Information processing system

Abstract

The present invention provides an information processing system comprising: means for receiving data collected by a terminal; means for analyzing the received data using a generative model and generating dictionary data for data compression; means for distributing the generated dictionary data to the terminal and setting the dictionary data to be used by the terminal in the next data communication; and means for ensuring the security of data communication using an encryption technique.

Description

Technical Field

[0001] The technology disclosed herein relates to an information processing system. Background Technology

[0002] Japanese Patent Application Publication No. 2022-180282 discloses a method for controlling a role-based chatbot executed by at least one processor. The method includes the following steps: receiving a user's speech; adding the user's speech to a prompt word, the prompt word containing instruction statements associated with an explanation of the chatbot's role; encoding the prompt word; and inputting the encoded prompt word into a language model to generate a chatbot response to the user's speech.

[0003] Existing Internet of Things (IoT) terminals are typically resource-constrained, resulting in issues such as large data volumes, low bandwidth utilization, and insufficient security in data communication. Traditional compression methods struggle to adapt to various dynamically changing data characteristics, and encrypted communication often increases the computational and energy consumption burden on terminals. Therefore, achieving efficient and secure data communication on low-power, low-computing-power terminals has become a pressing technical challenge. Summary of the Invention

[0004] This invention employs a generative model to dynamically analyze data collected by terminals and generate targeted data compression dictionaries. The system distributes this dictionary data to terminals via a server, allowing terminals to efficiently compress data during subsequent transmissions. Simultaneously, the system utilizes encryption technology to ensure security during data communication. Furthermore, the server can decode and process the compressed data, significantly improving terminal communication efficiency and ensuring data transmission security, thus meeting the needs of resource-constrained terminals for efficient and secure communication.

[0005] "Terminal" refers to information processing equipment that can collect environmental or user-related data and communicate with servers, such as sensors, smart home appliances, and mobile devices.

[0006] A "server" refers to a computing device capable of receiving, analyzing, storing, and processing data, responsible for centrally managing data sent from terminals and issuing relevant configurations or instructions.

[0007] "Generative models" refer to algorithmic models based on artificial intelligence technology that automatically discover data patterns by learning and analyzing data, thereby generating specific processing rules or structures.

[0008] "Dictionary data" refers to the set of encoding and mapping rules used for data compression and decompression, obtained by analyzing the original data using a generative model.

[0009] "Data compression" refers to the process of using specific algorithms or dictionaries to convert raw data into a smaller but reversible format in order to reduce the amount of data transmitted.

[0010] "Encryption technology" refers to security measures that use specific algorithms to encrypt data to ensure that the data is not stolen or tampered with by unauthorized parties during transmission.

[0011] "Distribution" refers to the server sending the generated dictionary data to the terminal, enabling the terminal to use the dictionary data in subsequent data communication. Attached Figure Description

[0012] Figure 1 This is a conceptual diagram illustrating an example of the configuration of the data processing system according to the first embodiment.

[0013] Figure 2 This is a conceptual diagram illustrating an example of the main functions of the data processing apparatus and smart device according to the first embodiment.

[0014] Figure 3 This is a conceptual diagram illustrating an example of the configuration of the data processing system according to the second embodiment.

[0015] Figure 4 This is a conceptual diagram illustrating an example of the main functions of the data processing device and smart glasses according to the second embodiment.

[0016] Figure 5 This is a conceptual diagram illustrating an example of the configuration of the data processing system according to the third embodiment.

[0017] Figure 6 This is a conceptual diagram illustrating an example of the main functions of the data processing apparatus and head-mounted terminal according to the third embodiment.

[0018] Figure 7 This is a conceptual diagram illustrating an example of the configuration of the data processing system according to the fourth embodiment.

[0019] Figure 8 This is a conceptual diagram illustrating an example of the main functions of the data processing device and robot according to the fourth embodiment.

[0020] Figure 9 This represents an emotion map that maps multiple emotions.

[0021] Figure 10 This represents an emotion map that maps multiple emotions.

[0022] Figure 11 This is a sequence diagram illustrating the processing flow of the data processing system of Embodiment 1.

[0023] Figure 12This is a sequence diagram illustrating the processing flow of the data processing system in Application Example 1.

[0024] Figure 13 This is a sequence diagram illustrating the processing flow of the data processing system in Embodiment 2.

[0025] Figure 14 This is a sequence diagram illustrating the processing flow of the data processing system in Application Example 2. Detailed Implementation

[0026] Hereinafter, an example of an implementation of the system according to the present disclosure will be described with reference to the accompanying drawings.

[0027] First, let me explain the terminology used in the following instructions.

[0028] In the following embodiments, the processor (hereinafter referred to as "processor") with reference numerals may be a single computing device or a combination of multiple computing devices. Furthermore, the processor may be a single computing device or a combination of multiple computing devices. Examples of computing devices include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), etc.

[0029] In the following embodiments, RAM (Random Access Memory), as indicated in the figures, is a memory that temporarily stores information and is used as working memory by the processor.

[0030] In the following embodiments, the memory, as indicated by the reference numerals, is one or more non-volatile storage devices that store various programs and parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), disks (e.g., hard disks), or magnetic tapes.

[0031] In the following embodiments, the communication I / F (Interface) with reference numerals is an interface that includes a communication processor and an antenna, etc. The communication I / F is responsible for communication between multiple computers. As an example of a communication specification applicable to the communication I / F, wireless communication specifications such as 5G (5th Generation Mobile Communication System), Wi-Fi (wireless fidelity) (registered trademark), or Bluetooth (registered trademark) can be listed.

[0032] 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 can be only A, only B, or a combination of A and B. Furthermore, in this specification, when "and / or" connects to express more than three items, the same interpretation as "A and / or B" applies.

[0033] First Implementation Method Figure 1 An example of the configuration of the data processing system 10 according to the first embodiment is shown.

[0034] like Figure 1 As shown, the data processing system 10 includes a data processing device 12 and an intelligent device 14. A server can be cited as an example of the data processing device 12.

[0035] The data processing apparatus 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" as understood in this disclosure. The computer 22 includes a processor 28, RAM 30, and memory 32. The processor 28, RAM 30, and memory 32 are connected to a bus 34. Furthermore, the database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0036] The smart device 14 includes a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, RAM 48, and memory 50. The processor 46, RAM 48, and memory 50 are connected to a bus 52. In addition, the receiving device 38, output device 40, camera 42, and communication I / F 44 are also connected to the bus 52.

[0037] The receiving device 38 includes a touchscreen 38A and a microphone 38B, and receives user input. The touchscreen 38A receives user input via touch by detecting contact with an indicator (e.g., a pen or finger). The microphone 38B receives user input via sound by detecting the user's voice. The control unit 46A in the processor 46 sends data representing the user input received by the touchscreen 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data representing the user input.

[0038] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting data in a form perceptible to the user 20 (e.g., sound and / or text). The display 40A displays visual information such as text and images according to instructions from the processor 46. The speaker 40B outputs sound 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 imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0039] Communication I / F44 is connected to network 54. Communication I / F44 and 26 are responsible for sending and receiving various information between processor 46 and processor 28 via network 54.

[0040] Figure 2 The diagram shows an example of the main functions of the data processing device 12 and the smart device 14.

[0041] like Figure 2 As shown, in the data processing apparatus 12, specific processing is performed by the processor 28. A specific processing program 56 is stored in the memory 32. The specific processing program 56 is an example of a "program" as understood in this disclosure. The processor 28 reads the specific processing program 56 from the memory 32 and executes the read specific processing program 56 on the RAM 30. Specific processing is implemented by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0042] The memory 32 stores a data generation model 58 and an emotion-specific model 59. The data generation model 58 and the emotion-specific model 59 are used by the specific processing unit 290. The specific processing unit 290 can use the emotion-specific model 59 to infer the user's emotions and perform specific processing based on the user's emotions. In the emotion inference function (emotion-specific function) using the emotion-specific model 59, various inferences and predictions related to the user's emotions are performed, including inferences and predictions of the user's emotions, but this is not limited to this example. Furthermore, emotion inference and prediction may also include, for example, emotion analysis (parsing).

[0043] In the smart device 14, the processor 46 performs the acceptance output processing. The memory 50 stores the acceptance output program 60. The acceptance output program 60 is used in conjunction with the data processing system 10 and the specific processing program 56. The processor 46 reads the acceptance output program 60 from the memory 50 and executes the read acceptance output program 60 on the RAM 48. The acceptance output processing is implemented by the processor 46 acting as the control unit 46A according to the acceptance output program 60 executed on the RAM 48. Furthermore, the smart device 14 has the same data generation model and emotion-specific model as the data generation model 58 and the emotion-specific model 59, and these models can also be used to perform the same processing as the specific processing unit 290. The acceptance output processing is implemented by the processor 46 acting as the control unit 46A according to the acceptance output program 60 executed on the RAM 48.

[0044] Alternatively, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains the processing results (prediction results, etc.) using the data generation model 58 by communicating with the server device that has the data generation model 58. Furthermore, the data processing device 12 may be a server device or a user-held terminal device (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of the processing of the data processing system 10 of the first embodiment will be described.

[0045] Example 1 The flow of a specific process in Example 1 will be described. Each part of the system described below is implemented by the data processing device 12 and the smart device 14. Furthermore, the data processing device 12 is referred to as the "server," and the smart device 14 is referred to as the "terminal."

[0046] With the development of information technology, low-performance information terminals are often limited by communication efficiency and data security when conducting real-time communication of large amounts of data. Existing technologies still have many shortcomings in reducing the processing burden of information terminals while ensuring efficient and secure communication, and enabling users to monitor and analyze various environmental or business data in real time and conveniently. For example, traditional data compression methods cannot dynamically adjust the compression dictionary, and their secure communication and real-time visualization analysis functions are relatively limited, making it difficult to meet the actual needs of fields such as the Internet of Things and smart homes.

