system

Abstract

We provide the system. [Solution] A means for receiving user data in natural language format input from a user device, A means of analyzing the user data and utilizing a machine learning model to generate response data related to self-esteem or self-understanding, Means for transmitting the response data to the user device, A means for converting the response data into speech via an audio output device and providing it to the user, A means for recognizing user speech using a voice input device and receiving it as user data in text format, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method 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 a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In recent years, as digital communication has increased, the problem that users compare themselves with others and their sense of self-affirmation has declined has become more serious. Also, due to insufficient self-understanding, it has become difficult to take actions towards self-realization. Means for solving these problems are required.

Means for Solving the Problems

[0005] This invention provides a system that receives and analyzes natural language input from a user device to generate responses related to self-esteem and self-understanding. Specifically, it uses a large-scale language model to process user input and generate and transmit appropriate feedback to the user. Furthermore, the input data is standardized through preprocessing, which makes it possible to support users in deepening their self-understanding and enhancing their self-esteem.

[0006] "User equipment" refers to digital devices used by users, such as computers, smartphones, and tablets.

[0007] "Natural language form" refers to text data entered into a computer in the form of language that humans use on a daily basis.

[0008] "User data" refers to information entered by users, encompassing the specific input content of each individual user.

[0009] "Analysis" is the process of extracting information based on input data and interpreting its meaning and intent.

[0010] "Self-esteem" is the feeling of recognizing oneself as valuable and viewing oneself in a positive light.

[0011] "Self-understanding" means grasping and understanding one's own nature, abilities, emotions, and thoughts.

[0012] "Response data" refers to data that includes feedback and responses generated in response to user data.

[0013] A "machine learning model" is an algorithm or system used by computers to identify and learn data patterns.

[0014] "Transmission" refers to the act of sending data or information from one point to another.

[0015] A "large language model" is a machine learning model trained based on an enormous amount of data and designed to understand and generate natural language.

[0016] "Preprocessing" is a process of performing prior processing such as standardization and cleaning on data in order to make it easier to analyze or process.

Brief Explanation of Drawings

[0017] [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 multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple 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 Embodiment 2 when the 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 the emotion engine is combined.

Mode for Carrying Out the Invention

[0018] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, the numbered 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.

[0021] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0022] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0023] 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).

[0024] 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."

[0025] [First Embodiment]

[0026] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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".

[0038] In this embodiment of the present invention, the process begins with the user inputting information about their self-esteem and self-understanding through a terminal. The user can input their worries and questions in natural language in text format. The terminal receives this input data and transmits it to a central server via the internet.

[0039] The server first preprocesses the received data. This preprocessing includes cleaning and standardizing the data, preparing it for smooth subsequent analysis. Next, the preprocessed data is input into a machine learning model on the server. This model is a large-scale language model that enables advanced language analysis based on user input.

[0040] Specifically, the model analyzes the user's natural language input, understands their intent, and generates appropriate responses to enhance the user's self-esteem. These responses may include words of encouragement or specific action suggestions.

[0041] The generated response data is sent from the server to the user's terminal. The terminal receives this data and displays it in a user-friendly format. This display uses an interface that is intuitively easy for the user to understand.

[0042] For example, when a user inputs "I've been lacking confidence lately," the server analyzes this and generates a response such as, "Recall your past successes and use those experiences to take your next step." In this way, the present invention aims to support users in deepening their self-understanding and increasing their self-esteem.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The user inputs questions or concerns in natural language format using a device. The device then receives this user input as text data and prepares it.

[0046] Step 2:

[0047] The terminal transmits user input data to the server via the internet. During this process, the data transmission protocol employs appropriate encryption to protect user privacy.

[0048] Step 3:

[0049] The server receives text data sent from the terminal. After receiving the data, the server preprocesses it by removing unnecessary characters and special symbols, and standardizing the data format.

[0050] Step 4:

[0051] The pre-processed data is input into a machine learning model on the server. The server uses a large-scale language model to analyze the input data and understand the user's intentions and situation.

[0052] Step 5:

[0053] Based on the server's analysis, it generates response data that promotes the user's self-esteem and self-understanding. This may include encouraging messages or suggestions for the next course of action.

[0054] Step 6:

[0055] The generated response data is sent from the server to the terminal. This transmission also uses a secure communication protocol, taking user privacy into consideration.

[0056] Step 7:

[0057] The terminal displays the response data received from the server on the user interface. The user can review the displayed information, consider the next steps appropriate to their situation, and take action.

[0058] (Example 1)

[0059] 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."

[0060] Traditional systems made it difficult for users to receive appropriate support in real time to deepen their self-esteem and self-understanding. In particular, the lack of means to accurately analyze user intent using natural language and generate individually optimized responses meant that rapid and effective feedback could not be obtained, resulting in a limited user experience.

[0061] 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.

[0062] In this invention, the server includes means for receiving user information in natural language format input from a user terminal, means for preprocessing the user information to standardize its format, and means for analyzing the preprocessed information and utilizing a learning algorithm to generate response information that promotes self-esteem and self-understanding. As a result, users can quickly receive individually optimized responses and more effectively deepen their self-esteem and self-understanding.

[0063] A "user terminal" is a communication device used by a user to provide input information.

[0064] "Natural language forms" are forms expressed in human language used in everyday conversation.

[0065] "User information" refers to text data provided by users that relates to their self-esteem and self-understanding.

[0066] "Preprocessing" refers to the cleaning and standardization procedures used to prepare data for analysis.

[0067] "Standardization" is the process of unifying data formats and structures into a consistent format.

[0068] A "learning algorithm" is a computer program used to generate an appropriate response based on input data.

[0069] A "large-scale language processing model" is an advanced computer model that has the capability to understand and generate a wide variety of natural languages.

[0070] "Response information" refers to messages generated based on user input, designed to promote self-esteem and self-understanding.

[0071] An "information processing device" refers to the entire system used for receiving, analyzing, and transmitting data.

[0072] This invention begins with a user inputting information about their self-esteem and self-understanding through a communication device. The user inputs text data using natural language, and this information is received on the terminal. The terminal transmits the received user data to a server via the internet. The server preprocesses the data by cleaning and standardizing it, and then analyzes the preprocessed information. A large-scale language processing model is used for the analysis, and based on this model, an appropriate response is generated to enhance the user's self-esteem. The generated response is sent from the server to the user's terminal, which displays the response in a format that is easy for the user to understand.

[0073] For example, if a user inputs "I've been feeling insecure lately" into the terminal, the server analyzes this and generates a response message such as "Recall your past successes and use those experiences to take your next step." In this way, the invention supports users in deepening their self-understanding and improving their self-esteem. Another example of a prompt message might be one in the form of "If the user inputs 'I've been feeling insecure lately,' generate a response that will boost self-esteem."

[0074] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0075] Step 1:

[0076] The user inputs text data in natural language using a communication device. This input is based on the user's current worries and questions and is provided directly to the terminal. Specifically, the user enters the text "I've been feeling insecure lately" into the terminal's input field and presses the send button. Natural language text is provided as input and is recognized directly by the terminal.

[0077] Step 2:

[0078] The terminal receives input text from the user and sends it to the server via the internet. Here, security is ensured because the text data is packaged in an appropriate format (e.g., JSON) and sent to the server using the HTTPS protocol. The input is natural language text from the user, and the output sent is in a data format that the server can process.

[0079] Step 3:

[0080] The server preprocesses the received data, performing data cleaning and standardization. Specifically, it removes unnecessary whitespace and special characters and converts the data into a format that is easily understood by the language processing engine. It receives packaged natural language text as input and generates standardized text data as output.

[0081] Step 4:

[0082] The server uses a large-scale language processing model to analyze pre-processed data, understand the user's intent, and generate responses that enhance self-esteem. The model receives standardized text as input and outputs a message as response information such as, "Recall your past successes and use those experiences to take your next step."

[0083] Step 5:

[0084] The server sends the generated response data to the user's terminal. The data is then encoded again in an appropriate format (e.g., JSON) and securely sent to the terminal. The server receives response data as input and sends it back as output in a format that the user's terminal can display.

[0085] Step 6:

[0086] The terminal displays received responses in a user-friendly format. Specifically, it displays response messages on the terminal's chat interface and notifies the user. It receives formatted response information sent from the server as input and displays it as output in an intuitive user interface.

[0087] (Application Example 1)

[0088] 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."

[0089] In recent years, there has been a growing demand for technologies that support individual self-esteem and self-understanding. However, many technologies merely provide textual feedback in response to natural language input from users, and systems that offer intuitive and warm responses via voice are limited. This invention aims to improve users' mental well-being by providing a system that offers more natural and emotionally rich communication through voice input and output.

[0090] 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.

[0091] In this invention, the server includes means for receiving user data in natural language format input from a user device; means for analyzing the user data and utilizing a machine learning model to generate response data related to self-esteem or self-understanding; means for transmitting the response data to the user device; means for converting the response data into speech via a speech output device and providing it to the user; and means for recognizing the user's utterance using a speech input device and receiving it as user data in text format. This enables the user to intuitively receive mental care through voice.

[0092] A "user device" is a terminal device used by a user to input information and receive output.

[0093] "Natural language form" refers to data expressed in the language form that humans use on a daily basis.

[0094] "User data" refers to data that includes information entered by the user.

[0095] A "machine learning model" is a collection of algorithms that learn patterns based on data and perform predictions and classifications.

[0096] "Response data" refers to information generated based on user data and provided to the user.

[0097] An "audio output device" refers to a device that converts electronic data into sound and allows the user to hear it.

[0098] A "voice input device" is a device used to convert audio into a digital format.

[0099] "Natural language input" refers to the act of a user entering information using their own words, either through voice or text.

[0100] To realize this invention, a user device, a server, a voice input device, and a voice output device are required. The user speaks in natural language through the voice input device. This speech is converted into digital data by the voice input device and transmitted to the server as text data by the user device.

[0101] The server inputs the received user data into a machine learning model. This model includes a large-scale language model that generates response data based on the user data. The generated response data is converted into speech data using automatic speech synthesis technology and delivered to the user via a speech output device.

[0102] Specifically, speech input processing utilizes speech recognition software, such as "Google® Speech-to-Text," to convert the speech into digital data. The generated text data is sent to a server, where it is analyzed using "OpenAI®'s large-scale language model" to generate appropriate response data. The generated response is then converted into speech using a speech synthesis engine such as "Amazon Polly."

[0103] For example, if a user says, "I'm feeling a little down today," the server recognizes this input and generates and provides encouraging words such as, "It's important to always look at the positive side. How about we take a little break together?"

[0104] An example of a prompt for a generative AI model is: "To provide mental support to the user, acknowledge what he / she is feeling and offer appropriate encouragement and action suggestions. Input: 'I'm feeling a little down today.'"

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

[0106] Step 1:

[0107] The user speaks in natural language through a voice input device. This voice data is input and sent to speech recognition software.

[0108] Step 2:

[0109] The voice input device uses speech recognition software (e.g., Google Speech-to-Text) to convert voice data into text data. This converted text data is then output to the terminal.

[0110] Step 3:

[0111] The terminal sends the acquired text data to the server via the internet. The server receives this text data as input.

[0112] Step 4:

[0113] The server uses a generative AI model (e.g., OpenAI's large-scale language model) to analyze the received text data. Based on the input text, the model generates response data designed to enhance the user's self-esteem. This response data is then output.

[0114] Step 5:

[0115] The server inputs the generated response data into a speech synthesis engine (e.g., Amazon Polly) and converts it into speech data. This converted speech data is then output.

