaction in a distributed ledger. In this process, the purchase decision information is provided as input, and that information is stored in the distributed ledger as output, ensuring data integrity while preventing unauthorized modification.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] [Second Embodiment]

[0187] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0188] 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.

[0189] 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).

[0190] 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.

[0191] 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.

[0192] 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).

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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".

[0199] The system of the present invention enables multiple artificial intelligence modules to collaborate on a distributed data communication structure, thereby achieving efficient processing of large-scale data and secure decision-making. Each module implements an algorithm specialized for a specific task and performs optimal processing according to a pre-defined objective.

[0200] The server is responsible for building the distributed network and providing the infrastructure for each terminal to connect. This allows the artificial intelligence modules on the terminals to seamlessly participate in the network and creates an environment where data can be easily shared with each other. Furthermore, the server plays a role in improving the overall security of the system by recording transactions through distributed ledger technology.

[0201] The terminal uses a connected artificial intelligence module to process data acquired from external sources. This processing includes data preprocessing, model application, and result analysis. The processed results are securely shared with the artificial intelligence modules of other terminals using encryption technology. This enables scalable operation while maintaining high overall system reliability.

[0202] Users receive insights from multiple artificial intelligence modules via their devices in real time and use them to make decisions. A specific example of this system is market forecasting in the financial sector. The AI ​​modules on the device collect and analyze vast amounts of market data and share the results with other devices via the blockchain. Users can then make investment decisions based on the analysis results from each module.

[0203] In this way, the system of the present invention overcomes the limitations of known technologies and realizes a more efficient and secure data processing environment. By using a distributed architecture and reliable ledger technology, it promotes collaboration among artificial intelligence modules and delivers superior performance in a wide range of applications.

[0204] The following describes the processing flow.

[0205] Step 1:

[0206] The terminal starts up the artificial intelligence module and loads a model suited to the specific task. Once initialization is complete, the module connects to the network and prepares to communicate with other modules.

[0207] Step 2:

[0208] The server initiates the construction of a distributed network. It manages the connections of each terminal, records transactions using distributed ledger technology, and maintains overall security.

[0209] Step 3:

[0210] The device collects data from external data sources (e.g., sensors, databases). The collected data is preprocessed, including noise reduction and conversion to the required format.

[0211] Step 4:

[0212] The device's artificial intelligence module analyzes pre-processed data. This analysis includes applying machine learning models and executing algorithms, generating results tailored to the specific task.

[0213] Step 5:

[0214] The terminal shares analysis results with other artificial intelligence modules. Data is securely transmitted using encryption technology, and the information shared via the server is recorded on the blockchain.

[0215] Step 6:

[0216] The terminal receives data shared from other modules and adjusts its own task processing based on that data. Real-time information exchange enables efficient collaboration.

[0217] Step 7:

[0218] Users receive analysis results from their devices and make decisions based on them. Generative AI models provide additional insights and future predictions, which are then used as a basis for their decisions.

[0219] (Example 1)

[0220] 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."

[0221] The challenge lies in building a reliable system that efficiently and securely processes data from multiple information processing devices in a distributed environment, thereby supporting real-time decision-making. In particular, ensuring the security of data sharing, the reliability of analysis results, and real-time capabilities to enable users to make rapid decisions are crucial.

[0222] 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.

[0223] In this invention, the server includes means for constructing a distributed network infrastructure, means for preprocessing and analyzing data, and means for securely sharing data using encryption technology. This enables the information processing device to efficiently process data and facilitates data sharing and analysis in a distributed environment. Users are supported in real-time decision-making, and the system as a whole becomes highly reliable.

[0224] An "information processing device" is a computer system that has the functions of collecting, processing, and analyzing data.

[0225] A "distributed network infrastructure" refers to a network structure that serves as the foundation for multiple information processing devices to connect with each other and communicate data.

[0226] A "machine learning algorithm" is a data analysis technique used to analyze large amounts of data and discover specific patterns or rules.

[0227] "Encryption technology" refers to the technology used to prevent unauthorized access and tampering by third parties by encrypting data.

[0228] "Distributed recording technology" refers to a technology that prevents tampering by recording data transactions and change histories in a distributed manner across multiple information processing devices.

[0229] A "user" is an individual or organization that makes decisions using data and analysis results provided through an information processing device.

[0230] "Receiving in real time" refers to the format and timing of receiving information provided by an information processing device immediately.

[0231] "Feedback" refers to opinions and improvement suggestions provided by users based on the results obtained from the system, which the system then incorporates into future data processing and analysis.

[0232] This system achieves an efficient and reliable data processing environment by enabling multiple information processing devices to collaborate on a distributed network infrastructure.

[0233] The server is responsible for building the distributed network infrastructure and providing the foundation for each terminal to connect. Specifically, this involves configuring communication protocols and using routing technologies to optimize data flow. The server also implements processes to ensure data confidentiality and integrity using encryption technologies.

[0234] Each terminal is an information processing device equipped with artificial intelligence. The terminals collect external data and clean it through preprocessing. This includes using software frameworks (e.g., Python, TensorFlow) to normalize the dataset and extract features. Subsequently, the data is analyzed using applicable machine learning algorithms, and the insights gained are shared with other terminals. Throughout this process, secure data transmission is ensured using AES encryption technology.

[0235] Users receive analysis results in real time via their devices and make decisions based on them. For example, regarding market forecasts based on financial market data, users decide on an investment strategy based on the analyzed results. The feedback obtained at this time is reflected in the next analysis model by the information processing device, further improving accuracy.

[0236] A concrete example is collecting market data and using machine learning models to predict stock price fluctuations. These predictions are encrypted and transmitted to other participating nodes via a decentralized network. Users can then make investment decisions based on these results.

[0237] An example of a prompt to input into the generated AI model is, "How does this system enable collaboration between AI modules in a distributed environment?"

[0238] In this way, the system enables efficient and secure data processing that was difficult with existing technologies, and supports user decision-making.

[0239] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0240] Step 1:

[0241] The server establishes a distributed network. First, it configures the network protocol and provides an environment where terminals can connect securely. As input, the server receives authentication information and network configuration data from terminals, and as output, it grants connection permission to terminals. This allows each terminal to participate stably within the distributed network.

[0242] Step 2:

[0243] The terminal collects data from external sources. For example, it obtains real-time market data from a financial market API. This collected data is the input, and the terminal performs preprocessing such as data formatting and noise reduction, outputting a cleaned dataset. This processing ensures that the less noisy data is passed on to the next analysis step.

[0244] Step 3:

[0245] The device uses a pre-trained machine learning model to analyze pre-processed data. This involves applying deep learning algorithms to learn market trend patterns as a model. The input is processed data, and the output is a prediction result as the analysis result. The data obtained here is specific data, such as future stock price predictions.

[0246] Step 4:

[0247] The terminal shares the obtained analysis results with other terminals using encryption technology. Here, AES encryption technology is used to protect the prediction results, and the results are transmitted using distributed recording technologies such as blockchain. The input is the analysis results, and the output is encrypted data sent over the network. This process ensures the security and confidentiality of the data.

[0248] Step 5:

[0249] Users receive analysis results from their devices and make decisions based on them. Recommended actions based on the analysis results are provided as user input, which they then use to make decisions such as investment decisions. The output is returned to the device as feedback for improvement and used to refine subsequent data analyses. Users can make quick decisions by reviewing this data in real time.

[0250] (Application Example 1)

[0251] 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."

[0252] Modern cities face challenges such as traffic congestion and inefficient road use due to rapid population growth and increasing traffic volume. Traditional transportation systems are unable to effectively utilize distributed data, making it difficult to provide citizens with comfortable and efficient means of transportation. To solve this problem, an advanced system is needed that processes diverse data in real time and provides users with optimal routes and traffic information.

[0253] 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.

[0254] In this invention, the server includes means for enabling multiple information processing modules to cooperate with each other on a distributed communication structure, means for securely sharing data among these information processing modules using encryption technology, means for each information processing module to individually perform a specific analysis task, means for integrating environmental data in real time and providing decision support information, and means for presenting results to a user terminal and dynamically updating the information. This enables an efficient traffic information provision system in urban environments.

[0255] An "information processing module" is a separate processor that analyzes data and generates results according to a specific task.

[0256] A "distributed communication structure" is a structure in which different network nodes cooperate independently with each other and exchange data, without requiring centralized management.

[0257] "Encryption technology" is a technique that transforms data and communication content in a way that prevents others from deciphering it, and is a means of ensuring security.

[0258] "Environmental data integration" is the process of centrally collecting and analyzing data acquired from different sensors and devices.

