system

Abstract

We provide the system. [Solution] Means of acquiring multilingual information, A means of converting acquired multilingual information into a unified format, A means of compressing and storing the converted information, A means of learning using unified information, A system that includes means for providing learned information in response to user requests.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern society, there are limitations in effectively obtaining and integrating multilingual information existing in the Internet and various databases and using it in an integrated form. In particular, information provided in different languages is specialized for each language circle, and information is often managed separately. Therefore, it is required to integrate information from a global perspective and utilize it quickly and accurately. By solving this problem, the efficiency of information utilization can be improved, and the creation of new knowledge can be promoted.

Means for Solving the Problems

[0005] This invention provides a system for effectively acquiring information provided in multiple languages ​​and converting it into a unified format. The system includes means for acquiring multilingual information and means for converting that information into a unified format. Furthermore, it includes means for compressing and storing the converted information, means for performing AI-based learning using the compressed information, and means for providing the learned information according to user requests. This configuration enables centralized handling of information dispersed across multiple languages, facilitating efficient information retrieval and utilization.

[0006] "Multilingual information" refers to a collection of data and information provided in different languages, and is not limited to any particular language.

[0007] "Means of acquisition" refers to the function of collecting multilingual information and storing it in a format accessible to the system.

[0008] A "unified format" refers to a data structure that standardizes information from different languages ​​and represents it in a consistent format.

[0009] "Means of conversion" refers to the technologies and processes used to translate multilingual information into a unified format.

[0010] "Compression methods" refer to functions that reduce the redundancy of converted information and minimize the amount of data stored.

[0011] "Means of preservation" refers to systems and methods for persistently and efficiently storing compressed information so that it can be searched and used later.

[0012] "Means of learning" refers to the process of acquiring new knowledge using artificial intelligence by referring to stored compressed information.

[0013] "Means of delivery" refers to functions that present learned knowledge to the user in an appropriate format based on the user's requirements. [Brief explanation of the drawing]

[0014] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

MODE FOR CARRYING OUT THE INVENTION

[0015] An example of an embodiment of the system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, a labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention provides a system that efficiently collects information provided in multiple languages, converts and compresses it into a unified format, and uses artificial intelligence for learning. This system operates through the collaboration of a server, terminals, and users, enabling the handling of multilingual information in a unified format.

[0036] Data collection and conversion

[0037] The terminal retrieves multilingual data from the internet and various databases. During this process, data is collected from information sources specified by the user and sent to the server. The server receives this data and converts it into a standardized language format, taking language differences into account. Machine translation and natural language processing technologies are used for this conversion.

[0038] Data compression and storage

[0039] The server parses the converted standard format data and compresses redundant information. The compressed data is indexed and stored in a database to enable effective searching and use. The stored data is later utilized in a learning process.

[0040] Learning process

[0041] The server uses the stored data to train the AI ​​model. In this training process, unified information is used as the overall dataset, and the AI ​​learns new knowledge. Based on the results of this learning, the terminal prepares to provide information according to the user's requests.

[0042] Information provision and response

[0043] When a user requests specific information, the device accesses the server to retrieve the necessary knowledge. The server uses its learned results to respond with the most relevant information to the user's request. The device then translates that information back into the user's native language or a specified language and displays it in an easy-to-understand format.

[0044] Specific example

[0045] For example, if a user seeks information on engineering papers written in multiple languages, the terminal collects the necessary paper data, and the server converts it into a unified format for learning. By providing the optimal answer to the user's specific question based on the learned knowledge, information can be obtained across language barriers. In this way, the present invention supports the efficient use of information and the creation of new knowledge.

[0046] The following describes the processing flow.

[0047] Step 1:

[0048] The user specifies the source of multilingual information via the terminal and inputs the type and scope of data they wish to collect. The terminal then collects the relevant information from the internet and various databases according to the user's specifications.

[0049] Step 2:

[0050] The terminal sends the collected multilingual data to the server. The server analyzes the received data, assigns language tags to each piece of data, and classifies it. This classification prepares each piece of language data for appropriate processing.

[0051] Step 3:

[0052] The server utilizes natural language processing technology to convert the collected multilingual data into a unified format. This conversion process uses translation techniques to analyze the context and meaning between different languages ​​and arrange them into a unified format.

[0053] Step 4:

[0054] The server compresses the data after it has been converted to a unified format. This compression process removes redundant information and duplicate data, reducing the amount of data. The compressed information is then indexed to enable effective searching and storage, and stored in a database.

[0055] Step 5:

[0056] The server uses the stored data to train the AI ​​model. In this learning process, the AI ​​model acquires new knowledge based on the integrated information and understands the overall context of the data.

[0057] Step 6:

[0058] When a user requests specific information via a device, the device sends the request to the server. The server scrutinizes the requested information based on its learned knowledge and quickly searches for data that matches the user's request.

[0059] Step 7:

[0060] After the server retrieves the search results, it re-translates them into the user's preferred language as needed. The terminal displays the data received from the server in a user-friendly format. It also ensures that the information provided to the user is specific and appropriate.

[0061] (Example 1)

[0062] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0063] In recent years, while the amount of information provided in multiple languages ​​has increased, there is a growing need for effective ways to utilize it. The lack of systems to integrate information across different languages ​​and efficiently use it for learning and retrieval hinders its effective use. Furthermore, it is crucial to transfer acquired multilingual data quickly and securely, and to easily access information in the user's native language or a specified language.

[0064] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0065] In this invention, the server includes a device for acquiring multilingual information, a device for converting the acquired multilingual information into a unified format, a device for compressing and storing the converted information, a device for performing learning using the unified information, a device for providing the learned information according to the user's request, a device for collecting data based on a user-specified information source, a communication device for securely transferring the collected data, and a device for re-converting the learned information and displaying it in a specified language. This makes it possible to centrally manage and efficiently utilize information in different languages.

[0066] "Multilingual information" refers to various types of data and knowledge provided in different languages.

[0067] A "unified format" refers to a standardized format used to organize data expressed in multiple different languages ​​or formats into a consistent format.

[0068] "Compression" refers to the process of removing redundancy from information to reduce the amount of data, thereby improving the efficiency of storage and transfer.

[0069] "Storage devices" refer to tools and hardware used to physically or digitally record data and maintain it in a state that makes it accessible at a later date.

[0070] "A device for learning" refers to a computer or algorithm used to analyze data and extract patterns and knowledge.

[0071] "User" refers to a person or organization that requests information through the system and receives the results.

[0072] "Communication equipment" refers to hardware or software used to send and receive data with other devices or networks.

[0073] A "catalog" refers to an index associated with data, used to quickly search for and access that information.

[0074] This invention is a system for efficiently acquiring, converting, and compressing information provided in multiple languages, learning from it using artificial intelligence, and providing it to users. The system is primarily operated through the collaboration of a server, terminals, and users.

[0075] The device collects multilingual data from the internet and various databases based on information sources specified by the user. This collection uses common programming languages ​​such as Python and JavaScript (registered trademark), and employs APIs and web scraping techniques via an internet connection.

[0076] The data collected by the device is securely transferred to the server. Security technologies such as the SSL / TLS protocol are applied during the transfer. The server analyzes the received data and converts it into a standardized language format using machine translation services such as the Google Translate API or NLP libraries (e.g., NLTK, spaCy).

[0077] The converted data is compressed using compression algorithms such as Gzip or Zstandard to compress and store redundant information. The compressed data is then indexed using an information retrieval system such as Elasticsearch®, enabling rapid searching.

[0078] The server trains the generative AI model using compressed and stored data. Deep learning frameworks such as PyTorch and TENSORFLOW® are used for model training, and processing is accelerated using GPUs and TPUs.

[0079] When a user requests information, the device retrieves the learned information from the server. For example, if a user requests "information about 2023 technology trends using a generative AI model," the server generates the optimal answer from its trained model. The device then translates this information into the user's specified language and displays it clearly on a web browser using HTML and CSS.

[0080] This system allows users to acquire information comprehensively, transcending language barriers, and efficiently utilize new knowledge.

[0081] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0082] Step 1:

[0083] The device receives information sources specified by the user and accesses the internet and databases to retrieve multilingual data. For example, if the user specifies a particular news site, the device will scrape articles from that site. The input is the URL or API key of the information source, and the output is raw data in multiple languages.

[0084] The process involves web scraping using Python libraries and data retrieval via APIs.

[0085] Step 2:

[0086] The terminal securely transfers the acquired multilingual data to the server using the SSL / TLS protocol. The input is the raw data acquired in step 1, and the output is the data securely sent to the server.

[0087] Specifically, the process involves sending data via HTTP requests and performing secure communication.

[0088] Step 3:

[0089] The server analyzes the received multilingual data and converts it into a standardized language format. This process utilizes the Google Translate API and NLP libraries. Input is raw data from the terminal, and output is data in a unified format.

[0090] We use natural language processing techniques to standardize data and perform translation.

[0091] Step 4:

[0092] The server compresses standardized format data and stores it in the database. Compression is performed using Gzip, and the data is indexed in Elasticsearch. The input is standardized data, and the output is compressed and stored data.

[0093] A compression algorithm is applied to persistently store information in data storage.

[0094] Step 5:

[0095] The server uses stored data to train a generative AI model. The input is a compressed dataset, and the output is the trained AI model. Model optimization is performed using PyTorch or TensorFlow.

[0096] Computational resources are used to carry out an intensive training process for the model.

[0097] Step 6:

[0098] When a user requests information, the device retrieves the learned information via the server. For example, if a user wants to know about technology trends in 2023, the server parses the request and returns the most relevant information from the training data. The input is the user's prompt, and the output is the answer to the user's question.

[0099] Data retrieval and generation of necessary information are performed based on the information request.

[0100] Step 7:

[0101] The terminal re-translates the information provided to the user into the specified language and displays it in the appropriate format. Input is response data from the server, and output is the user's visual information.

[0102] The information is converted into a visual display format using HTML and CSS, and presented to aid user understanding.

[0103] (Application Example 1)

[0104] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0105] There is a need for a system that can efficiently collect vast amounts of information written in multiple languages ​​and provide it to users in a unified format. Furthermore, there is a lack of technology to optimize multilingual information according to user-specified themes and language settings, and to quickly provide information tailored to user interests.

[0106] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0107] In this invention, the server includes means for acquiring multilingual information, means for converting the acquired multilingual information into a unified format, means for compressing and storing the converted information, means for performing learning using the unified information, means for providing the learned information according to the user's request, means for collecting relevant content based on a theme specified by the user, and means for displaying the information in a format optimized for the user's language settings. This enables efficient collection of multilingual information and optimized information provision.

[0108] "Multilingual information" refers to all information obtained across different languages, including data that is processed uniformly while taking language differences into account.

[0109] "Means of acquisition" refers to the technologies and devices used to collect the target information from the internet or databases.

[0110] "Means of converting to a unified format" refers to the process of converting information written in different languages ​​or formats into a standardized, consistent format.

[0111] "Methods of compression and storage" refer to technologies that reduce the amount of information and store it, with the aim of eliminating redundancy and saving it efficiently.

[0112] "Means of learning" refers to the process by which an artificial intelligence model extracts new insights and relationships through learning, based on accumulated unified data.

[0113] "Means of providing information in response to user requests" refers to technologies that provide information that meets user needs at the appropriate time.

[0114] "Means of collecting relevant content based on a theme" refers to the process of appropriately collecting information and content that aligns with the theme specified by the user.

[0115] "Means of displaying information in a format optimized for language settings" refers to technologies that display information in the most optimal way, tailored to the user's language settings.

[0116] To implement this invention, a system must be built through collaboration between a server, terminals, and users. The server plays a central role in efficiently processing content provided in various languages ​​and utilizes a cloud server. Specifically, infrastructure such as Amazon Web Services (AWS®) or Google Cloud Platform is suitable.

[0117] Data collection

[0118] The device collects multilingual data from the internet according to the user's instructions. This involves using smartphones or computers, employing scraping techniques with programming languages ​​such as Python.

[0119] Data conversion

[0120] The server translates the acquired multilingual data and converts it into a unified format. Google Translate API and Microsoft Azure's natural language processing technologies are used here.

[0121] Data compression and storage

[0122] The converted data is compressed on the server using zlib with Python. The compressed data is stored in a database such as MySQL®.

[0123] Learning process

[0124] The server trains generative AI models using machine learning libraries such as TensorFlow. It analyzes compressed data and extracts relationships and patterns.