[0047] The specific processing performed by the specific processing unit 290 of the data processing apparatus 12 in Embodiment 1 is achieved by the following means.

[0048] In this invention, the server includes a data receiving device for receiving collected data from an information terminal; a data analysis device for analyzing the received data using a generative artificial intelligence model and generating encoding rule information required for compression; a distribution device for distributing the encoding rule information to the information terminal; a communication security device for encrypting the compressed data based on the encoding rule information; a visualization device for real-time visualization of the received and stored data and the analyzed and processed data; shared general information processing resources for information compression and decompression; and a control device for receiving generative artificial intelligence input prompts and initiating corresponding analysis and processing. This ensures secure data communication and efficient compression while reducing the computational burden on the information terminal, enabling real-time data visualization management, and meeting users' needs for efficient, secure, and intelligent data processing.

[0049] "Information terminal" refers to an electronic device that can collect, receive, send and process information, including but not limited to devices with sensor or user input functions.

[0050] A "server" is a computing device that responds to external requests and provides data processing, storage, analysis, and control functions.

[0051] "Data receiving device" refers to a hardware or software component used to receive collected data from an information terminal.

[0052] Generative artificial intelligence refers to artificial intelligence technology that can automatically generate relevant information or model content based on input data.

[0053] "Analysis device" refers to a system component that uses artificial intelligence methods to process received data, such as pattern recognition, feature extraction, and pattern analysis.

[0054] "Encoding rule information" refers to the symbol correspondence, dictionary, or pattern information used for data compression and decompression, which specifies the data encoding and decompression methods.

[0055] "Distribution device" refers to a hardware or software device used to send the generated encoding rule information to the information terminal and ensure that the information terminal can use the information.

[0056] "Communication security device" refers to a component that implements security functions such as encryption and authentication to protect the integrity and confidentiality of data during data transmission.

[0057] "Visualization device" refers to a system or tool that presents collected or analyzed data to users in a visual format such as charts and reports.

[0058] "General information processing resources" refers to hardware and / or software resources that can simultaneously support multiple information processing tasks such as compression, decompression, and data processing.

[0059] "Control device" refers to a system component that receives operation instructions input by the user or system and coordinates, manages and controls various data processing flows.

[0060] "Prompt statements" refer to textual instructions that are used as input parameters for generative artificial intelligence models to trigger, limit, or guide the behavior of the model.

[0061] To facilitate understanding of the present invention, the following detailed description of the embodiments of the invention is provided in conjunction with specific examples.

[0062] This system includes a server, information terminals, and user interfaces. The server utilizes a high-performance general-purpose processor and ample storage resources, runs a general-purpose operating system, and can deploy functional units such as a data receiving module, a generative artificial intelligence analysis module, a dictionary information distribution module, a secure encrypted communication module, and a data visualization module. The server's software environment may include Python, a database management system (such as MySQL), an artificial intelligence development framework (such as TensorFlow), a compression library (such as zlib), and data visualization tools (such as ECharts or Grafana).

[0063] Information terminals are typically intelligent hardware devices that integrate sensors, communication modules (such as Wi-Fi, 4G / 5G), and local cache. They run embedded operating systems and have the ability to collect data, compress data, communicate, and receive server commands. Users can interact with the server through the terminal or a browser-based graphical interface.

[0064] In practice, the information terminal periodically collects sensor data such as temperature, humidity, and location information, and sends the raw data to the server via a communication module. After receiving the data, the server registers it in its database and uses a generative artificial intelligence analysis module to perform pattern mining on historical and current data. For example, if a custom generative model developed using TensorFlow is used, the server generates optimal compression encoding rules (dictionary information) based on the received data and then serializes this dictionary.

[0065] The server distributes the updated dictionary information to the terminals via secure communication protocols (such as SSL / TLS). Upon receiving the latest dictionary information, the terminals use it for local compression of subsequent data (based on compression libraries such as zlib). The compressed package is then sent back to the server via encryption methods such as HTTPS, achieving efficient and secure data transmission.

[0066] After receiving the compressed data, the server decompresses it to restore the original data and performs further analysis. The analysis results are graphically displayed through a visualization module, allowing users to monitor changes in the collected data and the operational status in real time. Users can log in to the corresponding web interface or mobile application to select data display methods, set alarm parameters, or control device behavior, achieving intelligent management and operation of various types of data.

[0067] For example, in smart home applications, users have temperature sensors installed in their homes. Information terminals collect room temperature data periodically and send it to a server. The server analyzes the accumulated temperature data, generates a compressed dictionary that matches the actual data distribution, and then distributes it to the terminals. The next time data is collected, the terminal compresses the temperature data using the new dictionary and sends it via an encrypted network. After the server collects and restores the data, the analysis results are displayed in charts, allowing users to intuitively understand changes in their home's temperature. In case of abnormal fluctuations, alarms can be triggered and appropriate controls can be implemented.

[0068] In this system, to generate compressed dictionaries and perform data analysis, the server supports flexible prompt statements as instructions for the generative artificial intelligence model. Example prompt statements include: "Please analyze the room temperature data collected in the last 24 hours and generate the dictionary information most suitable for achieving efficient compression." "Please perform cluster analysis on all received sensor data to generate new compression coding rules." "Please adjust and output the optimal data compression dictionary based on the current business scenario." Through the above structure and operation, the present invention can significantly optimize the data communication of low-performance information terminals, achieve efficient and secure data processing and real-time visualization, and meet the complex and ever-changing actual needs of users.

[0069] use Figure 11 The processing procedure is explained.

[0070] Step 1: The terminal collects data. It acquires raw data, such as indoor temperature, from the environment or user operations using integrated temperature and humidity sensors. The input is actual sensor data, and the output is a structured raw data file or data package. The terminal temporarily stores the collected data locally.

[0071] Step 2: The terminal sends the collected data to the server. The terminal assembles the temporarily stored raw data into a JSON data packet and sends it to the server via HTTP POST over a 4G / 5G or Wi-Fi network. The input is the raw data locally on the terminal, and the output is the data packet transmitted to the server. The terminal invokes the network module and communication protocol library to initiate the data transmission process.

[0072] Step 3: The server receives and stores data. It obtains data packets sent by the terminal through a web service interface, parses them, and writes them to the database management system. The input is received JSON data, and the output is structured data records written to the database. The server utilizes database insert operations and data validation.

[0073] Step 4: The server analyzes the stored data. It calls a data analysis program based on a generative artificial intelligence model to perform pattern mining and analysis on historical and newly arrived data in the database. The input is a set of raw data from the database, and the output is compressed dictionary information. The server loads the generative artificial intelligence model (such as a model trained using TensorFlow), performs inference computation tasks, and records the analysis results.

[0074] Step 5: The server generates encoding rules (compression dictionary) based on the analysis results. Based on the AI ​​model's output, the server organizes and constructs a compression encoding dictionary suitable for this batch of data. The input is the data pattern generated by the analysis, and the output is compressed dictionary information in JSON format. The server encodes the compression rules and prepares to push them to the terminal.

[0075] Step 6: The server distributes encoding rule information (compressed dictionary) to the terminal. The server pushes the latest generated compressed dictionary to the terminal via an encrypted communication protocol (such as HTTPS). The input is the generated compressed dictionary information, and the output is a JSON packet sent to the terminal. The server initiates the transmission by calling the interface and the security encryption module.

[0076] Step 7: The terminal receives and saves the new compressed dictionary. The terminal retrieves the latest compressed dictionary from the server and stores it locally for later compression. The input is the JSON dictionary data sent by the server, and the output is the local compressed dictionary file. The terminal checks and confirms that the dictionary file has been successfully updated.

[0077] Step 8: The terminal uses a compression dictionary to compress data. After collecting new data, the terminal calls compression libraries such as zlib and uses the current compression dictionary to encode and compress the new batch of raw data. The input is the latest collected raw data and the compression dictionary, and the output is the compressed data file. The terminal executes the compression algorithm and generates a smaller compressed package.

[0078] Step 9: The terminal sends the compressed data to the server via an encrypted channel. The terminal uses encryption protocols such as SSL / TLS to establish a secure connection with the server and transmits the compressed data as secure data. The input is the compressed data packet, and the output is the encrypted data stream arriving at the server. The terminal performs encrypted transmission to ensure that the data is not stolen or tampered with.

[0079] Step 10: The server receives and decompresses data. It retrieves compressed data from the terminal via a secure channel, restores the packet content using a decryption protocol, and then decompresses it using libraries such as zlib to recover the original format. The input is the received encrypted compressed packet, and the output is the restored raw sensor data. The server automatically completes the decryption and decompression processes.

[0080] Step 11: The server combines AI analysis results to visualize the data. The server inputs the reconstructed data into the visualization module, and uses tools such as ECharts and Grafana to present the analysis results to the user in the form of charts and graphs. The input consists of parsed data and AI model analysis conclusions; the output is visual graphs and reports. The server also pushes links to visualization pages or updates the web front-end interface.

[0081] Step 12: Users can view and manipulate data in real time through a browser or application. Users can log in to the server interface using mobile devices or computers to access the data visualization page and monitor, query, manipulate, and manage the collected and analyzed results. Input consists of user browsing behavior and operation commands; output includes the data displayed on the interface and possible business control commands. Users can set alarms, adjust parameters, or issue further data collection and analysis requests based on the results.

[0082] Application Example 1 The process flow corresponding to the specific processing in Use Case 1 will be described below. The various parts of the system described below are implemented by the data processing device 12 and the intelligent device 14. Furthermore, the data processing device 12 is referred to as the "server" and the intelligent device 14 is referred to as the "terminal".