[0259] "Decision support information" refers to information that serves as a guide for users to choose appropriate actions, based on data analysis results.

[0260] A "user terminal" is a device used by the end user to receive information and perform operations.

[0261] "Dynamic information updating" is a process in which information is revised in a timely manner based on data that changes in real time.

[0262] The system that realizes this application example includes a server with a distributed communication structure, multiple information processing modules, encryption technology, secure data sharing, real-time data integration, decision support information provision, and dynamic information updates on user terminals.

[0263] The server utilizes Apache Kafka or similar data streaming platforms to deliver real-time data collected from various sensors and devices to information processing modules. These modules use machine learning frameworks such as TensorFlow and PyTorch to perform data analysis and pattern detection. The results are managed on a blockchain using encryption technology to ensure security.

[0264] The terminal provides information to user devices, including smartphones and tablets, and presents optimized routes and modes of transport in real time. Users receive information through the application and are requested to recalculate the route as needed. For example, when a user launches the application to travel within the city, environmental data is analyzed in real time, and the optimal route is recommended.

[0265] An example of a prompt message is: "Analyze current traffic data within the city and recommend the smoothest commute route. Also, suggest ways to notify users, including real-time traffic disruption information."

[0266] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0267] Step 1:

[0268] The server collects traffic data from various sensors and devices installed throughout the city and uses Apache Kafka to transfer this data to a stream processing system. The input is real-time traffic data from the sensors, and the output is a data stream delivered to the information processing module. At this stage, the sensor information is formatted and the data format is standardized.

[0269] Step 2:

[0270] The information processing module receives a data stream from the server and performs real-time analysis of the data using TensorFlow or PyTorch. The input is formatted traffic data, and the output is analyzed traffic patterns and future congestion predictions. This process applies traffic pattern recognition algorithms to extract specific patterns (e.g., congestion predictions).

[0271] Step 3:

[0272] The server encrypts the analysis results from the information processing module and securely records them in a database using blockchain technology. The input is the analyzed traffic data, and the output is encrypted data entries. This prevents data tampering and ensures reliability.

[0273] Step 4:

[0274] The terminal receives a request from the user and sends a prompt message to the generating AI model that generates real-time travel route information. The input is the user's current location and destination, and the output is an optimized route suggestion. In this step, the generating AI model dynamically generates the route based on traffic information.

[0275] Step 5:

[0276] The user receives decision-making support information regarding optimal travel routes and traffic conditions through their device. The input is optimized route information, and the output is navigation information displayed on the user interface. Based on this information, the user selects actions to travel efficiently.

[0277] 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.

[0278] The system of the present invention enables more sophisticated data processing and decision-making by having multiple artificial intelligence modules collaborate on a distributed data communication structure and by combining them with an emotion engine that recognizes the user's emotions. Each module has an algorithm specialized for a specific task, and the emotion engine analyzes data from the user to identify the emotional state.

[0279] The server provides the infrastructure for the distributed network, creating an environment where terminals can connect and share data and sentiment information with each other over the network. The server also plays a role in ensuring system security by recording all data transactions and sentiment data transactions through distributed ledger technology.

[0280] The terminal processes external data through an artificial intelligence module and generates information in real time based on this. Furthermore, by utilizing an emotion engine, it can analyze the user's emotions and dynamically adjust the operations of each module based on this information. For example, when a positive emotional state is recognized, the system makes proactive decisions, and when it is negative, it focuses on risk management responses.

[0281] The user accesses the insights gathered from various modules via the terminal and makes decisions by referring to the emotion feedback provided by the emotion engine. A specific example is the improvement of the customer experience in an e-commerce platform. The terminal can read emotions from the user's eye movements and voice tones, and the system can improve product recommendations based on this information.

[0282] In this way, the system of the present invention realizes a new level of data processing efficiency and decision-making support by leveraging the combination of an emotion engine and an artificial intelligence module and implementing a highly interactive system.

[0283] The processing flow will be described below.

[0284] Step 1:

[0285] The terminal activates the emotion engine and acquires input data from the user. It analyzes data sources such as voice, images, and text to prepare for identifying the user's emotional state.

[0286] Step 2:

[0287] The artificial intelligence module of the terminal receives the emotion data obtained from the emotion engine and uses it to execute specific tasks. Based on the emotion, it dynamically adjusts the parameters of the algorithm to perform processing suitable for the user.

[0288] Step 3:

[0289] The server receives data and sentiment data sent from the terminal and records them within a distributed data communication structure. All information is stored securely using distributed ledger technology.

[0290] Step 4:

[0291] The device shares emotional data with other artificial intelligence modules in real time. Based on this data, the other modules adjust their collaborative actions and work together to complete tasks.

[0292] Step 5:

[0293] Users review the sentiment analysis results provided by their device and the resulting changes in task execution to make decisions. They receive feedback based on sentiment data and use it to make better decisions.

[0294] Step 6:

[0295] The device receives user feedback, readjusts its emotion engine and artificial intelligence module, and incorporates this feedback into subsequent data processing. The learning function is used to improve the overall accuracy of the system.

[0296] (Example 2)

[0297] 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".

[0298] Modern information systems require real-time decision support that reflects user emotions. However, conventional technologies have struggled to appropriately analyze user emotions and reflect them in the overall system decision-making process. As a result, providing information and decision support that meets user needs has been difficult.

[0299] 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.

[0300] In this invention, the server includes means for a plurality of intelligent modules to cooperate on a distributed information communication structure, means for securely sharing information between these intelligent modules using encryption technology, and means for analyzing the emotional state of the user using an emotion recognition engine and dynamically adjusting the operation of each intelligent module. Thereby, appropriate decision-making support considering the user's emotions becomes possible.

[0301] An "intelligent module" is a program based on artificial intelligence technology that can autonomously execute specific processing tasks.

[0302] An "information communication structure" is a network structure designed with the path and protocol when data flows within the system.

[0303] "Encryption technology" is a method for securely protecting data and is a technology used to ensure the confidentiality and integrity of information.

[0304] An "emotion recognition engine" is a system component including algorithms for processing voice, biometric information, etc. to analyze the emotional state of the user.

[0305] A "generative AI model" is a form of artificial intelligence technology that generates new information and recommendations based on given data and prompts.

[0306] "Distributed ledger technology" is a technology for securely and transparently recording data and is a form of distributed database that prevents information tampering.

[0307] As an embodiment of the present invention, a system combining a plurality of intelligent modules and an emotion recognition engine is used on a distributed network. The server constructs the foundation of the network and provides an environment for terminals to connect and securely share information and emotional information. In this system, encryption technology is utilized, and each information communication is performed in a secure state.

[0308] The device processes data through an intelligent module and uses a generative AI model to generate appropriate information and recommendations. The emotion recognition engine built into the device uses hardware such as microphones and cameras to analyze the user's emotional state. Based on this analysis, the intelligent module dynamically adjusts its operation to provide services tailored to the user's needs.

[0309] Users make decisions based on information provided by their devices. For example, on e-commerce sites, product recommendations are made based on the user's purchase history and current emotional state. In this case, the generative AI model constructs an optimal product list based on prompts such as, "Please suggest products that match my current emotional state."

[0310] This system integrates emotion recognition and artificial intelligence technology to create an interactive system that is more attuned to human emotions. This improves the user experience and enables efficient information provision and decision-making support.

[0311] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0312] Step 1:

[0313] The server receives user data and emotional information transmitted from terminals via the network. Input data includes biometric information and behavioral logs. The server analyzes this data and categorizes it appropriately. The output is a well-organized dataset, which serves as the foundational information for each intelligent module to begin processing.

[0314] Step 2:

[0315] The terminal utilizes an intelligent module to process datasets received from the server and analyze the user's emotional state using an emotion recognition engine. The input is organized data provided by the server. The terminal analyzes voice and facial expression data to identify the emotional state and plans real-time system actions to respond. The output is the analyzed emotional data and recommended actions based on it.

[0316] Step 3:

[0317] The device uses a generative AI model to generate appropriate information and recommendations based on the user's emotional state and past data. The input consists of emotional data and insights generated by the intelligent module. The device interprets this information based on the prompt, "Please suggest products that match my current emotional state," and provides the user with the most suitable suggestions. The output is a list of products and information recommendations provided to the user.

[0318] Step 4:

[0319] The user receives information from the device and makes a decision. Inputs include information recommendations and product lists from the device. The user evaluates this information and takes action to make a choice. The output is the user's choice and is recorded as data for the next processing cycle.

[0320] Step 5:

[0321] The server records data obtained from all processes in a distributed ledger and generates feedback to improve system performance. Inputs are data transactions and emotional data generated at every step. The server analyzes this data and delivers feedback to terminals to inform subsequent interactions. Outputs are feedback information for system improvement.