[0125] Providing information

[0126] Users access the server through their devices and request information based on specific themes and language settings. The server provides the most relevant information in response to the user's request and displays it on the device. Smartphones and computers fulfill this role.

[0127] A concrete example is the multilingual news app "GlobalReview." It allows users to collect news related to "environmental issues," translate it into the most suitable language, and display it. This system helps to smoothly deliver multilingual information to users.

[0128] Prompt example:

[0129] "Please collect and translate the latest multilingual news articles on environmental issues."

[0130] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0131] Step 1:

[0132] The device collects multilingual data related to a specific theme from the internet based on user instructions. The input is a search keyword specified by the user, and the output is a collection of related information. This process involves using scraping techniques to extract information from web pages and databases.

[0133] Step 2:

[0134] The terminal sends the collected data to the server. The input is raw data captured in multiple languages, and the output is data securely transmitted to the server. This step involves ensuring that the data is securely transferred using data encryption and communication protocols (HTTP or HTTPS).

[0135] Step 3:

[0136] The server converts the received multilingual data into a standard format using the Google Translate API and Microsoft Azure's natural language processing technology. The input is multilingual data, and the output is data in a unified format. This conversion includes the operation of linguistically standardizing the data through machine translation.

[0137] Step 4:

[0138] The server compresses data in a unified format using the Python zlib library and stores it in a MySQL database. The input is the converted data, and the output is the compressed and stored data. This step involves operations that compress the data and ensure efficient storage.

[0139] Step 5:

[0140] The server uses compressed data to train a generative AI model using libraries such as TensorFlow. The input is compressed data, and the output is the training result of the AI ​​model. This training process extracts relevant content patterns.

[0141] Step 6:

[0142] The user operates the terminal and requests information based on their preferred topics and language settings. The input is the user's request, and the output is the corresponding information. This step involves the user making a request for information retrieval through the terminal's interface.

[0143] Step 7:

[0144] The server searches for the most relevant information based on the user's request and provides it to the terminal. The input consists of a trained model and the user's request, while the output is information provided in an optimized format. This process involves rapid data retrieval and delivery of information in a format tailored to the user's preferences.

[0145] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0146] This invention provides a system for integrating information provided in multiple languages ​​into a unified format, and further recognizing and utilizing user emotions in information delivery. This system operates through the cooperation of a server, terminal, user, and emotion engine.

[0147] Collection and processing of multilingual information

[0148] The terminal collects multilingual data from the internet and various databases based on user requests. The collected data is sent to a server, which automatically classifies the information and converts it into a unified format using natural language processing technology. This step ensures information consistency and enables efficient management.

[0149] Utilizing the Emotion Engine

[0150] This system includes an emotion engine that detects the user's emotional state. When a user enters an information request or comment through a terminal, the emotion engine analyzes it and infers the user's emotional state in real time. This information is sent to the server and taken into consideration when providing information.

[0151] Information compression and learning

[0152] The server compresses and stores the converted information and uses an AI model for training. This process efficiently integrates information and lays the foundation for providing appropriate information based on the user's emotional state.

[0153] Customized information provision

[0154] When a user requests specific information, the device accesses the server to retrieve learned results. The server considers the user's emotional information obtained from the emotion engine and customizes and selects the necessary information. The device then presents this information to the user and provides feedback tailored to the user's emotional state.

[0155] Specific example

[0156] For example, if a user seeks information about relaxation due to work stress, the emotional engine detects a heightened stress level, and the server adjusts to prioritize providing information on videos and music specifically designed for relaxation. In this way, information tailored to the user's needs is provided.

[0157] This system enables the efficient integration of multilingual information and the customization of information to respond to user emotions, resulting in the provision of advanced information tailored to individual needs.

[0158] The following describes the processing flow.

[0159] Step 1:

[0160] The user enters a request for specific information through their device. In doing so, the user specifies the topics or information they are interested in.

[0161] Step 2:

[0162] The terminal receives the user's request and sends its contents to the server. The server parses the request and generates a search query to collect the appropriate information.

[0163] Step 3:

[0164] Based on the generated queries, the server collects relevant multilingual data from the internet and databases. Since this data may exist in different languages, the server categorizes each piece of data using language tags.

[0165] Step 4:

[0166] The server converts the collected multilingual data into a unified format using natural language processing techniques. This process utilizes machine translation technology to standardize different languages.

[0167] Step 5:

[0168] The emotion engine analyzes user input on the device and evaluates the user's emotional state in real time. This evaluation result is sent to the server and considered when providing information.

[0169] Step 6:

[0170] The server compresses the converted information and stores it in a database. The compressed data is then used to train an AI model, improving the information's effectiveness and relevance to the user.

[0171] Step 7:

[0172] When a user requests specific, emotionally relevant answers through their device, the server searches for the most appropriate information based on its learned knowledge.

[0173] Step 8:

[0174] The server customizes the search results to match the user's emotional state. The device then translates this information back into the appropriate language and presents it to the user.

[0175] Step 9:

[0176] The information displayed by the device to the user is tailored to the user's emotions, excluding information they dislike or find inappropriate. This allows the user to enjoy a consistent content experience.

[0177] (Example 2)

[0178] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0179] Because multilingual information is scattered across the internet, there is a need to address the challenge of users having difficulty quickly and efficiently obtaining information that is relevant to their emotional state. Furthermore, it is necessary to improve the quality of the information provided by appropriately organizing, translating, and presenting it.

[0180] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0181] In this invention, the server includes means for collecting multilingual information, means for converting the collected multilingual information into a unified format, and means for analyzing the user's emotional state. This makes it possible to provide information optimized to the user's emotions and needs.

[0182] "Multilingual information" refers to a collection of information provided in different languages, and the data collected through the internet and databases.

[0183] A "unified format" is a format that standardizes and maintains consistency for information in different languages ​​and formats.

[0184] "Compression" refers to the process of reducing the data size of information to make storage and transfer more efficient.

[0185] "Machine learning" is the process by which algorithms learn patterns using collected data and train models.

[0186] "User emotional state" refers to the psychological state that can be inferred from the user's input and actions.

[0187] "Customization" refers to tailoring and providing information and services based on the user's specific requests and conditions.

[0188] In order to implement this invention, the server, terminal, and user must cooperate to configure the system. Specifically, it is implemented as follows.

[0189] The server receives multilingual information collected from terminals via the internet and databases. The received information is converted into a unified format using natural language processing techniques. This process can utilize natural language processing libraries such as spaCy and NLTK as software libraries. Furthermore, commonly available machine translation APIs are used as translation APIs for the conversion to the unified format.

[0190] The server further compresses the converted information and stores it efficiently. A NoSQL database is suitable for this purpose. Machine learning is performed on the stored data using a generative AI model. Examples of AI models used include BERT and OpenAI® GPT.

[0191] The terminal collects necessary multilingual information in response to user requests and sends it to the server. The terminal also incorporates an emotion engine that analyzes user requests and comments to infer their psychological state. This uses an emotion analysis model to recognize the user's emotional state in real time.

[0192] When a user requests specific information through their device, the server customizes and provides the most relevant information to the device based on the generated learning results and the user's emotional state.

[0193] As a concrete example, consider a scenario where a user requests information about relaxation. For instance, the user might enter a prompt into their device saying, "Please suggest relaxation methods that would be helpful when I'm feeling stressed." The emotion engine detects the user's stress level, and the server adjusts to provide relaxation-focused information accordingly. In this way, it becomes possible to provide information that matches the user's emotions and needs.

[0194] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0195] Step 1:

[0196] The terminal receives search keywords and requests from the user. The information entered by the user is a specific request, such as "relaxation methods" or "latest news." Based on this input, the terminal uses the internet and default database APIs to collect relevant information from multilingual sources. The collected data is sent to the backend in JSON or XML format.

[0197] Step 2:

[0198] The server receives multilingual information sent from the terminal. The server uses a natural language processing library to classify the received information into specific categories. The classified data is converted into a unified format via a machine translation API. Here, the input is unstructured multilingual data, and the output is structured data in a unified format.

[0199] Step 3:

[0200] The server compresses the converted, unified format data and stores it in the database. It applies the optimal compression technique to minimize data size. The input is the unified format data, and the output is the compressed data. An index is also automatically generated for the stored data to support efficient searching.

[0201] Step 4:

[0202] The server trains on stored compressed data using a generating AI model. The training process extracts patterns from the dataset and optimizes future information delivery strategies. The input to this step is compressed information, and the output is the trained AI model.

[0203] Step 5:

[0204] The device passes real-time user input information to the emotion engine, which analyzes the user's psychological state. This analysis step aims to provide advanced information based on the user's emotions and uses a BERT-based emotion analysis model. The input to the analysis is the user's comments and requests, and the output is an evaluation of the user's emotional state.

[0205] Step 6:

[0206] The server selects the most relevant information for the user based on the user's sentiment data and a trained model, and sends it to the terminal. The input to this process is sentiment data and the trained model, while the output is a customized set of information. The terminal presents this information to the user and also includes appropriate feedback functions.

[0207] In this way, the system provides personalized information to users, achieving the integration of multilingual information and the delivery of information that is sensitive to emotions.

[0208] (Application Example 2)

[0209] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0210] In modern society, providing efficient and emotionally sensitive information to a large number of users who speak different languages ​​is a major challenge. Conventional systems struggle to provide personalized information that considers multiple languages ​​and user emotional states, and there is a particular need to facilitate communication among international users. Furthermore, the processing and integration of multilingual information involves a massive amount of data, necessitating improvements in processing efficiency. Moreover, current technologies have not adequately achieved the ability to appropriately adjust and deliver information based on user emotions.

[0211] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0212] In this invention, the server includes means for acquiring multilingual information, means for converting the acquired multilingual information into a unified format, and means for performing sentiment analysis and customizing and providing information based on the user's emotional state. This makes it possible to provide personalized multilingual information that takes the user's emotional state into consideration.

[0213] "Multilingual information" refers to information written in multiple different languages.

[0214] A "unified format" refers to a state where data from different formats has been converted into a single, consistent format.

[0215] "Emotional analysis" refers to a technology that analyzes a user's facial expressions and voice to detect their emotional state.

[0216] "Customization" refers to appropriately adjusting and providing information and services based on the individual needs and circumstances of the user.

[0217] "Real-time" refers to a situation where processing or responses occur immediately, with virtually no time delay.

[0218] A "sensor" is a device that detects physical changes and outputs them as signals.

[0219] An "interface" refers to a common means or standard for different systems or devices to exchange information.

[0220] "Information provision" refers to the act of providing users with requested data or knowledge.

[0221] This invention begins with a user terminal acquiring multilingual information from the internet or other sources and sending it to a server. The server uses natural language processing technology to convert the information in each language into a unified format and stores the compressed data. The stored data can be quickly searched using an index, enabling efficient information provision. Furthermore, the user's emotional state is detected by an emotion analysis engine installed in the terminal. This engine analyzes the user's current emotions in real time based on input from sensors (e.g., camera and microphone) and transmits the analysis to the server.

[0222] When the server receives an information request from a user, it considers this sentiment information and generates customized information using a trained AI model. This customized information is provided through the interface in the user's language. Smooth information delivery across different languages ​​is crucial, and the generative AI model handles multilingual translation and content adjustment.

[0223] For example, if a user requests relaxation-related information in a stressful situation, the device's emotion analysis engine will detect the stress level, and the server will adjust its settings to prioritize providing relaxing music or videos. A possible prompt for this purpose might be, "What relaxing content should be provided when the user is feeling stressed?"

[0224] This allows users to instantly obtain information that suits their emotions, resulting in a more personalized user experience.

[0225] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0226] Step 1:

[0227] The user requests information using a terminal. The terminal receives the user's voice or text input, and the sentiment analysis engine starts working. This analyzes the user's current emotional state in real time, structures the information, and sends it to the server.

[0228] Step 2:

[0229] The server receives a multilingual information request sent from the terminal. It collects information in the requested language from the internet and other databases. This completes the collection of multilingual data, preparing it for the next step.

[0230] Step 3:

[0231] The server uses natural language processing technology to convert the collected multilingual data into a unified format. The input multilingual data is analyzed and organized into a unified format. The converted data is consistent, which streamlines subsequent processing.

[0232] Step 4:

[0233] The server compresses the data, which has been converted to a unified format, and stores it in a database for storage. This step uses a specialized algorithm to preserve information while minimizing data size. An index is then generated to streamline subsequent searches.

[0234] Step 5:

[0235] The server uses stored data to train an AI model and prepares customized information delivery based on the user's emotional state. The trained model then forms the foundation for specific information selection as a generative AI model.

