system

Abstract

We provide the system. [Solution] A speech recognition means that receives the user's voice and converts the voice into text data, A natural language processing means for analyzing user requests from the aforementioned text data, A data learning means that generates suggestions using user behavior history and preference data based on analyzed requests, An output means for notifying the user of the proposal, 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 method for controlling a persona chatbot, which is performed by at least one processor, including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern times, busy people have difficulties in schedule management and efficiency improvement of daily tasks, which has become a stress factor. To solve this problem, there is a need for a device that learns the user's behavior and preferences and provides support at an appropriate timing. However, conventional methods have the problem that they cannot flexibly respond to various user needs and it is difficult to provide efficient support.

Means for Solving the Problems

[0005] To solve this problem, the present invention provides a system including speech recognition means for receiving user voice and converting the voice into text data, natural language processing means for analyzing user requests from the text data, data learning means for generating suggestions based on the analyzed requests using the user's behavior history and preference data, and output means for notifying the user of the suggestions. Furthermore, it is equipped with schedule management means and has a function to acquire user schedule information and automatically generate reminders, thereby prioritizing the user's tasks and realizing efficient daily support.

[0006] "Voice recognition means" refers to technology that converts a user's voice into a digital signal and then into text data.

[0007] "Natural language processing means" refers to technology that analyzes text data obtained through speech recognition, understands the user's requests and intentions, and converts them into appropriate instructions.

[0008] "Data learning methods" refer to technologies that use machine learning algorithms to generate optimal suggestions for users based on their behavioral history and preference data.

[0009] "Output means" refers to devices or interfaces for notifying the user of generated suggestions or instructions.

[0010] A "schedule management system" is a function that collects and organizes the user's schedule information, automatically generates reminders, and notifies the user.

[0011] A "task management tool" is a function that analyzes a user's task information and prioritizes and organizes it according to its importance and urgency. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2]This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

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

[0015] In the following embodiments, a processor with a reference number (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

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

[0017] In the following embodiments, a storage with a reference number 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.

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

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

[0020] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0033] This invention is a digital butler system that uses a wearable device to efficiently support the busy lives of users. The system functions by combining voice recognition means, natural language processing means, data learning means, output means, schedule management means, and task management means. Its specific operation is described below.

[0034] This system's speech recognition mechanism receives user voice input through a microphone built into the terminal and converts the voice data into digital format. Next, the server receives the voice data, converts it into text using natural language processing technology, and analyzes its content. This identifies the user's requests and questions and prepares an appropriate response.

[0035] Based on the analyzed information, the server uses data learning tools to learn the user's daily patterns and preferences. This learning enables the server to generate personalized suggestions and information for the user and deliver them through output tools. For example, if the server learns that a user tends to set an alarm at 7:00 AM, it will continuously set an alarm at that time.

[0036] Furthermore, the system automatically retrieves the user's schedule using a scheduling tool and creates reminders. For example, if there is a meeting scheduled, it can be set to send a notification at the appropriate time. The task management tool organizes and prioritizes the tasks that the user must manage. By prioritizing important and urgent tasks, the system enables efficient task management.

[0037] As a concrete example, if a user uses voice input to say, "Tell me what my schedule is for tomorrow," the device picks up the voice and sends it to the server. The server analyzes the request through natural language processing, and, referring to the data learning results, generates information based on the user's schedule. Finally, the device conveys that information to the user via voice.

[0038] This system allows users to receive support in all aspects of their daily lives, enabling them to make more effective use of their time.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] User: Gives a voice command to the wearable device saying, "Tell me the weather for tomorrow."

[0042] Step 2:

[0043] Terminal: The built-in microphone captures the user's voice and converts it into a digital signal. This signal is then sent to the server as digital data.

[0044] Step 3:

[0045] Server: Converts received audio data into text data using a speech recognition engine.

[0046] Step 4:

[0047] Server: Uses natural language processing (NLP) techniques to analyze text data to determine if it is a request for a "weather forecast".

[0048] Step 5:

[0049] Server: Based on the analysis results, retrieves necessary weather data from the weather information API.

[0050] Step 6:

[0051] Server: Formats acquired weather data into a user-friendly format and generates voice response messages.

[0052] Step 7:

[0053] Terminal: Performs speech synthesis to convey the generated voice response message to the user, and plays the result as audio.

[0054] Step 8:

[0055] User: Listen to the voice response from the device and give the following instructions by voice as needed.

[0056] (Example 1)

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

[0058] There is a challenge in providing support to help users make better use of their time by streamlining the busy schedule management and task processing in their daily lives. In particular, there is a need for automated information management with a natural interface that utilizes voice input.

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

[0060] In this invention, the server includes an acoustic information recognition means for receiving user voice and converting the voice into text information, a natural language processing means for analyzing the user's requests from the text information, and an information learning means for generating suggestions based on the analyzed requests and using the user's behavioral history and preference information. This makes it possible to efficiently manage daily tasks and schedules and to quickly provide personalized suggestions to the user.