[0322] (Application Example 2)

[0323] 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 as the "terminal".

[0324] In modern electronic payment services, personalizing the purchasing experience by considering user emotions is a challenging task. Traditional systems struggle to appropriately adjust services based on the user's emotional state, and there is a need for optimal methods to maximize user satisfaction and purchasing intent.

[0325] 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.

[0326] In this invention, the server includes means for enabling multiple information processing modules to cooperate with each other on a distributed information transmission structure, means for securely sharing data among these information processing modules using encryption technology, and means for an emotion analysis device to analyze the user's emotional state and dynamically adjust the operation of the information processing modules based on the emotional information. This enables the personalization of the purchasing experience based on the user's emotions.

[0327] An "information processing module" is an element that individually performs specific information processing tasks and works in cooperation with other modules to realize the overall system function.

[0328] A "distributed information transmission structure" is a structure in which information is distributed and held across multiple nodes on a network, rather than on a centralized server.

[0329] "Encryption technology" is a technique that uses specific algorithms to convert information into an unreadable format in order to protect data from unauthorized access.

[0330] An "emotion analysis device" is a device that identifies a user's emotional state based on data such as their facial expressions and voice.

[0331] "Distributed ledger technology" is a technology that manages and operates ledgers, such as blockchains, on a decentralized network in order to record data transactions and prevent unauthorized alteration.

[0332] "Inference" refers to the process of drawing conclusions or insights based on multiple data and pieces of information.

[0333] "Emotional information" refers to data that indicates a user's emotional state, or information based on that data.

[0334] The system implementing this invention provides an innovative method for personalizing the user's purchasing experience in electronic payment services. The server can have multiple information processing modules collaborate on a distributed information transmission structure, thereby processing large amounts of data rapidly. Each information processing module is responsible for a specific information processing task, such as natural language processing or inference, and data sharing between modules is securely performed using encryption technology.

[0335] The terminal uses an emotion analysis device to acquire real-time emotional information from the user and transmit it to a central server. For example, by using the terminal's camera and microphone, it analyzes the user's facial expressions and tone of voice to identify the user's current emotional state. This emotional information is used to dynamically adjust the operation of the information processing module, optimizing the entire system so that the user can complete the payment process comfortably and without stress.

[0336] Through this system, users can receive emotion-based services. For example, if emotion analysis detects excitement when a user is hesitant about purchasing a new product, the system will immediately present relevant product reviews and tutorials to support their purchase decision. Additionally, the prompt used for the generative AI model is, "When a user is undecided about a product, show how to provide additional information and options to help them make a decision."

[0337] Such a system will enable personalized payment services based on user emotions, which is expected to improve purchasing intent and enhance customer satisfaction.

[0338] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0339] Step 1:

[0340] The device uses a camera and microphone to capture the user's facial expressions and voice tone. This input data is sent to an emotion analysis device, where it is processed in real time to identify the user's emotional state. The output is an analysis result indicating which emotional state the user is currently experiencing, such as excitement, relief, or confusion.

[0341] Step 2:

[0342] The server receives emotion information sent from the terminal and distributes it to the information processing module. Here, the emotion information received as input is encrypted to share the infrastructure with other modules and transmitted securely. The output at this stage is encrypted emotion information.

[0343] Step 3:

[0344] The information processing module dynamically adjusts product recommendations to the user based on received sentiment information. Using a generative AI model, it generates prompts based on the user's emotional state and selects highly relevant product reviews and tutorials. The input to this process is encrypted sentiment information, and the output is personalized product recommendations for the user.

[0345] Step 4:

[0346] The user receives product information suggested through the terminal and makes a purchase decision based on that information. The terminal displays details of products the user is interested in and provides a user interface for entering payment information. The input consists of product suggestions and the user's selection, and the output is the final purchase decision.

[0347] Step 5:

[0348] Once the purchase is complete, the server records the transaction in a distributed ledger. In this process, the purchase decision information is provided as input, and that information is stored in the distributed ledger as output, ensuring data integrity while preventing unauthorized modification.

[0349] 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.

[0350] 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.

[0351] 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.

[0352] [Third Embodiment]

[0353] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0354] 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.

[0355] 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).

[0356] 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.

[0357] 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.

[0358] 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).

[0359] 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.

[0360] 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.

[0361] 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.

[0362] 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.

[0363] 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.

[0364] 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".

[0365] The system of the present invention enables multiple artificial intelligence modules to collaborate on a distributed data communication structure, thereby achieving efficient processing of large-scale data and secure decision-making. Each module implements an algorithm specialized for a specific task and performs optimal processing according to a pre-defined objective.

[0366] The server is responsible for building the distributed network and providing the infrastructure for each terminal to connect. This allows the artificial intelligence modules on the terminals to seamlessly participate in the network and creates an environment where data can be easily shared with each other. Furthermore, the server plays a role in improving the overall security of the system by recording transactions through distributed ledger technology.

[0367] The terminal uses a connected artificial intelligence module to process data acquired from external sources. This processing includes data preprocessing, model application, and result analysis. The processed results are securely shared with the artificial intelligence modules of other terminals using encryption technology. This enables scalable operation while maintaining high overall system reliability.

[0368] Users receive insights from multiple artificial intelligence modules via their devices in real time and use them to make decisions. A specific example of this system is market forecasting in the financial sector. The AI ​​modules on the device collect and analyze vast amounts of market data and share the results with other devices via the blockchain. Users can then make investment decisions based on the analysis results from each module.

[0369] In this way, the system of the present invention overcomes the limitations of known technologies and realizes a more efficient and secure data processing environment. By using a distributed architecture and reliable ledger technology, it promotes collaboration among artificial intelligence modules and delivers superior performance in a wide range of applications.

[0370] The following describes the processing flow.

[0371] Step 1:

[0372] The terminal starts up the artificial intelligence module and loads a model suited to the specific task. Once initialization is complete, the module connects to the network and prepares to communicate with other modules.

[0373] Step 2:

[0374] The server initiates the construction of a distributed network. It manages the connections of each terminal, records transactions using distributed ledger technology, and maintains overall security.

[0375] Step 3:

[0376] The device collects data from external data sources (e.g., sensors, databases). The collected data is preprocessed, including noise reduction and conversion to the required format.

[0377] Step 4:

[0378] The device's artificial intelligence module analyzes pre-processed data. This analysis includes applying machine learning models and executing algorithms, generating results tailored to the specific task.

[0379] Step 5:

[0380] The terminal shares analysis results with other artificial intelligence modules. Data is securely transmitted using encryption technology, and the information shared via the server is recorded on the blockchain.

[0381] Step 6:

[0382] The terminal receives data shared from other modules and adjusts its own task processing based on that data. Real-time information exchange enables efficient collaboration.

[0383] Step 7:

[0384] Users receive analysis results from their devices and make decisions based on them. Generative AI models provide additional insights and future predictions, which are then used as a basis for their decisions.

[0385] (Example 1)

[0386] 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."

[0387] The challenge lies in building a reliable system that efficiently and securely processes data from multiple information processing devices in a distributed environment, thereby supporting real-time decision-making. In particular, ensuring the security of data sharing, the reliability of analysis results, and real-time capabilities to enable users to make rapid decisions are crucial.

[0388] 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.

[0389] In this invention, the server includes means for constructing a distributed network infrastructure, means for preprocessing and analyzing data, and means for securely sharing data using encryption technology. This enables the information processing device to efficiently process data and facilitates data sharing and analysis in a distributed environment. Users are supported in real-time decision-making, and the system as a whole becomes highly reliable.

[0390] An "information processing device" is a computer system that has the functions of collecting, processing, and analyzing data.

[0391] A "distributed network infrastructure" refers to a network structure that serves as the foundation for multiple information processing devices to connect with each other and communicate data.

[0392] A "machine learning algorithm" is a data analysis technique used to analyze large amounts of data and discover specific patterns or rules.

[0393] "Encryption technology" refers to the technology used to prevent unauthorized access and tampering by third parties by encrypting data.

[0394] "Distributed recording technology" refers to a technology that prevents tampering by recording data transactions and change histories in a distributed manner across multiple information processing devices.

[0395] A "user" is an individual or organization that makes decisions using data and analysis results provided through an information processing device.

[0396] "Receiving in real time" refers to the format and timing of receiving information provided by an information processing device immediately.

[0397] "Feedback" refers to opinions and improvement suggestions provided by users based on the results obtained from the system, which the system then incorporates into future data processing and analysis.

[0398] This system achieves an efficient and reliable data processing environment by enabling multiple information processing devices to collaborate on a distributed network infrastructure.