[0083] In industrial settings and IoT environments, a large volume of diverse sensor data needs to be transmitted efficiently and securely to a central processing unit. Existing technologies often face problems such as insufficient processing power, high bandwidth consumption, and inadequate security during data communication. Furthermore, they struggle to dynamically adapt to different data characteristics and user states, and cannot flexibly adjust compression and security strategies based on data content and user emotional states. This results in reduced data communication efficiency, delayed responses, and a poor user experience.

[0084] The specific processing performed by the specific processing unit 290 of the data processing apparatus 12 in Application Example 1 is achieved by the following means.

[0085] In this invention, the server includes means for receiving information from multiple information processing devices, means for parsing information using a generative information processing algorithm and generating encoded information for information compression, means for distributing the encoded information to information processing devices for subsequent communication, means for protecting information communication through encryption, means for inferring the user's state when user attribute data is included and controlling the encoded information and information communication process accordingly, and means for automatically switching and optimizing the encoded information and encryption methods. This enables efficient and secure transmission of industrial data in diverse application scenarios, and dynamically optimizes compression and security strategies based on data characteristics and user status, improving data communication efficiency and security, and enhancing user experience.

[0086] "Information processing device" refers to computing and control equipment that has information acquisition, processing and communication functions, and is used to collect, preprocess and send data.

[0087] "Generative information processing algorithms" refer to algorithms that analyze data through machine learning or artificial intelligence techniques, automatically discover data features, and generate models or rules to drive data processing.

[0088] "Encoding information" refers to a set of compression rules, dictionaries, or related mapping information generated based on data characteristics to improve data compression efficiency.

[0089] "Information and communication" refers to the entire process of data transmission and exchange between system components such as information processing devices and information analysis devices.

[0090] "Encryption methods" refer to technical measures that use cryptographic methods to encrypt data in order to prevent unauthorized access and data leakage.

[0091] "Information parsing device" refers to a computing device or system that decodes, analyzes, and processes received data packets.

[0092] "Personal attribute data" refers to a collection of data related to the status, identity, facial expressions, voice, and other information associated with the device operator or user.

[0093] "Personal state inference algorithm" refers to an artificial intelligence algorithm or model that infers a person's emotions, behavior, stress and other states by analyzing a person's attribute data.

[0094] "Automatic encoding information switching or optimization device" refers to a system component that can dynamically adjust, select or optimize compression rules and encryption methods based on data or system status.

[0095] The embodiments of the present invention are as follows: This system comprises multiple terminals and one server. The terminals can be industrial data acquisition terminals, embedded devices, industrial tablets, smart sensor gateways, etc., while the server can be deployed on a cloud platform or a local data center. The terminals are equipped with sensing devices such as temperature sensors, humidity sensors, cameras, and microphones, and run software for data acquisition and processing. The server deploys functional modules for data reception, parsing, generative artificial intelligence models (such as the Transformers framework and GPT model), dictionary generation, encryption / decryption, and sentiment analysis. Commonly used software includes the Python language, the requests library, the zlib module, and the cryptography.fernet module.

[0096] Users can operate the terminal to trigger the collection of raw environmental data, including temperature, humidity, images, audio, and user interaction information. The terminal performs preliminary processing and formatting of the collected data before sending it to the server via HTTP / HTTPS protocol. The terminal uses the requests library to complete data upload, and the data format is generally JSON for structure. To improve data security, the terminal uses the cryptography.fernet module or SSL / TLS to encrypt data transmission. To reduce communication bandwidth, the terminal can use the zlib module for efficient data compression based on the compression rules (i.e., "dictionary information") issued by the server.

[0097] The server is responsible for receiving data sent by the terminals. It first verifies the data's integrity and validity, then uses a generative artificial intelligence model to analyze the raw data. The server automatically searches for feature patterns in the data, dynamically generates an optimal compression dictionary, and distributes this dictionary to each terminal via HTTP, MQTT, or other methods. The server also integrates sentiment analysis modules (such as OpenCV for image expression analysis and SpeechEmotionRecognition for audio emotion recognition). When it receives information containing user attribute data, it infers the user's state and adjusts data compression and communication strategies accordingly.

[0098] In practical industrial applications, users can periodically or regularly collect environmental parameters, equipment images, and operator voice and facial expression data via terminals. The server dynamically adjusts its dictionary compression strategy and encryption method based on the received data, further improving communication efficiency and adapting to unstable network environments. Simultaneously, the server uses sentiment inference results to adjust the priority of subsequent data communication content, enhancing the human-computer interaction experience.

[0099] Specific use case: In a smart manufacturing workshop, users operate on a terminal to collect real-time temperature, humidity, and their own facial expressions and voice. When a production line malfunctions, the terminal automatically uploads both environmental and user emotional data. After analyzing this information, the server automatically increases the communication priority of safety-related data and applies higher compression rates and encryption levels to subsequent anomaly monitoring information.

[0100] Examples of prompts for generative artificial intelligence models include: "Please tell me how to efficiently compress and securely send temperature and humidity data from the factory to the server." "I've collected a large amount of sensor data and want to send it to the server efficiently, while ensuring data transmission security and compression efficiency. What suggestions do you have?" "I want the system to adjust the data sending priority based on the operator's emotional state. Please provide a implementation process." Through the above-described structure and process, the present invention can achieve efficient, intelligent, and secure data communication and dynamic processing in complex and ever-changing industrial and IoT environments.

[0101] use Figure 12 The processing procedure is explained.

[0102] Step 1: Users initiate data acquisition tasks via a terminal. The terminal connects to sensors such as temperature, humidity, camera, and microphone to collect environmental data, images, and audio. The input is the raw signals collected by the environmental sensors, camera, and microphone. The terminal performs preliminary data processing, such as numerical correction, image compression, and audio noise reduction, and outputs processed multimedia data.

[0103] Step 2: The terminal formats the collected and processed data, typically encoding it into a JSON structure. The input consists of pre-processed multi-source sensor data such as temperature, humidity, images, and audio. The output is a JSON data packet with a unified structure.

[0104] Step 3: The terminal uses the requests library to create HTTP or HTTPS transport requests, sending formatted JSON data packets to the server. The input is a JSON-formatted data packet. The output is either a confirmation message for the uploaded data or a response from the server.

[0105] Step 4: The server receives data packets uploaded by the terminal and verifies the format integrity and security of the data packets. The input is a JSON data packet. The server checks the content consistency and data source validity, and saves the valid data to the database. The output is the verification result and storage confirmation information.

[0106] Step 5: The server uses generative artificial intelligence models (such as transformers, GPT, etc.) to analyze stored data and extract data features and patterns. The input is raw or preprocessed data from the database. Based on the model analysis results, the server finds high-frequency, recurring values ​​or fragments, performs pattern summarization, and generates a compressed dictionary tailored to the characteristics of the current data. The output is a compressed dictionary file or a data structure.

[0107] Step 6: The server sends the generated compressed dictionary to the terminal via HTTP or MQTT. The input consists of the newly generated compressed dictionary and information about the target terminal. The server sends the dictionary as a data packet. The output is an acknowledgment message from the terminal confirming receipt of the compressed dictionary.

[0108] Step 7: The terminal receives the compression dictionary from the server, stores it in the local file system or memory, and updates the compression parameter settings. The input is the compression dictionary data pushed by the server. The terminal completes the local storage and configuration of the dictionary. The output is the parameter update status of the terminal's local compression system.

[0109] Step 8: In the next data collection cycle, the user or terminal collects new environmental data. The terminal uses the received compression dictionary and a zlib module or similar algorithm to efficiently compress the collected data. The input consists of the raw data from the new round of collection and the locally stored compression dictionary. The output is a small, effectively compressed data packet.

[0110] Step 9: The terminal uses the cryptography.fernet module to encrypt the compressed data packets and securely manages the encryption key. The inputs are the compressed data packets and the encryption key. The output is the encrypted data packets.

[0111] Step 10: The terminal uses the requests library to send encrypted data packets to a specified interface on the server via HTTPS. The input is the encrypted data packet. The output is the server's upload confirmation response.

[0112] Step 11: The server receives encrypted data packets, decrypts them using a synchronized key, and decompresses the data using a generated compression dictionary. The input consists of the encrypted compressed data packet, a valid key, and a compression dictionary. The server restores the original data and performs an integrity check. The output is the restored original data, along with the decompression and verification results.

[0113] Step 12: The server performs business analysis on the restored data. If the data contains user attribute information, it further calls the sentiment analysis module. The input is the restored multimedia data (including images, audio, etc.). The server infers the user's emotional state by analyzing the user's facial expressions and voice. The output is the user's sentiment type, state, or related indicators.

[0114] Step 13: Based on sentiment analysis and data analysis results, the server dynamically adjusts subsequent compression strategies, data communication priorities, or pushed content, and pushes the updated encoding information or business instructions to the terminal via HTTP, MQTT, etc. Inputs are the analysis results and strategy adjustment requirements. Outputs are confirmation messages for the latest strategy or instruction issuance.

[0115] Alternatively, an emotion engine for inferring user emotions can be combined. That is, the specific processing unit 290 can also use the emotion-specific model 59 to infer user emotions and perform specific processing using user emotions.

[0116] Example 2 The flow of a specific process in Example 2 will be described. Each part of the system described below is implemented by the data processing device 12 and the smart device 14. The data processing device 12 will be referred to as the "server," and the smart device 14 as the "terminal."