[0236] Step 6:

[0237] The server considers the user's emotional data from the emotion analysis engine and uses a trained AI model to select information appropriate for the user. Based on the emotional state and requests, appropriate content (e.g., relaxing music or videos) is selected.

[0238] Step 7:

[0239] The server provides the selected information to the terminal. The terminal then presents the information through its interface, tailored to the user's language. This allows the user to obtain real-time, customized information.

[0240] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0241] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0242] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0243] [Second Embodiment]

[0244] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0245] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0246] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0247] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0248] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0249] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0250] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0251] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0252] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0253] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0254] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0255] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0256] This invention provides a system that efficiently collects information provided in multiple languages, converts and compresses it into a unified format, and uses artificial intelligence for learning. This system operates through the collaboration of a server, terminals, and users, enabling the handling of multilingual information in a unified format.

[0257] Data collection and conversion

[0258] The terminal retrieves multilingual data from the internet and various databases. During this process, data is collected from information sources specified by the user and sent to the server. The server receives this data and converts it into a standardized language format, taking language differences into account. Machine translation and natural language processing technologies are used for this conversion.

[0259] Data compression and storage

[0260] The server parses the converted standard format data and compresses redundant information. The compressed data is indexed and stored in a database to enable effective searching and use. The stored data is later utilized in a learning process.

[0261] Learning process

[0262] The server uses the stored data to train the AI ​​model. In this training process, unified information is used as the overall dataset, and the AI ​​learns new knowledge. Based on the results of this learning, the terminal prepares to provide information according to the user's requests.

[0263] Information provision and response

[0264] When a user requests specific information, the device accesses the server to retrieve the necessary knowledge. The server uses its learned results to respond with the most relevant information to the user's request. The device then translates that information back into the user's native language or a specified language and displays it in an easy-to-understand format.

[0265] Specific example

[0266] For example, if a user seeks information on engineering papers written in multiple languages, the terminal collects the necessary paper data, and the server converts it into a unified format for learning. By providing the optimal answer to the user's specific question based on the learned knowledge, information can be obtained across language barriers. In this way, the present invention supports the efficient use of information and the creation of new knowledge.

[0267] The following describes the processing flow.

[0268] Step 1:

[0269] The user specifies the source of multilingual information via the terminal and inputs the type and scope of data they wish to collect. The terminal then collects the relevant information from the internet and various databases according to the user's specifications.

[0270] Step 2:

[0271] The terminal sends the collected multilingual data to the server. The server analyzes the received data, assigns language tags to each piece of data, and classifies it. This classification prepares each piece of language data for appropriate processing.

[0272] Step 3:

[0273] The server utilizes natural language processing technology to convert the collected multilingual data into a unified format. This conversion process uses translation techniques to analyze the context and meaning between different languages ​​and arrange them into a unified format.

[0274] Step 4:

[0275] The server compresses the data after it has been converted to a unified format. This compression process removes redundant information and duplicate data, reducing the amount of data. The compressed information is then indexed to enable effective searching and storage, and stored in a database.

[0276] Step 5:

[0277] The server uses the stored data to perform the training of the AI model. In this learning process, based on the integrated information, the AI model acquires new knowledge and understands the overall context of the data.

[0278] Step 6:

[0279] When the user requests specific information via the terminal, the terminal sends that request to the server. The server examines the requested information based on the learned knowledge and quickly searches for the data that meets the user's request.

[0280] Step 7:

[0281] After the server obtains the search results, it reconverts them into the language desired by the user if necessary. The terminal displays the data received from the server in an easy-to-understand format for the user. And it ensures that the information provided to the user is specific and appropriate.

[0282] (Example 1)

[0283] Next, Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0284] In recent years, while the amount of information provided in multiple languages has been increasing, there is a need for effective ways to utilize it. Since there is a lack of systems for integrating information between different languages and efficiently using it for learning and searching, the utilization of information is hindered. Furthermore, it is important to transfer the acquired multilingual data quickly and securely and easily obtain information in the user's native language or designated language.

[0285] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0286] In this invention, the server includes a device for acquiring multilingual information, a device for converting the acquired multilingual information into a unified format, a device for compressing and storing the converted information, a device for performing learning using the unified information, a device for providing the learned information according to the user's request, a device for collecting data based on the information source specified by the user, a communication device for securely transferring the collected data, and a device for re-converting the learned information and displaying it in the specified language. Thereby, it becomes possible to manage information in different languages in a unified manner and utilize it efficiently.

[0287] "Multilingual information" refers to various data and knowledge provided in different languages.

[0288] "Unified format" means a standardized format for arranging data expressed in multiple different languages and formats into a consistent format.

[0289] "Compression" refers to a process of removing the redundancy of information to reduce the amount of data and improve the efficiency of storage and transfer.

[0290] "Device for storage" means tools or hardware for physically or digitally recording data and maintaining it in an accessible state later.

[0291] "Device for performing learning" refers to computers or algorithms used for analyzing data and extracting patterns and knowledge.

[0292] "User" means a person or group who requests information through the system and receives the result.

[0293] "Communication device" refers to hardware or software used for transmitting and receiving data to other devices or networks.

[0294] "Catalog" means an index associated with the data for quickly searching and accessing information.

[0295] This invention is a system for efficiently acquiring, converting, and compressing information provided in multiple languages, learning from it using artificial intelligence, and providing it to users. The system is primarily operated through the collaboration of a server, terminals, and users.

[0296] The device collects multilingual data from the internet and various databases based on information sources specified by the user. This collection uses common programming languages ​​such as Python and JavaScript, and utilizes APIs and web scraping techniques via an internet connection.

[0297] The data collected by the device is securely transferred to the server. Security technologies such as the SSL / TLS protocol are applied during the transfer. The server analyzes the received data and converts it into a standardized language format using machine translation services such as the Google Translate API or NLP libraries (e.g., NLTK, spaCy).

[0298] The converted data is compressed using compression algorithms such as Gzip or Zstandard to remove redundant information and save it. The compressed data is then indexed using an information retrieval system such as Elasticsearch, enabling rapid searching.

[0299] The server trains the generative AI model using compressed and stored data. Deep learning frameworks such as PyTorch and TensorFlow are used for model training, and processing is accelerated using GPUs and TPUs.

[0300] When a user requests information, the device retrieves the learned information from the server. For example, if a user requests "information about 2023 technology trends using a generative AI model," the server generates the optimal answer from its trained model. The device then translates this information into the user's specified language and displays it clearly on a web browser using HTML and CSS.

[0301] With this system, users can integratively obtain information beyond language barriers and efficiently utilize new knowledge.

[0302] The flow of the specific process in Example 1 will be described using FIG. 11.

[0303] Step 1:

[0304] The terminal receives the information source specified by the user, accesses the Internet or a database to obtain multilingual data. For example, when the user specifies a particular news site, the terminal scrapes articles from that site. The input is the URL or API key of the information source, and the output is raw multilingual data.

[0305] As processing, web scraping using Python libraries or data acquisition via APIs is performed.

[0306] Step 2:

[0307] The terminal securely transfers the obtained multilingual data to the server using the SSL / TLS protocol. The input is the raw data obtained in Step 1, and the output is the data securely transmitted to the server.

[0308] As a specific operation, the data is sent via an HTTP request to perform secure communication.

[0309] Step 3:

[0310] The server analyzes the received multilingual data and converts it into a standardized language format. Here, the Google Translate API or NLP libraries are used. The input is the raw data from the terminal, and the output is data in a unified format.

[0311] Using natural language processing technology, the data is standardized and translation is practiced.

[0312] Step 4:

[0313] The server compresses standardized format data and stores it in the database. Compression is performed using Gzip, and the data is indexed in Elasticsearch. The input is standardized data, and the output is compressed and stored data.

[0314] A compression algorithm is applied to persistently store information in data storage.

[0315] Step 5:

[0316] The server uses stored data to train a generative AI model. The input is a compressed dataset, and the output is the trained AI model. Model optimization is performed using PyTorch or TensorFlow.

[0317] Computational resources are used to carry out an intensive training process for the model.

[0318] Step 6:

[0319] When a user requests information, the device retrieves the learned information via the server. For example, if a user wants to know about technology trends in 2023, the server parses the request and returns the most relevant information from the training data. The input is the user's prompt, and the output is the answer to the user's question.

[0320] Data retrieval and generation of necessary information are performed based on the information request.

[0321] Step 7:

[0322] The terminal re-translates the information provided to the user into the specified language and displays it in the appropriate format. Input is response data from the server, and output is the user's visual information.

[0323] The information is converted into a visual display format using HTML and CSS, and presented to aid user understanding.

[0324] (Application Example 1)

[0325] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0326] There is a need for a system that can efficiently collect vast amounts of information written in multiple languages ​​and provide it to users in a unified format. Furthermore, there is a lack of technology to optimize multilingual information according to user-specified themes and language settings, and to quickly provide information tailored to user interests.

[0327] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0328] In this invention, the server includes means for acquiring multilingual information, means for converting the acquired multilingual information into a unified format, means for compressing and storing the converted information, means for performing learning using the unified information, means for providing the learned information according to the user's request, means for collecting relevant content based on a theme specified by the user, and means for displaying the information in a format optimized for the user's language settings. This enables efficient collection of multilingual information and optimized information provision.

[0329] "Multilingual information" refers to all information obtained across different languages, including data that is processed uniformly while taking language differences into account.

[0330] "Means of acquisition" refers to the technologies and devices used to collect the target information from the internet or databases.

[0331] "Means of converting to a unified format" refers to the process of converting information written in different languages ​​or formats into a standardized, consistent format.

[0332] "Methods of compression and storage" refer to technologies that reduce the amount of information and store it, with the aim of eliminating redundancy and saving it efficiently.

[0333] "Means of learning" refers to the process by which an artificial intelligence model extracts new insights and relationships through learning, based on accumulated unified data.

[0334] "Means of providing information in response to user requests" refers to technologies that provide information that meets user needs at the appropriate time.

[0335] "Means of collecting relevant content based on a theme" refers to the process of appropriately collecting information and content that aligns with the theme specified by the user.

[0336] "Means of displaying information in a format optimized for language settings" refers to technologies that display information in the most optimal way, tailored to the user's language settings.

[0337] To implement this invention, the server, terminals, and users must collaborate to build the system. The server plays a central role in efficiently processing content provided in various languages ​​and utilizes a cloud server. Specifically, infrastructure such as Amazon Web Services (AWS) or Google Cloud Platform is suitable.

[0338] Data collection

[0339] The device collects multilingual data from the internet according to the user's instructions. This involves using smartphones or computers, employing scraping techniques with programming languages ​​such as Python.

[0340] Data conversion

[0341] The server translates the acquired multilingual data and converts it into a unified format. Google Translate API and Microsoft Azure's natural language processing technology are used here.

[0342] Data compression and storage

[0343] The converted data is compressed on the server using zlib with Python. The compressed data is then stored in a database such as MySQL.

[0344] Learning process

[0345] The server trains generative AI models using machine learning libraries such as TensorFlow. It analyzes compressed data and extracts relationships and patterns.

[0346] Providing information

[0347] Users access the server through their devices and request information based on specific themes and language settings. The server provides the most relevant information in response to the user's request and displays it on the device. Smartphones and computers fulfill this role.

[0348] A concrete example is the multilingual news app "GlobalReview." It allows users to collect news related to "environmental issues," translate it into the most suitable language, and display it. This system helps to smoothly deliver multilingual information to users.

[0349] Prompt example:

[0350] "Please collect and translate the latest multilingual news articles on environmental issues."

[0351] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0352] Step 1:

[0353] The device collects multilingual data related to a specific theme from the internet based on user instructions. The input is a search keyword specified by the user, and the output is a collection of related information. This process involves using scraping techniques to extract information from web pages and databases.

[0354] Step 2:

[0355] The terminal sends the collected data to the server. The input is raw data captured in multiple languages, and the output is data securely transmitted to the server. This step involves ensuring that the data is securely transferred using data encryption and communication protocols (HTTP or HTTPS).

[0356] Step 3:

[0357] The server converts the received multilingual data into a standard format using the Google Translate API and Microsoft Azure's natural language processing technology. The input is multilingual data, and the output is data in a unified format. This conversion includes the operation of linguistically standardizing the data through machine translation.

[0358] Step 4:

[0359] The server compresses data in a unified format using the Python zlib library and stores it in a MySQL database. The input is the converted data, and the output is the compressed and stored data. This step involves operations that compress the data and ensure efficient storage.