[0116] Step 6:

[0117] The server transmits audio data to the terminal via the internet. The terminal then forwards this audio data to the audio output device.

[0118] Step 7:

[0119] The audio output device plays the received audio data and lets the user listen to it. This allows the user to receive mental care intuitively.

[0120] 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.

[0121] In embodiments of the present invention, the process begins with the user inputting their emotions or state in natural language via a terminal. The user can input text about their emotions or situation, and this data is received by the terminal. The received data is transmitted to a central server via the internet.

[0122] The server first preprocesses the received user data, cleaning and standardizing its format. This preprocessing makes the data easier to analyze using the emotion engine and machine learning models.

[0123] Next, the server supplies the pre-processed data to the emotion engine. This emotion engine analyzes the emotional elements contained in the user input to detect and recognize the user's emotional state. In this process, it identifies basic emotions (e.g., joy, sadness, anger, etc.) from keywords and phrases contained in the text.

[0124] Subsequently, the emotional information recognized by the emotion engine is used in conjunction with a large-scale language model on the server to generate appropriate response data. The response data is adjusted to the user's emotional state, providing more personalized feedback. The responses generated at this stage aim to take emotional changes into account and offer the most appropriate encouragement and action suggestions to the user.

[0125] For example, if a user types "I'm feeling really down today," the emotion engine detects the emotion, and the large-scale language model provides a response such as "Don't worry, tomorrow will be a better day."

[0126] Finally, the generated response data is sent from the server to the terminal and displayed to the user via the user interface. Based on this response, the user can decide on their next action and use it as a means to improve their emotions and situation. This invention realizes a system that enables advanced responses tailored to the individual needs of users by integrating emotion recognition functionality.

[0127] The following describes the processing flow.

[0128] Step 1:

[0129] The user uses the device to input their feelings or questions in natural language. The device receives this input as text data.

[0130] Step 2:

[0131] The device sends text data from the user to the server. The data is communicated over the internet and protected by a secure protocol.

[0132] Step 3:

[0133] The server preprocesses the received text data. This preprocessing involves filtering out unnecessary information and standardizing the data format to facilitate subsequent analysis.

[0134] Step 4:

[0135] The pre-processed data is input into the emotion engine on the server. The emotion engine analyzes the text to recognize the emotions expressed by the user. Specifically, it identifies emotions such as joy, sadness, and anger based on certain words and phrases.

[0136] Step 5:

[0137] The server uses the output of the emotion engine to input data into a large-scale language model, which is a machine learning model, to generate a response appropriate to the user's emotions and context. This response is personalized according to the user's emotional state.

[0138] Step 6:

[0139] The server sends the generated response data to the terminal. As with other communications, the data is transmitted using appropriate security measures.

[0140] Step 7:

[0141] The terminal displays response data received from the server to the user. Based on the displayed response, the user can consider actions to manage their own situation and emotions.

[0142] (Example 2)

[0143] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0144] In modern society, many individuals face challenges in managing their emotions and mental state. In particular, a lack of adequate means to obtain individually tailored emotional feedback prevents users from receiving appropriate responses to their emotional changes. This project aims to address this problem and provide prompt and effective support tailored to each individual's emotional state.

[0145] 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.

[0146] In this invention, the server includes means for receiving user data in natural language format input from a user device, means for preprocessing the user data, cleaning the data and standardizing its format, and means for analyzing the preprocessed data and utilizing an emotion engine and machine learning models to generate response data related to the user's emotional state. This makes it possible to quickly provide personalized feedback based on each user's emotional state.

[0147] A "user device" is a device used by a user to input information, and includes smartphones, computers, and other similar devices.

[0148] "Natural language form" refers to forms expressed in the language that humans normally use, and includes text and conversational text.

[0149] "User data" refers to information entered by users, including text information related to emotions and situations.

[0150] "Preprocessing" refers to initial processing to make data easier to analyze, and includes cleaning and formatting standardization.

[0151] "Data cleaning" refers to the process of removing unnecessary elements from data, including the removal of noise and special characters.

[0152] "Format standardization" is the process of converting data into a unified format, and it is an effort to ensure consistency.

[0153] An "emotion engine" is a device or program that analyzes user data to identify emotions, and utilizes natural language processing technology.

[0154] A "machine learning model" is an algorithm or mathematical model used to recognize data patterns and make predictions or classifications.

[0155] "Response data" refers to information generated based on the analysis results and is provided to the user as feedback.

[0156] A "user interface" is a means for a user to interact with a system, and includes screen displays and control panels.

[0157] This invention relates to a system that provides personalized responses tailored to the user's emotions. This system is primarily implemented using a user device, a server, an emotion engine, and a large-scale language model.

[0158] Users input their emotions and states in natural language format through user devices such as smartphones and computers that they use daily. This input information is recorded on the device as user data.

[0159] The terminal transmits the received user data to the server via the internet. The server uses a secure communication protocol and takes care to protect the data during transmission.

[0160] The server preprocesses the received user data. This process includes cleaning and standardizing the data format to prepare it for smooth analysis.

[0161] The pre-processed data is analyzed by an emotion engine. The emotion engine utilizes natural language processing techniques to identify basic emotions from keywords and phrases within the text.

[0162] Subsequently, based on the analysis results of the emotion engine, a large-scale language model generates response data for the user. This model learns past data patterns using machine learning algorithms, specifically employing a generative AI model.

[0163] For example, if a user types "I'm feeling really down today," the sentiment engine, which includes a large-scale language model, recognizes the emotion "down" and generates a response such as "Don't worry, tomorrow will be a better day."

[0164] After completing the above procedures, the server sends the generated response data to the user's device, and the terminal displays it through the user interface. This allows the user to receive feedback from the system and use it to manage and improve their emotions in their daily life.

[0165] A concrete example of a prompt statement is, "When the user says, 'Something good happened today,' generate a response." This allows the system to generate responses tailored to the user's emotions.

[0166] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0167] Step 1:

[0168] The user inputs natural language text about their emotions and state into the user device. This input text is received by the user device and treated directly as user data. This process incorporates specific information about the user's emotions into the system.

[0169] Step 2:

[0170] The terminal transmits received user data to the server via the internet. The input here is the user's raw text data, and the output is ready to be sent to the server. Throughout this process, encrypted communication protocols are used to ensure the data remains secure.

[0171] Step 3:

[0172] The server preprocesses the received user data. This step involves cleaning the input data, removing noise and unnecessary whitespace. It also converts the data into an easily parseable format through format standardization. The output is clean, standardized text data.

[0173] Step 4:

[0174] The server supplies pre-processed data to the emotion engine. Based on the input data, the emotion engine uses natural language processing techniques to analyze keywords and phrases in the text and identify basic emotions such as joy and sadness. As output, data about the user's emotional state is generated.

[0175] Step 5:

[0176] The server generates response data using a large-scale language model based on emotional state data generated by the emotion engine. Using prompts based on the generative AI model, it devises appropriate feedback for the user's emotions. For example, it might generate something like, "Don't worry, tomorrow will be a better day." The output is the optimal response data for the user.

[0177] Step 6:

[0178] The generated response data is sent from the server to the user device. The terminal displays this response data through the user interface. This allows the user to see feedback on their emotions. The output is a text message presented in the user interface.

[0179] (Application Example 2)

[0180] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0181] In modern society, users face various stresses and emotional fluctuations in their daily lives. In particular, a challenge lies in the lack of immediate, appropriate feedback and encouragement tailored to their emotional state, resulting in insufficient personal emotional support. Furthermore, there is a lack of effective and rapid methods for providing personalized support tailored to individual situations using emotion recognition technology. Therefore, there is a need for technology that accurately analyzes users' emotions and provides appropriate responses quickly.

[0182] 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.

[0183] In this invention, the server includes means for receiving user data in natural language format input from a user device; means for analyzing the user data and utilizing a model for generating response data related to self-esteem or self-understanding; means for transmitting the response data to the user device; means including an emotion analysis device for analyzing the user's emotional state and providing appropriate feedback; means for generating response data for making action suggestions to the user based on the emotion analysis results; and means for displaying the response data on the user device and providing it as audio output. This makes it possible to analyze the user's emotional state in real time, provide action suggestions and encouragement tailored to individual needs, and effectively support the user's mental well-being.

[0184] A "user device" is a device used by a user to input data in natural language format, and includes smartphones and computers.

[0185] "Natural language" refers to the forms of language that humans use on a daily basis, and is a means of expressing emotions and thoughts.

[0186] "User data" refers to information about emotions and states that users input through the device.

[0187] A "model" refers to a computational method used to analyze data and generate responses using machine learning.

[0188] "Response data" refers to information including feedback and suggestions generated as a result of analyzing user data.

[0189] An "emotion analysis device" refers to a system that identifies the user's emotional state from their input data and provides appropriate feedback.

[0190] "Action suggestions" refer to instructions or advice that indicate what actions a user should take, based on their emotional state.

[0191] "Display" refers to the act of visually presenting the generated response data on the screen of the user's device.

[0192] "Voice output" refers to a means of transmitting generated response data to the user as voice.

[0193] To realize this invention, the user first inputs their emotions or state of mind into a user device using natural language. The user device includes smartphones and computers equipped with voice recognition and touch input functions. The input data is transmitted via the internet to a service provider's server.

[0194] When the server receives data, it first uses cloud platforms such as Amazon Web Services (AWS®) or Microsoft Azure® to preprocess the received data. This preprocessing involves cleaning the data and standardizing its format. As a result, sentiment analysis becomes easier.

[0195] Next, the server analyzes the user's emotional state using tools such as the Google Cloud Natural Language API. This emotion analyzer identifies emotional elements from the user's natural language data, recognizing basic emotions such as "joy" and "anger." Then, a large-scale language model generates response data using the identified emotional data.

[0196] The generated response data is adjusted according to the user's emotional state and sent to the user's device as personalized feedback. The response data is then presented to the user through a display or speaker on the user's device. This process makes it possible to provide the user with appropriate behavioral suggestions and encouragement.

[0197] For example, if a user enters "I'm very tired today," the server will perform sentiment analysis on this as "fatigue" and generate a response such as, "You worked hard today. Let's take some time to relax." This response may also be provided as voice output.

[0198] An example of a prompt would be, "User's mood: 'I'm nervous about a new project today.' Please think of an appropriate response and offer gentle encouragement." This prompt instructs the generative AI model to generate appropriate feedback based on the user's input.

[0199] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0200] Step 1:

[0201] The user inputs their emotions and state of mind into the device in natural language. The device captures the user's input as digital data using voice recognition and touch input functions. The input data can be in the form of text or voice data. As output, digital data in natural language format representing the user's emotions and state of mind is generated.

[0202] Step 2:

[0203] The terminal sends the input natural language data to the service provider's server over the internet. This data is encoded and transmitted using a secure protocol. As input, the terminal receives the captured natural language data, and as output, the same data is accurately sent to the server.

[0204] Step 3:

[0205] The server performs preprocessing of received natural language data on cloud platforms such as Amazon Web Services (AWS) and Microsoft Azure. This preprocessing includes noise reduction and formatting standardization to prepare the data for sentiment analysis. It receives raw natural language data as input and generates formatted data as output.

[0206] Step 4:

[0207] The server uses the formatted data to power the Google Cloud Natural Language API, which analyzes the user's emotional state. This API extracts emotional elements from the text, identifying emotions such as "joy" and "anger." It accepts pre-processed text data as input and generates emotional analysis information as output.

[0208] Step 5:

[0209] The server generates response data using a generative AI model based on information obtained from sentiment analysis. The model utilizes OpenAI's GPT and other technologies to generate optimal feedback for the user based on the prompt text. It uses sentiment analysis information as input and produces response data as output.