[0399] The server is responsible for building the distributed network infrastructure and providing the foundation for each terminal to connect. Specifically, this involves configuring communication protocols and using routing technologies to optimize data flow. The server also implements processes to ensure data confidentiality and integrity using encryption technologies.

[0400] Each terminal is an information processing device equipped with artificial intelligence. The terminals collect external data and clean it through preprocessing. This includes using software frameworks (e.g., Python, TensorFlow) to normalize the dataset and extract features. Subsequently, the data is analyzed using applicable machine learning algorithms, and the insights gained are shared with other terminals. Throughout this process, secure data transmission is ensured using AES encryption technology.

[0401] Users receive analysis results in real time via their devices and make decisions based on them. For example, regarding market forecasts based on financial market data, users decide on an investment strategy based on the analyzed results. The feedback obtained at this time is reflected in the next analysis model by the information processing device, further improving accuracy.

[0402] A concrete example is collecting market data and using machine learning models to predict stock price fluctuations. These predictions are encrypted and transmitted to other participating nodes via a decentralized network. Users can then make investment decisions based on these results.

[0403] An example of a prompt to input into the generated AI model is, "How does this system enable collaboration between AI modules in a distributed environment?"

[0404] In this way, the system enables efficient and secure data processing that was difficult with existing technologies, and supports user decision-making.

[0405] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0406] Step 1:

[0407] The server establishes a distributed network. First, it configures the network protocol and provides an environment where terminals can connect securely. As input, the server receives authentication information and network configuration data from terminals, and as output, it grants connection permission to terminals. This allows each terminal to participate stably within the distributed network.

[0408] Step 2:

[0409] The terminal collects data from external sources. For example, it obtains real-time market data from a financial market API. This collected data is the input, and the terminal performs preprocessing such as data formatting and noise reduction, outputting a cleaned dataset. This processing ensures that the less noisy data is passed on to the next analysis step.

[0410] Step 3:

[0411] The device uses a pre-trained machine learning model to analyze pre-processed data. This involves applying deep learning algorithms to learn market trend patterns as a model. The input is processed data, and the output is a prediction result as the analysis result. The data obtained here is specific data, such as future stock price predictions.

[0412] Step 4:

[0413] The terminal shares the obtained analysis results with other terminals using encryption technology. Here, AES encryption technology is used to protect the prediction results, and the results are transmitted using distributed recording technologies such as blockchain. The input is the analysis results, and the output is encrypted data sent over the network. This process ensures the security and confidentiality of the data.

[0414] Step 5:

[0415] Users receive analysis results from their devices and make decisions based on them. Recommended actions based on the analysis results are provided as user input, which they then use to make decisions such as investment decisions. The output is returned to the device as feedback for improvement and used to refine subsequent data analyses. Users can make quick decisions by reviewing this data in real time.

[0416] (Application Example 1)

[0417] 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."

[0418] Modern cities face challenges such as traffic congestion and inefficient road use due to rapid population growth and increasing traffic volume. Traditional transportation systems are unable to effectively utilize distributed data, making it difficult to provide citizens with comfortable and efficient means of transportation. To solve this problem, an advanced system is needed that processes diverse data in real time and provides users with optimal routes and traffic information.

[0419] 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.

[0420] In this invention, the server includes means for enabling multiple information processing modules to cooperate with each other on a distributed communication structure, means for securely sharing data among these information processing modules using encryption technology, means for each information processing module to individually perform a specific analysis task, means for integrating environmental data in real time and providing decision support information, and means for presenting results to a user terminal and dynamically updating the information. This enables an efficient traffic information provision system in urban environments.

[0421] An "information processing module" is a separate processor that analyzes data and generates results according to a specific task.

[0422] A "distributed communication structure" is a structure in which different network nodes cooperate independently with each other and exchange data, without requiring centralized management.

[0423] "Encryption technology" is a technique that transforms data and communication content in a way that prevents others from deciphering it, and is a means of ensuring security.

[0424] "Environmental data integration" is the process of centrally collecting and analyzing data acquired from different sensors and devices.

[0425] "Decision support information" refers to information that serves as a guide for users to choose appropriate actions, based on data analysis results.

[0426] A "user terminal" is a device used by the end user to receive information and perform operations.

[0427] "Dynamic information updating" is a process in which information is revised in a timely manner based on data that changes in real time.

[0428] The system that realizes this application example includes a server with a distributed communication structure, multiple information processing modules, encryption technology, secure data sharing, real-time data integration, decision support information provision, and dynamic information updates on user terminals.

[0429] The server utilizes Apache Kafka or similar data streaming platforms to deliver real-time data collected from various sensors and devices to information processing modules. These modules use machine learning frameworks such as TensorFlow and PyTorch to perform data analysis and pattern detection. The results are managed on a blockchain using encryption technology to ensure security.

[0430] The terminal provides information to user devices, including smartphones and tablets, and presents optimized routes and modes of transport in real time. Users receive information through the application and are requested to recalculate the route as needed. For example, when a user launches the application to travel within the city, environmental data is analyzed in real time, and the optimal route is recommended.

[0431] An example of a prompt message is: "Analyze current traffic data within the city and recommend the smoothest commute route. Also, suggest ways to notify users, including real-time traffic disruption information."

[0432] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0433] Step 1:

[0434] The server collects traffic data from various sensors and devices installed throughout the city and uses Apache Kafka to transfer this data to a stream processing system. The input is real-time traffic data from the sensors, and the output is a data stream delivered to the information processing module. At this stage, the sensor information is formatted and the data format is standardized.

[0435] Step 2:

[0436] The information processing module receives a data stream from the server and performs real-time analysis of the data using TensorFlow or PyTorch. The input is formatted traffic data, and the output is analyzed traffic patterns and future congestion predictions. This process applies traffic pattern recognition algorithms to extract specific patterns (e.g., congestion predictions).

[0437] Step 3:

[0438] The server encrypts the analysis results from the information processing module and securely records them in a database using blockchain technology. The input is the analyzed traffic data, and the output is encrypted data entries. This prevents data tampering and ensures reliability.

[0439] Step 4:

[0440] The terminal receives a request from the user and sends a prompt message to the generating AI model that generates real-time travel route information. The input is the user's current location and destination, and the output is an optimized route suggestion. In this step, the generating AI model dynamically generates the route based on traffic information.

[0441] Step 5:

[0442] The user receives decision-making support information regarding optimal travel routes and traffic conditions through their device. The input is optimized route information, and the output is navigation information displayed on the user interface. Based on this information, the user selects actions to travel efficiently.

[0443] 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.

[0444] The system of the present invention enables more sophisticated data processing and decision-making by having multiple artificial intelligence modules collaborate on a distributed data communication structure and by combining them with an emotion engine that recognizes the user's emotions. Each module has an algorithm specialized for a specific task, and the emotion engine analyzes data from the user to identify the emotional state.

[0445] The server provides the infrastructure for the distributed network, creating an environment where terminals can connect and share data and sentiment information with each other over the network. The server also plays a role in ensuring system security by recording all data transactions and sentiment data transactions through distributed ledger technology.

[0446] The device processes external data through an artificial intelligence module and generates information in real time based on it. Furthermore, by utilizing an emotion engine, it can analyze the user's emotions and dynamically adjust the operation of each module based on that information. For example, if a positive emotional state is recognized, the system will make proactive decisions, while if it is negative, it will focus on risk management.

[0447] Users access insights gathered from various modules via their devices and make decisions based on emotional feedback provided by the emotion engine. A concrete example is improving the customer experience on e-commerce platforms. The device can read emotions from the user's eye movements and tone of voice, and the system can use this information to improve product recommendations.

[0448] Thus, the system of the present invention utilizes a combination of an emotion engine and an artificial intelligence module to implement an advanced interactive system, thereby achieving a new level of data processing efficiency and decision support.

[0449] The following describes the processing flow.

[0450] Step 1:

[0451] The device activates its emotion engine and acquires input data from the user. It analyzes data sources such as voice, images, and text to prepare for identifying the user's emotional state.

[0452] Step 2:

[0453] The device's artificial intelligence module receives emotional data from the emotion engine and uses it to perform specific tasks. Based on emotions, it dynamically adjusts the algorithm's parameters to perform processing appropriate for the user.

[0454] Step 3:

[0455] The server receives data and sentiment data sent from the terminal and records them within a distributed data communication structure. All information is stored securely using distributed ledger technology.

[0456] Step 4:

[0457] The device shares emotional data with other artificial intelligence modules in real time. Based on this data, the other modules adjust their collaborative actions and work together to complete tasks.