[0360] Step 5:

[0361] The server uses compressed data to train a generative AI model using libraries such as TensorFlow. The input is compressed data, and the output is the training result of the AI ​​model. This training process extracts relevant content patterns.

[0362] Step 6:

[0363] The user operates the terminal and requests information based on their preferred topics and language settings. The input is the user's request, and the output is the corresponding information. This step involves the user making a request for information retrieval through the terminal's interface.

[0364] Step 7:

[0365] The server searches for the most relevant information based on the user's request and provides it to the terminal. The input consists of a trained model and the user's request, while the output is information provided in an optimized format. This process involves rapid data retrieval and delivery of information in a format tailored to the user's preferences.

[0366] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0367] This invention provides a system for integrating information provided in multiple languages ​​into a unified format, and further recognizing and utilizing user emotions in information delivery. This system operates through the cooperation of a server, terminal, user, and emotion engine.

[0368] Collection and processing of multilingual information

[0369] The terminal collects multilingual data from the internet and various databases based on user requests. The collected data is sent to a server, which automatically classifies the information and converts it into a unified format using natural language processing technology. This step ensures information consistency and enables efficient management.

[0370] Utilizing the Emotion Engine

[0371] This system includes an emotion engine that detects the user's emotional state. When a user enters an information request or comment through a terminal, the emotion engine analyzes it and infers the user's emotional state in real time. This information is sent to the server and taken into consideration when providing information.

[0372] Information compression and learning

[0373] The server compresses and stores the converted information and uses an AI model for training. This process efficiently integrates information and lays the foundation for providing appropriate information based on the user's emotional state.

[0374] Customized information provision

[0375] When a user requests specific information, the device accesses the server to retrieve learned results. The server considers the user's emotional information obtained from the emotion engine and customizes and selects the necessary information. The device then presents this information to the user and provides feedback tailored to the user's emotional state.

[0376] Specific example

[0377] For example, if a user seeks information about relaxation due to work stress, the emotional engine detects a heightened stress level, and the server adjusts to prioritize providing information on videos and music specifically designed for relaxation. In this way, information tailored to the user's needs is provided.

[0378] This system enables the efficient integration of multilingual information and the customization of information to respond to user emotions, resulting in the provision of advanced information tailored to individual needs.

[0379] The following describes the processing flow.

[0380] Step 1:

[0381] The user enters a request for specific information through their device. In doing so, the user specifies the topics or information they are interested in.

[0382] Step 2:

[0383] The terminal receives the user's request and sends its contents to the server. The server parses the request and generates a search query to collect the appropriate information.

[0384] Step 3:

[0385] Based on the generated queries, the server collects relevant multilingual data from the internet and databases. Since this data may exist in different languages, the server categorizes each piece of data using language tags.

[0386] Step 4:

[0387] The server converts the collected multilingual data into a unified format using natural language processing techniques. This process utilizes machine translation technology to standardize different languages.

[0388] Step 5:

[0389] The emotion engine analyzes user input on the device and evaluates the user's emotional state in real time. This evaluation result is sent to the server and considered when providing information.

[0390] Step 6:

[0391] The server compresses the converted information and stores it in a database. The compressed data is then used to train an AI model, improving the information's effectiveness and relevance to the user.

[0392] Step 7:

[0393] When a user requests specific, emotionally relevant answers through their device, the server searches for the most appropriate information based on its learned knowledge.

[0394] Step 8:

[0395] The server customizes the search results to match the user's emotional state. The device then translates this information back into the appropriate language and presents it to the user.

[0396] Step 9:

[0397] The information displayed by the device to the user is tailored to the user's emotions, excluding information they dislike or find inappropriate. This allows the user to enjoy a consistent content experience.

[0398] (Example 2)

[0399] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0400] Because multilingual information is scattered across the internet, there is a need to address the challenge of users having difficulty quickly and efficiently obtaining information that is relevant to their emotional state. Furthermore, it is necessary to improve the quality of the information provided by appropriately organizing, translating, and presenting it.

[0401] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0402] In this invention, the server includes means for collecting multilingual information, means for converting the collected multilingual information into a unified format, and means for analyzing the user's emotional state. This makes it possible to provide information optimized to the user's emotions and needs.

[0403] "Multilingual information" refers to a collection of information provided in different languages, and the data collected through the internet and databases.

[0404] A "unified format" is a format that standardizes and maintains consistency for information in different languages ​​and formats.

[0405] "Compression" refers to the process of reducing the data size of information to make storage and transfer more efficient.

[0406] "Machine learning" is the process by which algorithms learn patterns using collected data and train models.

[0407] "User emotional state" refers to the psychological state that can be inferred from the user's input and actions.

[0408] "Customization" refers to tailoring and providing information and services based on the user's specific requests and conditions.

[0409] In order to implement this invention, the server, terminal, and user must cooperate to configure the system. Specifically, it is implemented as follows.

[0410] The server receives multilingual information collected from terminals via the internet and databases. The received information is converted into a unified format using natural language processing techniques. This process can utilize natural language processing libraries such as spaCy and NLTK as software libraries. Furthermore, commonly available machine translation APIs are used as translation APIs for the conversion to the unified format.

[0411] The server further compresses the converted information and stores it efficiently. A NoSQL database is suitable for this purpose. Machine learning is performed on the stored data using a generative AI model. Examples of AI models used include BERT and OpenAI GPT.

[0412] The terminal collects necessary multilingual information in response to user requests and sends it to the server. The terminal also incorporates an emotion engine that analyzes user requests and comments to infer their psychological state. This uses an emotion analysis model to recognize the user's emotional state in real time.

[0413] When a user requests specific information through their device, the server customizes and provides the most relevant information to the device based on the generated learning results and the user's emotional state.

[0414] As a concrete example, consider a scenario where a user requests information about relaxation. For instance, the user might enter a prompt into their device saying, "Please suggest relaxation methods that would be helpful when I'm feeling stressed." The emotion engine detects the user's stress level, and the server adjusts to provide relaxation-focused information accordingly. In this way, it becomes possible to provide information that matches the user's emotions and needs.

[0415] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0416] Step 1:

[0417] The terminal receives search keywords and requests from the user. The information entered by the user is a specific request, such as "relaxation methods" or "latest news." Based on this input, the terminal uses the internet and default database APIs to collect relevant information from multilingual sources. The collected data is sent to the backend in JSON or XML format.

[0418] Step 2:

[0419] The server receives multilingual information sent from the terminal. The server uses a natural language processing library to classify the received information into specific categories. The classified data is converted into a unified format via a machine translation API. Here, the input is unstructured multilingual data, and the output is structured data in a unified format.

[0420] Step 3:

[0421] The server compresses the converted, unified format data and stores it in the database. It applies the optimal compression technique to minimize data size. The input is the unified format data, and the output is the compressed data. An index is also automatically generated for the stored data to support efficient searching.

[0422] Step 4:

[0423] The server trains on stored compressed data using a generating AI model. The training process extracts patterns from the dataset and optimizes future information delivery strategies. The input to this step is compressed information, and the output is the trained AI model.

[0424] Step 5:

[0425] The device passes real-time user input information to the emotion engine, which analyzes the user's psychological state. This analysis step aims to provide advanced information based on the user's emotions and uses a BERT-based emotion analysis model. The input to the analysis is the user's comments and requests, and the output is an evaluation of the user's emotional state.

[0426] Step 6:

[0427] The server selects the most relevant information for the user based on the user's sentiment data and a trained model, and sends it to the terminal. The input to this process is sentiment data and the trained model, while the output is a customized set of information. The terminal presents this information to the user and also includes appropriate feedback functions.

[0428] In this way, the system provides personalized information to users, achieving the integration of multilingual information and the delivery of information that is sensitive to emotions.

[0429] (Application Example 2)

[0430] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0431] In modern society, providing efficient and emotionally sensitive information to a large number of users who speak different languages ​​is a major challenge. Conventional systems struggle to provide personalized information that considers multiple languages ​​and user emotional states, and there is a particular need to facilitate communication among international users. Furthermore, the processing and integration of multilingual information involves a massive amount of data, necessitating improvements in processing efficiency. Moreover, current technologies have not adequately achieved the ability to appropriately adjust and deliver information based on user emotions.

[0432] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0433] In this invention, the server includes means for acquiring multilingual information, means for converting the acquired multilingual information into a unified format, and means for performing sentiment analysis and customizing and providing information based on the user's emotional state. This makes it possible to provide personalized multilingual information that takes the user's emotional state into consideration.

[0434] "Multilingual information" refers to information written in multiple different languages.

[0435] A "unified format" refers to a state where data from different formats has been converted into a single, consistent format.

[0436] "Emotional analysis" refers to a technology that analyzes a user's facial expressions and voice to detect their emotional state.

[0437] "Customization" refers to appropriately adjusting and providing information and services based on the individual needs and circumstances of the user.

[0438] "Real-time" refers to a situation where processing or responses occur immediately, with virtually no time delay.

[0439] A "sensor" is a device that detects physical changes and outputs them as signals.

[0440] An "interface" refers to a common means or standard for different systems or devices to exchange information.

[0441] "Information provision" refers to the act of providing users with requested data or knowledge.

[0442] This invention begins with a user terminal acquiring multilingual information from the internet or other sources and sending it to a server. The server uses natural language processing technology to convert the information in each language into a unified format and stores the compressed data. The stored data can be quickly searched using an index, enabling efficient information provision. Furthermore, the user's emotional state is detected by an emotion analysis engine installed in the terminal. This engine analyzes the user's current emotions in real time based on input from sensors (e.g., camera and microphone) and transmits the analysis to the server.

[0443] When the server receives an information request from a user, it considers this sentiment information and generates customized information using a trained AI model. This customized information is provided through the interface in the user's language. Smooth information delivery across different languages ​​is crucial, and the generative AI model handles multilingual translation and content adjustment.

[0444] For example, if a user requests relaxation-related information in a stressful situation, the device's emotion analysis engine will detect the stress level, and the server will adjust its settings to prioritize providing relaxing music or videos. A possible prompt for this purpose might be, "What relaxing content should be provided when the user is feeling stressed?"

[0445] This allows users to instantly obtain information that suits their emotions, resulting in a more personalized user experience.

[0446] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0447] Step 1:

[0448] The user requests information using a terminal. The terminal receives the user's voice or text input, and the sentiment analysis engine starts working. This analyzes the user's current emotional state in real time, structures the information, and sends it to the server.

[0449] Step 2:

[0450] The server receives a multilingual information request sent from the terminal. It collects information in the requested language from the internet and other databases. This completes the collection of multilingual data, preparing it for the next step.

[0451] Step 3:

[0452] The server uses natural language processing technology to convert the collected multilingual data into a unified format. The input multilingual data is analyzed and organized into a unified format. The converted data is consistent, which streamlines subsequent processing.

[0453] Step 4:

[0454] The server compresses the data, which has been converted to a unified format, and stores it in a database for storage. This step uses a specialized algorithm to preserve information while minimizing data size. An index is then generated to streamline subsequent searches.

[0455] Step 5:

[0456] The server uses stored data to train an AI model and prepares customized information delivery based on the user's emotional state. The trained model then forms the foundation for specific information selection as a generative AI model.

[0457] Step 6:

[0458] The server considers the user's emotional data from the emotion analysis engine and uses a trained AI model to select information appropriate for the user. Based on the emotional state and requests, appropriate content (e.g., relaxing music or videos) is selected.

[0459] Step 7:

[0460] The server provides the selected information to the terminal. The terminal then presents the information through its interface, tailored to the user's language. This allows the user to obtain real-time, customized information.

[0461] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0462] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0463] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0464] [Third Embodiment]

[0465] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0466] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0467] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0468] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0469] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0470] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0471] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0472] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0473] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0474] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0475] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0476] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0477] This invention provides a system that efficiently collects information provided in multiple languages, converts and compresses it into a unified format, and uses artificial intelligence for learning. This system operates through the collaboration of a server, terminals, and users, enabling the handling of multilingual information in a unified format.

[0478] Data collection and conversion

[0479] The terminal retrieves multilingual data from the internet and various databases. During this process, data is collected from information sources specified by the user and sent to the server. The server receives this data and converts it into a standardized language format, taking language differences into account. Machine translation and natural language processing technologies are used for this conversion.

[0480] Data compression and storage

[0481] The server parses the converted standard format data and compresses redundant information. The compressed data is indexed and stored in a database to enable effective searching and use. The stored data is later utilized in a learning process.

[0482] Learning process

[0483] The server uses the stored data to train the AI ​​model. In this training process, unified information is used as the overall dataset, and the AI ​​learns new knowledge. Based on the results of this learning, the terminal prepares to provide information according to the user's requests.