[0117] Existing information and communication systems face several challenges in achieving efficient data compression, secure communication, and information prioritization based on user emotions. For example, how to dynamically adjust information content to improve user experience while ensuring the secure and high-speed transmission of large amounts of data, especially in recognizing user emotions based on multimodal data (such as voice and images) and optimizing communication services and resource allocation accordingly, is a challenge that current technologies cannot simultaneously address the needs of data processing efficiency and personalized intelligent services. Therefore, designing a comprehensive system capable of securely and efficiently collecting, transmitting, and analyzing information, and performing targeted data compression and service adaptation based on user emotional states, has become an urgent technical issue to be addressed.

[0118] The specific processing performed by the specific processing unit 290 of the data processing apparatus 12 in Embodiment 2 is achieved by the following means.

[0119] In this invention, the server includes a device for receiving information collected from an information acquisition device; a device for analyzing the received information using a generative artificial intelligence model and generating reference data for information compression; a device for sending the generated reference data to the information acquisition device and setting it for use in the next information communication; a device for ensuring the security of information communication using encryption technology; a device for determining emotional states through an emotion analysis device based on perceived data and input data from the information acquisition device; a device for setting the priority of communication information based on the determined emotional information; and an instruction management device for controlling actions by inputting predetermined instruction statements to the generative artificial intelligence model. This allows for intelligent analysis and compression based on artificial intelligence while ensuring information security, effectively improving data communication efficiency, and flexibly adjusting the content and priority of information transmission according to the user's current emotional state, thereby greatly enhancing the user experience and the system's intelligence level.

[0120] "Information acquisition device" refers to a device used to collect raw data (such as sensor data, images, audio, text input, etc.) from the environment, users or other resources, including but not limited to smart terminals, wearable devices, embedded systems, etc.

[0121] "Generative AI models" refer to a set of AI algorithms that can automatically generate analysis results, predictions, or optimization solutions based on input data, including but not limited to deep learning models and natural language generation models.

[0122] "Reference data" refers to a set of data or templates generated by generative artificial intelligence models after analyzing information to optimize information compression and encoding efficiency, which can be used for efficient processing of subsequent data transmission.

[0123] "Encryption technology" refers to information security and encryption methods used in the process of information transmission to protect data from being illegally obtained or tampered with, including but not limited to symmetric encryption, asymmetric encryption, and other methods.

[0124] "Sentiment analysis device" refers to a software and hardware system used to identify and judge the emotional state expressed by users or data objects. It is usually based on the analysis of voice, image or text information and outputs corresponding emotional results.

[0125] "Priority" refers to assigning different importance orders to multiple pieces of information or tasks to be processed based on certain evaluation criteria, in order to determine the order in which they are processed or sent.

[0126] "Instruction management device" refers to a functional module used to input predetermined instruction statements into generative artificial intelligence models and realize action control or model behavior scheduling.

[0127] The specific forms of the invention are as follows.

[0128] The information processing system involved in this invention includes collaboration among a server, a terminal, and a user to achieve efficient, secure, and user-responsive intelligent data communication services.

[0129] The terminal can be implemented using various hardware devices, such as smartphones, tablets, embedded devices, and IoT home appliances, and includes built-in temperature sensors, cameras, microphones, and motion detection sensors. The terminal collects environmental data, user facial expressions and voice input, and related information through these sensors. It comes pre-installed with data formatting software and an encryption module (which can use Android Keystore, the Linux OpenSSL algorithm library, or an embedded chip supporting AES encryption) to format, organize, and encrypt the collected data, storing the encrypted data in a local temporary storage area.

[0130] The terminal securely sends encrypted data to a data server located on a cloud platform via a network (such as Wi-Fi or 4G / 5G cellular communication) using the HTTPS protocol. The server typically employs a high-performance x86 server, a Linux operating system server, a scalable GPU-accelerated server, or a cloud virtual host, and is equipped with generative artificial intelligence models (such as BERT, GPT, or self-developed models based on deep learning frameworks like PyTorch and TensorFlow). The server first uses decryption tools (such as OpenSSL) to restore the received encrypted data, and then calls the generative artificial intelligence model to extract features, analyze content, and generate compression templates (i.e., reference data) from image, audio, and text data. Simultaneously, the server integrates sentiment analysis devices (such as a facial expression recognition module based on OpenFace, or a voice emotion recognition API based on Azure) to analyze user emotions, such as satisfaction, dissatisfaction, and stress.

[0131] The server dynamically sets communication content and priorities based on analysis results. For example, when user dissatisfaction is detected, it automatically increases the push level of information highly relevant to the user's needs. Furthermore, the server can perform fine-grained dynamic control over data analysis and actions through specific prompts (i.e., prompts input into the generative artificial intelligence model). The generated compressed reference data is sent back to the terminal by the server, which uses it for efficient compression and transmission of future data.

[0132] Users can indirectly participate in the system's intelligent decision-making process through everyday behaviors (such as opening the refrigerator, issuing voice commands, and making facial expressions) without having to actively operate the system, thus enjoying a smarter, more personalized, and more efficient service experience.

[0133] Hardware examples include: Terminals: Raspberry Pi, smartphones, embedded control boards; Servers: General-purpose x86 servers, cloud virtual hosts, computing resources with GPUs; Sensors: CMOS camera, MEMS microphone, NTC temperature sensor, etc.

[0134] Software and model examples include: Server operating systems: Linux, Windows Server; Encryption libraries: OpenSSL, Android Keystore; Artificial intelligence frameworks: PyTorch, TensorFlow; Sentiment analysis software: OpenFace, commercial voice emotion API.

[0135] Examples of specific applications: In a smart refrigerator scenario, when a user opens the refrigerator, the terminal automatically records the user's facial expressions and voice. If the user expresses dissatisfaction due to a lack of ingredients, the terminal collects the data and sends it to the server. After analysis, the server identifies the user's dissatisfaction and automatically pushes ingredient purchasing suggestions to the terminal for priority display, or pushes relevant recipes to improve user satisfaction.

[0136] Example of a prompt statement: "If a user is unhappy that the milk in the refrigerator has run out, how should the system respond in real time and optimize the push notifications?" "Based on users' dissatisfaction expressions and comments, please generate a data compression reference scheme suitable for smart home appliances and create a push priority list." "If users exhibit stress in front of their devices, how should the communication system adjust its data service strategy?" use Figure 13 The processing procedure is explained.

[0137] Step 1: The terminal uses hardware such as temperature sensors, cameras, and microphones to collect user and environmental data. Input includes raw information such as user facial expressions, voice, and temperature. The terminal formats the data (e.g., compressing images to JPEG, transcoding voice to WAV or MP3, and organizing temperature data into CSV format) and integrates various data types into a unified data packet. Output is a structured data packet.

[0138] Step 2: The terminal encrypts structured data packets. The input is a formatted data packet. The terminal invokes a local encryption module (such as an embedded encryption chip using the AES algorithm or the OpenSSL library) to perform encryption operations on the data packet, preventing unauthorized access. The output is the encrypted data packet.

[0139] Step 3: The terminal uploads encrypted data packets to the server via HTTPS. The input consists of the encrypted data packets and the secure connection information established with the server. After network transmission, the data is reliably delivered to the server's designated interface via a secure channel. The output is the data received on the server.

[0140] Step 4: The server receives and decrypts data packets uploaded by the terminal. The input consists of an encryption packet and the relevant key. The server uses decryption software (such as OpenSSL) to decrypt the data packets, restoring them to their original structured information, such as images, audio, and sensor data. The output is the decrypted original multimedia and numerical data.

[0141] Step 5: The server uses a generative artificial intelligence model to analyze the decrypted information. The input consists of raw multimedia and numerical data. The server uses deep learning models (such as BERT or GPT and facial recognition algorithms) to transcribe the speech content into text, extract features from facial expressions, and analyze temperature and other sensor data. The output includes feature descriptions, emotional state recognition results, and data classification results.

[0142] Step 6: The server invokes a sentiment analysis device to identify the user's emotional state based on image and voice features. The input consists of an emoji image and spoken text. Through sentiment recognition algorithms (such as OpenFace facial recognition and a voice emotion API), it determines whether the user exhibits emotions such as "anger," "dissatisfaction," or "stress." The output is a label representing the user's current sentiment state.

[0143] Step 7: The server prioritizes communication content based on user sentiment information and data analysis results. Inputs include sentiment status tags and data classification information. The server uses a priority sorting algorithm to adjust the order of push notifications, allocating highly relevant and important data first. For example, information about users' urgent needs is prioritized at the top of the push list. Output is a weighted list of push notifications.

[0144] Step 8: The server uses a generative artificial intelligence model to generate reference data needed for data compression. The input consists of the analyzed raw dataset and sentiment recognition results. The server generates encoding templates, dictionaries, or data difference reference data to improve subsequent data compression efficiency. The output is new reference data (such as code tables, templates, etc.).

[0145] Step 9: The server sends the generated reference data to the terminal via HTTPS. The input consists of the reference data and terminal information. The terminal uses the new reference data for efficient encoding and transmission during subsequent data acquisition, processing, and compression. The output is the latest reference data stored locally on the terminal.

[0146] Step 10: When users use the terminal daily, the system automatically senses and collects their behavioral data and emotional responses, requiring no additional user interaction. Input consists of natural user behavior and feedback. Through this end-to-end process, users receive faster, more personalized data services and experience intelligently optimized information interaction. Output includes data feedback and service push notifications that are instantly adapted to user needs.

[0147] Application Example 2 The process flow corresponding to the specific processing in Use Case 2 will be described below. The various parts of the system described below are implemented by the data processing device 12 and the intelligent device 14. In addition, the data processing device 12 is referred to as the "server" and the intelligent device 14 is referred to as the "terminal".