[0458] Step 5:

[0459] Users review the sentiment analysis results provided by their device and the resulting changes in task execution to make decisions. They receive feedback based on sentiment data and use it to make better decisions.

[0460] Step 6:

[0461] The device receives user feedback, readjusts its emotion engine and artificial intelligence module, and incorporates this feedback into subsequent data processing. The learning function is used to improve the overall accuracy of the system.

[0462] (Example 2)

[0463] 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."

[0464] Modern information systems require real-time decision support that reflects user emotions. However, conventional technologies have struggled to appropriately analyze user emotions and reflect them in the overall system decision-making process. As a result, providing information and decision support that meets user needs has been difficult.

[0465] 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.

[0466] In this invention, the server includes means for multiple intelligent modules to cooperate on a distributed information communication structure, means for securely sharing information among these intelligent modules using encryption technology, and means for analyzing the user's emotional state using an emotion recognition engine and dynamically adjusting the operation of each intelligent module. This enables appropriate decision-making support that takes the user's emotions into consideration.

[0467] An "intelligent module" is a program based on artificial intelligence technology that can autonomously perform specific processing tasks.

[0468] "Information and communication structure" refers to a network structure that designs the paths and protocols through which data flows within a system.

[0469] "Encryption technology" is a method for securely protecting data and is a technology used to ensure the confidentiality and integrity of information.

[0470] An "emotion recognition engine" is a system component that includes algorithms that process voice, biometric information, and other data in order to analyze the user's emotional state.

[0471] A "generative AI model" is a form of artificial intelligence technology that generates new information and recommendations based on given data and prompts.

[0472] "Distributed ledger technology" is a technology for recording data securely and transparently, and is a form of distributed database that prevents information tampering.

[0473] In one embodiment of the present invention, a system combining multiple intelligent modules and an emotion recognition engine is used on a distributed network. A server builds the network infrastructure and provides an environment where terminals can connect and securely share information and emotional information. Encryption technology is utilized in this system, and each information communication is conducted in a secure state.

[0474] The device processes data through an intelligent module and uses a generative AI model to generate appropriate information and recommendations. The emotion recognition engine built into the device uses hardware such as microphones and cameras to analyze the user's emotional state. Based on this analysis, the intelligent module dynamically adjusts its operation to provide services tailored to the user's needs.

[0475] Users make decisions based on information provided by their devices. For example, on e-commerce sites, product recommendations are made based on the user's purchase history and current emotional state. In this case, the generative AI model constructs an optimal product list based on prompts such as, "Please suggest products that match my current emotional state."

[0476] This system integrates emotion recognition and artificial intelligence technology to create an interactive system that is more attuned to human emotions. This improves the user experience and enables efficient information provision and decision-making support.

[0477] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0478] Step 1:

[0479] The server receives user data and emotional information transmitted from terminals via the network. Input data includes biometric information and behavioral logs. The server analyzes this data and categorizes it appropriately. The output is a well-organized dataset, which serves as the foundational information for each intelligent module to begin processing.

[0480] Step 2:

[0481] The terminal utilizes an intelligent module to process datasets received from the server and analyze the user's emotional state using an emotion recognition engine. The input is organized data provided by the server. The terminal analyzes voice and facial expression data to identify the emotional state and plans real-time system actions to respond. The output is the analyzed emotional data and recommended actions based on it.

[0482] Step 3:

[0483] The device uses a generative AI model to generate appropriate information and recommendations based on the user's emotional state and past data. The input consists of emotional data and insights generated by the intelligent module. The device interprets this information based on the prompt, "Please suggest products that match my current emotional state," and provides the user with the most suitable suggestions. The output is a list of products and information recommendations provided to the user.

[0484] Step 4:

[0485] The user receives information from the device and makes a decision. Inputs include information recommendations and product lists from the device. The user evaluates this information and takes action to make a choice. Outputs are the user's choices and are recorded as data for the next processing cycle.

[0486] Step 5:

[0487] The server records data obtained from all processes in a distributed ledger and generates feedback to improve system performance. Inputs are data transactions and emotional data generated at every step. The server analyzes this data and delivers feedback to terminals to inform subsequent interactions. Outputs are feedback information for system improvement.

[0488] (Application Example 2)

[0489] 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."

[0490] In modern electronic payment services, personalizing the purchasing experience by considering user emotions is a challenging task. Traditional systems struggle to appropriately adjust services based on the user's emotional state, and there is a need for optimal methods to maximize user satisfaction and purchasing intent.

[0491] 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.

[0492] In this invention, the server includes means for enabling multiple information processing modules to cooperate with each other on a distributed information transmission structure, means for securely sharing data among these information processing modules using encryption technology, and means for an emotion analysis device to analyze the user's emotional state and dynamically adjust the operation of the information processing modules based on the emotional information. This enables the personalization of the purchasing experience based on the user's emotions.

[0493] An "information processing module" is an element that individually performs specific information processing tasks and works in cooperation with other modules to realize the overall system function.

[0494] A "distributed information transmission structure" is a structure in which information is distributed and held across multiple nodes on a network, rather than on a centralized server.

[0495] "Encryption technology" is a technique that uses specific algorithms to convert information into an unreadable format in order to protect data from unauthorized access.

[0496] An "emotion analysis device" is a device that identifies a user's emotional state based on data such as their facial expressions and voice.

[0497] "Distributed ledger technology" is a technology that manages and operates ledgers, such as blockchains, on a decentralized network in order to record data transactions and prevent unauthorized alteration.

[0498] "Inference" refers to the process of drawing conclusions or insights based on multiple data and pieces of information.

[0499] "Emotional information" refers to data that indicates a user's emotional state, or information based on that data.

[0500] The system implementing this invention provides an innovative method for personalizing the user's purchasing experience in electronic payment services. The server can have multiple information processing modules collaborate on a distributed information transmission structure, thereby processing large amounts of data rapidly. Each information processing module is responsible for a specific information processing task, such as natural language processing or inference, and data sharing between modules is securely performed using encryption technology.

[0501] The terminal uses an emotion analysis device to acquire real-time emotional information from the user and transmit it to a central server. For example, by using the terminal's camera and microphone, it analyzes the user's facial expressions and tone of voice to identify the user's current emotional state. This emotional information is used to dynamically adjust the operation of the information processing module, optimizing the entire system so that the user can complete the payment process comfortably and without stress.

[0502] Through this system, users can receive emotion-based services. For example, if emotion analysis detects excitement when a user is hesitant about purchasing a new product, the system will immediately present relevant product reviews and tutorials to support their purchase decision. Additionally, the prompt used for the generative AI model is, "When a user is undecided about a product, show how to provide additional information and options to help them make a decision."

[0503] Such a system will enable personalized payment services based on user emotions, which is expected to improve purchasing intent and enhance customer satisfaction.

[0504] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0505] Step 1:

[0506] The device uses a camera and microphone to capture the user's facial expressions and voice tone. This input data is sent to an emotion analysis device, where it is processed in real time to identify the user's emotional state. The output is an analysis result indicating which emotional state the user is currently experiencing, such as excitement, relief, or confusion.

[0507] Step 2:

[0508] The server receives emotion information sent from the terminal and distributes it to the information processing module. Here, the emotion information received as input is encrypted to share the infrastructure with other modules and transmitted securely. The output at this stage is encrypted emotion information.

[0509] Step 3:

[0510] The information processing module dynamically adjusts product recommendations to the user based on received sentiment information. Using a generative AI model, it generates prompts based on the user's emotional state and selects highly relevant product reviews and tutorials. The input to this process is encrypted sentiment information, and the output is personalized product recommendations for the user.

[0511] Step 4:

[0512] The user receives product information suggested through the terminal and makes a purchase decision based on that information. The terminal displays details of products the user is interested in and provides a user interface for entering payment information. The input consists of product suggestions and the user's selection, and the output is the final purchase decision.

[0513] Step 5:

[0514] Once the purchase is complete, the server records the transaction in a distributed ledger. In this process, the purchase decision information is provided as input, and that information is stored in the distributed ledger as output, ensuring data integrity while preventing unauthorized modification.

[0515] 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.

[0516] 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.

[0517] 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.

[0518] [Fourth Embodiment]

[0519] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0520] 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.

[0521] 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).

[0522] 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.

[0523] 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.

[0524] 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).

[0525] 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.

[0526] 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.

[0527] 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.

[0528] 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.

[0529] 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.

[0530] 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.

[0531] 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".

[0532] The system of the present invention enables multiple artificial intelligence modules to collaborate on a distributed data communication structure, thereby achieving efficient processing of large-scale data and secure decision-making. Each module implements an algorithm specialized for a specific task and performs optimal processing according to a pre-defined objective.