[0210] Step 6:

[0211] The server sends the generated response data to the terminal. The terminal presents this response data to the user as either a display or audio output. A display is used for display, and a speaker is used for audio output. The terminal receives response data from the server as input and presents it to the user in an appropriate format as output.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] [Second Embodiment]

[0216] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0217] 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.

[0218] 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).

[0219] 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.

[0220] 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.

[0221] 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).

[0222] 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.

[0223] 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.

[0224] 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.

[0225] 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.

[0226] 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.

[0227] 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".

[0228] In this embodiment of the present invention, the process begins with the user inputting information about their self-esteem and self-understanding through a terminal. The user can input their worries and questions in natural language in text format. The terminal receives this input data and transmits it to a central server via the internet.

[0229] The server first preprocesses the received data. This preprocessing includes cleaning and standardizing the data, preparing it for smooth subsequent analysis. Next, the preprocessed data is input into a machine learning model on the server. This model is a large-scale language model that enables advanced language analysis based on user input.

[0230] Specifically, the model analyzes the user's natural language input, understands their intent, and generates appropriate responses to enhance the user's self-esteem. These responses may include words of encouragement or specific action suggestions.

[0231] The generated response data is sent from the server to the user's terminal. The terminal receives this data and displays it in a user-friendly format. This display uses an interface that is intuitively easy for the user to understand.

[0232] For example, when a user inputs "I've been lacking confidence lately," the server analyzes this and generates a response such as, "Recall your past successes and use those experiences to take your next step." In this way, the present invention aims to support users in deepening their self-understanding and increasing their self-esteem.

[0233] The following describes the processing flow.

[0234] Step 1:

[0235] The user inputs questions or concerns in natural language format using a device. The device then receives this user input as text data and prepares it.

[0236] Step 2:

[0237] The terminal transmits user input data to the server via the internet. During this process, the data transmission protocol employs appropriate encryption to protect user privacy.

[0238] Step 3:

[0239] The server receives text data sent from the terminal. After receiving the data, the server preprocesses it by removing unnecessary characters and special symbols, and standardizing the data format.

[0240] Step 4:

[0241] The pre-processed data is input into a machine learning model on the server. The server uses a large-scale language model to analyze the input data and understand the user's intentions and situation.

[0242] Step 5:

[0243] Based on the server's analysis, it generates response data that promotes the user's self-esteem and self-understanding. This may include encouraging messages or suggestions for the next course of action.

[0244] Step 6:

[0245] The generated response data is sent from the server to the terminal. This transmission also uses a secure communication protocol, taking user privacy into consideration.

[0246] Step 7:

[0247] The terminal displays the response data received from the server on the user interface. The user can review the displayed information, consider the next steps appropriate to their situation, and take action.

[0248] (Example 1)

[0249] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0250] Traditional systems made it difficult for users to receive appropriate support in real time to deepen their self-esteem and self-understanding. In particular, the lack of means to accurately analyze user intent using natural language and generate individually optimized responses meant that rapid and effective feedback could not be obtained, resulting in a limited user experience.

[0251] 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.

[0252] In this invention, the server includes means for receiving user information in natural language format input from a user terminal, means for preprocessing the user information to standardize its format, and means for analyzing the preprocessed information and utilizing a learning algorithm to generate response information that promotes self-esteem and self-understanding. As a result, users can quickly receive individually optimized responses and more effectively deepen their self-esteem and self-understanding.

[0253] A "user terminal" is a communication device used by a user to provide input information.

[0254] "Natural language forms" are forms expressed in human language used in everyday conversation.

[0255] "User information" refers to text data provided by users that relates to their self-esteem and self-understanding.

[0256] "Preprocessing" refers to the cleaning and standardization procedures used to prepare data for analysis.

[0257] "Standardization" is the process of unifying data formats and structures into a consistent format.

[0258] A "learning algorithm" is a computer program used to generate an appropriate response based on input data.

[0259] A "large-scale language processing model" is an advanced computer model that has the capability to understand and generate a wide variety of natural languages.

[0260] "Response information" refers to messages generated based on user input, designed to promote self-esteem and self-understanding.

[0261] An "information processing device" refers to the entire system used for receiving, analyzing, and transmitting data.

[0262] This invention begins with a user inputting information about their self-esteem and self-understanding through a communication device. The user inputs text data using natural language, and this information is received on the terminal. The terminal transmits the received user data to a server via the internet. The server preprocesses the data by cleaning and standardizing it, and then analyzes the preprocessed information. A large-scale language processing model is used for the analysis, and based on this model, an appropriate response is generated to enhance the user's self-esteem. The generated response is sent from the server to the user's terminal, which displays the response in a format that is easy for the user to understand.

[0263] For example, if a user inputs "I've been feeling insecure lately" into the terminal, the server analyzes this and generates a response message such as "Recall your past successes and use those experiences to take your next step." In this way, the invention supports users in deepening their self-understanding and improving their self-esteem. Another example of a prompt message might be one in the form of "If the user inputs 'I've been feeling insecure lately,' generate a response that will boost self-esteem."

[0264] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0265] Step 1:

[0266] The user inputs text data in natural language using a communication device. This input is based on the user's current worries and questions and is provided directly to the terminal. Specifically, the user enters the text "I've been feeling insecure lately" into the terminal's input field and presses the send button. Natural language text is provided as input and is recognized directly by the terminal.

[0267] Step 2:

[0268] The terminal receives input text from the user and sends it to the server via the internet. Here, security is ensured because the text data is packaged in an appropriate format (e.g., JSON) and sent to the server using the HTTPS protocol. The input is natural language text from the user, and the output sent is in a data format that the server can process.

[0269] Step 3:

[0270] The server preprocesses the received data, performing data cleaning and standardization. Specifically, it removes unnecessary whitespace and special characters and converts the data into a format that is easily understood by the language processing engine. It receives packaged natural language text as input and generates standardized text data as output.

[0271] Step 4:

[0272] The server uses a large-scale language processing model to analyze pre-processed data, understand the user's intent, and generate responses that enhance self-esteem. The model receives standardized text as input and outputs a message as response information such as, "Recall your past successes and use those experiences to take your next step."

[0273] Step 5:

[0274] The server sends the generated response data to the user's terminal. The data is then encoded again in an appropriate format (e.g., JSON) and securely sent to the terminal. The server receives response data as input and sends it back as output in a format that the user's terminal can display.

[0275] Step 6:

[0276] The terminal displays received responses in a user-friendly format. Specifically, it displays response messages on the terminal's chat interface and notifies the user. It receives formatted response information sent from the server as input and displays it as output in an intuitive user interface.

[0277] (Application Example 1)

[0278] 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."

[0279] In recent years, there has been a growing demand for technologies that support individual self-esteem and self-understanding. However, many technologies merely provide textual feedback in response to natural language input from users, and systems that offer intuitive and warm responses via voice are limited. This invention aims to improve users' mental well-being by providing a system that offers more natural and emotionally rich communication through voice input and output.

[0280] 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.

[0281] In this invention, the server includes means for receiving user data in natural language format input from a user device; means for analyzing the user data and utilizing a machine learning model to generate response data related to self-esteem or self-understanding; means for transmitting the response data to the user device; means for converting the response data into speech via a speech output device and providing it to the user; and means for recognizing the user's utterance using a speech input device and receiving it as user data in text format. This enables the user to intuitively receive mental care through voice.

[0282] A "user device" is a terminal device used by a user to input information and receive output.

[0283] "Natural language form" refers to data expressed in the language forms commonly used by humans in daily life.

[0284] "User data" is data that includes information input by the user.

[0285] "Machine learning model" is a set of algorithms that learn patterns based on data and perform predictions and classifications.

[0286] "Response data" is information that is generated based on user data and provided to the user.

[0287] "Voice output device" refers to a device that converts electronic data into voice and plays it for the user.

[0288] "Voice input device" is a device for converting voice into digital form.

[0289] "Input in natural language" refers to the act of a user inputting information using their voice or text in the exact words.

[0290] To implement this invention, a user device, a server, a voice input device, and a voice output device are required. The user makes a speech in natural language through the voice input device. This speech is converted into digital data by the voice input device and transmitted as text data to the server by the user device.

[0291] The server inputs the received user data into the machine learning model. This model includes a large language model and generates response data based on the user data. The generated response data is converted into voice data using automatic speech synthesis technology and delivered to the user via the voice output device.

[0292] Specifically, speech input processing utilizes speech recognition software, such as "Google Speech-to-Text," to convert the speech into digital data. The generated text data is sent to a server, where it is analyzed using "OpenAI's large-scale language model" to generate appropriate response data. The generated response is then converted into speech using a speech synthesis engine such as "Amazon Polly."

[0293] For example, if a user says, "I'm feeling a little down today," the server recognizes this input and generates and provides encouraging words such as, "It's important to always look at the positive side. How about we take a little break together?"

[0294] An example of a prompt for a generative AI model is: "To provide mental support to the user, acknowledge what he / she is feeling and offer appropriate encouragement and action suggestions. Input: 'I'm feeling a little down today.'"

[0295] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0296] Step 1:

[0297] The user speaks in natural language through a voice input device. This voice data is input and sent to speech recognition software.

[0298] Step 2:

[0299] The voice input device uses speech recognition software (e.g., Google Speech-to-Text) to convert voice data into text data. This converted text data is then output to the terminal.

[0300] Step 3:

[0301] The terminal transmits the acquired text data to the server via the Internet. The server receives this text data as input.

[0302] Step 4:

[0303] The server uses a generated AI model (e.g., OpenAI's large language model) to analyze the received text data. Based on the input text, the model generates response data to enhance the user's sense of self - affirmation. This response data is output.

[0304] Step 5:

[0305] The server inputs the generated response data into a text - to - speech engine (e.g., Amazon Polly) and converts it into audio data. This converted audio data is output.

[0306] Step 6:

[0307] The server transmits the audio data to the terminal via the Internet. The terminal transfers this audio data to an audio output device.

[0308] Step 7:

[0309] The audio output device plays the received audio data and presents it to the user. Thus, the user can intuitively receive mental care.

[0310] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion recognition model 59 and perform specific processing using the user's emotion.

[0311] In embodiments of the present invention, the process begins with the user inputting their emotions or state in natural language via a terminal. The user can input text about their emotions or situation, and this data is received by the terminal. The received data is transmitted to a central server via the internet.

[0312] The server first preprocesses the received user data, cleaning and standardizing its format. This preprocessing makes the data easier to analyze using the emotion engine and machine learning models.

[0313] Next, the server supplies the pre-processed data to the emotion engine. This emotion engine analyzes the emotional elements contained in the user input to detect and recognize the user's emotional state. In this process, it identifies basic emotions (e.g., joy, sadness, anger, etc.) from keywords and phrases contained in the text.

[0314] Subsequently, the emotional information recognized by the emotion engine is used in conjunction with a large-scale language model on the server to generate appropriate response data. The response data is adjusted to the user's emotional state, providing more personalized feedback. The responses generated at this stage aim to take emotional changes into account and offer the most appropriate encouragement and action suggestions to the user.

[0315] For example, if a user types "I'm feeling really down today," the emotion engine detects the emotion, and the large-scale language model provides a response such as "Don't worry, tomorrow will be a better day."

[0316] Finally, the generated response data is sent from the server to the terminal and displayed to the user via the user interface. Based on this response, the user can decide on their next action and use it as a means to improve their emotions and situation. This invention realizes a system that enables advanced responses tailored to the individual needs of users by integrating emotion recognition functionality.

[0317] The following describes the processing flow.