[0061] "Acoustic information recognition means" refers to a device or process for receiving voice input from a user and converting it into text information.

[0062] "Natural language processing means" refers to a technology or method for analyzing textual information converted from speech and understanding user requests.

[0063] "Information learning means" refers to technologies or methods for generating appropriate suggestions and responses for users by utilizing their behavioral history and preference information.

[0064] "Information output means" refers to a device or process for notifying the user of generated proposals or responses.

[0065] A "task management method" is a technique or system for organizing, prioritizing, and managing a user's task information.

[0066] A "schedule management system" is a method or system for collecting a user's schedule information and automatically generating reminders.

[0067] "Audio output means" refers to a device or process for converting a generated proposal into an audio format using speech synthesis and conveying it audibly to the user.

[0068] The system for implementing this invention consists of a wearable device used by the user and a server operating in a cloud environment. The hardware and software used, as well as the details of the processing, are described below.

[0069] First, the device is equipped with a microphone to receive the user's voice. For voice recognition, the recorded voice data is converted into a digital format. Examples of usable devices include smartphones and smartwatches. The voice data is then transmitted to a server via a communication network.

[0070] After receiving audio data, the server converts it into text using the Google® Cloud Speech-to-Text API. Next, natural language processing techniques are used to analyze the converted text. This process utilizes natural language processing libraries such as NLTK and spaCy to accurately extract the user's requests and intentions.

[0071] Based on the analyzed information, the server uses machine learning frameworks such as TENSORFLOW® and PyTorch to learn from the data and generate personalized suggestions based on the user's behavior patterns and preferences. This allows, for example, the alarm settings to be automatically adjusted according to the user's usual schedule and preferences.

[0072] The generated suggestions are converted into speech format using speech synthesis technology and sent to the terminal. The terminal then outputs back to the user. For example, open-source speech synthesis libraries such as Festival or commercial engines can be used as speech synthesis engines.

[0073] As a concrete example, when a user asks the device by voice, "Tell me what I have to do tomorrow," the device sends the voice input to the server, which then analyzes the request using natural language processing. Based on the user's calendar information, the server then generates content such as, "You have a meeting at 10 o'clock," converts it into speech using speech synthesis, and plays it back to the user. This allows the user to efficiently check their daily schedule.

[0074] Examples of prompts generated using the AI ​​model in this system include "Tell me my schedule for tomorrow" and "Set an alarm." This allows users to receive support from the system in various situations in their daily lives.

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

[0076] Step 1:

[0077] The terminal receives the user's voice input through the microphone. The received voice data is digitally converted into an audio data format. The digital audio data generated through this conversion undergoes pre-processing such as noise reduction and is then transmitted to the server via the communication network.

[0078] Step 2:

[0079] The server passes the digital audio data received from the terminal to the speech recognition API, which converts the audio into text information. Based on the input audio data, the speech recognition API performs phoneme analysis and generates text data. The output text data is used in the next step to analyze the user's intent.

[0080] Step 3:

[0081] The server analyzes text data generated using a natural language processing library. The input text data undergoes processing such as tokenization, part-of-speech tagging, and dependency analysis to be transformed into structured data that helps understand user requests. As a result of this analysis, the server identifies the information and instructions the user is seeking.

[0082] Step 4:

[0083] The server retrieves necessary information from the database based on the analyzed user requests and generates personalized suggestions using an information learning algorithm. Here, user behavior history and preference information are used as input, and data calculations are performed by a machine learning model. The output is a suggestion optimized for the user.

[0084] Step 5:

[0085] The generated suggestions are converted into audio data by the server. By inputting the text information into a speech synthesis engine and generating natural-sounding audio data, this audio data is ready to be sent to the terminal. The audio data, as output, functions as a response to the user.

[0086] Step 6:

[0087] The terminal plays audio data received from the server and outputs it through the speaker so that the user can hear it. Specifically, it uses the terminal's built-in audio playback function to output the audio. By listening to the audio guidance, the user can take action based on the information and suggestions received from the system.

[0088] (Application Example 1)

[0089] 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."

[0090] In today's busy lifestyle, users face many challenges in efficiently managing their daily lives and maintaining a comfortable home environment. Manually managing schedules and tasks is time-consuming and laborious, and operating various household appliances is also cumbersome. This invention aims to solve these problems and provide a system that improves the efficiency and comfort of users' daily lives.

[0091] 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.

[0092] In this invention, the server includes: speech recognition means for receiving user voice and converting said voice into text data; natural language processing means for analyzing the user's requests from the text data; data learning means for generating suggestions based on the analyzed requests and using the user's behavioral history and preference data; output means for notifying the user of the suggestions; and control means for coordinating with the user's environment control device to automatically adjust home environment settings based on the presented information. This makes it possible to improve the user's lifestyle efficiency and home comfort.