[0533] The server is responsible for building the distributed network and providing the infrastructure for each terminal to connect. This allows the artificial intelligence modules on the terminals to seamlessly participate in the network and creates an environment where data can be easily shared with each other. Furthermore, the server plays a role in improving the overall security of the system by recording transactions through distributed ledger technology.

[0534] The terminal uses a connected artificial intelligence module to process data acquired from external sources. This processing includes data preprocessing, model application, and result analysis. The processed results are securely shared with the artificial intelligence modules of other terminals using encryption technology. This enables scalable operation while maintaining high overall system reliability.

[0535] Users receive insights from multiple artificial intelligence modules via their devices in real time and use them to make decisions. A specific example of this system is market forecasting in the financial sector. The AI ​​modules on the device collect and analyze vast amounts of market data and share the results with other devices via the blockchain. Users can then make investment decisions based on the analysis results from each module.

[0536] In this way, the system of the present invention overcomes the limitations of known technologies and realizes a more efficient and secure data processing environment. By using a distributed architecture and reliable ledger technology, it promotes collaboration among artificial intelligence modules and delivers superior performance in a wide range of applications.

[0537] The following describes the processing flow.

[0538] Step 1:

[0539] The terminal starts up the artificial intelligence module and loads a model suited to the specific task. Once initialization is complete, the module connects to the network and prepares to communicate with other modules.

[0540] Step 2:

[0541] The server initiates the construction of a distributed network. It manages the connections of each terminal, records transactions using distributed ledger technology, and maintains overall security.

[0542] Step 3:

[0543] The device collects data from external data sources (e.g., sensors, databases). The collected data is preprocessed, including noise reduction and conversion to the required format.

[0544] Step 4:

[0545] The device's artificial intelligence module analyzes pre-processed data. This analysis includes applying machine learning models and executing algorithms, generating results tailored to the specific task.

[0546] Step 5:

[0547] The terminal shares analysis results with other artificial intelligence modules. Data is securely transmitted using encryption technology, and the information shared via the server is recorded on the blockchain.

[0548] Step 6:

[0549] The terminal receives data shared from other modules and adjusts its own task processing based on that data. Real-time information exchange enables efficient collaboration.

[0550] Step 7:

[0551] Users receive analysis results from their devices and make decisions based on them. Generative AI models provide additional insights and future predictions, which are then used as a basis for their decisions.

[0552] (Example 1)

[0553] 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".

[0554] The challenge lies in building a reliable system that efficiently and securely processes data from multiple information processing devices in a distributed environment, thereby supporting real-time decision-making. In particular, ensuring the security of data sharing, the reliability of analysis results, and real-time capabilities to enable users to make rapid decisions are crucial.

[0555] 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.

[0556] In this invention, the server includes means for constructing a distributed network infrastructure, means for preprocessing and analyzing data, and means for securely sharing data using encryption technology. This enables the information processing device to efficiently process data and facilitates data sharing and analysis in a distributed environment. Users are supported in real-time decision-making, and the system as a whole becomes highly reliable.

[0557] An "information processing device" is a computer system that has the functions of collecting, processing, and analyzing data.

[0558] A "distributed network infrastructure" refers to a network structure that serves as the foundation for multiple information processing devices to connect with each other and communicate data.

[0559] A "machine learning algorithm" is a data analysis technique used to analyze large amounts of data and discover specific patterns or rules.

[0560] "Encryption technology" refers to the technology used to prevent unauthorized access and tampering by third parties by encrypting data.

[0561] "Distributed recording technology" refers to a technology that prevents tampering by recording data transactions and change histories in a distributed manner across multiple information processing devices.

[0562] A "user" is an individual or organization that makes decisions using data and analysis results provided through an information processing device.

[0563] "Receiving in real time" refers to the format and timing of receiving information provided by an information processing device immediately.

[0564] "Feedback" refers to opinions and improvement suggestions provided by users based on the results obtained from the system, which the system then incorporates into future data processing and analysis.

[0565] This system achieves an efficient and reliable data processing environment by enabling multiple information processing devices to collaborate on a distributed network infrastructure.

[0566] The server is responsible for building the distributed network infrastructure and providing the foundation for each terminal to connect. Specifically, this involves configuring communication protocols and using routing technologies to optimize data flow. The server also implements processes to ensure data confidentiality and integrity using encryption technologies.

[0567] Each terminal is an information processing device equipped with artificial intelligence. The terminals collect external data and clean it through preprocessing. This includes using software frameworks (e.g., Python, TensorFlow) to normalize the dataset and extract features. Subsequently, the data is analyzed using applicable machine learning algorithms, and the insights gained are shared with other terminals. Throughout this process, secure data transmission is ensured using AES encryption technology.

[0568] Users receive analysis results in real time via their devices and make decisions based on them. For example, regarding market forecasts based on financial market data, users decide on an investment strategy based on the analyzed results. The feedback obtained at this time is reflected in the next analysis model by the information processing device, further improving accuracy.

[0569] A concrete example is collecting market data and using machine learning models to predict stock price fluctuations. These predictions are encrypted and transmitted to other participating nodes via a decentralized network. Users can then make investment decisions based on these results.

[0570] An example of a prompt to input into the generated AI model is, "How does this system enable collaboration between AI modules in a distributed environment?"

[0571] In this way, the system enables efficient and secure data processing that was difficult with existing technologies, and supports user decision-making.

[0572] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0573] Step 1:

[0574] The server establishes a distributed network. First, it configures the network protocol and provides an environment where terminals can connect securely. As input, the server receives authentication information and network configuration data from terminals, and as output, it grants connection permission to terminals. This allows each terminal to participate stably within the distributed network.

[0575] Step 2:

[0576] The terminal collects data from external sources. For example, it obtains real-time market data from a financial market API. This collected data is the input, and the terminal performs preprocessing such as data formatting and noise reduction, outputting a cleaned dataset. This processing ensures that the less noisy data is passed on to the next analysis step.

[0577] Step 3:

[0578] The device uses a pre-trained machine learning model to analyze pre-processed data. This involves applying deep learning algorithms to learn market trend patterns as a model. The input is processed data, and the output is a prediction result as the analysis result. The data obtained here is specific data, such as future stock price predictions.

[0579] Step 4:

[0580] The terminal shares the obtained analysis results with other terminals using encryption technology. Here, AES encryption technology is used to protect the prediction results, and the results are transmitted using distributed recording technologies such as blockchain. The input is the analysis results, and the output is encrypted data sent over the network. This process ensures the security and confidentiality of the data.

[0581] Step 5:

[0582] Users receive analysis results from their devices and make decisions based on them. Recommended actions based on the analysis results are provided as user input, which they then use to make decisions such as investment decisions. The output is returned to the device as feedback for improvement and used to refine subsequent data analyses. Users can make quick decisions by reviewing this data in real time.

[0583] (Application Example 1)

[0584] 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".

[0585] Modern cities face challenges such as traffic congestion and inefficient road use due to rapid population growth and increasing traffic volume. Traditional transportation systems are unable to effectively utilize distributed data, making it difficult to provide citizens with comfortable and efficient means of transportation. To solve this problem, an advanced system is needed that processes diverse data in real time and provides users with optimal routes and traffic information.

[0586] 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.

[0587] In this invention, the server includes means for enabling multiple information processing modules to cooperate with each other on a distributed communication structure, means for securely sharing data among these information processing modules using encryption technology, means for each information processing module to individually perform a specific analysis task, means for integrating environmental data in real time and providing decision support information, and means for presenting results to a user terminal and dynamically updating the information. This enables an efficient traffic information provision system in urban environments.

[0588] An "information processing module" is a separate processor that analyzes data and generates results according to a specific task.

[0589] A "distributed communication structure" is a structure in which different network nodes cooperate independently with each other and exchange data, without requiring centralized management.

[0590] "Encryption technology" is a technique that transforms data and communication content in a way that prevents others from deciphering it, and is a means of ensuring security.

[0591] "Environmental data integration" is the process of centrally collecting and analyzing data acquired from different sensors and devices.

[0592] "Decision support information" refers to information that serves as a guide for users to choose appropriate actions, based on data analysis results.

[0593] A "user terminal" is a device used by the end user to receive information and perform operations.

[0594] "Dynamic information updating" is a process in which information is revised in a timely manner based on data that changes in real time.

[0595] The system that realizes this application example includes a server with a distributed communication structure, multiple information processing modules, encryption technology, secure data sharing, real-time data integration, decision support information provision, and dynamic information updates on user terminals.