[0318] Step 1:

[0319] The user uses the device to input their feelings or questions in natural language. The device receives this input as text data.

[0320] Step 2:

[0321] The device sends text data from the user to the server. The data is communicated over the internet and protected by a secure protocol.

[0322] Step 3:

[0323] The server preprocesses the received text data. This preprocessing involves filtering out unnecessary information and standardizing the data format to facilitate subsequent analysis.

[0324] Step 4:

[0325] The pre-processed data is input into the emotion engine on the server. The emotion engine analyzes the text to recognize the emotions expressed by the user. Specifically, it identifies emotions such as joy, sadness, and anger based on certain words and phrases.

[0326] Step 5:

[0327] The server uses the output of the emotion engine to input data into a large-scale language model, which is a machine learning model, to generate a response appropriate to the user's emotions and context. This response is personalized according to the user's emotional state.

[0328] Step 6:

[0329] The server sends the generated response data to the terminal. As with other communications, the data is transmitted using appropriate security measures.

[0330] Step 7:

[0331] The terminal displays response data received from the server to the user. Based on the displayed response, the user can consider actions to manage their own situation and emotions.

[0332] (Example 2)

[0333] 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".

[0334] In modern society, many individuals face challenges in managing their emotions and mental state. In particular, a lack of adequate means to obtain individually tailored emotional feedback prevents users from receiving appropriate responses to their emotional changes. This project aims to address this problem and provide prompt and effective support tailored to each individual's emotional state.

[0335] 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.

[0336] In this invention, the server includes means for receiving user data in natural language format input from a user device, means for preprocessing the user data, cleaning the data and standardizing its format, and means for analyzing the preprocessed data and utilizing an emotion engine and machine learning models to generate response data related to the user's emotional state. This makes it possible to quickly provide personalized feedback based on each user's emotional state.

[0337] A "user device" is a device used by a user to input information, and includes smartphones, computers, and other similar devices.

[0338] "Natural language form" refers to forms expressed in the language that humans normally use, and includes text and conversational text.

[0339] "User data" refers to information entered by users, including text information related to emotions and situations.

[0340] "Preprocessing" refers to initial processing to make data easier to analyze, and includes cleaning and formatting standardization.

[0341] "Data cleaning" refers to the process of removing unnecessary elements from data, including the removal of noise and special characters.

[0342] "Format standardization" is the process of converting data into a unified format, and it is an effort to ensure consistency.

[0343] An "emotion engine" is a device or program that analyzes user data to identify emotions, and utilizes natural language processing technology.

[0344] A "machine learning model" is an algorithm or mathematical model used to recognize data patterns and make predictions or classifications.

[0345] "Response data" refers to information generated based on the analysis results and is provided to the user as feedback.

[0346] A "user interface" is a means for a user to interact with a system, and includes screen displays and control panels.

[0347] This invention relates to a system that provides personalized responses tailored to the user's emotions. This system is primarily implemented using a user device, a server, an emotion engine, and a large-scale language model.

[0348] Users input their emotions and states in natural language format through user devices such as smartphones and computers that they use daily. This input information is recorded on the device as user data.

[0349] The terminal transmits the received user data to the server via the internet. The server uses a secure communication protocol and takes care to protect the data during transmission.

[0350] The server preprocesses the received user data. This process includes cleaning and standardizing the data format to prepare it for smooth analysis.

[0351] The pre-processed data is analyzed by an emotion engine. The emotion engine utilizes natural language processing techniques to identify basic emotions from keywords and phrases within the text.

[0352] Subsequently, based on the analysis results of the emotion engine, a large-scale language model generates response data for the user. This model learns past data patterns using machine learning algorithms, specifically employing a generative AI model.

[0353] For example, if a user types "I'm feeling really down today," the sentiment engine, which includes a large-scale language model, recognizes the emotion "down" and generates a response such as "Don't worry, tomorrow will be a better day."

[0354] After completing the above procedures, the server sends the generated response data to the user's device, and the terminal displays it through the user interface. This allows the user to receive feedback from the system and use it to manage and improve their emotions in their daily life.

[0355] A concrete example of a prompt statement is, "When the user says, 'Something good happened today,' generate a response." This allows the system to generate responses tailored to the user's emotions.

[0356] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0357] Step 1:

[0358] The user inputs natural language text about their emotions and state into the user device. This input text is received by the user device and treated directly as user data. This process incorporates specific information about the user's emotions into the system.

[0359] Step 2:

[0360] The terminal transmits received user data to the server via the internet. The input here is the user's raw text data, and the output is ready to be sent to the server. Throughout this process, encrypted communication protocols are used to ensure the data remains secure.

[0361] Step 3:

[0362] The server preprocesses the received user data. This step involves cleaning the input data, removing noise and unnecessary whitespace. It also converts the data into an easily parseable format through format standardization. The output is clean, standardized text data.

[0363] Step 4:

[0364] The server supplies pre-processed data to the emotion engine. Based on the input data, the emotion engine uses natural language processing techniques to analyze keywords and phrases in the text and identify basic emotions such as joy and sadness. As output, data about the user's emotional state is generated.

[0365] Step 5:

[0366] The server generates response data using a large-scale language model based on emotional state data generated by the emotion engine. Using prompts based on the generative AI model, it devises appropriate feedback for the user's emotions. For example, it might generate something like, "Don't worry, tomorrow will be a better day." The output is the optimal response data for the user.

[0367] Step 6:

[0368] The generated response data is sent from the server to the user device. The terminal displays this response data through the user interface. This allows the user to see feedback on their emotions. The output is a text message presented in the user interface.

[0369] (Application Example 2)

[0370] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0371] In modern society, users face various stresses and emotional fluctuations in their daily lives. In particular, a challenge lies in the lack of immediate, appropriate feedback and encouragement tailored to their emotional state, resulting in insufficient personal emotional support. Furthermore, there is a lack of effective and rapid methods for providing personalized support tailored to individual situations using emotion recognition technology. Therefore, there is a need for technology that accurately analyzes users' emotions and provides appropriate responses quickly.

[0372] 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.

[0373] In this invention, the server includes means for receiving user data in natural language format input from a user device; means for analyzing the user data and utilizing a model for generating response data related to self-esteem or self-understanding; means for transmitting the response data to the user device; means including an emotion analysis device for analyzing the user's emotional state and providing appropriate feedback; means for generating response data for making action suggestions to the user based on the emotion analysis results; and means for displaying the response data on the user device and providing it as audio output. This makes it possible to analyze the user's emotional state in real time, provide action suggestions and encouragement tailored to individual needs, and effectively support the user's mental well-being.

[0374] A "user device" is a device used by a user to input data in natural language format, and includes smartphones and computers.

[0375] "Natural language" refers to the forms of language that humans use on a daily basis, and is a means of expressing emotions and thoughts.

[0376] "User data" refers to information about emotions and states that users input through the device.

[0377] A "model" refers to a computational method used to analyze data and generate responses using machine learning.

[0378] "Response data" refers to information including feedback and suggestions generated as a result of analyzing user data.

[0379] An "emotion analysis device" refers to a system that identifies the user's emotional state from their input data and provides appropriate feedback.

[0380] "Action suggestions" refer to instructions or advice that indicate what actions a user should take, based on their emotional state.

[0381] "Display" refers to the act of visually presenting the generated response data on the screen of the user's device.

[0382] "Voice output" refers to a means of transmitting generated response data to the user as voice.

[0383] To realize this invention, the user first inputs their emotions or state of mind into a user device using natural language. The user device includes smartphones and computers equipped with voice recognition and touch input functions. The input data is transmitted via the internet to a service provider's server.

[0384] When a server receives data, it first uses a cloud platform such as Amazon Web Services (AWS) or Microsoft Azure to preprocess the incoming data. This preprocessing involves cleaning the data and standardizing its format. As a result, sentiment analysis becomes easier.

[0385] Next, the server analyzes the user's emotional state using tools such as the Google Cloud Natural Language API. This emotion analyzer identifies emotional elements from the user's natural language data, recognizing basic emotions such as "joy" and "anger." Then, a large-scale language model generates response data using the identified emotional data.

[0386] The generated response data is adjusted according to the user's emotional state and sent to the user's device as personalized feedback. The response data is then presented to the user through a display or speaker on the user's device. This process makes it possible to provide the user with appropriate behavioral suggestions and encouragement.

[0387] For example, if a user enters "I'm very tired today," the server will perform sentiment analysis on this as "fatigue" and generate a response such as, "You worked hard today. Let's take some time to relax." This response may also be provided as voice output.

[0388] An example of a prompt would be, "User's mood: 'I'm nervous about a new project today.' Please think of an appropriate response and offer gentle encouragement." This prompt instructs the generative AI model to generate appropriate feedback based on the user's input.

[0389] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0390] Step 1:

[0391] The user inputs their emotions and state of mind into the device in natural language. The device captures the user's input as digital data using voice recognition and touch input functions. The input data can be in the form of text or voice data. As output, digital data in natural language format representing the user's emotions and state of mind is generated.

[0392] Step 2:

[0393] The terminal sends the input natural language data to the service provider's server over the internet. This data is encoded and transmitted using a secure protocol. As input, the terminal receives the captured natural language data, and as output, the same data is accurately sent to the server.

[0394] Step 3:

[0395] The server performs preprocessing of received natural language data on cloud platforms such as Amazon Web Services (AWS) and Microsoft Azure. This preprocessing includes noise reduction and formatting standardization to prepare the data for sentiment analysis. It receives raw natural language data as input and generates formatted data as output.

[0396] Step 4:

[0397] The server uses the formatted data to power the Google Cloud Natural Language API, which analyzes the user's emotional state. This API extracts emotional elements from the text, identifying emotions such as "joy" and "anger." It accepts pre-processed text data as input and generates emotional analysis information as output.

[0398] Step 5:

[0399] The server generates response data using a generative AI model based on information obtained from sentiment analysis. The model utilizes OpenAI's GPT and other technologies to generate optimal feedback for the user based on the prompt text. It uses sentiment analysis information as input and produces response data as output.

[0400] Step 6:

[0401] The server sends the generated response data to the terminal. The terminal presents this response data to the user as either a display or audio output. A display is used for display, and a speaker is used for audio output. The terminal receives response data from the server as input and presents it to the user in an appropriate format as output.

[0402] 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.

[0403] 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.

[0404] 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.

[0405] [Third Embodiment]

[0406] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0407] 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.

[0408] 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).

[0409] 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.

[0410] 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.

[0411] 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).

[0412] 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.

[0413] 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.

[0414] 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.

[0415] 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.

[0416] 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.

[0417] 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".

[0418] In this embodiment of the present invention, the process begins with the user inputting information about their self-esteem and self-understanding through a terminal. The user can input their worries and questions in natural language in text format. The terminal receives this input data and transmits it to a central server via the internet.

[0419] The server first preprocesses the received data. This preprocessing includes cleaning and standardizing the data, preparing it for smooth subsequent analysis. Next, the preprocessed data is input into a machine learning model on the server. This model is a large-scale language model that enables advanced language analysis based on user input.

[0420] Specifically, the model analyzes the user's natural language input, understands their intent, and generates appropriate responses to enhance the user's self-esteem. These responses may include words of encouragement or specific action suggestions.

[0421] The generated response data is sent from the server to the user's terminal. The terminal receives this data and displays it in a user-friendly format. This display uses an interface that is intuitively easy for the user to understand.

[0422] For example, when a user inputs "I've been lacking confidence lately," the server analyzes this and generates a response such as, "Recall your past successes and use those experiences to take your next step." In this way, the present invention aims to support users in deepening their self-understanding and increasing their self-esteem.