[0093] "Speech recognition means" refers to an element that has the function of receiving the user's voice and converting said voice into text data.

[0094] A "natural language processing tool" is an element that analyzes user requests from text data and performs processing to understand their content.

[0095] A "data learning tool" is an element that generates user-optimized suggestions based on analyzed requests, using the user's behavioral history and preference data.

[0096] An "output mechanism" is an element that has the function of notifying and providing the generated proposal to the user.

[0097] A "control device" is an element that works in conjunction with the user's environmental control device to automatically adjust home environment settings based on the information provided.

[0098] This invention is a digital butler system designed to efficiently manage a user's life and improve their comfort. Specific embodiments are described below.

[0099] The server receives the user's voice using speech recognition and converts the voice into text data. Commercially available speech recognition software can be used for this process; for example, Google Cloud Speech-to-Text is available. The converted text data is then analyzed by natural language processing to understand the user's request. Here, a platform such as Dialogflow is utilized for natural language processing.

[0100] Based on the analysis results, the server activates a data learning mechanism, referencing the user's past behavioral history and preference data to generate suggestions. This data learning utilizes a machine learning model to learn the user's patterns. As a result, personalized suggestions are generated for the user.

[0101] The generated suggestions are notified to the user via an output device. For example, information is provided through a voice assistant or a screen display device. Furthermore, the server, through a control device, interacts with environmental control systems in the user's home and automatically adjusts settings such as lighting and air conditioning based on the obtained information. Smart home devices and IoT platforms are used for this process.

[0102] For example, if a user asks, "Tell me about my plans for this weekend," the system quickly converts the voice into text and analyzes it. Based on the analyzed information, it searches for the user's schedule and provides information via voice or display, such as, "You have plans for lunch with a friend on Saturday."

[0103] As an example of a prompt, a user can ask the voice assistant, "What's the next task?", and information based on the task list's priority will be provided immediately.

[0104] As described above, the present invention makes it possible to provide a practical system that improves the efficiency and comfort of users' daily lives.

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

[0106] Step 1:

[0107] The terminal receives voice input from the user via its microphone. The input is captured as compressed audio data, and this audio data is sent to the server.

[0108] Step 2:

[0109] The server converts the received audio data into text data using speech recognition. This process uses speech recognition software to analyze the audio signal and convert it into text based on a language model. The output is then sent as text data to the next processing step.

[0110] Step 3:

[0111] The server analyzes the converted text data using natural language processing techniques. It extracts keywords and intent from the input text to understand the user's request. The output is the analyzed request information.

[0112] Step 4:

[0113] The server generates suggestions based on requests analyzed using data learning tools. It references past behavioral history and user profiles, and uses machine learning algorithms to construct personalized suggestions. The output is the suggestion information to be presented to the user.

[0114] Step 5:

[0115] The server transmits the generated suggestion information to the terminal using an output device. The user can then review the suggestion via audio or display. The output here is information provided to the user visually or audibly.

[0116] Step 6:

[0117] The server interacts with the user's environmental control device through a control mechanism. Based on the proposed information, it automatically adjusts settings such as lighting and temperature. The input is the user's current environmental settings, and the output is the new, adjusted settings.

[0118] 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.

[0119] This invention is a system that utilizes an emotion recognition engine embedded in a wearable device to provide personalized support based on the user's emotional state. In addition to conventional speech recognition means, natural language processing means, data learning means, and output means, this system improves the user experience by using an emotion recognition engine.

[0120] The emotion recognition engine analyzes the user's voice and text data collected through the device to identify subtle emotional states. The server receives this data and adjusts suggestions and notification methods to match the user's emotional state. For example, if a user types "I'm tired today," the emotion recognition engine identifies "fatigue," and the server suggests relaxing music or adjusts the user's schedule for the next day.

[0121] Furthermore, the emotion recognition engine continuously learns the user's emotional data and integrates it with data learning methods to understand the user's long-term trends. This allows the server to respond immediately to changes in the user's emotions, for example, by providing recommendations for meditation or rest through output methods if stress levels are rising.

[0122] For example, if a user urgently says in the morning that they might be late for a meeting, the system will sense their anxiety and suggest the shortest route, while also offering a breathing exercise video to help them calm down upon arrival. By incorporating emotion recognition in this way, flexible responses tailored to the user's emotional needs become possible. This allows users to receive more comprehensive support, ultimately improving their quality of life.

[0123] The following describes the processing flow.

[0124] Step 1:

[0125] User: Speaks to the wearable device, saying, "The project isn't going well."

[0126] Step 2:

[0127] Terminal: The microphone captures audio and converts it into a digital signal. This is then sent to the server as digital data.

[0128] Step 3:

[0129] Server: Converts received audio data into text data using a speech recognition engine.

[0130] Step 4:

[0131] Server: Using natural language processing (NLP) technology, it analyzes user requests from text data and infers emotions such as "feeling stressed."