[0596] The server utilizes Apache Kafka or similar data streaming platforms to deliver real-time data collected from various sensors and devices to information processing modules. These modules use machine learning frameworks such as TensorFlow and PyTorch to perform data analysis and pattern detection. The results are managed on a blockchain using encryption technology to ensure security.

[0597] The terminal provides information to user devices, including smartphones and tablets, and presents optimized routes and modes of transport in real time. Users receive information through the application and are requested to recalculate the route as needed. For example, when a user launches the application to travel within the city, environmental data is analyzed in real time, and the optimal route is recommended.

[0598] An example of a prompt message is: "Analyze current traffic data within the city and recommend the smoothest commute route. Also, suggest ways to notify users, including real-time traffic disruption information."

[0599] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0600] Step 1:

[0601] The server collects traffic data from various sensors and devices installed throughout the city and uses Apache Kafka to transfer this data to a stream processing system. The input is real-time traffic data from the sensors, and the output is a data stream delivered to the information processing module. At this stage, the sensor information is formatted and the data format is standardized.

[0602] Step 2:

[0603] The information processing module receives a data stream from the server and performs real-time analysis of the data using TensorFlow or PyTorch. The input is formatted traffic data, and the output is analyzed traffic patterns and future congestion predictions. This process applies traffic pattern recognition algorithms to extract specific patterns (e.g., congestion predictions).

[0604] Step 3:

[0605] The server encrypts the analysis results from the information processing module and securely records them in a database using blockchain technology. The input is the analyzed traffic data, and the output is encrypted data entries. This prevents data tampering and ensures reliability.

[0606] Step 4:

[0607] The terminal receives a request from the user and sends a prompt message to the generating AI model that generates real-time travel route information. The input is the user's current location and destination, and the output is an optimized route suggestion. In this step, the generating AI model dynamically generates the route based on traffic information.

[0608] Step 5:

[0609] The user receives decision-making support information regarding optimal travel routes and traffic conditions through their device. The input is optimized route information, and the output is navigation information displayed on the user interface. Based on this information, the user selects actions to travel efficiently.

[0610] 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.

[0611] The system of the present invention enables more sophisticated data processing and decision-making by having multiple artificial intelligence modules collaborate on a distributed data communication structure and by combining them with an emotion engine that recognizes the user's emotions. Each module has an algorithm specialized for a specific task, and the emotion engine analyzes data from the user to identify the emotional state.

[0612] The server provides the infrastructure for the distributed network, creating an environment where terminals can connect and share data and sentiment information with each other over the network. The server also plays a role in ensuring system security by recording all data transactions and sentiment data transactions through distributed ledger technology.

[0613] The device processes external data through an artificial intelligence module and generates information in real time based on it. Furthermore, by utilizing an emotion engine, it can analyze the user's emotions and dynamically adjust the operation of each module based on that information. For example, if a positive emotional state is recognized, the system will make proactive decisions, while if it is negative, it will focus on risk management.

[0614] Users access insights gathered from various modules via their devices and make decisions based on emotional feedback provided by the emotion engine. A concrete example is improving the customer experience on e-commerce platforms. The device can read emotions from the user's eye movements and tone of voice, and the system can use this information to improve product recommendations.

[0615] Thus, the system of the present invention utilizes a combination of an emotion engine and an artificial intelligence module to implement an advanced interactive system, thereby achieving a new level of data processing efficiency and decision support.

[0616] The following describes the processing flow.

[0617] Step 1:

[0618] The device activates its emotion engine and acquires input data from the user. It analyzes data sources such as voice, images, and text to prepare for identifying the user's emotional state.

[0619] Step 2:

[0620] The device's artificial intelligence module receives emotional data from the emotion engine and uses it to perform specific tasks. Based on emotions, it dynamically adjusts the algorithm's parameters to perform processing appropriate for the user.

[0621] Step 3:

[0622] The server receives data and sentiment data sent from the terminal and records them within a distributed data communication structure. All information is stored securely using distributed ledger technology.

[0623] Step 4:

[0624] The device shares emotional data with other artificial intelligence modules in real time. Based on this data, the other modules adjust their collaborative actions and work together to complete tasks.

[0625] Step 5:

[0626] Users review the sentiment analysis results provided by their device and the resulting changes in task execution to make decisions. They receive feedback based on sentiment data and use it to make better decisions.

[0627] Step 6:

[0628] The device receives user feedback, readjusts its emotion engine and artificial intelligence module, and incorporates this feedback into subsequent data processing. The learning function is used to improve the overall accuracy of the system.

[0629] (Example 2)

[0630] 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".

[0631] Modern information systems require real-time decision support that reflects user emotions. However, conventional technologies have struggled to appropriately analyze user emotions and reflect them in the overall system decision-making process. As a result, providing information and decision support that meets user needs has been difficult.

[0632] 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.

[0633] In this invention, the server includes means for multiple intelligent modules to cooperate on a distributed information communication structure, means for securely sharing information among these intelligent modules using encryption technology, and means for analyzing the user's emotional state using an emotion recognition engine and dynamically adjusting the operation of each intelligent module. This enables appropriate decision-making support that takes the user's emotions into consideration.

[0634] An "intelligent module" is a program based on artificial intelligence technology that can autonomously perform specific processing tasks.

[0635] "Information and communication structure" refers to a network structure that designs the paths and protocols through which data flows within a system.

[0636] "Encryption technology" is a method for securely protecting data and is a technology used to ensure the confidentiality and integrity of information.

[0637] An "emotion recognition engine" is a system component that includes algorithms that process voice, biometric information, and other data in order to analyze the user's emotional state.

[0638] A "generative AI model" is a form of artificial intelligence technology that generates new information and recommendations based on given data and prompts.

[0639] "Distributed ledger technology" is a technology for recording data securely and transparently, and is a form of distributed database that prevents information tampering.

[0640] In one embodiment of the present invention, a system combining multiple intelligent modules and an emotion recognition engine is used on a distributed network. A server builds the network infrastructure and provides an environment where terminals can connect and securely share information and emotional information. Encryption technology is utilized in this system, and each information communication is conducted in a secure state.

[0641] The device processes data through an intelligent module and uses a generative AI model to generate appropriate information and recommendations. The emotion recognition engine built into the device uses hardware such as microphones and cameras to analyze the user's emotional state. Based on this analysis, the intelligent module dynamically adjusts its operation to provide services tailored to the user's needs.

[0642] Users make decisions based on information provided by their devices. For example, on e-commerce sites, product recommendations are made based on the user's purchase history and current emotional state. In this case, the generative AI model constructs an optimal product list based on prompts such as, "Please suggest products that match my current emotional state."

[0643] This system integrates emotion recognition and artificial intelligence technology to create an interactive system that is more attuned to human emotions. This improves the user experience and enables efficient information provision and decision-making support.

[0644] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0645] Step 1:

[0646] The server receives user data and emotional information transmitted from terminals via the network. Input data includes biometric information and behavioral logs. The server analyzes this data and categorizes it appropriately. The output is a well-organized dataset, which serves as the foundational information for each intelligent module to begin processing.

[0647] Step 2:

[0648] The terminal utilizes an intelligent module to process datasets received from the server and analyze the user's emotional state using an emotion recognition engine. The input is organized data provided by the server. The terminal analyzes voice and facial expression data to identify the emotional state and plans real-time system actions to respond. The output is the analyzed emotional data and recommended actions based on it.

[0649] Step 3:

[0650] The device uses a generative AI model to generate appropriate information and recommendations based on the user's emotional state and past data. The input consists of emotional data and insights generated by the intelligent module. The device interprets this information based on the prompt, "Please suggest products that match my current emotional state," and provides the user with the most suitable suggestions. The output is a list of products and information recommendations provided to the user.

[0651] Step 4:

[0652] The user receives information from the device and makes a decision. Inputs include information recommendations and product lists from the device. The user evaluates this information and takes action to make a choice. Outputs are the user's choices and are recorded as data for the next processing cycle.

[0653] Step 5:

[0654] The server records data obtained from all processes in a distributed ledger and generates feedback to improve system performance. Inputs are data transactions and emotional data generated at every step. The server analyzes this data and delivers feedback to terminals to inform subsequent interactions. Outputs are feedback information for system improvement.

[0655] (Application Example 2)

[0656] 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".

[0657] In modern electronic payment services, personalizing the purchasing experience by considering user emotions is a challenging task. Traditional systems struggle to appropriately adjust services based on the user's emotional state, and there is a need for optimal methods to maximize user satisfaction and purchasing intent.

[0658] 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.

[0659] In this invention, the server includes means for enabling multiple information processing modules to cooperate with each other on a distributed information transmission structure, means for securely sharing data among these information processing modules using encryption technology, and means for an emotion analysis device to analyze the user's emotional state and dynamically adjust the operation of the information processing modules based on the emotional information. This enables the personalization of the purchasing experience based on the user's emotions.