[0423] The following describes the processing flow.

[0424] Step 1:

[0425] The user inputs questions or concerns in natural language format using a device. The device then receives this user input as text data and prepares it.

[0426] Step 2:

[0427] The terminal transmits user input data to the server via the internet. During this process, the data transmission protocol employs appropriate encryption to protect user privacy.

[0428] Step 3:

[0429] The server receives text data sent from the terminal. After receiving the data, the server preprocesses it by removing unnecessary characters and special symbols, and standardizing the data format.

[0430] Step 4:

[0431] The pre-processed data is input into a machine learning model on the server. The server uses a large-scale language model to analyze the input data and understand the user's intentions and situation.

[0432] Step 5:

[0433] Based on the server's analysis, it generates response data that promotes the user's self-esteem and self-understanding. This may include encouraging messages or suggestions for the next course of action.

[0434] Step 6:

[0435] The generated response data is sent from the server to the terminal. This transmission also uses a secure communication protocol, taking user privacy into consideration.

[0436] Step 7:

[0437] The terminal displays the response data received from the server on the user interface. The user can review the displayed information, consider the next steps appropriate to their situation, and take action.

[0438] (Example 1)

[0439] 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."

[0440] Traditional systems made it difficult for users to receive appropriate support in real time to deepen their self-esteem and self-understanding. In particular, the lack of means to accurately analyze user intent using natural language and generate individually optimized responses meant that rapid and effective feedback could not be obtained, resulting in a limited user experience.

[0441] 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.

[0442] In this invention, the server includes means for receiving user information in natural language format input from a user terminal, means for preprocessing the user information to standardize its format, and means for analyzing the preprocessed information and utilizing a learning algorithm to generate response information that promotes self-esteem and self-understanding. As a result, users can quickly receive individually optimized responses and more effectively deepen their self-esteem and self-understanding.

[0443] A "user terminal" is a communication device used by a user to provide input information.

[0444] "Natural language forms" are forms expressed in human language used in everyday conversation.

[0445] "User information" refers to text data provided by users that relates to their self-esteem and self-understanding.

[0446] "Preprocessing" refers to the cleaning and standardization procedures used to prepare data for analysis.

[0447] "Standardization" is the process of unifying data formats and structures into a consistent format.

[0448] A "learning algorithm" is a computer program used to generate an appropriate response based on input data.

[0449] A "large-scale language processing model" is an advanced computer model that has the capability to understand and generate a wide variety of natural languages.

[0450] "Response information" refers to messages generated based on user input, designed to promote self-esteem and self-understanding.

[0451] An "information processing device" refers to the entire system used for receiving, analyzing, and transmitting data.

[0452] This invention begins with a user inputting information about their self-esteem and self-understanding through a communication device. The user inputs text data using natural language, and this information is received on the terminal. The terminal transmits the received user data to a server via the internet. The server preprocesses the data by cleaning and standardizing it, and then analyzes the preprocessed information. A large-scale language processing model is used for the analysis, and based on this model, an appropriate response is generated to enhance the user's self-esteem. The generated response is sent from the server to the user's terminal, which displays the response in a format that is easy for the user to understand.

[0453] For example, if a user inputs "I've been feeling insecure lately" into the terminal, the server analyzes this and generates a response message such as "Recall your past successes and use those experiences to take your next step." In this way, the invention supports users in deepening their self-understanding and improving their self-esteem. Another example of a prompt message might be one in the form of "If the user inputs 'I've been feeling insecure lately,' generate a response that will boost self-esteem."

[0454] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0455] Step 1:

[0456] The user inputs text data in natural language using a communication device. This input is based on the user's current worries and questions and is provided directly to the terminal. Specifically, the user enters the text "I've been feeling insecure lately" into the terminal's input field and presses the send button. Natural language text is provided as input and is recognized directly by the terminal.

[0457] Step 2:

[0458] The terminal receives input text from the user and sends it to the server via the internet. Here, security is ensured because the text data is packaged in an appropriate format (e.g., JSON) and sent to the server using the HTTPS protocol. The input is natural language text from the user, and the output sent is in a data format that the server can process.

[0459] Step 3:

[0460] The server preprocesses the received data, performing data cleaning and standardization. Specifically, it removes unnecessary whitespace and special characters and converts the data into a format that is easily understood by the language processing engine. It receives packaged natural language text as input and generates standardized text data as output.

[0461] Step 4:

[0462] The server uses a large-scale language processing model to analyze pre-processed data, understand the user's intent, and generate responses that enhance self-esteem. The model receives standardized text as input and outputs a message as response information such as, "Recall your past successes and use those experiences to take your next step."

[0463] Step 5:

[0464] The server sends the generated response data to the user's terminal. The data is then encoded again in an appropriate format (e.g., JSON) and securely sent to the terminal. The server receives response data as input and sends it back as output in a format that the user's terminal can display.

[0465] Step 6:

[0466] The terminal displays received responses in a user-friendly format. Specifically, it displays response messages on the terminal's chat interface and notifies the user. It receives formatted response information sent from the server as input and displays it as output in an intuitive user interface.

[0467] (Application Example 1)

[0468] 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."

[0469] In recent years, there has been a growing demand for technologies that support individual self-esteem and self-understanding. However, many technologies merely provide textual feedback in response to natural language input from users, and systems that offer intuitive and warm responses via voice are limited. This invention aims to improve users' mental well-being by providing a system that offers more natural and emotionally rich communication through voice input and output.

[0470] 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.

[0471] In this invention, the server includes means for receiving user data in natural language format input from a user device; means for analyzing the user data and utilizing a machine learning model to generate response data related to self-esteem or self-understanding; means for transmitting the response data to the user device; means for converting the response data into speech via a speech output device and providing it to the user; and means for recognizing the user's utterance using a speech input device and receiving it as user data in text format. This enables the user to intuitively receive mental care through voice.

[0472] A "user device" is a terminal device used by a user to input information and receive output.

[0473] "Natural language form" refers to data expressed in the language form that humans use on a daily basis.

[0474] "User data" refers to data that includes information entered by the user.

[0475] A "machine learning model" is a collection of algorithms that learn patterns based on data and perform predictions and classifications.

[0476] "Response data" refers to information generated based on user data and provided to the user.

[0477] An "audio output device" refers to a device that converts electronic data into sound and allows the user to hear it.

[0478] A "voice input device" is a device used to convert audio into a digital format.

[0479] "Natural language input" refers to the act of a user entering information using their own words, either through voice or text.

[0480] To realize this invention, a user device, a server, a voice input device, and a voice output device are required. The user speaks in natural language through the voice input device. This speech is converted into digital data by the voice input device and transmitted to the server as text data by the user device.

[0481] The server inputs the received user data into a machine learning model. This model includes a large-scale language model that generates response data based on the user data. The generated response data is converted into speech data using automatic speech synthesis technology and delivered to the user via a speech output device.

[0482] Specifically, speech input processing utilizes speech recognition software, such as "Google Speech-to-Text," to convert the speech into digital data. The generated text data is sent to a server, where it is analyzed using "OpenAI's large-scale language model" to generate appropriate response data. The generated response is then converted into speech using a speech synthesis engine such as "Amazon Polly."

[0483] For example, if a user says, "I'm feeling a little down today," the server recognizes this input and generates and provides encouraging words such as, "It's important to always look at the positive side. How about we take a little break together?"

[0484] An example of a prompt for a generative AI model is: "To provide mental support to the user, acknowledge what he / she is feeling and offer appropriate encouragement and action suggestions. Input: 'I'm feeling a little down today.'"

[0485] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0486] Step 1:

[0487] The user speaks in natural language through a voice input device. This voice data is input and sent to speech recognition software.

[0488] Step 2:

[0489] The voice input device uses speech recognition software (e.g., Google Speech-to-Text) to convert voice data into text data. This converted text data is then output to the terminal.

[0490] Step 3:

[0491] The terminal sends the acquired text data to the server via the internet. The server receives this text data as input.

[0492] Step 4:

[0493] The server uses a generative AI model (e.g., OpenAI's large-scale language model) to analyze the received text data. Based on the input text, the model generates response data designed to enhance the user's self-esteem. This response data is then output.

[0494] Step 5:

[0495] The server inputs the generated response data into a speech synthesis engine (e.g., Amazon Polly) and converts it into speech data. This converted speech data is then output.

[0496] Step 6:

[0497] The server transmits audio data to the terminal via the internet. The terminal then forwards this audio data to the audio output device.

[0498] Step 7:

[0499] The audio output device plays the received audio data and lets the user listen to it. This allows the user to receive mental care intuitively.

[0500] 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.

[0501] In embodiments of the present invention, the process begins with the user inputting their emotions or state in natural language via a terminal. The user can input text about their emotions or situation, and this data is received by the terminal. The received data is transmitted to a central server via the internet.

[0502] The server first preprocesses the received user data, cleaning and standardizing its format. This preprocessing makes the data easier to analyze using the emotion engine and machine learning models.

[0503] Next, the server supplies the pre-processed data to the emotion engine. This emotion engine analyzes the emotional elements contained in the user input to detect and recognize the user's emotional state. In this process, it identifies basic emotions (e.g., joy, sadness, anger, etc.) from keywords and phrases contained in the text.

[0504] Subsequently, the emotional information recognized by the emotion engine is used in conjunction with a large-scale language model on the server to generate appropriate response data. The response data is adjusted to the user's emotional state, providing more personalized feedback. The responses generated at this stage aim to take emotional changes into account and offer the most appropriate encouragement and action suggestions to the user.

[0505] For example, if a user types "I'm feeling really down today," the emotion engine detects the emotion, and the large-scale language model provides a response such as "Don't worry, tomorrow will be a better day."

[0506] Finally, the generated response data is sent from the server to the terminal and displayed to the user via the user interface. Based on this response, the user can decide on their next action and use it as a means to improve their emotions and situation. This invention realizes a system that enables advanced responses tailored to the individual needs of users by integrating emotion recognition functionality.

[0507] The following describes the processing flow.

[0508] Step 1:

[0509] The user uses the device to input their feelings or questions in natural language. The device receives this input as text data.

[0510] Step 2:

[0511] The device sends text data from the user to the server. The data is communicated over the internet and protected by a secure protocol.

[0512] Step 3:

[0513] The server preprocesses the received text data. This preprocessing involves filtering out unnecessary information and standardizing the data format to facilitate subsequent analysis.

[0514] Step 4:

[0515] The pre-processed data is input into the emotion engine on the server. The emotion engine analyzes the text to recognize the emotions expressed by the user. Specifically, it identifies emotions such as joy, sadness, and anger based on certain words and phrases.

[0516] Step 5:

[0517] The server uses the output of the emotion engine to input data into a large-scale language model, which is a machine learning model, to generate a response appropriate to the user's emotions and context. This response is personalized according to the user's emotional state.

[0518] Step 6:

[0519] The server sends the generated response data to the terminal. As with other communications, the data is transmitted using appropriate security measures.

[0520] Step 7:

[0521] The terminal displays response data received from the server to the user. Based on the displayed response, the user can consider actions to manage their own situation and emotions.

[0522] (Example 2)

[0523] 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."

[0524] In modern society, many individuals face challenges in managing their emotions and mental state. In particular, a lack of adequate means to obtain individually tailored emotional feedback prevents users from receiving appropriate responses to their emotional changes. This project aims to address this problem and provide prompt and effective support tailored to each individual's emotional state.

[0525] 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.