[0148] In existing technologies, physical venues cannot accurately obtain users' emotional states in real time and flexibly adjust services based on emotional dynamics, making it difficult to improve customer satisfaction. At the same time, the large-scale transmission of emotional data poses challenges to communication efficiency and data security. How to achieve efficient identification, data compression, and secure communication of user emotions has become an urgent technical problem to be solved.

[0149] The specific processing performed by the specific processing unit 290 of the data processing apparatus 12 in Application Example 2 is achieved by the following means.

[0150] In this invention, the server includes a device for acquiring status information from a terminal device, a device for analyzing the status information and identifying the user's psychological state using a built-in generative artificial intelligence algorithm, and for generating compressed data encoding information, a device for sending the generated encoded information to the terminal device for subsequent data transmission, a device for automatically setting information priorities based on the analysis results, and a device for ensuring information encryption during communication. This enables real-time identification of the user's emotional state and dynamic service adjustment, improves information transmission efficiency, and enhances data security, thereby effectively improving the end-user experience and the overall system performance.

[0151] "Terminal device" refers to hardware devices used to collect user facial expressions, voice and other status information and send them to information processing devices, including but not limited to wearable devices, mobile devices, fixed sensing terminals, etc.

[0152] "Information processing device" refers to a central processing unit that receives, stores, and processes status information from terminal devices, including servers, data centers, etc.

[0153] "Analysis device" refers to a data processing module used to extract features from state information and recognize emotions, usually based on generative artificial intelligence algorithms.

[0154] "Generative artificial intelligence algorithms" refer to machine learning or deep learning methods that can automatically extract features from input data and generate relevant output results.

[0155] "Status information" refers to data collected by terminal devices that reflects the user's current physiological and psychological state, including but not limited to image data, audio data, and behavioral data.

[0156] "Psychological state" refers to the emotions, attitudes, or psychological tendencies inferred from the analysis of a user's facial expressions, voice, and other characteristics, such as pleasure, confusion, or tension.

[0157] "Encoding information" refers to the encoding dictionary or compression reference data generated by the server and distributed to terminal devices in order to achieve efficient data compression and transmission.

[0158] "Information priority" refers to the order in which different data are transmitted or processed by a communication system based on factors such as sentiment analysis results.

[0159] "Encryption method" refers to security technologies and protocols used to protect data from unauthorized access during transmission, such as SSL and TLS.

[0160] The embodiments of the present invention are described below.

[0161] This system consists of three parts: a server, terminal devices, and users. Users move around in physical locations (such as physical stores), and the terminal devices are responsible for collecting users' facial expressions and voice status information in real time. The hardware of the terminal devices can be wearable devices with cameras and microphones (such as smart glasses or smart wristbands), mobile terminals (such as smartphones), or fixed terminals equipped with environmental sensors. The terminal devices integrate acquisition and encryption modules, enabling them to package and transmit the acquired user image, audio, and other status information to the server via encrypted communication protocols such as SSL / TLS.

[0162] As the central information processing unit of the system, the server can be a high-performance general-purpose computing server, preferably equipped with a GPU-accelerated processing unit to meet the computational needs of large-scale artificial intelligence models. The server operating system can be a mainstream server operating system such as Linux. Core software includes a Python environment, deep learning development libraries such as TensorFlow, facial expression recognition algorithms (e.g., CNN-based face analysis models), and speech sentiment analysis models (e.g., RNN, Transformer architecture).

[0163] After receiving encrypted data from the terminal device, the server first decrypts it using a local key to restore the original image and audio data. Then, the server inputs this data into a pre-trained generative artificial intelligence model. By comprehensively analyzing the user's facial expressions and audio tone, the model identifies the user's psychological state (such as pleasure, confusion, anxiety, etc.) and outputs metadata containing emotion category and confidence level.

[0164] Based on the analyzed sentiment metadata and the currently collected status information, the server automatically generates more efficient data encoding information (compression dictionary) using a built-in algorithm. This encoded information is then re-encrypted and sent back to the terminal device. In the next round of data transmission, the terminal device uses the new encoded information to compress data packets more efficiently, improving data transmission efficiency and reducing network bandwidth usage. The entire process ensures end-to-end encryption of user status data, preventing data leakage during transmission and storage.

[0165] The server automatically prioritizes information based on the user's psychological state. For example, when it detects that a user is exhibiting negative emotions such as confusion or anxiety, the server will mark relevant information for that type of user as high priority and push it to the staff's terminal or the back-end system, enabling service personnel to respond and intervene in a timely manner, optimize the user experience, and improve the overall service quality.

[0166] Real-world application example: In a coffee shop setting, when a user enters, their smart glasses automatically capture facial video and voice clips. The data is encrypted and uploaded to a central server. The server analyzes the data using an AI model, determining that the user's expression is "confused, with an emotional score of 70%." It then pushes a high-priority task to the staff's tablet, prompting them to proactively offer assistance to the user. Simultaneously, the server automatically updates the compressed dictionary for subsequent high-frequency data collection and synchronizes it with all front-end terminals.

[0167] Examples of prompts for generative artificial intelligence models include: "Based on the input customer facial expression image and audio file, please analyze and output the current emotion category and intensity level." "Write a program that can recognize the facial expressions and voice emotions of users captured in real-time camera footage and microphone recordings, and output the corresponding emotion category and confidence level." "Build a system based on TensorFlow to realize emotion recognition and metadata output of customers' facial expressions and voices in the store." "For in-store customer service scenarios, write AI model code to achieve facial expression and audio data analysis, emotion priority allocation, and efficient data compression." Through the aforementioned hardware and software components and workflow, real-time identification of user psychological states, priority data processing, efficient compression, and encrypted secure communication can be achieved, thereby improving the actual user experience and enhancing the overall system's data processing capabilities and response speed.

[0168] use Figure 14 The processing procedure is explained.

[0169] Step 1: The terminal uses a built-in camera and microphone to capture real-time images of the user's facial expressions and audio recordings in a real-world environment, generating status data. The input is the user's dynamic behavior in the environment, and the output is timestamped image and audio files. The terminal formats and performs preliminary archiving of the raw data in preparation for subsequent transmission.

[0170] Step 2: The terminal uses an encryption module to encrypt the acquired image and audio data using encryption algorithms such as SSL / TLS. The input is unencrypted state data, and the output is an encrypted data packet. The terminal calls its local encryption protocol stack to prepare the data packet for transmission.

[0171] Step 3: The terminal transmits encrypted status data to a designated port on the server via a wireless network. The input is an encrypted data packet, and the output is the data packet received by the server. The terminal monitors the network status and automatically retransmits data in case of disconnection, ensuring reliable data upload.

[0172] Step 4: After receiving the encrypted data packet from the terminal, the server first decrypts it using the corresponding key to recover the original image and audio data. The input is an encrypted data packet, and the output is the original image and audio files. The server then performs a data integrity check to ensure the data has not been tampered with.

[0173] Step 5: The server inputs the decrypted image and audio data into a deployed generative artificial intelligence model. Based on the model's facial expression recognition and speech analysis algorithms, it extracts features and predicts emotions from the user's state data. The input consists of image and audio data; the server uses deep learning software such as TensorFlow to process this data, outputting the user's emotion label (e.g., happy, confused) and confidence level. The server records the emotion recognition results in a metadata database.

[0174] Step 6: The server automatically prioritizes communication-related information based on emotion tags and current environmental information. Inputs include sentiment analysis metadata and contextual information; outputs are a queue of data tasks with priority attributes. For example, the server might mark user data indicating confusion or anxiety as high priority and immediately push notifications to store staff terminals via an internal messaging mechanism.

[0175] Step 7: Based on historical uploaded status data, the server uses a generative artificial intelligence model to generate a new encoding dictionary for compression optimization. The input is a large amount of historical status data; the server analyzes the data distribution and characteristics, and the output is encoded information (the compressed dictionary). The server then encrypts this encoded information and synchronously distributes it to all terminals.

[0176] Step 8: After receiving new encoded information, the terminal integrates it into its local data compression module. During the next data collection and upload, the new status data will be compressed more efficiently. The input consists of a new encoding dictionary and newly collected status data. The terminal performs data compression based on encoding logic, outputting highly compressed data packets to prepare for subsequent communication.

[0177] Step 9: The customer service experience in the store has been optimized. When customers express confusion or other negative emotions, on-site staff can respond immediately and provide personalized service due to server priority allocation and automatic reminders. The input is the customer's real-time needs and emotional state, and the output is more timely and considerate service feedback and actions.

[0178] The specific processing unit 290 sends 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 sound representing user input regarding the result of the specific processing. The control unit 46A sends the sound data representing 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 sound data.

[0179] Data generation model 58 is a so-called generative AI (Artificial Intelligence). Examples of data generation models 58 include ChatGPT (registered trademark) (accessible via the internet (URL: https: / / openai.com / blog / chatgpt)). Data generation model 58 is obtained through deep learning on a neural network. Input to data generation model 58 are prompt words containing instructions, and inference data such as sound data representing sound, text data representing text, and image data representing images (e.g., still image data or animation data). Data generation model 58 infers from the input inference data based on the instructions represented by the prompt words and outputs the inference result in one or more data forms, such as sound data, text data, and image data. Data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or induction. The specific processing unit 290 performs the aforementioned specific processing while using data generation model 58. The data generation model 58 can also be a model finely tuned to output inference results from prompts that do not contain instructions. In this case, the data generation model 58 can output inference results based on prompts that do not contain instructions. The data processing apparatus 12, etc., includes various data generation models 58, including AI other than the generation AI. AI other than the generation AI can be, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or Naive Bayes, and can perform various processes, but is not limited to this example. Furthermore, the AI ​​can also be an AI agent. Furthermore, when the processing of the above-mentioned parts is performed by AI, the processing can be performed partially or entirely by AI, but is not limited to this example. Furthermore, the processing performed by the AI ​​including the generation AI can be replaced by processing in the rule base, and the processing in the rule base can also be replaced by processing performed by the AI ​​including the generation AI.