[0660] An "information processing module" is an element that individually performs specific information processing tasks and works in cooperation with other modules to realize the overall system function.

[0661] A "distributed information transmission structure" is a structure in which information is distributed and held across multiple nodes on a network, rather than on a centralized server.

[0662] "Encryption technology" is a technique that uses specific algorithms to convert information into an unreadable format in order to protect data from unauthorized access.

[0663] An "emotion analysis device" is a device that identifies a user's emotional state based on data such as their facial expressions and voice.

[0664] "Distributed ledger technology" is a technology that manages and operates ledgers, such as blockchains, on a decentralized network in order to record data transactions and prevent unauthorized alteration.

[0665] "Inference" refers to the process of drawing conclusions or insights based on multiple data and pieces of information.

[0666] "Emotional information" refers to data that indicates a user's emotional state, or information based on that data.

[0667] The system implementing this invention provides an innovative method for personalizing the user's purchasing experience in electronic payment services. The server can have multiple information processing modules collaborate on a distributed information transmission structure, thereby processing large amounts of data rapidly. Each information processing module is responsible for a specific information processing task, such as natural language processing or inference, and data sharing between modules is securely performed using encryption technology.

[0668] The terminal uses an emotion analysis device to acquire real-time emotional information from the user and transmit it to a central server. For example, by using the terminal's camera and microphone, it analyzes the user's facial expressions and tone of voice to identify the user's current emotional state. This emotional information is used to dynamically adjust the operation of the information processing module, optimizing the entire system so that the user can complete the payment process comfortably and without stress.

[0669] Through this system, users can receive emotion-based services. For example, if emotion analysis detects excitement when a user is hesitant about purchasing a new product, the system will immediately present relevant product reviews and tutorials to support their purchase decision. Additionally, the prompt used for the generative AI model is, "When a user is undecided about a product, show how to provide additional information and options to help them make a decision."

[0670] Such a system will enable personalized payment services based on user emotions, which is expected to improve purchasing intent and enhance customer satisfaction.

[0671] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0672] Step 1:

[0673] The device uses a camera and microphone to capture the user's facial expressions and voice tone. This input data is sent to an emotion analysis device, where it is processed in real time to identify the user's emotional state. The output is an analysis result indicating which emotional state the user is currently experiencing, such as excitement, relief, or confusion.

[0674] Step 2:

[0675] The server receives emotion information sent from the terminal and distributes it to the information processing module. Here, the emotion information received as input is encrypted to share the infrastructure with other modules and transmitted securely. The output at this stage is encrypted emotion information.

[0676] Step 3:

[0677] The information processing module dynamically adjusts product recommendations to the user based on received sentiment information. Using a generative AI model, it generates prompts based on the user's emotional state and selects highly relevant product reviews and tutorials. The input to this process is encrypted sentiment information, and the output is personalized product recommendations for the user.

[0678] Step 4:

[0679] The user receives product information suggested through the terminal and makes a purchase decision based on that information. The terminal displays details of products the user is interested in and provides a user interface for entering payment information. The input consists of product suggestions and the user's selection, and the output is the final purchase decision.

[0680] Step 5:

[0681] Once the purchase is complete, the server records the transaction in a distributed ledger. In this process, the purchase decision information is provided as input, and that information is stored in the distributed ledger as output, ensuring data integrity while preventing unauthorized modification.

[0682] 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.

[0683] 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.

[0684] 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.

[0685] 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.

[0686] 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.

[0687] 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.

[0688] 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.

[0689] 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.

[0690] 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."

[0691] 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.

[0692] 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.

[0693] 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.

[0694] 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.

[0695] 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.

[0696] 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.

[0697] 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.

[0698] 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.

[0699] 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.

[0700] 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.

[0701] 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.

[0702] 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.

[0703] The following is further disclosed regarding the embodiments described above.

[0704] (Claim 1)

[0705] A means to enable multiple artificial intelligence modules to cooperate with each other on a distributed data communication structure,

[0706] A means of securely sharing data between these artificial intelligence modules using encryption technology,

[0707] A system characterized in that each artificial intelligence module is equipped with means for individually executing a specific processing task.

[0708] (Claim 2)

[0709] The system according to claim 1, comprising distributed ledger technology for recording data transactions within a distributed data communication structure and preventing unauthorized alteration.

[0710] (Claim 3)

[0711] The system according to claim 1, comprising means for sharing the insights generated by each artificial intelligence module with other modules in real time and for collaborative decision-making.

[0712] "Example 1"

[0713] (Claim 1)

[0714] A means that enables multiple information processing devices to collaborate on a distributed network infrastructure,

[0715] A means for collecting and pre-processing data,

[0716] Methods for performing analysis by applying machine learning algorithms,

[0717] A means of securely sharing data between information processing devices using encryption technology,

[0718] Each information processing device has means for individually executing a specific process,

[0719] A means for recording the results of information processing and incorporating distributed recording technology to prevent unauthorized alteration,

[0720] A means for users to receive information processing results in real time and use them for decision-making,

[0721] ...

[0722] A system that includes this.

[0723] (Claim 2)

[0724] The system according to claim 1, comprising means for sharing the insights generated by each information processing device with other devices in real time and for collaborative decision-making.

[0725] (Claim 3)

[0726] The system according to claim 1, comprising feedback for improving the analysis results obtained by the information processing device.

[0727] "Application Example 1"

[0728] (Claim 1)

[0729] A means that enables multiple information processing modules to cooperate with each other on a distributed communication structure,

[0730] A means for securely sharing data between these information processing modules using encryption technology,

[0731] Each information processing module has a means to individually perform a specific analysis task,

[0732] A means of integrating environmental data in real time and providing decision support information,

[0733] A means of displaying results on the user's terminal and dynamically updating the information,

[0734] A system that includes this.

[0735] (Claim 2)

[0736] The system according to claim 1, comprising distributed ledger technology for recording data processing within a distributed communication structure and preventing unauthorized modifications.

[0737] (Claim 3)

[0738] The system according to claim 1, comprising means for sharing analysis results generated by each information processing module with other modules in real time and for collaborative decision-making based on environmental conditions.

[0739] "Example 2 of combining an emotion engine"

[0740] (Claim 1)

[0741] A means by which multiple intelligent modules cooperate with each other on a distributed information and communication structure,

[0742] A means of securely sharing information between these intelligent modules using encryption technology,

[0743] Each intelligent module has a means to individually execute a specific processing task,

[0744] A means for analyzing the user's emotional state using an emotion recognition engine and dynamically adjusting the operation of each intelligent module,

[0745] A means of generating information to support decision-making using a generative AI model,

[0746] A system that includes this.

[0747] (Claim 2)

[0748] Distributed ledger technology for recording information transactions within a distributed information communication structure and preventing unauthorized alteration,

[0749] The system according to claim 1, comprising means for integrating and recording emotional information and data transactions.

[0750] (Claim 3)

[0751] A means of sharing the insights generated by each intelligent module with other modules in real time and making collaborative decisions,

[0752] The system according to claim 1, comprising a dynamic decision-making adjustment means that is performed based on an emotional state.

[0753] "Application example 2 when combining with an emotional engine"

[0754] (Claim 1)

[0755] A means that enables multiple information processing modules to cooperate with each other on a distributed information transmission structure,

[0756] A means for securely sharing data between these information processing modules using encryption technology,

[0757] Each information processing module has means to individually execute specific processing tasks,

[0758] A system that includes an emotion analysis device that analyzes the user's emotional state and means for dynamically adjusting the operation of an information processing module based on the emotional information.

[0759] (Claim 2)

[0760] The system according to claim 1, comprising distributed ledger technology for recording data transactions within a distributed information transmission structure and preventing unauthorized alteration.

[0761] (Claim 3)

[0762] The system according to claim 1, comprising means for sharing the inferences generated by each information processing module with other modules in real time and for collaboratively making decisions based on emotional information. [Explanation of Symbols]

[0763] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means that enables multiple information processing modules to cooperate with each other on a distributed communication structure, A means for securely sharing data between these information processing modules using encryption technology, Each information processing module has a means to individually perform a specific analysis task, A means of integrating environmental data in real time and providing decision support information, A means of displaying results on the user's terminal and dynamically updating the information, A system that includes this.

2. The system according to claim 1, comprising distributed ledger technology for recording data processing within a distributed communication structure and preventing unauthorized modifications.

3. The system according to claim 1, comprising means for sharing analysis results generated by each information processing module with other modules in real time and for making decisions based on environmental conditions in a collaborative manner.

Images