[0526] In this invention, the server includes means for receiving user data in natural language format input from a user device, means for preprocessing the user data, cleaning the data and standardizing its format, and means for analyzing the preprocessed data and utilizing an emotion engine and machine learning models to generate response data related to the user's emotional state. This makes it possible to quickly provide personalized feedback based on each user's emotional state.

[0527] A "user device" is a device used by a user to input information, and includes smartphones, computers, and other similar devices.

[0528] "Natural language form" refers to forms expressed in the language that humans normally use, and includes text and conversational text.

[0529] "User data" refers to information entered by users, including text information related to emotions and situations.

[0530] "Preprocessing" refers to initial processing to make data easier to analyze, and includes cleaning and formatting standardization.

[0531] "Data cleaning" refers to the process of removing unnecessary elements from data, including the removal of noise and special characters.

[0532] "Format standardization" is the process of converting data into a unified format, and it is an effort to ensure consistency.

[0533] An "emotion engine" is a device or program that analyzes user data to identify emotions, and utilizes natural language processing technology.

[0534] A "machine learning model" is an algorithm or mathematical model used to recognize data patterns and make predictions or classifications.

[0535] "Response data" refers to information generated based on the analysis results and is provided to the user as feedback.

[0536] A "user interface" is a means for a user to interact with a system, and includes screen displays and control panels.

[0537] This invention relates to a system that provides personalized responses tailored to the user's emotions. This system is primarily implemented using a user device, a server, an emotion engine, and a large-scale language model.

[0538] Users input their emotions and states in natural language format through user devices such as smartphones and computers that they use daily. This input information is recorded on the device as user data.

[0539] The terminal transmits the received user data to the server via the internet. The server uses a secure communication protocol and takes care to protect the data during transmission.

[0540] The server preprocesses the received user data. This process includes cleaning and standardizing the data format to prepare it for smooth analysis.

[0541] The pre-processed data is analyzed by an emotion engine. The emotion engine utilizes natural language processing techniques to identify basic emotions from keywords and phrases within the text.

[0542] Subsequently, based on the analysis results of the emotion engine, a large-scale language model generates response data for the user. This model learns past data patterns using machine learning algorithms, specifically employing a generative AI model.

[0543] For example, if a user types "I'm feeling really down today," the sentiment engine, which includes a large-scale language model, recognizes the emotion "down" and generates a response such as "Don't worry, tomorrow will be a better day."

[0544] After completing the above procedures, the server sends the generated response data to the user's device, and the terminal displays it through the user interface. This allows the user to receive feedback from the system and use it to manage and improve their emotions in their daily life.

[0545] A concrete example of a prompt statement is, "When the user says, 'Something good happened today,' generate a response." This allows the system to generate responses tailored to the user's emotions.

[0546] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0547] Step 1:

[0548] The user inputs natural language text about their emotions and state into the user device. This input text is received by the user device and treated directly as user data. This process incorporates specific information about the user's emotions into the system.

[0549] Step 2:

[0550] The terminal transmits received user data to the server via the internet. The input here is the user's raw text data, and the output is ready to be sent to the server. Throughout this process, encrypted communication protocols are used to ensure the data remains secure.

[0551] Step 3:

[0552] The server preprocesses the received user data. This step involves cleaning the input data, removing noise and unnecessary whitespace. It also converts the data into an easily parseable format through format standardization. The output is clean, standardized text data.

[0553] Step 4:

[0554] The server supplies pre-processed data to the emotion engine. Based on the input data, the emotion engine uses natural language processing techniques to analyze keywords and phrases in the text and identify basic emotions such as joy and sadness. As output, data about the user's emotional state is generated.

[0555] Step 5:

[0556] The server generates response data using a large-scale language model based on emotional state data generated by the emotion engine. Using prompts based on the generative AI model, it devises appropriate feedback for the user's emotions. For example, it might generate something like, "Don't worry, tomorrow will be a better day." The output is the optimal response data for the user.

[0557] Step 6:

[0558] The generated response data is sent from the server to the user device. The terminal displays this response data through the user interface. This allows the user to see feedback on their emotions. The output is a text message presented in the user interface.

[0559] (Application Example 2)

[0560] 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."

[0561] In modern society, users face various stresses and emotional fluctuations in their daily lives. In particular, a challenge lies in the lack of immediate, appropriate feedback and encouragement tailored to their emotional state, resulting in insufficient personal emotional support. Furthermore, there is a lack of effective and rapid methods for providing personalized support tailored to individual situations using emotion recognition technology. Therefore, there is a need for technology that accurately analyzes users' emotions and provides appropriate responses quickly.

[0562] 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.

[0563] In this invention, the server includes means for receiving user data in natural language format input from a user device; means for analyzing the user data and utilizing a model for generating response data related to self-esteem or self-understanding; means for transmitting the response data to the user device; means including an emotion analysis device for analyzing the user's emotional state and providing appropriate feedback; means for generating response data for making action suggestions to the user based on the emotion analysis results; and means for displaying the response data on the user device and providing it as audio output. This makes it possible to analyze the user's emotional state in real time, provide action suggestions and encouragement tailored to individual needs, and effectively support the user's mental well-being.

[0564] A "user device" is a device used by a user to input data in natural language format, and includes smartphones and computers.

[0565] "Natural language" refers to the forms of language that humans use on a daily basis, and is a means of expressing emotions and thoughts.

[0566] "User data" refers to information about emotions and states that users input through the device.

[0567] A "model" refers to a computational method used to analyze data and generate responses using machine learning.

[0568] "Response data" refers to information including feedback and suggestions generated as a result of analyzing user data.

[0569] An "emotion analysis device" refers to a system that identifies the user's emotional state from their input data and provides appropriate feedback.

[0570] "Action suggestions" refer to instructions or advice that indicate what actions a user should take, based on their emotional state.

[0571] "Display" refers to the act of visually presenting the generated response data on the screen of the user's device.

[0572] "Voice output" refers to a means of transmitting generated response data to the user as voice.

[0573] To realize this invention, the user first inputs their emotions or state of mind into a user device using natural language. The user device includes smartphones and computers equipped with voice recognition and touch input functions. The input data is transmitted via the internet to a service provider's server.

[0574] When a server receives data, it first uses a cloud platform such as Amazon Web Services (AWS) or Microsoft Azure to preprocess the incoming data. This preprocessing involves cleaning the data and standardizing its format. As a result, sentiment analysis becomes easier.

[0575] Next, the server analyzes the user's emotional state using tools such as the Google Cloud Natural Language API. This emotion analyzer identifies emotional elements from the user's natural language data, recognizing basic emotions such as "joy" and "anger." Then, a large-scale language model generates response data using the identified emotional data.

[0576] The generated response data is adjusted according to the user's emotional state and sent to the user's device as personalized feedback. The response data is then presented to the user through a display or speaker on the user's device. This process makes it possible to provide the user with appropriate behavioral suggestions and encouragement.

[0577] For example, if a user enters "I'm very tired today," the server will perform sentiment analysis on this as "fatigue" and generate a response such as, "You worked hard today. Let's take some time to relax." This response may also be provided as voice output.

[0578] An example of a prompt would be, "User's mood: 'I'm nervous about a new project today.' Please think of an appropriate response and offer gentle encouragement." This prompt instructs the generative AI model to generate appropriate feedback based on the user's input.

[0579] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0580] Step 1:

[0581] The user inputs their emotions and state of mind into the device in natural language. The device captures the user's input as digital data using voice recognition and touch input functions. The input data can be in the form of text or voice data. As output, digital data in natural language format representing the user's emotions and state of mind is generated.

[0582] Step 2:

[0583] The terminal sends the input natural language data to the service provider's server over the internet. This data is encoded and transmitted using a secure protocol. As input, the terminal receives the captured natural language data, and as output, the same data is accurately sent to the server.

[0584] Step 3:

[0585] The server performs preprocessing of received natural language data on cloud platforms such as Amazon Web Services (AWS) and Microsoft Azure. This preprocessing includes noise reduction and formatting standardization to prepare the data for sentiment analysis. It receives raw natural language data as input and generates formatted data as output.

[0586] Step 4:

[0587] The server uses the formatted data to power the Google Cloud Natural Language API, which analyzes the user's emotional state. This API extracts emotional elements from the text, identifying emotions such as "joy" and "anger." It accepts pre-processed text data as input and generates emotional analysis information as output.

[0588] Step 5:

[0589] The server generates response data using a generative AI model based on information obtained from sentiment analysis. The model utilizes OpenAI's GPT and other technologies to generate optimal feedback for the user based on the prompt text. It uses sentiment analysis information as input and produces response data as output.

[0590] Step 6:

[0591] The server sends the generated response data to the terminal. The terminal presents this response data to the user as either a display or audio output. A display is used for display, and a speaker is used for audio output. The terminal receives response data from the server as input and presents it to the user in an appropriate format as output.

[0592] 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.

[0593] 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.

[0594] 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.

[0595] [Fourth Embodiment]

[0596] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0597] 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.

[0598] 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).

[0599] 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.

[0600] 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.

[0601] 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).

[0602] 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.

[0603] 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.

[0604] 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.

[0605] 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.

[0606] 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.

[0607] 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.

[0608] 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".

[0609] In this embodiment of the present invention, the process begins with the user inputting information about their self-esteem and self-understanding through a terminal. The user can input their worries and questions in natural language in text format. The terminal receives this input data and transmits it to a central server via the internet.

[0610] The server first preprocesses the received data. This preprocessing includes cleaning and standardizing the data, preparing it for smooth subsequent analysis. Next, the preprocessed data is input into a machine learning model on the server. This model is a large-scale language model that enables advanced language analysis based on user input.

[0611] Specifically, the model analyzes the user's natural language input, understands their intent, and generates appropriate responses to enhance the user's self-esteem. These responses may include words of encouragement or specific action suggestions.

[0612] The generated response data is sent from the server to the user's terminal. The terminal receives this data and displays it in a user-friendly format. This display uses an interface that is intuitively easy for the user to understand.

[0613] For example, when a user inputs "I've been lacking confidence lately," the server analyzes this and generates a response such as, "Recall your past successes and use those experiences to take your next step." In this way, the present invention aims to support users in deepening their self-understanding and increasing their self-esteem.

[0614] The following describes the processing flow.

[0615] Step 1:

[0616] The user inputs questions or concerns in natural language format using a device. The device then receives this user input as text data and prepares it.

[0617] Step 2:

[0618] The terminal transmits user input data to the server via the internet. During this process, the data transmission protocol employs appropriate encryption to protect user privacy.

[0619] Step 3:

[0620] The server receives text data sent from the terminal. After receiving the data, the server preprocesses it by removing unnecessary characters and special symbols, and standardizing the data format.

[0621] Step 4:

[0622] The pre-processed data is input into a machine learning model on the server. The server uses a large-scale language model to analyze the input data and understand the user's intentions and situation.

[0623] Step 5:

[0624] Based on the server's analysis, it generates response data that promotes the user's self-esteem and self-understanding. This may include encouraging messages or suggestions for the next course of action.

[0625] Step 6:

[0626] The generated response data is sent from the server to the terminal. This transmission also uses a secure communication protocol, taking user privacy into consideration.

[0627] Step 7:

[0628] The terminal displays the response data received from the server on the user interface. The user can review the displayed information, consider the next steps appropriate to their situation, and take action.

[0629] (Example 1)

[0630] 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".

[0631] Traditional systems made it difficult for users to receive appropriate support in real time to deepen their self-esteem and self-understanding. In particular, the lack of means to accurately analyze user intent using natural language and generate individually optimized responses meant that rapid and effective feedback could not be obtained, resulting in a limited user experience.

[0632] 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.