[0132] Step 5:

[0133] Server: The emotion recognition engine evaluates the emotional state in detail and generates emotional parameters such as "stress" and "anxiety."

[0134] Step 6:

[0135] Server: Based on emotional parameters, it plans to suggest relaxation methods and stress-relief activities recommended for the user.

[0136] Step 7:

[0137] Server: Generates suggestions and selects specific examples such as "5-minute deep breathing exercises" and "relaxation music."

[0138] Step 8:

[0139] Terminal: Outputs the suggestion to the user via voice, and displays further visual instructions on the device's display if needed.

[0140] Step 9:

[0141] User: Perform the provided relaxation techniques to regain a relaxed state of mind.

[0142] This entire process allows the system to provide information tailored to the user's emotions, enabling efficient and effective responses.

[0143] (Example 2)

[0144] 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."

[0145] Conventional systems could only offer suggestions based on simple history and preferences in response to user requests, making it difficult to provide flexible support that took into account the user's emotional state. Furthermore, a challenge was the inability to fully utilize user feedback, resulting in insufficient improvement in the accuracy of suggestions.

[0146] 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.

[0147] In this invention, the server includes a speech conversion means for receiving user speech and converting it into text data, a natural language processing means for analyzing requests and emotional states from the text data, and a data analysis means for analyzing data based on the analysis results and generating suggestions. This enables suggestions that are appropriate to the user's emotional state and allows for continuous improvement of the accuracy of the suggestions through feedback.

[0148] "Voice conversion means" refers to a function that processes audio information received from a user into text information.

[0149] A "natural language processing tool" is a function that performs processing to analyze and identify user requests and emotional states from textual information.

[0150] "Data analysis means" refers to a function that generates appropriate suggestions by referencing user behavior history and trend data based on analyzed requests and emotional states.

[0151] The "information output means" is a function that notifies the user of the generated suggestions and also receives feedback.

[0152] "Knowledge acquisition means" refers to a function that learns from user feedback and performs processing to improve the accuracy of suggestions.

[0153] The "schedule management method" is a function that acquires the user's schedule information, generates reminders, and adjusts suggestions as appropriate, taking into account the user's emotional state.

[0154] A "task management system" is a function that collects the user's task information and dynamically adjusts priorities according to their emotional state.

[0155] This invention relates to a system that processes user voice and text information to identify the user's emotional state and generate optimal suggestions. To realize this system, the following hardware and software are utilized.

[0156] Users input voice and text data into the system using devices such as wearable devices or smartphones. These devices are equipped with a microphone for voice input and a touchscreen for text input.

[0157] The device uses speech-to-text software such as the Google Cloud Speech-to-Text API to convert speech data into text data. Next, spaCy or a similar natural language processing library is used as a natural language analysis tool to analyze the user's requests and emotional state from the text data.

[0158] Subsequently, these analysis results are sent to the server. The server uses machine learning frameworks such as PyTorch and scikit-learn as data analysis tools to generate appropriate suggestions based on the user's behavior history and trend data. The generated suggestions are sent to the terminal via an information output device and notified to the user.

[0159] For example, if a user enters "I'm tired today" into their device, the emotion analysis engine identifies "fatigue." The server then suggests relaxing music to the device via services like Spotify and provides advice on adjusting the next day's schedule based on this emotional state.

[0160] Furthermore, as a means of acquiring knowledge by receiving user feedback, the server continuously learns the AI ​​model and improves the accuracy of its suggestions. This feedback is received, for example, through comments entered via a touchscreen or voice comments.

[0161] An example of a prompt message would be, "What kind of support would you offer if the user is experiencing fatigue?"

[0162] Thus, the present invention is a flexible and dynamic suggestion system capable of providing optimal support according to the user's emotional state.

[0163] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0164] Step 1:

[0165] The device receives the user's voice. At this time, it uses the microphone to collect voice data and temporarily stores it within the device. The voice data is the input, and this data is formatted for the next processing step.

[0166] Step 2:

[0167] The terminal converts audio data into text data. This process uses speech conversion software (e.g., a speech recognition API). The input is audio data, and the output is text data. The specific operation involves detecting phonemes from the audio waveform and converting them into text.

[0168] Step 3:

[0169] The terminal analyzes the user's requests and emotional state using the converted text data. This process utilizes a natural language processing library. The input is text data, and the output is the analyzed request and emotional state data. This involves analyzing keywords and context within the text data to extract emotions and intentions.

[0170] Step 4:

[0171] The terminal sends the analyzed data to the server. Here, the analysis results are securely transferred via HTTPS communication. The input is the analyzed request and sentiment state data, and the output is the secure transmission of data to the server.

[0172] Step 5:

[0173] The server uses the received analysis data to match user behavior history and trend data and generate appropriate suggestions. A machine learning framework is used for this process. The input is the user's requests and emotional state, and the output is the generated suggestions. The suggestion generation operation is based on predictive calculations by the machine learning model.