[0484] Information provision and response

[0485] When a user requests specific information, the device accesses the server to retrieve the necessary knowledge. The server uses its learned results to respond with the most relevant information to the user's request. The device then translates that information back into the user's native language or a specified language and displays it in an easy-to-understand format.

[0486] Specific example

[0487] For example, if a user seeks information on engineering papers written in multiple languages, the terminal collects the necessary paper data, and the server converts it into a unified format for learning. By providing the optimal answer to the user's specific question based on the learned knowledge, information can be obtained across language barriers. In this way, the present invention supports the efficient use of information and the creation of new knowledge.

[0488] The following describes the processing flow.

[0489] Step 1:

[0490] The user specifies the source of multilingual information via the terminal and inputs the type and scope of data they wish to collect. The terminal then collects the relevant information from the internet and various databases according to the user's specifications.

[0491] Step 2:

[0492] The terminal sends the collected multilingual data to the server. The server analyzes the received data, assigns language tags to each piece of data, and classifies it. This classification prepares each piece of language data for appropriate processing.

[0493] Step 3:

[0494] The server utilizes natural language processing technology to convert the collected multilingual data into a unified format. This conversion process uses translation techniques to analyze the context and meaning between different languages ​​and arrange them into a unified format.

[0495] Step 4:

[0496] The server compresses the data after it has been converted to a unified format. This compression process removes redundant information and duplicate data, reducing the amount of data. The compressed information is then indexed to enable effective searching and storage, and stored in a database.

[0497] Step 5:

[0498] The server uses the stored data to train the AI ​​model. In this learning process, the AI ​​model acquires new knowledge based on the integrated information and understands the overall context of the data.

[0499] Step 6:

[0500] When a user requests specific information via a device, the device sends the request to the server. The server scrutinizes the requested information based on its learned knowledge and quickly searches for data that matches the user's request.

[0501] Step 7:

[0502] After the server retrieves the search results, it re-translates them into the user's preferred language as needed. The terminal displays the data received from the server in a user-friendly format. It also ensures that the information provided to the user is specific and appropriate.

[0503] (Example 1)

[0504] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0505] In recent years, while the amount of information provided in multiple languages ​​has increased, there is a growing need for effective ways to utilize it. The lack of systems to integrate information across different languages ​​and efficiently use it for learning and retrieval hinders its effective use. Furthermore, it is crucial to transfer acquired multilingual data quickly and securely, and to easily access information in the user's native language or a specified language.

[0506] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0507] In this invention, the server includes a device for acquiring multilingual information, a device for converting the acquired multilingual information into a unified format, a device for compressing and storing the converted information, a device for performing learning using the unified information, a device for providing the learned information according to the user's request, a device for collecting data based on a user-specified information source, a communication device for securely transferring the collected data, and a device for re-converting the learned information and displaying it in a specified language. This makes it possible to centrally manage and efficiently utilize information in different languages.

[0508] "Multilingual information" refers to various types of data and knowledge provided in different languages.

[0509] A "unified format" refers to a standardized format used to organize data expressed in multiple different languages ​​or formats into a consistent format.

[0510] "Compression" refers to the process of removing redundancy from information to reduce the amount of data, thereby improving the efficiency of storage and transfer.

[0511] "Storage devices" refer to tools and hardware used to physically or digitally record data and maintain it in a state that makes it accessible at a later date.

[0512] "A device for learning" refers to a computer or algorithm used to analyze data and extract patterns and knowledge.

[0513] "User" refers to a person or organization that requests information through the system and receives the results.

[0514] "Communication equipment" refers to hardware or software used to send and receive data with other devices or networks.

[0515] A "catalog" refers to an index associated with data, used to quickly search for and access that information.

[0516] This invention is a system for efficiently acquiring, converting, and compressing information provided in multiple languages, learning from it using artificial intelligence, and providing it to users. The system is primarily operated through the collaboration of a server, terminals, and users.

[0517] The device collects multilingual data from the internet and various databases based on information sources specified by the user. This collection uses common programming languages ​​such as Python and JavaScript, and utilizes APIs and web scraping techniques via an internet connection.

[0518] The data collected by the device is securely transferred to the server. Security technologies such as the SSL / TLS protocol are applied during the transfer. The server analyzes the received data and converts it into a standardized language format using machine translation services such as the Google Translate API or NLP libraries (e.g., NLTK, spaCy).

[0519] The converted data is compressed using compression algorithms such as Gzip or Zstandard to remove redundant information and save it. The compressed data is then indexed using an information retrieval system such as Elasticsearch, enabling rapid searching.

[0520] The server trains the generative AI model using compressed and stored data. Deep learning frameworks such as PyTorch and TensorFlow are used for model training, and processing is accelerated using GPUs and TPUs.

[0521] When a user requests information, the device retrieves the learned information from the server. For example, if a user requests "information about 2023 technology trends using a generative AI model," the server generates the optimal answer from its trained model. The device then translates this information into the user's specified language and displays it clearly on a web browser using HTML and CSS.

[0522] This system allows users to acquire information comprehensively, transcending language barriers, and efficiently utilize new knowledge.

[0523] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0524] Step 1:

[0525] The device receives information sources specified by the user and accesses the internet and databases to retrieve multilingual data. For example, if the user specifies a particular news site, the device will scrape articles from that site. The input is the URL or API key of the information source, and the output is raw data in multiple languages.

[0526] The process involves web scraping using Python libraries and data retrieval via APIs.

[0527] Step 2:

[0528] The terminal securely transfers the acquired multilingual data to the server using the SSL / TLS protocol. The input is the raw data acquired in step 1, and the output is the data securely sent to the server.

[0529] Specifically, the process involves sending data via HTTP requests and performing secure communication.

[0530] Step 3:

[0531] The server analyzes the received multilingual data and converts it into a standardized language format. This process utilizes the Google Translate API and NLP libraries. Input is raw data from the terminal, and output is data in a unified format.

[0532] We use natural language processing techniques to standardize data and perform translation.

[0533] Step 4:

[0534] The server compresses standardized format data and stores it in the database. Compression is performed using Gzip, and the data is indexed in Elasticsearch. The input is standardized data, and the output is compressed and stored data.

[0535] A compression algorithm is applied to persistently store information in data storage.

[0536] Step 5:

[0537] The server uses stored data to train a generative AI model. The input is a compressed dataset, and the output is the trained AI model. Model optimization is performed using PyTorch or TensorFlow.

[0538] Computational resources are used to carry out an intensive training process for the model.

[0539] Step 6:

[0540] When a user requests information, the device retrieves the learned information via the server. For example, if a user wants to know about technology trends in 2023, the server parses the request and returns the most relevant information from the training data. The input is the user's prompt, and the output is the answer to the user's question.

[0541] Data retrieval and generation of necessary information are performed based on the information request.

[0542] Step 7:

[0543] The terminal re-translates the information provided to the user into the specified language and displays it in the appropriate format. Input is response data from the server, and output is the user's visual information.

[0544] The information is converted into a visual display format using HTML and CSS, and presented to aid user understanding.

[0545] (Application Example 1)

[0546] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0547] There is a need for a system that can efficiently collect vast amounts of information written in multiple languages ​​and provide it to users in a unified format. Furthermore, there is a lack of technology to optimize multilingual information according to user-specified themes and language settings, and to quickly provide information tailored to user interests.

[0548] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0549] In this invention, the server includes means for acquiring multilingual information, means for converting the acquired multilingual information into a unified format, means for compressing and storing the converted information, means for performing learning using the unified information, means for providing the learned information according to the user's request, means for collecting relevant content based on a theme specified by the user, and means for displaying the information in a format optimized for the user's language settings. This enables efficient collection of multilingual information and optimized information provision.

[0550] "Multilingual information" refers to all information obtained across different languages, including data that is processed uniformly while taking language differences into account.

[0551] "Means of acquisition" refers to the technologies and devices used to collect the target information from the internet or databases.

[0552] "Means of converting to a unified format" refers to the process of converting information written in different languages ​​or formats into a standardized, consistent format.

[0553] "Methods of compression and storage" refer to technologies that reduce the amount of information and store it, with the aim of eliminating redundancy and saving it efficiently.

[0554] "Means of learning" refers to the process by which an artificial intelligence model extracts new insights and relationships through learning, based on accumulated unified data.

[0555] "Means of providing information in response to user requests" refers to technologies that provide information that meets user needs at the appropriate time.

[0556] "Means of collecting relevant content based on a theme" refers to the process of appropriately collecting information and content that aligns with the theme specified by the user.

[0557] "Means of displaying information in a format optimized for language settings" refers to technologies that display information in the most optimal way, tailored to the user's language settings.

[0558] To implement this invention, the server, terminals, and users must collaborate to build the system. The server plays a central role in efficiently processing content provided in various languages ​​and utilizes a cloud server. Specifically, infrastructure such as Amazon Web Services (AWS) or Google Cloud Platform is suitable.

[0559] Data collection

[0560] The device collects multilingual data from the internet according to the user's instructions. This involves using smartphones or computers, employing scraping techniques with programming languages ​​such as Python.

[0561] Data conversion

[0562] The server translates the acquired multilingual data and converts it into a unified format. Google Translate API and Microsoft Azure's natural language processing technology are used here.

[0563] Data compression and storage

[0564] The converted data is compressed on the server using zlib with Python. The compressed data is then stored in a database such as MySQL.

[0565] Learning process

[0566] The server trains generative AI models using machine learning libraries such as TensorFlow. It analyzes compressed data and extracts relationships and patterns.

[0567] Providing information

[0568] Users access the server through their devices and request information based on specific themes and language settings. The server provides the most relevant information in response to the user's request and displays it on the device. Smartphones and computers fulfill this role.

[0569] A concrete example is the multilingual news app "GlobalReview." It allows users to collect news related to "environmental issues," translate it into the most suitable language, and display it. This system helps to smoothly deliver multilingual information to users.

[0570] Prompt example:

[0571] "Please collect and translate the latest multilingual news articles on environmental issues."

[0572] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0573] Step 1:

[0574] The device collects multilingual data related to a specific theme from the internet based on user instructions. The input is a search keyword specified by the user, and the output is a collection of related information. This process involves using scraping techniques to extract information from web pages and databases.

[0575] Step 2:

[0576] The terminal sends the collected data to the server. The input is raw data captured in multiple languages, and the output is data securely transmitted to the server. This step involves ensuring that the data is securely transferred using data encryption and communication protocols (HTTP or HTTPS).

[0577] Step 3:

[0578] The server converts the received multilingual data into a standard format using the Google Translate API and Microsoft Azure's natural language processing technology. The input is multilingual data, and the output is data in a unified format. This conversion includes the operation of linguistically standardizing the data through machine translation.

[0579] Step 4:

[0580] The server compresses data in a unified format using the Python zlib library and stores it in a MySQL database. The input is the converted data, and the output is the compressed and stored data. This step involves operations that compress the data and ensure efficient storage.

[0581] Step 5:

[0582] The server uses compressed data to train a generative AI model using libraries such as TensorFlow. The input is compressed data, and the output is the training result of the AI ​​model. This training process extracts relevant content patterns.

[0583] Step 6:

[0584] The user operates the terminal and requests information based on their preferred topics and language settings. The input is the user's request, and the output is the corresponding information. This step involves the user making a request for information retrieval through the terminal's interface.

[0585] Step 7:

[0586] The server searches for the most relevant information based on the user's request and provides it to the terminal. The input consists of a trained model and the user's request, while the output is information provided in an optimized format. This process involves rapid data retrieval and delivery of information in a format tailored to the user's preferences.

[0587] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0588] This invention provides a system for integrating information provided in multiple languages ​​into a unified format, and further recognizing and utilizing user emotions in information delivery. This system operates through the cooperation of a server, terminal, user, and emotion engine.

[0589] Collection and processing of multilingual information

[0590] The terminal collects multilingual data from the internet and various databases based on user requests. The collected data is sent to a server, which automatically classifies the information and converts it into a unified format using natural language processing technology. This step ensures information consistency and enables efficient management.

[0591] Utilizing the Emotion Engine

[0592] This system includes an emotion engine that detects the user's emotional state. When a user enters an information request or comment through a terminal, the emotion engine analyzes it and infers the user's emotional state in real time. This information is sent to the server and taken into consideration when providing information.

[0593] Information compression and learning

[0594] The server compresses and stores the converted information and uses an AI model for training. This process efficiently integrates information and lays the foundation for providing appropriate information based on the user's emotional state.