[0180] Furthermore, the processing of the aforementioned data processing system 10 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it can also be performed by both the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Additionally, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or external devices, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or external devices.

[0181] For example, the collection unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit uses the camera 42 or communication I / F 44 of the smart device 14 to acquire step data, which is then processed by the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12, which analyzes the data from the collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12, which uses a generation AI to generate a menu. For example, the serving unit is implemented by the output device 40 of the smart device 14 or the specific processing unit 290 of the data processing device 12, which provides the generated menu to the user. The correspondence between each unit and the device or control unit is not limited to the above examples and various changes can be made.

[0182] In the above embodiments, examples of specific processing by the data processing device 12 are given, but the technology disclosed herein is not limited to this, and specific processing may also be performed by the smart device 14.

[0183] Second Implementation Method Figure 3 An example of the configuration of the data processing system 210 according to the second embodiment is shown.

[0184] like Figure 3 As shown, the data processing system 210 includes a data processing device 12 and smart glasses 214. A server can be cited as an example of the data processing device 12.

[0185] The data processing apparatus 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" as understood in this disclosure. The computer 22 includes a processor 28, RAM 30, and memory 32. The processor 28, RAM 30, and memory 32 are connected to a bus 34. Furthermore, the database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0186] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, RAM 48, and memory 50. The processor 46, RAM 48, and memory 50 are connected to a bus 52. Furthermore, the microphone 238, speaker 240, camera 42, and communication I / F 44 are also connected to the bus 52.

[0187] Microphone 238 receives instructions from user 20 by receiving sounds emitted by user 20. Microphone 238 captures sounds emitted by user 20 and converts the captured sounds into sound data, which is then output to processor 46. Speaker 240 outputs sound according to instructions from processor 46.

[0188] Camera 42 is a small digital camera equipped with an optical system such as a lens, aperture and shutter, and imaging elements such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the user 20's surroundings (e.g., the field of view defined by an angle equivalent to the field of vision of an average healthy person).

[0189] Communication I / F44 is connected to network 54. Communication I / F44 and 26 are responsible for the transmission and reception of various information between processor 46 and processor 28 via network 54. The transmission and reception of various information between processor 46 and processor 28 using communication I / F44 and 26 is performed in a secure state.

[0190] Figure 4 This illustrates an example of the main functions of the data processing device 12 and the smart glasses 214. For example... Figure 4 As shown, in the data processing device 12, specific processing is performed by the processor 28. The specific processing program 56 is stored in the memory 32.

[0191] The specific processing program 56 is an example of a "program" involved in the technology of this disclosure. The processor 28 reads the specific processing program 56 from the memory 32 and executes the read specific processing program 56 on the RAM 30. Specific processing is implemented by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0192] The memory 32 stores a data generation model 58 and an emotion-specific model 59. The data generation model 58 and the emotion-specific model 59 are used by the specific processing unit 290. The specific processing unit 290 can use the emotion-specific model 59 to infer the user's emotions and perform specific processing based on the user's emotions. In the emotion inference function (emotion-specific function) using the emotion-specific model 59, various inferences and predictions related to the user's emotions are performed, including inferences and predictions of the user's emotions, but this is not limited to this example. Furthermore, emotion inference and prediction may also include, for example, emotion analysis (parsing).

[0193] In the smart glasses 214, the processor 46 performs reception and output processing. The memory 50 stores the reception and output program 60. The processor 46 reads the reception and output program 60 from the memory 50 and executes the read reception and output program 60 on the RAM 48. The reception and output processing is implemented by the processor 46 operating as a control unit 46A according to the reception and output program 60 executed on the RAM 48. Furthermore, the smart glasses 214 has the same data generation model and emotion-specific model as the data generation model 58 and the emotion-specific model 59, and these models can also be used to perform the same processing as the specific processing unit 290.

[0194] Next, the specific processing of the specific processing unit 290 of the data processing device 12 will be described. Each part of the system described below is implemented by the data processing device 12 and the smart glasses 214. 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".

[0195] Example 1 The process is the same as that of the specific process described in Embodiment 1 in the first embodiment above, so the description is omitted.

[0196] Application Example 1 The process is the same as that in the specific processing described in Application Example 1 of the first embodiment above, so the description is omitted.

[0197] Example 2 The process is the same as that of the specific process in Embodiment 2 described in the first embodiment above, so the description is omitted.

[0198] Application Example 2 The process is the same as that in the specific processing described in Application Example 2 of the first embodiment above, so the description is omitted.

[0199] The specific processing unit 290 sends the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A outputs the result of the specific processing to the speaker 240. The microphone 238 acquires sound input representing the user's input regarding the result of the specific processing. The control unit 46A sends the sound data representing the user's input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the sound data.

[0200] Data generation model 58 is a so-called generative AI (Artificial Intelligence). Examples of data generation models 58 include ChatGPT (registered trademark) (accessible via the internet (URL: https: / / openai.com / blog / chatgpt)). Data generation model 58 is obtained through deep learning on a neural network. Input to data generation model 58 are prompt words containing instructions, and inference data such as sound data representing sound, text data representing text, and image data representing images (e.g., still image data or animation data). Data generation model 58 infers from the input inference data based on the instructions represented by the prompt words and outputs the inference result in one or more data forms, such as sound data, text data, and image data. Data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or induction. The specific processing unit 290 performs the aforementioned specific processing while using data generation model 58. The data generation model 58 can also be a model finely tuned to output inference results from prompts that do not contain instructions. In this case, the data generation model 58 can output inference results based on prompts that do not contain instructions. The data processing apparatus 12, etc., includes various data generation models 58, including AI other than the generation AI. AI other than the generation AI can be, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or Naive Bayes, and can perform various processes, but is not limited to this example. Furthermore, the AI ​​can also be an AI agent. Furthermore, when the processing of the above-mentioned parts is performed by AI, the processing can be performed partially or entirely by AI, but is not limited to this example. Furthermore, the processing performed by the AI ​​including the generation AI can be replaced by processing in the rule base, and the processing in the rule base can also be replaced by processing performed by the AI ​​including the generation AI.

[0201] Furthermore, the processing of the aforementioned data processing system 10 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it can also be performed by both the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Additionally, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or external devices, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or external devices.

[0202] For example, the collection unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit uses the camera 42 or communication I / F 44 of the smart glasses 214 to acquire step data, which is then processed by the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12, which analyzes the data from the collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12, which uses a generation AI to generate a menu. For example, the serving unit is implemented by the speaker 240 of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, which provides the generated menu to the user. The correspondence between each unit and the device or control unit is not limited to the above examples and various changes can be made.

[0203] In the above embodiments, examples of specific processing by the data processing device 12 are given, but the technology disclosed herein is not limited to this, and specific processing may also be performed by the smart glasses 214.

[0204] Third Implementation Method Figure 5 An example of the configuration of the data processing system 310 according to the third embodiment is shown.

[0205] like Figure 5 As shown, the data processing system 310 includes a data processing device 12 and a head-mounted terminal 314. A server can be cited as an example of the data processing device 12.

[0206] The data processing apparatus 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" as understood in this disclosure. The computer 22 includes a processor 28, RAM 30, and memory 32. The processor 28, RAM 30, and memory 32 are connected to a bus 34. Furthermore, the database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0207] The head-mounted terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and memory 50. The processor 46, RAM 48, and memory 50 are connected to a bus 52. Furthermore, the microphone 238, speaker 240, camera 42, display 343, and communication I / F 44 are also connected to the bus 52.

[0208] Microphone 238 receives instructions from user 20 by receiving sounds emitted by user 20. Microphone 238 captures sounds emitted by user 20 and converts the captured sounds into sound data, which is then output to processor 46. Speaker 240 outputs sound according to instructions from processor 46.

[0209] Camera 42 is a small digital camera equipped with an optical system such as a lens, aperture and shutter, and imaging elements such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the user 20's surroundings (e.g., the field of view defined by an angle equivalent to the field of vision of an average healthy person).

[0210] Communication I / F44 is connected to network 54. Communication I / F44 and 26 are responsible for the transmission and reception of various information between processor 46 and processor 28 via network 54. The transmission and reception of various information between processor 46 and processor 28 using communication I / F44 and 26 is performed in a secure state.

[0211] Figure 6 This illustrates an example of the main functions of the data processing device 12 and the head-mounted terminal 314. For example... Figure 6 As shown, in the data processing device 12, specific processing is performed by the processor 28. The specific processing program 56 is stored in the memory 32.

[0212] The specific processing program 56 is an example of a "program" involved in the technology of this disclosure. The processor 28 reads the specific processing program 56 from the memory 32 and executes the read specific processing program 56 on the RAM 30. Specific processing is implemented by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0213] The memory 32 stores the data generation model 58 and the emotion-specific model 59. The data generation model 58 and the emotion-specific model 59 are used by the specific processing unit 290.

[0214] In the head-mounted terminal 314, the processor 46 performs the acceptance / output processing. The memory 50 stores the acceptance / output program 60. The processor 46 reads the acceptance / output program 60 from the memory 50 and executes the read acceptance / output program 60 on the RAM 48. The acceptance / output processing is implemented by the processor 46 operating as a control unit 46A according to the acceptance / output program 60 executed on the RAM 48.

[0215] Next, the specific processing of the specific processing unit 290 of the data processing device 12 will be described. Each part of the system described below is implemented by the data processing device 12 and the head-mounted terminal 314. In the following description, the data processing device 12 will be referred to as the "server" and the head-mounted terminal 314 will be referred to as the "terminal".