[0174] Step 6:

[0175] The server sends the generated suggestions to the terminal and notifies the user. Here, the terminal's notification system is used to display prompts. The input is the generated suggestions, and the output is a visual or audible notification to the user. This includes actions such as generating notification pop-ups and outputting audio guidance.

[0176] Step 7:

[0177] The user acts according to the received suggestions and provides feedback on the results. Feedback is entered via the device as text or voice. The input is the user's feedback, and the output is the transmission of feedback data to the server. The action of filling out the feedback form is the concrete action.

[0178] Step 8:

[0179] The server updates its AI model using knowledge acquisition methods based on feedback, improving the accuracy of its suggestions. The input is feedback data, and the output is the improved AI model. This includes running a data learning algorithm to retrain the model.

[0180] (Application Example 2)

[0181] 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".

[0182] In today's living environment, there is a need for systems that can accurately understand users' emotional states and provide personalized care based on those states. In particular, in caregiving settings, it is crucial to respond flexibly and appropriately to the emotional states of the elderly and patients, but the technology to effectively achieve this is limited. This problem necessitates a system that can detect emotional changes and propose appropriate care in real time.

[0183] 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.

[0184] In this invention, the server includes: speech recognition means for receiving user voice and converting the voice into text data; natural language processing means for analyzing the user's requests from the text data; data learning means for generating suggestions based on the analyzed requests and using the user's behavioral history and preference data; emotion recognition means for identifying the user's emotional state using an emotion recognition engine; suggestion generation means for generating personalized care suggestions based on the identified emotional state; and output means for notifying the user of the suggestions. This makes it possible to grasp the user's emotional changes in real time, improve the quality of care, and improve the quality of life.

[0185] "Speech recognition means" refers to technology that receives speech signals from a user and converts them into text data.

[0186] "Natural language processing" refers to technologies that analyze text data to understand user requests and intentions.

[0187] "Data learning methods" are technologies that use user behavior history and preference data to generate suggestions that respond to analyzed requests.

[0188] "Emotion recognition means" refers to a technology that uses an emotion recognition engine to identify the user's emotional state from their voice or text data.

[0189] The "proposal generation means" is a technology that generates personalized care suggestions to be provided to the user based on the identified emotional state.

[0190] "Output means" refers to technology for notifying the user of the generated suggestions and providing them with information.

[0191] This invention provides a system for understanding the emotional state of elderly people and patients in care settings and providing appropriate care. The server performs emotion identification and care suggestions according to the following procedure.

[0192] First, smart glasses are used as the terminal to receive the voices of elderly people and patients. The smart glasses acquire voice data via a built-in microphone and convert that data into text using a speech recognition system. High-precision speech recognition software is used for this purpose.

[0193] Next, the text data is analyzed on the server using natural language processing tools to extract user requests and intentions. A general-purpose natural language processing library is used for this process. Based on the analyzed information, a data learning tool references the user's behavioral history and preference data to generate appropriate care suggestions. This incorporates machine learning algorithms that utilize historical data.

[0194] Furthermore, a key feature of this system is its emotion recognition mechanism, which allows the emotion recognition engine to analyze audio data and identify subtle emotional states. The emotion recognition engine used here utilizes major APIs to determine emotions in real time.

[0195] Based on the identified emotional state, the server uses suggestion generation means to provide personalized care suggestions to the user. Specific care and suggestions are communicated to the smart glasses via output means. The output means includes the ability to visually display instructions on the display.

[0196] For example, if a resident in a care facility says, "I'm not feeling well today," the system immediately identifies that emotion and suggests light exercise or rest as a countermeasure to address the "discomfort." By providing care suggestions that are adapted to such emotional states, the quality of life for the elderly is improved.

[0197] An example of a prompt message is: "What kind of flexible care is best to provide when the user is not feeling well today? Example: When the emotion recognition engine detects discomfort, what relaxation suggestions should be presented to the care staff?"

[0198] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0199] Step 1:

[0200] The device acquires the user's voice through smart glasses. A microphone converts the audio signal from analog to digital and collects it as audio data. This data is then input into subsequent processing steps.

[0201] Step 2:

[0202] The server converts the audio data acquired using speech recognition into text data. Dedicated speech recognition software analyzes the waveform of the audio signal and converts it into a corresponding string. This process outputs the user's spoken words as text.

[0203] Step 3:

[0204] The server uses natural language processing to analyze user requests and intentions from text data. It divides the text data into tokens, performs grammatical analysis, and then extracts semantic information. The analysis results are used as input for data learning tools.

[0205] Step 4:

[0206] The server mobilizes data learning tools and references the user's behavioral history and preference data to generate appropriate suggestions. Machine learning algorithms are applied to identify patterns from past data, and predictive models determine the content of the suggestions. These suggestions are output as customized care information for the user.