[0633] In this invention, the server includes means for receiving user information in natural language format input from a user terminal, means for preprocessing the user information to standardize its format, and means for analyzing the preprocessed information and utilizing a learning algorithm to generate response information that promotes self-esteem and self-understanding. As a result, users can quickly receive individually optimized responses and more effectively deepen their self-esteem and self-understanding.

[0634] A "user terminal" is a communication device used by a user to provide input information.

[0635] "Natural language forms" are forms expressed in human language used in everyday conversation.

[0636] "User information" refers to text data provided by users that relates to their self-esteem and self-understanding.

[0637] "Preprocessing" refers to the cleaning and standardization procedures used to prepare data for analysis.

[0638] "Standardization" is the process of unifying data formats and structures into a consistent format.

[0639] A "learning algorithm" is a computer program used to generate an appropriate response based on input data.

[0640] A "large-scale language processing model" is an advanced computer model that has the capability to understand and generate a wide variety of natural languages.

[0641] "Response information" refers to messages generated based on user input, designed to promote self-esteem and self-understanding.

[0642] An "information processing device" refers to the entire system used for receiving, analyzing, and transmitting data.

[0643] This invention begins with a user inputting information about their self-esteem and self-understanding through a communication device. The user inputs text data using natural language, and this information is received on the terminal. The terminal transmits the received user data to a server via the internet. The server preprocesses the data by cleaning and standardizing it, and then analyzes the preprocessed information. A large-scale language processing model is used for the analysis, and based on this model, an appropriate response is generated to enhance the user's self-esteem. The generated response is sent from the server to the user's terminal, which displays the response in a format that is easy for the user to understand.

[0644] For example, if a user inputs "I've been feeling insecure lately" into the terminal, the server analyzes this and generates a response message such as "Recall your past successes and use those experiences to take your next step." In this way, the invention supports users in deepening their self-understanding and improving their self-esteem. Another example of a prompt message might be one in the form of "If the user inputs 'I've been feeling insecure lately,' generate a response that will boost self-esteem."

[0645] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0646] Step 1:

[0647] The user inputs text data in natural language using a communication device. This input is based on the user's current worries and questions and is provided directly to the terminal. Specifically, the user enters the text "I've been feeling insecure lately" into the terminal's input field and presses the send button. Natural language text is provided as input and is recognized directly by the terminal.

[0648] Step 2:

[0649] The terminal receives input text from the user and sends it to the server via the internet. Here, security is ensured because the text data is packaged in an appropriate format (e.g., JSON) and sent to the server using the HTTPS protocol. The input is natural language text from the user, and the output sent is in a data format that the server can process.

[0650] Step 3:

[0651] The server preprocesses the received data, performing data cleaning and standardization. Specifically, it removes unnecessary whitespace and special characters and converts the data into a format that is easily understood by the language processing engine. It receives packaged natural language text as input and generates standardized text data as output.

[0652] Step 4:

[0653] The server uses a large-scale language processing model to analyze pre-processed data, understand the user's intent, and generate responses that enhance self-esteem. The model receives standardized text as input and outputs a message as response information such as, "Recall your past successes and use those experiences to take your next step."

[0654] Step 5:

[0655] The server sends the generated response data to the user's terminal. The data is then encoded again in an appropriate format (e.g., JSON) and securely sent to the terminal. The server receives response data as input and sends it back as output in a format that the user's terminal can display.

[0656] Step 6:

[0657] The terminal displays received responses in a user-friendly format. Specifically, it displays response messages on the terminal's chat interface and notifies the user. It receives formatted response information sent from the server as input and displays it as output in an intuitive user interface.

[0658] (Application Example 1)

[0659] 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".

[0660] In recent years, there has been a growing demand for technologies that support individual self-esteem and self-understanding. However, many technologies merely provide textual feedback in response to natural language input from users, and systems that offer intuitive and warm responses via voice are limited. This invention aims to improve users' mental well-being by providing a system that offers more natural and emotionally rich communication through voice input and output.

[0661] 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.

[0662] In this invention, the server includes means for receiving user data in natural language format input from a user device; means for analyzing the user data and utilizing a machine learning model to generate response data related to self-esteem or self-understanding; means for transmitting the response data to the user device; means for converting the response data into speech via a speech output device and providing it to the user; and means for recognizing the user's utterance using a speech input device and receiving it as user data in text format. This enables the user to intuitively receive mental care through voice.

[0663] A "user device" is a terminal device used by a user to input information and receive output.

[0664] "Natural language form" refers to data expressed in the language form that humans use on a daily basis.

[0665] "User data" refers to data that includes information entered by the user.

[0666] A "machine learning model" is a collection of algorithms that learn patterns based on data and perform predictions and classifications.

[0667] "Response data" refers to information generated based on user data and provided to the user.

[0668] An "audio output device" refers to a device that converts electronic data into sound and allows the user to hear it.

[0669] A "voice input device" is a device used to convert audio into a digital format.

[0670] "Natural language input" refers to the act of a user entering information using their own words, either through voice or text.

[0671] To realize this invention, a user device, a server, a voice input device, and a voice output device are required. The user speaks in natural language through the voice input device. This speech is converted into digital data by the voice input device and transmitted to the server as text data by the user device.

[0672] The server inputs the received user data into a machine learning model. This model includes a large-scale language model that generates response data based on the user data. The generated response data is converted into speech data using automatic speech synthesis technology and delivered to the user via a speech output device.

[0673] Specifically, speech input processing utilizes speech recognition software, such as "Google Speech-to-Text," to convert the speech into digital data. The generated text data is sent to a server, where it is analyzed using "OpenAI's large-scale language model" to generate appropriate response data. The generated response is then converted into speech using a speech synthesis engine such as "Amazon Polly."

[0674] For example, if a user says, "I'm feeling a little down today," the server recognizes this input and generates and provides encouraging words such as, "It's important to always look at the positive side. How about we take a little break together?"

[0675] An example of a prompt for a generative AI model is: "To provide mental support to the user, acknowledge what he / she is feeling and offer appropriate encouragement and action suggestions. Input: 'I'm feeling a little down today.'"

[0676] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0677] Step 1:

[0678] The user speaks in natural language through a voice input device. This voice data is input and sent to speech recognition software.

[0679] Step 2:

[0680] The voice input device uses speech recognition software (e.g., Google Speech-to-Text) to convert voice data into text data. This converted text data is then output to the terminal.

[0681] Step 3:

[0682] The terminal sends the acquired text data to the server via the internet. The server receives this text data as input.

[0683] Step 4:

[0684] The server uses a generative AI model (e.g., OpenAI's large-scale language model) to analyze the received text data. Based on the input text, the model generates response data designed to enhance the user's self-esteem. This response data is then output.

[0685] Step 5:

[0686] The server inputs the generated response data into a speech synthesis engine (e.g., Amazon Polly) and converts it into speech data. This converted speech data is then output.

[0687] Step 6:

[0688] The server transmits audio data to the terminal via the internet. The terminal then forwards this audio data to the audio output device.

[0689] Step 7:

[0690] The audio output device plays the received audio data and lets the user listen to it. This allows the user to receive mental care intuitively.

[0691] 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.

[0692] In embodiments of the present invention, the process begins with the user inputting their emotions or state in natural language via a terminal. The user can input text about their emotions or situation, and this data is received by the terminal. The received data is transmitted to a central server via the internet.

[0693] The server first preprocesses the received user data, cleaning and standardizing its format. This preprocessing makes the data easier to analyze using the emotion engine and machine learning models.

[0694] Next, the server supplies the pre-processed data to the emotion engine. This emotion engine analyzes the emotional elements contained in the user input to detect and recognize the user's emotional state. In this process, it identifies basic emotions (e.g., joy, sadness, anger, etc.) from keywords and phrases contained in the text.

[0695] Subsequently, the emotional information recognized by the emotion engine is used in conjunction with a large-scale language model on the server to generate appropriate response data. The response data is adjusted to the user's emotional state, providing more personalized feedback. The responses generated at this stage aim to take emotional changes into account and offer the most appropriate encouragement and action suggestions to the user.

[0696] For example, if a user types "I'm feeling really down today," the emotion engine detects the emotion, and the large-scale language model provides a response such as "Don't worry, tomorrow will be a better day."

[0697] Finally, the generated response data is sent from the server to the terminal and displayed to the user via the user interface. Based on this response, the user can decide on their next action and use it as a means to improve their emotions and situation. This invention realizes a system that enables advanced responses tailored to the individual needs of users by integrating emotion recognition functionality.

[0698] The following describes the processing flow.

[0699] Step 1:

[0700] The user uses the device to input their feelings or questions in natural language. The device receives this input as text data.

[0701] Step 2:

[0702] The device sends text data from the user to the server. The data is communicated over the internet and protected by a secure protocol.

[0703] Step 3:

[0704] The server preprocesses the received text data. This preprocessing involves filtering out unnecessary information and standardizing the data format to facilitate subsequent analysis.

[0705] Step 4:

[0706] The pre-processed data is input into the emotion engine on the server. The emotion engine analyzes the text to recognize the emotions expressed by the user. Specifically, it identifies emotions such as joy, sadness, and anger based on certain words and phrases.

[0707] Step 5:

[0708] The server uses the output of the emotion engine to input data into a large-scale language model, which is a machine learning model, to generate a response appropriate to the user's emotions and context. This response is personalized according to the user's emotional state.

[0709] Step 6:

[0710] The server sends the generated response data to the terminal. As with other communications, the data is transmitted using appropriate security measures.

[0711] Step 7:

[0712] The terminal displays response data received from the server to the user. Based on the displayed response, the user can consider actions to manage their own situation and emotions.

[0713] (Example 2)

[0714] 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".

[0715] In modern society, many individuals face challenges in managing their emotions and mental state. In particular, a lack of adequate means to obtain individually tailored emotional feedback prevents users from receiving appropriate responses to their emotional changes. This project aims to address this problem and provide prompt and effective support tailored to each individual's emotional state.

[0716] 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.

[0717] In this invention, the server includes means for receiving user data in natural language format input from a user device, means for preprocessing the user data, cleaning the data and standardizing its format, and means for analyzing the preprocessed data and utilizing an emotion engine and machine learning models to generate response data related to the user's emotional state. This makes it possible to quickly provide personalized feedback based on each user's emotional state.

[0718] A "user device" is a device used by a user to input information, and includes smartphones, computers, and other similar devices.

[0719] "Natural language form" refers to forms expressed in the language that humans normally use, and includes text and conversational text.

[0720] "User data" refers to information entered by users, including text information related to emotions and situations.

[0721] "Preprocessing" refers to initial processing to make data easier to analyze, and includes cleaning and formatting standardization.

[0722] "Data cleaning" refers to the process of removing unnecessary elements from data, including the removal of noise and special characters.

[0723] "Format standardization" is the process of converting data into a unified format, and it is an effort to ensure consistency.

[0724] An "emotion engine" is a device or program that analyzes user data to identify emotions, and utilizes natural language processing technology.

[0725] A "machine learning model" is an algorithm or mathematical model used to recognize data patterns and make predictions or classifications.

[0726] "Response data" refers to information generated based on the analysis results and is provided to the user as feedback.

[0727] A "user interface" is a means for a user to interact with a system, and includes screen displays and control panels.

[0728] This invention relates to a system that provides personalized responses tailored to the user's emotions. This system is primarily implemented using a user device, a server, an emotion engine, and a large-scale language model.

[0729] Users input their emotions and states in natural language format through user devices such as smartphones and computers that they use daily. This input information is recorded on the device as user data.

[0730] The terminal transmits the received user data to the server via the internet. The server uses a secure communication protocol and takes care to protect the data during transmission.