[0216] Example 1 The process is the same as that of the specific process described in Embodiment 1 in the first embodiment above, so the description is omitted.

[0217] Application Example 1 The process is the same as that in the specific processing described in Application Example 1 of the first embodiment above, so the description is omitted.

[0218] Example 2 The process is the same as that of the specific process in Embodiment 2 described in the first embodiment above, so the description is omitted.

[0219] Application Example 2 The process is the same as that in the specific processing described in Application Example 2 of the first embodiment above, so the description is omitted.

[0220] The specific processing unit 290 sends the result of the specific processing to the head-mounted terminal 314. In the head-mounted terminal 314, the control unit 46A outputs the result of the specific processing to the speaker 240 and the display 343. The microphone 238 acquires sound input representing the result of the specific processing. The control unit 46A sends the sound data representing the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the sound data.

[0221] Data generation model 58 is a so-called generative AI (Artificial Intelligence). Examples of data generation models 58 include ChatGPT (registered trademark) (accessible via the internet (URL: https: / / openai.com / blog / chatgpt)). Data generation model 58 is obtained through deep learning on a neural network. Input to data generation model 58 includes prompt words containing instructions, and inference data such as sound data representing sound, text data representing text, and image data representing images (e.g., still image data or animation data). Data generation model 58 infers the input inference data based on the instructions represented by the prompt words and outputs the inference result in one or more data forms such as sound data, text data, and image data. Data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or induction. The specific processing unit 290 performs the aforementioned specific processing while using data generation model 58. The data generation model 58 can also be a model finely tuned to output inference results from prompts that do not contain instructions. In this case, the data generation model 58 can output inference results based on prompts that do not contain instructions. The data processing apparatus 12, etc., includes various data generation models 58, including AI other than the generation AI. AI other than the generation AI can be, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or Naive Bayes, and can perform various processes, but is not limited to this example. Furthermore, the AI ​​can also be an AI agent. Furthermore, when the processing of the above-mentioned parts is performed by AI, the processing can be performed partially or entirely by AI, but is not limited to this example. Furthermore, the processing performed by the AI ​​including the generation AI can be replaced by processing in the rule base, and the processing in the rule base can also be replaced by processing performed by the AI ​​including the generation AI.

[0222] Furthermore, the processing of the aforementioned data processing system 10 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the head-mounted terminal 314, but it can also be performed by both the specific processing unit 290 of the data processing device 12 and the control unit 46A of the head-mounted terminal 314. Additionally, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the head-mounted terminal 314 or external devices, and the head-mounted terminal 314 acquires or collects information required for processing from the data processing device 12 or external devices.

[0223] For example, the collection unit is implemented by the control unit 46A of the head-mounted terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit uses the camera 42 or communication I / F 44 of the head-mounted terminal 314 to acquire step data, which is then processed by the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12 to analyze the data from the collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12 to generate a menu using a generation AI. For example, the serving unit is implemented by the speaker 240 and display 343 of the head-mounted terminal 314 or the specific processing unit 290 of the data processing device 12 to provide the generated menu to the user. The correspondence between each unit and the device or control unit is not limited to the above examples and various changes can be made.

[0224] In the above embodiments, examples of specific processing by the data processing device 12 are given, but the technology disclosed herein is not limited to this, and specific processing may also be performed by the head-mounted terminal 314.

[0225] Fourth Implementation Method Figure 7 An example of the configuration of the data processing system 410 according to the fourth embodiment is shown.

[0226] like Figure 7 As shown, the data processing system 410 includes a data processing device 12 and a robot 414. A server can be cited as an example of the data processing device 12.

[0227] The data processing apparatus 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" as understood in this disclosure. The computer 22 includes a processor 28, RAM 30, and memory 32. The processor 28, RAM 30, and memory 32 are connected to a bus 34. Furthermore, the database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0228] Robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and memory 50. The processor 46, RAM 48, and memory 50 are connected to a bus 52. Furthermore, the microphone 238, speaker 240, camera 42, controlled object 443, and communication I / F 44 are also connected to the bus 52.

[0229] Microphone 238 receives instructions from user 20 by receiving sounds emitted by user 20. Microphone 238 captures sounds emitted by user 20 and converts the captured sounds into sound data, which is then output to processor 46. Speaker 240 outputs sound according to instructions from processor 46.

[0230] Camera 42 is a small digital camera equipped with an optical system such as a lens, aperture and shutter, and imaging elements such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, to photograph the area around robot 414 (e.g., the field of view defined by a perspective equivalent to the field of vision of an average healthy person).

[0231] Communication I / F44 is connected to network 54. Communication I / F44 and 26 are responsible for the transmission and reception of various information between processor 46 and processor 28 via network 54. The transmission and reception of various information between processor 46 and processor 28 using communication I / F44 and 26 is performed in a secure state.

[0232] The controlled object 443 includes a display device, LEDs (light-emitting diodes) for the eyes, and motors for driving the arms, hands, and feet. The posture or movement of the robot 414 is controlled by controlling the motors in the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. In addition, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0233] Figure 8 This illustrates an example of the main functions of the data processing device 12 and the robot 414. For example... Figure 8 As shown, in the data processing device 12, specific processing is performed by the processor 28. The specific processing program 56 is stored in the memory 32.

[0234] The specific processing program 56 is an example of a "program" involved in the technology of this disclosure. The processor 28 reads the specific processing program 56 from the memory 32 and executes the read specific processing program 56 on the RAM 30. Specific processing is implemented by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0235] The memory 32 stores the data generation model 58 and the emotion-specific model 59. The data generation model 58 and the emotion-specific model 59 are used by the specific processing unit 290.

[0236] In robot 414, the processor 46 performs the acceptance and output processing. The memory 50 stores the acceptance and output program 60. The processor 46 reads the acceptance and output program 60 from the memory 50 and executes the read acceptance and output program 60 on RAM 48. The acceptance and output processing is implemented by the processor 46 acting as the control unit 46A according to the acceptance and output program 60 executed on RAM 48.

[0237] Next, the specific processing of the specific processing unit 290 of the data processing device 12 will be described. Each part of the system described below is implemented by the data processing device 12 and the robot 414. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 will be referred to as the "terminal".

[0238] Example 1 The process is the same as that of the specific process described in Embodiment 1 in the first embodiment above, so the description is omitted.

[0239] Application Example 1 The process is the same as that in the specific processing described in Application Example 1 of the first embodiment above, so the description is omitted.

[0240] Example 2 The process is the same as that of the specific process in Embodiment 2 described in the first embodiment above, so the description is omitted.

[0241] Application Example 2 The process is the same as that in the specific processing described in Application Example 2 of the first embodiment above, so the description is omitted.

[0242] The specific processing unit 290 sends the result of the specific processing to the robot 414. In the robot 414, the control unit 46A outputs the result of the specific processing to the speaker 240 and the controlled object 443. The microphone 238 acquires sound input representing the result of the specific processing. The control unit 46A sends the sound data representing the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the sound data.

[0243] Data generation model 58 is a so-called generative AI (Artificial Intelligence). Examples of data generation models 58 include ChatGPT (registered trademark) (accessible via the internet (URL: https: / / openai.com / blog / chatgpt)). Data generation model 58 is obtained through deep learning on a neural network. Input to data generation model 58 are prompt words containing instructions, and inference data such as sound data representing sound, text data representing text, and image data representing images (e.g., still image data or animation data). Data generation model 58 infers from the input inference data based on the instructions represented by the prompt words and outputs the inference result in one or more data forms, such as sound data, text data, and image data. Data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or induction. The specific processing unit 290 performs the aforementioned specific processing while using data generation model 58. The data generation model 58 can also be a model finely tuned to output inference results from prompts that do not contain instructions. In this case, the data generation model 58 can output inference results based on prompts that do not contain instructions. The data processing apparatus 12, etc., includes various data generation models 58, including AI other than the generation AI. AI other than the generation AI can be, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or Naive Bayes, and can perform various processes, but is not limited to this example. Furthermore, the AI ​​can also be an AI agent. Furthermore, when the processing of the above-mentioned parts is performed by AI, the processing can be performed partially or entirely by AI, but is not limited to this example. Furthermore, the processing performed by the AI ​​including the generation AI can be replaced by processing in the rule base, and the processing in the rule base can also be replaced by processing performed by the AI ​​including the generation AI.

[0244] Furthermore, the processing of the aforementioned data processing system 10 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it can also be performed by both the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Additionally, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or external devices, and the robot 414 acquires or collects information required for processing from the data processing device 12 or external devices.

[0245] For example, the collection unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit uses the camera 42 or communication I / F 44 of the robot 414 to acquire step data, which is then processed by the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12, which analyzes the data from the collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12, which uses a generation AI to generate a menu. For example, the serving unit is implemented by the speaker 240 of the robot 414 and the control object 443 or the specific processing unit 290 of the data processing device 12, which provides the generated menu to the user. The correspondence between each unit and the device or control unit is not limited to the above examples and various changes can be made.

[0246] In the above embodiments, examples of specific processing by the data processing device 12 are given, but the technology disclosed herein is not limited to this, and specific processing may also be performed by the robot 414.

[0247] Furthermore, the emotion-specific model 59, acting as an emotion engine, can determine a user's emotion based on a specific mapping. Specifically, the emotion-specific model 59 can determine a user's emotion based on an emotion graph that serves as a specific mapping (see [reference]). Figure 9 The emotion-specific model 59 can also determine the robot's emotions, and the specific processing unit 290 performs specific processing based on the robot's emotions.