[0207] Step 5:

[0208] The server identifies emotional states from voice data using emotion recognition means. An emotion analysis engine analyzes the intonation and pitch of the voice to identify the user's emotions. These analysis results are then used as input for the suggestion generation means.

[0209] Step 6:

[0210] The server, using a suggestion generation mechanism, concretizes care suggestions that take into account the identified emotional state. For example, if a high stress level is detected, it recommends providing relaxation techniques. These care suggestions are presented in a viewable format by an output mechanism.

[0211] Step 7:

[0212] The device notifies the user of generated care suggestions through the smart glasses' display. A visual UI is configured to allow the user to easily understand the suggestions. The notified information can be immediately applied to the situation the user is facing.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] [Second Embodiment]

[0217] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0218] 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.

[0219] 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).

[0220] 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.

[0221] 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.

[0222] 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).

[0223] 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.

[0224] 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.

[0225] 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.

[0226] 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.

[0227] 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.

[0228] 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".

[0229] This invention is a digital butler system that uses a wearable device to efficiently support the busy lives of users. The system functions by combining voice recognition means, natural language processing means, data learning means, output means, schedule management means, and task management means. Its specific operation is described below.

[0230] This system's speech recognition mechanism receives user voice input through a microphone built into the terminal and converts the voice data into digital format. Next, the server receives the voice data, converts it into text using natural language processing technology, and analyzes its content. This identifies the user's requests and questions and prepares an appropriate response.

[0231] Based on the analyzed information, the server uses data learning tools to learn the user's daily patterns and preferences. This learning enables the server to generate personalized suggestions and information for the user and deliver them through output tools. For example, if the server learns that a user tends to set an alarm at 7:00 AM, it will continuously set an alarm at that time.

[0232] Furthermore, the system automatically retrieves the user's schedule using a scheduling tool and creates reminders. For example, if there is a meeting scheduled, it can be set to send a notification at the appropriate time. The task management tool organizes and prioritizes the tasks that the user must manage. By prioritizing important and urgent tasks, the system enables efficient task management.

[0233] As a concrete example, if a user uses voice input to say, "Tell me what my schedule is for tomorrow," the device picks up the voice and sends it to the server. The server analyzes the request through natural language processing, and, referring to the data learning results, generates information based on the user's schedule. Finally, the device conveys that information to the user via voice.

[0234] This system allows users to receive support in all aspects of their daily lives, enabling them to make more effective use of their time.

[0235] The following describes the processing flow.

[0236] Step 1:

[0237] User: Gives a voice command to the wearable device saying, "Tell me the weather for tomorrow."

[0238] Step 2:

[0239] Terminal: The built-in microphone captures the user's voice and converts it into a digital signal. This signal is then sent to the server as digital data.

[0240] Step 3:

[0241] Server: Converts received audio data into text data using a speech recognition engine.

[0242] Step 4:

[0243] Server: Uses natural language processing (NLP) techniques to analyze text data to determine if it is a request for a "weather forecast".

[0244] Step 5:

[0245] Server: Based on the analysis results, retrieves necessary weather data from the weather information API.

[0246] Step 6:

[0247] Server: Formats acquired weather data into a user-friendly format and generates voice response messages.

[0248] Step 7:

[0249] Terminal: Performs speech synthesis to convey the generated voice response message to the user, and plays the result as audio.

[0250] Step 8:

[0251] User: Listen to the voice response from the device and give the following instructions by voice as needed.

[0252] (Example 1)

[0253] 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."

[0254] There is a challenge in providing support to help users make better use of their time by streamlining the busy schedule management and task processing in their daily lives. In particular, there is a need for automated information management with a natural interface that utilizes voice input.

[0255] 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.

[0256] In this invention, the server includes an acoustic information recognition means for receiving user voice and converting the voice into text information, a natural language processing means for analyzing the user's requests from the text information, and an information learning means for generating suggestions based on the analyzed requests and using the user's behavioral history and preference information. This makes it possible to efficiently manage daily tasks and schedules and to quickly provide personalized suggestions to the user.

[0257] "Acoustic information recognition means" refers to a device or process for receiving voice input from a user and converting it into text information.

[0258] "Natural language processing means" refers to a technology or method for analyzing textual information converted from speech and understanding user requests.

[0259] "Information learning means" refers to technologies or methods for generating appropriate suggestions and responses for users by utilizing their behavioral history and preference information.

[0260] "Information output means" refers to a device or process for notifying the user of generated proposals or responses.

[0261] A "task management method" is a technique or system for organizing, prioritizing, and managing a user's task information.

[0262] A "schedule management system" is a method or system for collecting a user's schedule information and automatically generating reminders.

[0263] "Audio output means" refers to a device or process for converting a generated proposal into an audio format using speech synthesis and conveying it audibly to the user.

[0264] The system for implementing this invention consists of a wearable device used by the user and a server operating in a cloud environment. The hardware and software used, as well as the details of the processing, are described below.