[0595] Customized information provision

[0596] When a user requests specific information, the device accesses the server to retrieve learned results. The server considers the user's emotional information obtained from the emotion engine and customizes and selects the necessary information. The device then presents this information to the user and provides feedback tailored to the user's emotional state.

[0597] Specific example

[0598] For example, if a user seeks information about relaxation due to work stress, the emotional engine detects a heightened stress level, and the server adjusts to prioritize providing information on videos and music specifically designed for relaxation. In this way, information tailored to the user's needs is provided.

[0599] This system enables the efficient integration of multilingual information and the customization of information to respond to user emotions, resulting in the provision of advanced information tailored to individual needs.

[0600] The following describes the processing flow.

[0601] Step 1:

[0602] The user enters a request for specific information through their device. In doing so, the user specifies the topics or information they are interested in.

[0603] Step 2:

[0604] The terminal receives the user's request and sends its contents to the server. The server parses the request and generates a search query to collect the appropriate information.

[0605] Step 3:

[0606] Based on the generated queries, the server collects relevant multilingual data from the internet and databases. Since this data may exist in different languages, the server categorizes each piece of data using language tags.

[0607] Step 4:

[0608] The server converts the collected multilingual data into a unified format using natural language processing techniques. This process utilizes machine translation technology to standardize different languages.

[0609] Step 5:

[0610] The emotion engine analyzes user input on the device and evaluates the user's emotional state in real time. This evaluation result is sent to the server and considered when providing information.

[0611] Step 6:

[0612] The server compresses the converted information and stores it in a database. The compressed data is then used to train an AI model, improving the information's effectiveness and relevance to the user.

[0613] Step 7:

[0614] When a user requests specific, emotionally relevant answers through their device, the server searches for the most appropriate information based on its learned knowledge.

[0615] Step 8:

[0616] The server customizes the search results to match the user's emotional state. The device then translates this information back into the appropriate language and presents it to the user.

[0617] Step 9:

[0618] The information displayed by the device to the user is tailored to the user's emotions, excluding information they dislike or find inappropriate. This allows the user to enjoy a consistent content experience.

[0619] (Example 2)

[0620] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0621] Because multilingual information is scattered across the internet, there is a need to address the challenge of users having difficulty quickly and efficiently obtaining information that is relevant to their emotional state. Furthermore, it is necessary to improve the quality of the information provided by appropriately organizing, translating, and presenting it.

[0622] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0623] In this invention, the server includes means for collecting multilingual information, means for converting the collected multilingual information into a unified format, and means for analyzing the user's emotional state. This makes it possible to provide information optimized to the user's emotions and needs.

[0624] "Multilingual information" refers to a collection of information provided in different languages, and the data collected through the internet and databases.

[0625] A "unified format" is a format that standardizes and maintains consistency for information in different languages ​​and formats.

[0626] "Compression" refers to the process of reducing the data size of information to make storage and transfer more efficient.

[0627] "Machine learning" is the process by which algorithms learn patterns using collected data and train models.

[0628] "User emotional state" refers to the psychological state that can be inferred from the user's input and actions.

[0629] "Customization" refers to tailoring and providing information and services based on the user's specific requests and conditions.

[0630] In order to implement this invention, the server, terminal, and user must cooperate to configure the system. Specifically, it is implemented as follows.

[0631] The server receives multilingual information collected from terminals via the internet and databases. The received information is converted into a unified format using natural language processing techniques. This process can utilize natural language processing libraries such as spaCy and NLTK as software libraries. Furthermore, commonly available machine translation APIs are used as translation APIs for the conversion to the unified format.

[0632] The server further compresses the converted information and stores it efficiently. A NoSQL database is suitable for this purpose. Machine learning is performed on the stored data using a generative AI model. Examples of AI models used include BERT and OpenAI GPT.

[0633] The terminal collects necessary multilingual information in response to user requests and sends it to the server. The terminal also incorporates an emotion engine that analyzes user requests and comments to infer their psychological state. This uses an emotion analysis model to recognize the user's emotional state in real time.

[0634] When a user requests specific information through their device, the server customizes and provides the most relevant information to the device based on the generated learning results and the user's emotional state.

[0635] As a concrete example, consider a scenario where a user requests information about relaxation. For instance, the user might enter a prompt into their device saying, "Please suggest relaxation methods that would be helpful when I'm feeling stressed." The emotion engine detects the user's stress level, and the server adjusts to provide relaxation-focused information accordingly. In this way, it becomes possible to provide information that matches the user's emotions and needs.

[0636] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0637] Step 1:

[0638] The terminal receives search keywords and requests from the user. The information entered by the user is a specific request, such as "relaxation methods" or "latest news." Based on this input, the terminal uses the internet and default database APIs to collect relevant information from multilingual sources. The collected data is sent to the backend in JSON or XML format.

[0639] Step 2:

[0640] The server receives multilingual information sent from the terminal. The server uses a natural language processing library to classify the received information into specific categories. The classified data is converted into a unified format via a machine translation API. Here, the input is unstructured multilingual data, and the output is structured data in a unified format.

[0641] Step 3:

[0642] The server compresses the converted, unified format data and stores it in the database. It applies the optimal compression technique to minimize data size. The input is the unified format data, and the output is the compressed data. An index is also automatically generated for the stored data to support efficient searching.

[0643] Step 4:

[0644] The server trains on stored compressed data using a generating AI model. The training process extracts patterns from the dataset and optimizes future information delivery strategies. The input to this step is compressed information, and the output is the trained AI model.

[0645] Step 5:

[0646] The device passes real-time user input information to the emotion engine, which analyzes the user's psychological state. This analysis step aims to provide advanced information based on the user's emotions and uses a BERT-based emotion analysis model. The input to the analysis is the user's comments and requests, and the output is an evaluation of the user's emotional state.

[0647] Step 6:

[0648] The server selects the most relevant information for the user based on the user's sentiment data and a trained model, and sends it to the terminal. The input to this process is sentiment data and the trained model, while the output is a customized set of information. The terminal presents this information to the user and also includes appropriate feedback functions.

[0649] In this way, the system provides personalized information to users, achieving the integration of multilingual information and the delivery of information that is sensitive to emotions.

[0650] (Application Example 2)

[0651] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0652] In modern society, providing efficient and emotionally sensitive information to a large number of users who speak different languages ​​is a major challenge. Conventional systems struggle to provide personalized information that considers multiple languages ​​and user emotional states, and there is a particular need to facilitate communication among international users. Furthermore, the processing and integration of multilingual information involves a massive amount of data, necessitating improvements in processing efficiency. Moreover, current technologies have not adequately achieved the ability to appropriately adjust and deliver information based on user emotions.

[0653] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0654] In this invention, the server includes means for acquiring multilingual information, means for converting the acquired multilingual information into a unified format, and means for performing sentiment analysis and customizing and providing information based on the user's emotional state. This makes it possible to provide personalized multilingual information that takes the user's emotional state into consideration.

[0655] "Multilingual information" refers to information written in multiple different languages.

[0656] A "unified format" refers to a state where data from different formats has been converted into a single, consistent format.

[0657] "Emotional analysis" refers to a technology that analyzes a user's facial expressions and voice to detect their emotional state.

[0658] "Customization" refers to appropriately adjusting and providing information and services based on the individual needs and circumstances of the user.

[0659] "Real-time" refers to a situation where processing or responses occur immediately, with virtually no time delay.

[0660] A "sensor" is a device that detects physical changes and outputs them as signals.

[0661] An "interface" refers to a common means or standard for different systems or devices to exchange information.

[0662] "Information provision" refers to the act of providing users with requested data or knowledge.

[0663] This invention begins with a user terminal acquiring multilingual information from the internet or other sources and sending it to a server. The server uses natural language processing technology to convert the information in each language into a unified format and stores the compressed data. The stored data can be quickly searched using an index, enabling efficient information provision. Furthermore, the user's emotional state is detected by an emotion analysis engine installed in the terminal. This engine analyzes the user's current emotions in real time based on input from sensors (e.g., camera and microphone) and transmits the analysis to the server.

[0664] When the server receives an information request from a user, it considers this sentiment information and generates customized information using a trained AI model. This customized information is provided through the interface in the user's language. Smooth information delivery across different languages ​​is crucial, and the generative AI model handles multilingual translation and content adjustment.

[0665] For example, if a user requests relaxation-related information in a stressful situation, the device's emotion analysis engine will detect the stress level, and the server will adjust its settings to prioritize providing relaxing music or videos. A possible prompt for this purpose might be, "What relaxing content should be provided when the user is feeling stressed?"

[0666] This allows users to instantly obtain information that suits their emotions, resulting in a more personalized user experience.

[0667] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0668] Step 1:

[0669] The user requests information using a terminal. The terminal receives the user's voice or text input, and the sentiment analysis engine starts working. This analyzes the user's current emotional state in real time, structures the information, and sends it to the server.

[0670] Step 2:

[0671] The server receives a multilingual information request sent from the terminal. It collects information in the requested language from the internet and other databases. This completes the collection of multilingual data, preparing it for the next step.

[0672] Step 3:

[0673] The server uses natural language processing technology to convert the collected multilingual data into a unified format. The input multilingual data is analyzed and organized into a unified format. The converted data is consistent, which streamlines subsequent processing.

[0674] Step 4:

[0675] The server compresses the data, which has been converted to a unified format, and stores it in a database for storage. This step uses a specialized algorithm to preserve information while minimizing data size. An index is then generated to streamline subsequent searches.

[0676] Step 5:

[0677] The server uses stored data to train an AI model and prepares customized information delivery based on the user's emotional state. The trained model then forms the foundation for specific information selection as a generative AI model.

[0678] Step 6:

[0679] The server considers the user's emotional data from the emotion analysis engine and uses a trained AI model to select information appropriate for the user. Based on the emotional state and requests, appropriate content (e.g., relaxing music or videos) is selected.

[0680] Step 7:

[0681] The server provides the selected information to the terminal. The terminal then presents the information through its interface, tailored to the user's language. This allows the user to obtain real-time, customized information.

[0682] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0683] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0684] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0685] [Fourth Embodiment]

[0686] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0687] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0688] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0689] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0690] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0691] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0692] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0693] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0694] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0695] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0696] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0697] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0698] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0699] This invention provides a system that efficiently collects information provided in multiple languages, converts and compresses it into a unified format, and uses artificial intelligence for learning. This system operates through the collaboration of a server, terminals, and users, enabling the handling of multilingual information in a unified format.

[0700] Data collection and conversion

[0701] The terminal retrieves multilingual data from the internet and various databases. During this process, data is collected from information sources specified by the user and sent to the server. The server receives this data and converts it into a standardized language format, taking language differences into account. Machine translation and natural language processing technologies are used for this conversion.

[0702] Data compression and storage

[0703] The server parses the converted standard format data and compresses redundant information. The compressed data is indexed and stored in a database to enable effective searching and use. The stored data is later utilized in a learning process.

[0704] Learning process

[0705] The server uses the stored data to train the AI ​​model. In this training process, unified information is used as the overall dataset, and the AI ​​learns new knowledge. Based on the results of this learning, the terminal prepares to provide information according to the user's requests.

[0706] Information provision and response

[0707] When a user requests specific information, the device accesses the server to retrieve the necessary knowledge. The server uses its learned results to respond with the most relevant information to the user's request. The device then translates that information back into the user's native language or a specified language and displays it in an easy-to-understand format.

[0708] Specific example

[0709] For example, if a user seeks information on engineering papers written in multiple languages, the terminal collects the necessary paper data, and the server converts it into a unified format for learning. By providing the optimal answer to the user's specific question based on the learned knowledge, information can be obtained across language barriers. In this way, the present invention supports the efficient use of information and the creation of new knowledge.

[0710] The following describes the processing flow.

[0711] Step 1:

[0712] The user specifies the source of multilingual information via the terminal and inputs the type and scope of data they wish to collect. The terminal then collects the relevant information from the internet and various databases according to the user's specifications.

[0713] Step 2:

[0714] The terminal sends the collected multilingual data to the server. The server analyzes the received data, assigns language tags to each piece of data, and classifies it. This classification prepares each piece of language data for appropriate processing.

[0715] Step 3:

[0716] The server utilizes natural language processing technology to convert the collected multilingual data into a unified format. This conversion process uses translation techniques to analyze the context and meaning between different languages ​​and arrange them into a unified format.

[0717] Step 4:

[0718] The server compresses the data after it has been converted to a unified format. This compression process removes redundant information and duplicate data, reducing the amount of data. The compressed information is then indexed to enable effective searching and storage, and stored in a database.