[0248] Figure 9 This is a diagram representing an emotion map 400 that maps multiple emotions. 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 emotion is. On the outer side of the concentric circles, emotions representing states or behaviors arising from mood are arranged. Emotions are concepts that include feelings and mental states. Emotions generated by reactions occurring in the brain are arranged roughly to the left of the concentric circles. Emotions derived from situational judgments are arranged roughly to the right of the concentric circles. Emotions generated by reactions occurring in the brain and derived from situational judgments are arranged roughly above and below the concentric circles. Furthermore, "pleasant" emotions are arranged above the concentric circles, and "unpleasant" emotions are arranged below them. Thus, in the emotion map 400, multiple emotions are mapped based on the structure that generates emotions, and emotions that are likely to occur simultaneously are mapped close to each other.

[0249] These emotions are distributed at the three o'clock position of the emotion map 400, typically fluctuating between peace and unease. In the right half of the emotion map 400, situational awareness dominates over internal sensation, thus resulting in an impression of calm.

[0250] The inner side of the emotion map 400 represents the inner state, while the outer side represents behavior. Therefore, the further outward you are from the emotion map 400, the more visible the emotion becomes (manifested in behavior).

[0251] Here, human emotions are based on various balances such as posture and blood sugar levels. When these balances deviate from an ideal state, it indicates an unpleasant state; when they approach the ideal state, it indicates a pleasant state. Emotions in robots, cars, motorcycles, etc., can also be created in the following way: based on various balances such as posture and remaining battery power, when these balances deviate from an ideal state, it indicates an unpleasant state; when they approach the ideal state, it indicates a pleasant state. Emotion maps can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a Brain Physiological Signal Analysis System for Voice Emotion Recognition and Emotion, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). In the left half of the emotion map, emotions belonging to the sensory-dominated region, called "response," are arranged. Furthermore, in the right half of the emotion map, emotions belonging to the situational cognition-dominated region, called "situation," are arranged.

[0252] In the emotion map, two types of emotions that promote learning are defined. One is a negative emotion on the situational side, in the middle or peripheral region of "repentance" or "reflection." This occurs when the robot experiences negative emotions such as "I don't want to experience this feeling again" or "I don't want to be blamed again." The other is a positive emotion on the response side, near the "desire" region. This occurs when there are positive feelings such as "wanting more" or "wanting to know more."

[0253] The emotion-specific model 59 inputs user input into a pre-trained neural network to obtain emotion values ​​representing each emotion shown in the emotion map 400, thereby determining 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... Figure 10 As shown in the sentiment graph 900, it was trained in a way that sentiments that are configured close to each other have similar values. Figure 10 The text shows examples of emotions such as "peace of mind", "stability", and "reassurance" that have similar emotion values.

[0254] The above description focuses on the functions of the data processing device 12, but the system of this disclosure is not necessarily installed on a server. The system of this disclosure can also be installed as a general information processing system. This disclosure can also be installed, for example, as a software program running on a personal computer, an application running on a smartphone, etc. The method of this disclosure can also be provided to users in the form of SaaS (Software as a Service).

[0255] In the above embodiments, an example of a specific process being performed by a single computer 22 is given. However, the technology disclosed herein is not limited to this, and the specific process can also be distributed among multiple computers, including computer 22. For example, the data generation model 58 can be located on an external device of the data processing apparatus 12, where data is generated based on the input data.

[0256] In the above embodiments, examples of storing a specific processing program 56 in the memory 32 have been described, but the technology disclosed herein is not limited thereto. For example, the specific processing program 56 may also be stored in a portable computer-readable non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed into the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0257] Alternatively, a specific processing program 56 may be pre-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 according to the requirements of the data processing device 12.

[0258] In addition, it is not necessary to store all the specific processing program 56 in the storage device such as the server connected to the data processing device 12 via the network 54 or in the memory 32; a portion of the specific processing program 56 may be stored in advance.

[0259] As hardware resources for performing specific processes, various processors, as shown below, can be used. For example, a CPU can be listed as a processor, which functions as a general-purpose processor that performs specific processes by executing software, i.e., a program. Furthermore, processors can be listed as special-purpose circuits such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application-Specific Integrated Circuits), which are processors with circuitry specifically designed to perform specific processes. Each processor has built-in or connected memory, and each processor executes specific processes using that memory.

[0260] The hardware resources for performing a specific process can consist of one of these various processors, or a combination of two or more processors of the same or different types (e.g., a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resources for performing a specific process can be a single processor.

[0261] As an example of a single processor, there are two approaches: First, a processor is composed of a combination of one or more CPUs and software, which functions as a hardware resource to perform a specific process; second, as represented by a SoC (System-on-a-chip), a processor is used to implement the functionality of the entire system, which includes multiple hardware resources for performing a specific process, using a single IC (Integrated Circuit) chip. In this way, the specific process is implemented by using one or more of the aforementioned processors as hardware resources.

[0262] Furthermore, the hardware architecture of these various processors, more specifically, can utilize circuits that combine semiconductor elements and other circuit components. Moreover, the specific process described above is just one example. Therefore, without departing from the main point, unnecessary steps can certainly be deleted, new steps added, or the processing order changed.

[0263] The descriptions and illustrations above are detailed explanations of a portion of the technology disclosed herein, and are merely one example of the technology disclosed herein. For example, the above descriptions of the structure, function, effect, and results are just one example of the structure, function, effect, and results of a portion of the technology disclosed herein. Therefore, without departing from the spirit of the technology disclosed herein, unnecessary parts may be deleted, new elements added, or replacements may be made to the descriptions and illustrations above. Furthermore, to avoid confusion and facilitate understanding of a portion of the technology disclosed herein, explanations of common technical knowledge that do not require special explanation under the premise of being able to implement the technology disclosed herein have been omitted from the descriptions and illustrations above.

[0264] All documents, patent applications and technical specifications set forth in this specification are incorporated herein by reference to the same extent that each document, patent application and technical specification is specifically and individually described therein and referenced by reference.

[0265] In addition, the following notes are provided in response to the above explanation.

[0266] Example 1 (Note 1) An information processing system includes: a data receiving device for receiving collected information from an information terminal; a data analysis device for parsing the received information using an analysis device incorporating generative artificial intelligence and generating encoding rule information for information compression; a distribution device for distributing the generated encoding rule information to the information terminal and enabling the information terminal to apply the encoding rule information in subsequent information transmissions; a communication security device for encrypting data compressed based on the encoding rule information; a visualization device for real-time visualization of received and stored information and the analyzed and processed information; shared general information processing resources for information compression and decompression; and a control device for receiving prompt statements as input instructions for generative artificial intelligence and initiating analysis and processing.

[0267] (Note 2) According to the information processing system described in Appendix 1, the information terminal uses distributed encoding rule information to compress the collected information.

[0268] (Note 3) According to the information processing system described in Appendix 1, the information processing device decodes or decompresses information compressed using distributed encoding rule information.

[0269] Application Example 1 (Note 1) An information processing system includes: means for receiving information from multiple information processing devices; means for parsing the received information using a generative information processing algorithm and generating encoded information for information compression; means for distributing the generated encoded information to information processing devices for use in subsequent information communication; means for protecting information communication through encryption when information is transmitted from the information processing device to the information parsing device; means for estimating the status of a person using a person status inference algorithm when the analyzed information contains person attribute data, and controlling the encoded information or information communication processing content based on the estimation result; and means for automatically switching or optimizing the encoded information and encryption methods.

[0270] (Note 2) According to the information processing system described in Appendix 1, the information processing device compresses the information using the distributed coded information during subsequent information transmission.

[0271] (Note 3) According to the information processing system described in Appendix 1, after receiving information compressed using distributed encoded information, it decodes and expands the information.

[0272] Example 2 (Note 1) An information processing system includes: a device for receiving information collected by an information acquisition device; A device for analyzing received information using a generative artificial intelligence model and generating reference data for information compression; a device for sending the generated reference data to the information acquisition device and setting it for use in the next information communication; a device for ensuring the security of information communication using encryption processing technology; a device for determining emotional state using an emotion analysis device based on perceived data and input data obtained from the information acquisition device; a device for setting the priority of communication information based on the determined emotional information; and an instruction management device for performing action control by inputting predetermined instruction statements to the generative artificial intelligence model.

[0273] (Note 2) According to the information processing system described in Appendix 1, the information acquisition device compresses the information using the generated reference data during the next information transmission.

[0274] (Note 3) According to the information processing system described in Appendix 1, the compressed information is restored and processed using the generated reference data.

[0275] Application Example 2 (Note 1) An information processing system includes: a device for acquiring status information from a terminal device; a device for inputting the acquired status information into an analysis device, identifying the user's psychological state through a generative artificial intelligence algorithm built into the analysis device, and generating coded information for data compression based on the identification result and the status information; a device for sending the generated coded information to the terminal device and using it in subsequent information transmissions; a device for automatically setting the priority of information during communication based on the analysis result; and a device for applying encryption methods during transmission to ensure information confidentiality.

[0276] (Note 2) According to the information processing system described in Appendix 1, the terminal device compresses the information it sends using encoded information received from the information processing device.

[0277] (Note 3) According to the information processing system described in Appendix 1, the information processing device or terminal equipment uses the generated encoded information to decode and analyze the compressed information.

Claims

1. An information processing system, characterized in that, include: A device for receiving data collected by a terminal; A device for analyzing received data using a generative model and generating dictionary data for data compression; A means for distributing the generated dictionary data to the terminal and setting it for use by the terminal in the next data communication; and Devices used to ensure the security of data communication using encryption technology.

2. The information processing system according to claim 1, characterized in that, The system compresses the data using the generated dictionary data when the terminal sends data next time.

3. The information processing system according to claim 1, characterized in that, The system decompresses and processes the data compressed using the generated dictionary data.

Images