[0265] First, the device is equipped with a microphone to receive the user's voice. For voice recognition, the recorded voice data is converted into a digital format. Examples of usable devices include smartphones and smartwatches. The voice data is then transmitted to a server via a communication network.

[0266] After receiving audio data, the server converts it into text using the Google Cloud Speech-to-Text API. Next, natural language processing techniques are used to analyze the converted text. This process utilizes natural language processing libraries such as NLTK and spaCy to accurately extract the user's requests and intentions.

[0267] Based on the analyzed information, the server uses machine learning frameworks such as TensorFlow and PyTorch to train the data and generate personalized suggestions based on the user's behavior patterns and preferences. This allows, for example, the system to automatically adjust alarm settings according to the user's usual schedule and preferences.

[0268] The generated suggestions are converted into speech format using speech synthesis technology and sent to the terminal. The terminal then outputs back to the user. For example, open-source speech synthesis libraries such as Festival or commercial engines can be used as speech synthesis engines.

[0269] As a concrete example, when a user asks the device by voice, "Tell me what I have to do tomorrow," the device sends the voice input to the server, which then analyzes the request using natural language processing. Based on the user's calendar information, the server then generates content such as, "You have a meeting at 10 o'clock," converts it into speech using speech synthesis, and plays it back to the user. This allows the user to efficiently check their daily schedule.

[0270] Examples of prompts generated using the AI ​​model in this system include "Tell me my schedule for tomorrow" and "Set an alarm." This allows users to receive support from the system in various situations in their daily lives.

[0271] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0272] Step 1:

[0273] The terminal receives the user's voice input through the microphone. The received voice data is digitally converted into an audio data format. The digital audio data generated through this conversion undergoes pre-processing such as noise reduction and is then transmitted to the server via the communication network.

[0274] Step 2:

[0275] The server passes the digital audio data received from the terminal to the speech recognition API, which converts the audio into text information. Based on the input audio data, the speech recognition API performs phoneme analysis and generates text data. The output text data is used in the next step to analyze the user's intent.

[0276] Step 3:

[0277] The server analyzes the text data generated using the natural language processing library. The text data as input undergoes processes such as tokenization, part-of-speech tagging, and dependency parsing, and is converted into structured data for understanding the user's request. As a result of this analysis, the information and instructions requested by the user are identified.

[0278] Step 4:

[0279] Based on the analyzed user requests, the server retrieves the necessary information from the database and generates personalized proposals using an information learning algorithm. Here, the user's action history and preference information are used as input, and data calculations are performed using a machine learning model. As output, proposals optimized for the user are generated.

[0280] Step 5:

[0281] The generated proposals are converted into audio data by the server. By inputting the character information into the speech synthesis engine to generate natural audio data, this audio data is ready to be transmitted to the terminal. The audio data as output functions as a response to the user.

[0282] Step 6:

[0283] The terminal plays the audio data received from the server and outputs it from the speaker so that the user can hear it. Specifically, audio output is performed using the audio playback function within the terminal. The user can take actions based on the information and proposals received from the system by listening to the voice guidance.

[0284] (Application Example 1)

[0285] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0286] In the modern busy living environment, users have many challenges in the daily efficient management and maintenance of a comfortable home environment. Manual scheduling and task management require time and effort, and operating various household facilities is also time-consuming. The purpose of the present invention is to solve these problems and provide a system that improves the efficiency and comfort of users' daily lives.

[0287] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0288] In this invention, the server includes a voice recognition means for receiving the user's voice and converting the voice into text data, a natural language processing means for analyzing the user's request from the text data, a data learning means for generating a proposal using the user's behavior history and preference data based on the analyzed request, an output means for notifying the user of the proposal, and a control means for automatically adjusting the home environment settings based on the presented information in cooperation with the user's environmental control device. Thereby, it becomes possible to improve the user's living efficiency and home comfort.

[0289] The "voice recognition means" is an element having a function of receiving the user's voice and converting the voice into text data.

[0290] The "natural language processing means" is an element that analyzes the user's request from the text data and performs processing to understand its content.

[0291] The "data learning means" is an element that generates a proposal optimized for the user using the user's behavior history and preference data based on the analyzed request.

[0292] The "output means" is an element having a function of notifying and providing the generated proposal to the user.

[0293] A "control device" is an element that works in conjunction with the user's environmental control device to automatically adjust home environment settings based on the information provided.

[0294] This invention is a digital butler system designed to efficiently manage a user's life and improve their comfort. Specific embodiments are described below.

[0295] The server receives the user's voice using speech recognition and converts the voice into text data. Commercially available speech recognition software can be used for this process; for example, Google Cloud Speech-to-Text is available. The converted text data is then analyzed by natural language processing to understand the user's request. Here, a platform such as Dialogflow is utilized for natural language processing.