[0719] Step 5:

[0720] The server uses the stored data to train the AI ​​model. In this learning process, the AI ​​model acquires new knowledge based on the integrated information and understands the overall context of the data.

[0721] Step 6:

[0722] When a user requests specific information via a device, the device sends the request to the server. The server scrutinizes the requested information based on its learned knowledge and quickly searches for data that matches the user's request.

[0723] Step 7:

[0724] After the server retrieves the search results, it re-translates them into the user's preferred language as needed. The terminal displays the data received from the server in a user-friendly format. It also ensures that the information provided to the user is specific and appropriate.

[0725] (Example 1)

[0726] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0727] In recent years, while the amount of information provided in multiple languages ​​has increased, there is a growing need for effective ways to utilize it. The lack of systems to integrate information across different languages ​​and efficiently use it for learning and retrieval hinders its effective use. Furthermore, it is crucial to transfer acquired multilingual data quickly and securely, and to easily access information in the user's native language or a specified language.

[0728] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0729] In this invention, the server includes a device for acquiring multilingual information, a device for converting the acquired multilingual information into a unified format, a device for compressing and storing the converted information, a device for performing learning using the unified information, a device for providing the learned information according to the user's request, a device for collecting data based on a user-specified information source, a communication device for securely transferring the collected data, and a device for re-converting the learned information and displaying it in a specified language. This makes it possible to centrally manage and efficiently utilize information in different languages.

[0730] "Multilingual information" refers to various types of data and knowledge provided in different languages.

[0731] A "unified format" refers to a standardized format used to organize data expressed in multiple different languages ​​or formats into a consistent format.

[0732] "Compression" refers to the process of removing redundancy from information to reduce the amount of data, thereby improving the efficiency of storage and transfer.

[0733] "Storage devices" refer to tools and hardware used to physically or digitally record data and maintain it in a state that makes it accessible at a later date.

[0734] "A device for learning" refers to a computer or algorithm used to analyze data and extract patterns and knowledge.

[0735] "User" refers to a person or organization that requests information through the system and receives the results.

[0736] "Communication equipment" refers to hardware or software used to send and receive data with other devices or networks.

[0737] A "catalog" refers to an index associated with data, used to quickly search for and access that information.

[0738] This invention is a system for efficiently acquiring, converting, and compressing information provided in multiple languages, learning from it using artificial intelligence, and providing it to users. The system is primarily operated through the collaboration of a server, terminals, and users.

[0739] The device collects multilingual data from the internet and various databases based on information sources specified by the user. This collection uses common programming languages ​​such as Python and JavaScript, and utilizes APIs and web scraping techniques via an internet connection.

[0740] The data collected by the device is securely transferred to the server. Security technologies such as the SSL / TLS protocol are applied during the transfer. The server analyzes the received data and converts it into a standardized language format using machine translation services such as the Google Translate API or NLP libraries (e.g., NLTK, spaCy).

[0741] The converted data is compressed using compression algorithms such as Gzip or Zstandard to remove redundant information and save it. The compressed data is then indexed using an information retrieval system such as Elasticsearch, enabling rapid searching.

[0742] The server trains the generative AI model using compressed and stored data. Deep learning frameworks such as PyTorch and TensorFlow are used for model training, and processing is accelerated using GPUs and TPUs.

[0743] When a user requests information, the device retrieves the learned information from the server. For example, if a user requests "information about 2023 technology trends using a generative AI model," the server generates the optimal answer from its trained model. The device then translates this information into the user's specified language and displays it clearly on a web browser using HTML and CSS.

[0744] This system allows users to acquire information comprehensively, transcending language barriers, and efficiently utilize new knowledge.

[0745] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0746] Step 1:

[0747] The device receives information sources specified by the user and accesses the internet and databases to retrieve multilingual data. For example, if the user specifies a particular news site, the device will scrape articles from that site. The input is the URL or API key of the information source, and the output is raw data in multiple languages.

[0748] The process involves web scraping using Python libraries and data retrieval via APIs.

[0749] Step 2:

[0750] The terminal securely transfers the acquired multilingual data to the server using the SSL / TLS protocol. The input is the raw data acquired in step 1, and the output is the data securely sent to the server.

[0751] Specifically, the process involves sending data via HTTP requests and performing secure communication.

[0752] Step 3:

[0753] The server analyzes the received multilingual data and converts it into a standardized language format. This process utilizes the Google Translate API and NLP libraries. Input is raw data from the terminal, and output is data in a unified format.

[0754] We use natural language processing techniques to standardize data and perform translation.

[0755] Step 4:

[0756] The server compresses standardized format data and stores it in the database. Compression is performed using Gzip, and the data is indexed in Elasticsearch. The input is standardized data, and the output is compressed and stored data.

[0757] A compression algorithm is applied to persistently store information in data storage.

[0758] Step 5:

[0759] The server uses stored data to train a generative AI model. The input is a compressed dataset, and the output is the trained AI model. Model optimization is performed using PyTorch or TensorFlow.

[0760] Computational resources are used to carry out an intensive training process for the model.

[0761] Step 6:

[0762] When a user requests information, the device retrieves the learned information via the server. For example, if a user wants to know about technology trends in 2023, the server parses the request and returns the most relevant information from the training data. The input is the user's prompt, and the output is the answer to the user's question.

[0763] Data retrieval and generation of necessary information are performed based on the information request.

[0764] Step 7:

[0765] The terminal re-translates the information provided to the user into the specified language and displays it in the appropriate format. Input is response data from the server, and output is the user's visual information.

[0766] The information is converted into a visual display format using HTML and CSS, and presented to aid user understanding.

[0767] (Application Example 1)

[0768] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0769] There is a need for a system that can efficiently collect vast amounts of information written in multiple languages ​​and provide it to users in a unified format. Furthermore, there is a lack of technology to optimize multilingual information according to user-specified themes and language settings, and to quickly provide information tailored to user interests.

[0770] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0771] In this invention, the server includes means for acquiring multilingual information, means for converting the acquired multilingual information into a unified format, means for compressing and storing the converted information, means for performing learning using the unified information, means for providing the learned information according to the user's request, means for collecting relevant content based on a theme specified by the user, and means for displaying the information in a format optimized for the user's language settings. This enables efficient collection of multilingual information and optimized information provision.

[0772] "Multilingual information" refers to all information obtained across different languages, including data that is processed uniformly while taking language differences into account.

[0773] "Means of acquisition" refers to the technologies and devices used to collect the target information from the internet or databases.

[0774] "Means of converting to a unified format" refers to the process of converting information written in different languages ​​or formats into a standardized, consistent format.

[0775] "Methods of compression and storage" refer to technologies that reduce the amount of information and store it, with the aim of eliminating redundancy and saving it efficiently.

[0776] "Means of learning" refers to the process by which an artificial intelligence model extracts new insights and relationships through learning, based on accumulated unified data.

[0777] "Means of providing information in response to user requests" refers to technologies that provide information that meets user needs at the appropriate time.

[0778] "Means of collecting relevant content based on a theme" refers to the process of appropriately collecting information and content that aligns with the theme specified by the user.

[0779] "Means of displaying information in a format optimized for language settings" refers to technologies that display information in the most optimal way, tailored to the user's language settings.

[0780] To implement this invention, the server, terminals, and users must collaborate to build the system. The server plays a central role in efficiently processing content provided in various languages ​​and utilizes a cloud server. Specifically, infrastructure such as Amazon Web Services (AWS) or Google Cloud Platform is suitable.

[0781] Data collection

[0782] The device collects multilingual data from the internet according to the user's instructions. This involves using smartphones or computers, employing scraping techniques with programming languages ​​such as Python.

[0783] Data conversion

[0784] The server translates the acquired multilingual data and converts it into a unified format. Google Translate API and Microsoft Azure's natural language processing technology are used here.

[0785] Data compression and storage

[0786] The converted data is compressed on the server using zlib with Python. The compressed data is then stored in a database such as MySQL.

[0787] Learning process

[0788] The server trains generative AI models using machine learning libraries such as TensorFlow. It analyzes compressed data and extracts relationships and patterns.

[0789] Providing information

[0790] Users access the server through their devices and request information based on specific themes and language settings. The server provides the most relevant information in response to the user's request and displays it on the device. Smartphones and computers fulfill this role.

[0791] A concrete example is the multilingual news app "GlobalReview." It allows users to collect news related to "environmental issues," translate it into the most suitable language, and display it. This system helps to smoothly deliver multilingual information to users.

[0792] Prompt example:

[0793] "Please collect and translate the latest multilingual news articles on environmental issues."

[0794] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0795] Step 1:

[0796] The device collects multilingual data related to a specific theme from the internet based on user instructions. The input is a search keyword specified by the user, and the output is a collection of related information. This process involves using scraping techniques to extract information from web pages and databases.

[0797] Step 2:

[0798] The terminal sends the collected data to the server. The input is raw data captured in multiple languages, and the output is data securely transmitted to the server. This step involves ensuring that the data is securely transferred using data encryption and communication protocols (HTTP or HTTPS).

[0799] Step 3:

[0800] The server converts the received multilingual data into a standard format using the Google Translate API and Microsoft Azure's natural language processing technology. The input is multilingual data, and the output is data in a unified format. This conversion includes the operation of linguistically standardizing the data through machine translation.

[0801] Step 4:

[0802] The server compresses data in a unified format using the Python zlib library and stores it in a MySQL database. The input is the converted data, and the output is the compressed and stored data. This step involves operations that compress the data and ensure efficient storage.

[0803] Step 5:

[0804] The server uses compressed data to train a generative AI model using libraries such as TensorFlow. The input is compressed data, and the output is the training result of the AI ​​model. This training process extracts relevant content patterns.

[0805] Step 6:

[0806] The user operates the terminal and requests information based on their preferred topics and language settings. The input is the user's request, and the output is the corresponding information. This step involves the user making a request for information retrieval through the terminal's interface.

[0807] Step 7:

[0808] The server searches for the most relevant information based on the user's request and provides it to the terminal. The input consists of a trained model and the user's request, while the output is information provided in an optimized format. This process involves rapid data retrieval and delivery of information in a format tailored to the user's preferences.

[0809] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0810] This invention provides a system for integrating information provided in multiple languages ​​into a unified format, and further recognizing and utilizing user emotions in information delivery. This system operates through the cooperation of a server, terminal, user, and emotion engine.

[0811] Collection and processing of multilingual information

[0812] The terminal collects multilingual data from the internet and various databases based on user requests. The collected data is sent to a server, which automatically classifies the information and converts it into a unified format using natural language processing technology. This step ensures information consistency and enables efficient management.

[0813] Utilizing the Emotion Engine

[0814] This system includes an emotion engine that detects the user's emotional state. When a user enters an information request or comment through a terminal, the emotion engine analyzes it and infers the user's emotional state in real time. This information is sent to the server and taken into consideration when providing information.

[0815] Information compression and learning

[0816] The server compresses and stores the converted information and uses an AI model for training. This process efficiently integrates information and lays the foundation for providing appropriate information based on the user's emotional state.

[0817] Customized information provision

[0818] When a user requests specific information, the device accesses the server to retrieve learned results. The server considers the user's emotional information obtained from the emotion engine and customizes and selects the necessary information. The device then presents this information to the user and provides feedback tailored to the user's emotional state.

[0819] Specific example

[0820] For example, if a user seeks information about relaxation due to work stress, the emotional engine detects a heightened stress level, and the server adjusts to prioritize providing information on videos and music specifically designed for relaxation. In this way, information tailored to the user's needs is provided.

[0821] This system enables the efficient integration of multilingual information and the customization of information to respond to user emotions, resulting in the provision of advanced information tailored to individual needs.

[0822] The following describes the processing flow.

[0823] Step 1:

[0824] The user enters a request for specific information through their device. In doing so, the user specifies the topics or information they are interested in.

[0825] Step 2:

[0826] The terminal receives the user's request and sends its contents to the server. The server parses the request and generates a search query to collect the appropriate information.

[0827] Step 3:

[0828] Based on the generated queries, the server collects relevant multilingual data from the internet and databases. Since this data may exist in different languages, the server categorizes each piece of data using language tags.

[0829] Step 4:

[0830] The server converts the collected multilingual data into a unified format using natural language processing techniques. This process utilizes machine translation technology to standardize different languages.

[0831] Step 5:

[0832] The emotion engine analyzes user input on the device and evaluates the user's emotional state in real time. This evaluation result is sent to the server and considered when providing information.