[0731] The server preprocesses the received user data. This process includes cleaning and standardizing the data format to prepare it for smooth analysis.

[0732] The pre-processed data is analyzed by an emotion engine. The emotion engine utilizes natural language processing techniques to identify basic emotions from keywords and phrases within the text.

[0733] Subsequently, based on the analysis results of the emotion engine, a large-scale language model generates response data for the user. This model learns past data patterns using machine learning algorithms, specifically employing a generative AI model.

[0734] For example, if a user types "I'm feeling really down today," the sentiment engine, which includes a large-scale language model, recognizes the emotion "down" and generates a response such as "Don't worry, tomorrow will be a better day."

[0735] After completing the above procedures, the server sends the generated response data to the user's device, and the terminal displays it through the user interface. This allows the user to receive feedback from the system and use it to manage and improve their emotions in their daily life.

[0736] A concrete example of a prompt statement is, "When the user says, 'Something good happened today,' generate a response." This allows the system to generate responses tailored to the user's emotions.

[0737] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0738] Step 1:

[0739] The user inputs natural language text about their emotions and state into the user device. This input text is received by the user device and treated directly as user data. This process incorporates specific information about the user's emotions into the system.

[0740] Step 2:

[0741] The terminal transmits received user data to the server via the internet. The input here is the user's raw text data, and the output is ready to be sent to the server. Throughout this process, encrypted communication protocols are used to ensure the data remains secure.

[0742] Step 3:

[0743] The server preprocesses the received user data. This step involves cleaning the input data, removing noise and unnecessary whitespace. It also converts the data into an easily parseable format through format standardization. The output is clean, standardized text data.

[0744] Step 4:

[0745] The server supplies pre-processed data to the emotion engine. Based on the input data, the emotion engine uses natural language processing techniques to analyze keywords and phrases in the text and identify basic emotions such as joy and sadness. As output, data about the user's emotional state is generated.

[0746] Step 5:

[0747] The server generates response data using a large-scale language model based on emotional state data generated by the emotion engine. Using prompts based on the generative AI model, it devises appropriate feedback for the user's emotions. For example, it might generate something like, "Don't worry, tomorrow will be a better day." The output is the optimal response data for the user.

[0748] Step 6:

[0749] The generated response data is sent from the server to the user device. The terminal displays this response data through the user interface. This allows the user to see feedback on their emotions. The output is a text message presented in the user interface.

[0750] (Application Example 2)

[0751] 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".

[0752] In modern society, users face various stresses and emotional fluctuations in their daily lives. In particular, a challenge lies in the lack of immediate, appropriate feedback and encouragement tailored to their emotional state, resulting in insufficient personal emotional support. Furthermore, there is a lack of effective and rapid methods for providing personalized support tailored to individual situations using emotion recognition technology. Therefore, there is a need for technology that accurately analyzes users' emotions and provides appropriate responses quickly.

[0753] 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.

[0754] In this invention, the server includes means for receiving user data in natural language format input from a user device; means for analyzing the user data and utilizing a model for generating response data related to self-esteem or self-understanding; means for transmitting the response data to the user device; means including an emotion analysis device for analyzing the user's emotional state and providing appropriate feedback; means for generating response data for making action suggestions to the user based on the emotion analysis results; and means for displaying the response data on the user device and providing it as audio output. This makes it possible to analyze the user's emotional state in real time, provide action suggestions and encouragement tailored to individual needs, and effectively support the user's mental well-being.

[0755] A "user device" is a device used by a user to input data in natural language format, and includes smartphones and computers.

[0756] "Natural language" refers to the forms of language that humans use on a daily basis, and is a means of expressing emotions and thoughts.

[0757] "User data" refers to information about emotions and states that users input through the device.

[0758] A "model" refers to a computational method used to analyze data and generate responses using machine learning.

[0759] "Response data" refers to information including feedback and suggestions generated as a result of analyzing user data.

[0760] An "emotion analysis device" refers to a system that identifies the user's emotional state from their input data and provides appropriate feedback.

[0761] "Action suggestions" refer to instructions or advice that indicate what actions a user should take, based on their emotional state.

[0762] "Display" refers to the act of visually presenting the generated response data on the screen of the user's device.

[0763] "Voice output" refers to a means of transmitting generated response data to the user as voice.

[0764] To realize this invention, the user first inputs their emotions or state of mind into a user device using natural language. The user device includes smartphones and computers equipped with voice recognition and touch input functions. The input data is transmitted via the internet to a service provider's server.

[0765] When a server receives data, it first uses a cloud platform such as Amazon Web Services (AWS) or Microsoft Azure to preprocess the incoming data. This preprocessing involves cleaning the data and standardizing its format. As a result, sentiment analysis becomes easier.

[0766] Next, the server analyzes the user's emotional state using tools such as the Google Cloud Natural Language API. This emotion analyzer identifies emotional elements from the user's natural language data, recognizing basic emotions such as "joy" and "anger." Then, a large-scale language model generates response data using the identified emotional data.

[0767] The generated response data is adjusted according to the user's emotional state and sent to the user's device as personalized feedback. The response data is then presented to the user through a display or speaker on the user's device. This process makes it possible to provide the user with appropriate behavioral suggestions and encouragement.

[0768] For example, if a user enters "I'm very tired today," the server will perform sentiment analysis on this as "fatigue" and generate a response such as, "You worked hard today. Let's take some time to relax." This response may also be provided as voice output.

[0769] An example of a prompt would be, "User's mood: 'I'm nervous about a new project today.' Please think of an appropriate response and offer gentle encouragement." This prompt instructs the generative AI model to generate appropriate feedback based on the user's input.

[0770] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0771] Step 1:

[0772] The user inputs their emotions and state of mind into the device in natural language. The device captures the user's input as digital data using voice recognition and touch input functions. The input data can be in the form of text or voice data. As output, digital data in natural language format representing the user's emotions and state of mind is generated.

[0773] Step 2:

[0774] The terminal sends the input natural language data to the service provider's server over the internet. This data is encoded and transmitted using a secure protocol. As input, the terminal receives the captured natural language data, and as output, the same data is accurately sent to the server.

[0775] Step 3:

[0776] The server performs preprocessing of received natural language data on cloud platforms such as Amazon Web Services (AWS) and Microsoft Azure. This preprocessing includes noise reduction and formatting standardization to prepare the data for sentiment analysis. It receives raw natural language data as input and generates formatted data as output.

[0777] Step 4:

[0778] The server uses the formatted data to power the Google Cloud Natural Language API, which analyzes the user's emotional state. This API extracts emotional elements from the text, identifying emotions such as "joy" and "anger." It accepts pre-processed text data as input and generates emotional analysis information as output.

[0779] Step 5:

[0780] The server generates response data using a generative AI model based on information obtained from sentiment analysis. The model utilizes OpenAI's GPT and other technologies to generate optimal feedback for the user based on the prompt text. It uses sentiment analysis information as input and produces response data as output.

[0781] Step 6:

[0782] The server sends the generated response data to the terminal. The terminal presents this response data to the user as either a display or audio output. A display is used for display, and a speaker is used for audio output. The terminal receives response data from the server as input and presents it to the user in an appropriate format as output.

[0783] 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.

[0784] 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.

[0785] 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.

[0786] 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.

[0787] 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.

[0788] 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.

[0789] 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.

[0790] 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.

[0791] 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."

[0792] 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.

[0793] 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.

[0794] 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.

[0795] 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.

[0796] 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.

[0797] 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.

[0798] 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.

[0799] 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.

[0800] 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.

[0801] 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.

[0802] 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.

[0803] 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.

[0804] The following is further disclosed regarding the embodiments described above.

[0805] (Claim 1)

[0806] A means for receiving user data in natural language format input from a user device,

[0807] A means of analyzing the user data and utilizing a machine learning model to generate response data related to self-esteem or self-understanding,

[0808] Means for transmitting the response data to the user device,

[0809] A system that includes this.

[0810] (Claim 2)

[0811] The system according to claim 1, wherein the machine learning model includes a large-scale language model.

[0812] (Claim 3)

[0813] The system according to claim 1, further comprising means for preprocessing the user input data and standardizing the data format.

[0814] "Example 1"

[0815] (Claim 1)

[0816] A means for receiving user information in natural language format entered from a user terminal,

[0817] Means for preprocessing the user information and standardizing its format,

[0818] A means for analyzing the pre-processed information and utilizing a learning algorithm to generate response information that promotes self-esteem and self-understanding,

[0819] Means for transmitting the response information to the user terminal,

[0820] Information processing device including

[0821] (Claim 2)

[0822] The information processing apparatus according to claim 1, wherein the learning algorithm includes a large-scale language processing model.

[0823] (Claim 3)

[0824] The information processing apparatus according to claim 1, further comprising means for preprocessing the user information and standardizing the information format.

[0825] "Application Example 1"

[0826] (Claim 1)

[0827] A means for receiving user data in natural language format input from a user device,

[0828] A means of analyzing the user data and utilizing a machine learning model to generate response data related to self-esteem or self-understanding,

[0829] Means for transmitting the response data to the user device,

[0830] A means for converting the response data into speech via an audio output device and providing it to the user,

[0831] A means for recognizing user speech using a voice input device and receiving it as user data in text format,

[0832] A system that includes this.

[0833] (Claim 2)

[0834] The system according to claim 1, wherein the machine learning model includes a large-scale language model.

[0835] (Claim 3)

[0836] The system according to claim 1, further comprising means for preprocessing the user input data and standardizing the data format.

[0837] "Example 2 of combining an emotion engine"

[0838] (Claim 1)

[0839] A means for receiving user data in natural language format input from a user device,

[0840] Means for preprocessing the user data, cleaning the data, and standardizing the format,

[0841] A means of analyzing preprocessed data and utilizing an emotion engine and machine learning models to generate response data related to the user's emotional state,

[0842] Means for transmitting the response data to the user device and providing it via the user interface,

[0843] A system that includes this.

[0844] (Claim 2)

[0845] The system according to claim 1, wherein the machine learning model includes a large-scale language model.

[0846] (Claim 3)

[0847] The system according to claim 1, wherein the emotion engine includes means for analyzing keywords and phrases in text and identifying basic emotions.

[0848] "Application example 2 when combining with an emotional engine"

[0849] (Claim 1)

[0850] A means for receiving user data in natural language format input from a user device,

[0851] A means of analyzing the user data and utilizing a model to generate response data related to self-esteem or self-understanding,

[0852] Means for transmitting the response data to the user device,

[0853] Means including an emotion analysis device for analyzing the user's emotional state and providing appropriate feedback,

[0854] A means for generating response data to make action suggestions to the user based on the emotion analysis results,

[0855] A means for displaying response data on the user device and providing it as audio output,

[0856] A system that includes this.

[0857] (Claim 2)

[0858] The system according to claim 1, wherein the model includes a large-scale language model and is tuned to be consistent with emotion recognition.

[0859] (Claim 3)

[0860] The system according to claim 1, further comprising means for preprocessing the user input data and standardizing the data format. [Explanation of Symbols]

[0861] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for receiving user data in natural language format input from a user device, A means of analyzing the user data and utilizing a machine learning model to generate response data related to self-esteem or self-understanding, Means for transmitting the response data to the user device, A means for converting the response data into speech via an audio output device and providing it to the user, A means for recognizing user speech using a voice input device and receiving it as user data in text format, A system that includes this.

2. The system according to claim 1, wherein the machine learning model includes a large-scale language model.

3. The system according to claim 1, further comprising means for preprocessing the user input data and standardizing the data format.

Images