[0833] Step 6:

[0834] The server compresses the converted information and stores it in a database. The compressed data is then used to train an AI model, improving the information's effectiveness and relevance to the user.

[0835] Step 7:

[0836] When a user requests specific, emotionally relevant answers through their device, the server searches for the most appropriate information based on its learned knowledge.

[0837] Step 8:

[0838] The server customizes the search results to match the user's emotional state. The device then translates this information back into the appropriate language and presents it to the user.

[0839] Step 9:

[0840] The information displayed by the device to the user is tailored to the user's emotions, excluding information they dislike or find inappropriate. This allows the user to enjoy a consistent content experience.

[0841] (Example 2)

[0842] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0843] Because multilingual information is scattered across the internet, there is a need to address the challenge of users having difficulty quickly and efficiently obtaining information that is relevant to their emotional state. Furthermore, it is necessary to improve the quality of the information provided by appropriately organizing, translating, and presenting it.

[0844] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0845] In this invention, the server includes means for collecting multilingual information, means for converting the collected multilingual information into a unified format, and means for analyzing the user's emotional state. This makes it possible to provide information optimized to the user's emotions and needs.

[0846] "Multilingual information" refers to a collection of information provided in different languages, and the data collected through the internet and databases.

[0847] A "unified format" is a format that standardizes and maintains consistency for information in different languages ​​and formats.

[0848] "Compression" refers to the process of reducing the data size of information to make storage and transfer more efficient.

[0849] "Machine learning" is the process by which algorithms learn patterns using collected data and train models.

[0850] "User emotional state" refers to the psychological state that can be inferred from the user's input and actions.

[0851] "Customization" refers to tailoring and providing information and services based on the user's specific requests and conditions.

[0852] In order to implement this invention, the server, terminal, and user must cooperate to configure the system. Specifically, it is implemented as follows.

[0853] The server receives multilingual information collected from terminals via the internet and databases. The received information is converted into a unified format using natural language processing techniques. This process can utilize natural language processing libraries such as spaCy and NLTK as software libraries. Furthermore, commonly available machine translation APIs are used as translation APIs for the conversion to the unified format.

[0854] The server further compresses the converted information and stores it efficiently. A NoSQL database is suitable for this purpose. Machine learning is performed on the stored data using a generative AI model. Examples of AI models used include BERT and OpenAI GPT.

[0855] The terminal collects necessary multilingual information in response to user requests and sends it to the server. The terminal also incorporates an emotion engine that analyzes user requests and comments to infer their psychological state. This uses an emotion analysis model to recognize the user's emotional state in real time.

[0856] When a user requests specific information through their device, the server customizes and provides the most relevant information to the device based on the generated learning results and the user's emotional state.

[0857] As a concrete example, consider a scenario where a user requests information about relaxation. For instance, the user might enter a prompt into their device saying, "Please suggest relaxation methods that would be helpful when I'm feeling stressed." The emotion engine detects the user's stress level, and the server adjusts to provide relaxation-focused information accordingly. In this way, it becomes possible to provide information that matches the user's emotions and needs.

[0858] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0859] Step 1:

[0860] The terminal receives search keywords and requests from the user. The information entered by the user is a specific request, such as "relaxation methods" or "latest news." Based on this input, the terminal uses the internet and default database APIs to collect relevant information from multilingual sources. The collected data is sent to the backend in JSON or XML format.

[0861] Step 2:

[0862] The server receives multilingual information sent from the terminal. The server uses a natural language processing library to classify the received information into specific categories. The classified data is converted into a unified format via a machine translation API. Here, the input is unstructured multilingual data, and the output is structured data in a unified format.

[0863] Step 3:

[0864] The server compresses the converted, unified format data and stores it in the database. It applies the optimal compression technique to minimize data size. The input is the unified format data, and the output is the compressed data. An index is also automatically generated for the stored data to support efficient searching.

[0865] Step 4:

[0866] The server trains on stored compressed data using a generating AI model. The training process extracts patterns from the dataset and optimizes future information delivery strategies. The input to this step is compressed information, and the output is the trained AI model.

[0867] Step 5:

[0868] The device passes real-time user input information to the emotion engine, which analyzes the user's psychological state. This analysis step aims to provide advanced information based on the user's emotions and uses a BERT-based emotion analysis model. The input to the analysis is the user's comments and requests, and the output is an evaluation of the user's emotional state.

[0869] Step 6:

[0870] The server selects the most relevant information for the user based on the user's sentiment data and a trained model, and sends it to the terminal. The input to this process is sentiment data and the trained model, while the output is a customized set of information. The terminal presents this information to the user and also includes appropriate feedback functions.

[0871] In this way, the system provides personalized information to users, achieving the integration of multilingual information and the delivery of information that is sensitive to emotions.

[0872] (Application Example 2)

[0873] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0874] In modern society, providing efficient and emotionally sensitive information to a large number of users who speak different languages ​​is a major challenge. Conventional systems struggle to provide personalized information that considers multiple languages ​​and user emotional states, and there is a particular need to facilitate communication among international users. Furthermore, the processing and integration of multilingual information involves a massive amount of data, necessitating improvements in processing efficiency. Moreover, current technologies have not adequately achieved the ability to appropriately adjust and deliver information based on user emotions.

[0875] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0876] In this invention, the server includes means for acquiring multilingual information, means for converting the acquired multilingual information into a unified format, and means for performing sentiment analysis and customizing and providing information based on the user's emotional state. This makes it possible to provide personalized multilingual information that takes the user's emotional state into consideration.

[0877] "Multilingual information" refers to information written in multiple different languages.

[0878] A "unified format" refers to a state where data from different formats has been converted into a single, consistent format.

[0879] "Emotional analysis" refers to a technology that analyzes a user's facial expressions and voice to detect their emotional state.

[0880] "Customization" refers to appropriately adjusting and providing information and services based on the individual needs and circumstances of the user.

[0881] "Real-time" refers to a situation where processing or responses occur immediately, with virtually no time delay.

[0882] A "sensor" is a device that detects physical changes and outputs them as signals.

[0883] An "interface" refers to a common means or standard for different systems or devices to exchange information.

[0884] "Information provision" refers to the act of providing users with requested data or knowledge.

[0885] This invention begins with a user terminal acquiring multilingual information from the internet or other sources and sending it to a server. The server uses natural language processing technology to convert the information in each language into a unified format and stores the compressed data. The stored data can be quickly searched using an index, enabling efficient information provision. Furthermore, the user's emotional state is detected by an emotion analysis engine installed in the terminal. This engine analyzes the user's current emotions in real time based on input from sensors (e.g., camera and microphone) and transmits the analysis to the server.

[0886] When the server receives an information request from a user, it considers this sentiment information and generates customized information using a trained AI model. This customized information is provided through the interface in the user's language. Smooth information delivery across different languages ​​is crucial, and the generative AI model handles multilingual translation and content adjustment.

[0887] For example, if a user requests relaxation-related information in a stressful situation, the device's emotion analysis engine will detect the stress level, and the server will adjust its settings to prioritize providing relaxing music or videos. A possible prompt for this purpose might be, "What relaxing content should be provided when the user is feeling stressed?"

[0888] This allows users to instantly obtain information that suits their emotions, resulting in a more personalized user experience.

[0889] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0890] Step 1:

[0891] The user requests information using a terminal. The terminal receives the user's voice or text input, and the sentiment analysis engine starts working. This analyzes the user's current emotional state in real time, structures the information, and sends it to the server.

[0892] Step 2:

[0893] The server receives a multilingual information request sent from the terminal. It collects information in the requested language from the internet and other databases. This completes the collection of multilingual data, preparing it for the next step.

[0894] Step 3:

[0895] The server uses natural language processing technology to convert the collected multilingual data into a unified format. The input multilingual data is analyzed and organized into a unified format. The converted data is consistent, which streamlines subsequent processing.

[0896] Step 4:

[0897] The server compresses the data, which has been converted to a unified format, and stores it in a database for storage. This step uses a specialized algorithm to preserve information while minimizing data size. An index is then generated to streamline subsequent searches.

[0898] Step 5:

[0899] The server uses stored data to train an AI model and prepares customized information delivery based on the user's emotional state. The trained model then forms the foundation for specific information selection as a generative AI model.

[0900] Step 6:

[0901] The server considers the user's emotional data from the emotion analysis engine and uses a trained AI model to select information appropriate for the user. Based on the emotional state and requests, appropriate content (e.g., relaxing music or videos) is selected.

[0902] Step 7:

[0903] The server provides the selected information to the terminal. The terminal then presents the information through its interface, tailored to the user's language. This allows the user to obtain real-time, customized information.

[0904] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0905] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0906] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0907] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0908] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0909] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0910] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0911] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0912] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0913] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0914] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0915] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0916] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0917] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0918] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0919] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0920] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0921] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0922] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0923] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0924] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0925] The following is further disclosed regarding the embodiments described above.

[0926] (Claim 1)

[0927] Means of acquiring multilingual information,

[0928] A means of converting acquired multilingual information into a unified format,

[0929] A means of compressing and storing the converted information,

[0930] A means of learning using unified information,

[0931] A system that includes means for providing learned information in response to user requests.

[0932] (Claim 2)

[0933] The system according to claim 1, which uses natural language processing technology to translate information and convert it into a unified format.

[0934] (Claim 3)

[0935] The system according to claim 1, which generates an index for efficiently searching compressed information.

[0936] "Example 1"

[0937] (Claim 1)

[0938] A device for acquiring multilingual information,

[0939] A device for converting acquired multilingual information into a unified format,

[0940] A device for compressing and storing the converted information,

[0941] A device for learning using unified information,

[0942] A device for providing learned information in response to user requests,

[0943] A device for collecting data based on information sources specified by the user,

[0944] A communication device for securely transferring the collected data,

[0945] A system including a device for re-transforming learned information and displaying it in a specified language.

[0946] (Claim 2)

[0947] The system according to claim 1, which uses language processing technology to translate information and convert it into a unified format.

[0948] (Claim 3)

[0949] The system according to claim 1, which generates a catalog for effectively searching compressed information.

[0950] "Application Example 1"

[0951] (Claim 1)

[0952] Means of acquiring multilingual information,

[0953] A means of converting acquired multilingual information into a unified format,

[0954] A means of compressing and storing the converted information,

[0955] A means of learning using unified information,

[0956] A means of providing learned information in response to user requests,

[0957] A means of collecting relevant content based on a theme specified by the user,

[0958] A system that includes means for displaying information in a format optimized for the user's language settings.

[0959] (Claim 2)

[0960] The system according to claim 1, which uses natural language processing technology to translate information and convert it into a unified format.

[0961] (Claim 3)

[0962] The system according to claim 1, which generates an index for efficiently searching compressed information and recommends the most suitable content in response to user requests.

[0963] "Example 2 of combining an emotion engine"

[0964] (Claim 1)

[0965] Means of collecting multilingual information,

[0966] A means of converting collected multilingual information into a unified format,

[0967] A means of compressing and storing the converted information,

[0968] A means of performing machine learning using unified information,

[0969] A means of analyzing the user's emotional state,

[0970] A means of providing customized information based on analyzed emotional information,

[0971] A system that includes this.

[0972] (Claim 2)

[0973] The system according to claim 1, which uses natural language processing technology to translate information and convert it into a unified format.

[0974] (Claim 3)

[0975] The system according to claim 1, which generates an index for efficiently searching compressed information.

[0976] "Application example 2 when combining with an emotional engine"

[0977] (Claim 1)

[0978] Means of acquiring multilingual information,

[0979] A means of converting acquired multilingual information into a unified format,

[0980] A means of compressing and storing the converted information,

[0981] A means of learning using unified information,

[0982] A means of providing learned information in response to user requests,

[0983] A means of performing emotion analysis and providing customized information based on the user's emotional state,

[0984] A means of using a device equipped with sensors for detecting emotions in real time,

[0985] Interface means for providing information in different languages,

[0986] A system that includes this.

[0987] (Claim 2)

[0988] The system according to claim 1, which uses natural language processing technology to translate information and convert it into a unified format.

[0989] (Claim 3)

[0990] The system according to claim 1, which generates an index for efficiently searching compressed information. [Explanation of symbols]

[0991] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means of acquiring multilingual information, A means of converting acquired multilingual information into a unified format, A means of compressing and storing the converted information, A means of learning using unified information, A system that includes means for providing learned information in response to user requests.

2. The system according to claim 1, which uses natural language processing technology to translate information and convert it into a unified format.

3. The system according to claim 1, which generates an index for efficiently searching compressed information.

Images