[0296] Based on the analysis results, the server activates a data learning mechanism, referencing the user's past behavioral history and preference data to generate suggestions. This data learning utilizes a machine learning model to learn the user's patterns. As a result, personalized suggestions are generated for the user.

[0297] The generated suggestions are notified to the user via an output device. For example, information is provided through a voice assistant or a screen display device. Furthermore, the server, through a control device, interacts with environmental control systems in the user's home and automatically adjusts settings such as lighting and air conditioning based on the obtained information. Smart home devices and IoT platforms are used for this process.

[0298] For example, if a user asks, "Tell me about my plans for this weekend," the system quickly converts the voice into text and analyzes it. Based on the analyzed information, it searches for the user's schedule and provides information via voice or display, such as, "You have plans for lunch with a friend on Saturday."

[0299] As an example of a prompt sentence, when a user asks the voice assistant "What's the next task?", information based on the priority of the task list is immediately provided.

[0300] As described above, the present invention enables the provision of a practical system that improves the efficiency and comfort of the user's daily life.

[0301] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0302] Step 1:

[0303] The terminal receives voice input from the user using a microphone. The input is captured as compressed voice data, and the voice data is transmitted to the server.

[0304] Step 2:

[0305] The server converts the received voice data into text data using voice recognition means. In this process, voice recognition software is used to analyze the voice signal and convert it into text based on a language model. The output is sent to the next processing step as text data.

[0306] Step 3:

[0307] The server analyzes the converted text data using natural language processing means. Keywords and intentions are extracted from the input text to understand the user's request. The output is the analyzed request information.

[0308] Step 4:

[0309] The server generates a proposal based on the analyzed request using data learning means. Referring to past behavior history and the user's profile, a personalized proposal is constructed using a machine learning algorithm. The output is the proposal information to be presented to the user.

[0310] Step 5:

[0311] The server transmits the generated suggestion information to the terminal using an output device. The user can then review the suggestion via audio or display. The output here is information provided to the user visually or audibly.

[0312] Step 6:

[0313] The server interacts with the user's environmental control device through a control mechanism. Based on the proposed information, it automatically adjusts settings such as lighting and temperature. The input is the user's current environmental settings, and the output is the new, adjusted settings.

[0314] 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.

[0315] This invention is a system that utilizes an emotion recognition engine embedded in a wearable device to provide personalized support based on the user's emotional state. In addition to conventional speech recognition means, natural language processing means, data learning means, and output means, this system improves the user experience by using an emotion recognition engine.

[0316] The emotion recognition engine analyzes the user's voice and text data collected through the device to identify subtle emotional states. The server receives this data and adjusts suggestions and notification methods to match the user's emotional state. For example, if a user types "I'm tired today," the emotion recognition engine identifies "fatigue," and the server suggests relaxing music or adjusts the user's schedule for the next day.

[0317] Furthermore, the emotion recognition engine continuously learns the user's emotional data and integrates it with data learning methods to understand the user's long-term trends. This allows the server to respond immediately to changes in the user's emotions, for example, by providing recommendations for meditation or rest through output methods if stress levels are rising.

[0318] For example, if a user urgently says in the morning that they might be late for a meeting, the system will sense their anxiety and suggest the shortest route, while also offering a breathing exercise video to help them calm down upon arrival. By incorporating emotion recognition in this way, flexible responses tailored to the user's emotional needs become possible. This allows users to receive more comprehensive support, ultimately improving their quality of life.

[0319] The following describes the processing flow.

[0320] Step 1:

[0321] User: Speaks to the wearable device, saying, "The project isn't going well."

[0322] Step 2:

[0323] Terminal: The microphone captures audio and converts it into a digital signal. This is then sent to the server as digital data.

[0324] Step 3:

[0325] Server: Converts received audio data into text data using a speech recognition engine.

[0326] Step 4:

[0327] Server: Using natural language processing (NLP) technology, it analyzes user requests from text data and infers emotions such as "feeling stressed."

[0328] Step 5:

[0329] Server: The emotion recognition engine evaluates the emotional state in detail and generates emotional parameters such as "stress" and "anxiety."

[0330] Step 6:

[0331] Server: Based on emotional parameters, it plans to suggest relaxation methods and stress-relief activities recommended for the user.

[0332] Step 7:

[0333] Server: Generates suggestions and selects specific examples such as "5-minute deep breathing exercises" and "relaxation music."

[0334] Step 8:

[0335] Terminal: Outputs the suggestion to the user via voice, and displays further visual instructions on the device's display if needed.

[0336] Step 9:

[0337] User: Perform the provided relaxation techniques to regain a relaxed state of mind.

[0338] This entire process allows the system to provide information tailored to the user's emotions, enabling efficient and effective responses.

[0339] (Example 2)

[0340] 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".

[0341] Conventional systems could only offer suggestions based on simple history and preferences in response to user requests, making it difficult to provide flexible support that took into account the user's emotional state. Furthermore, a challenge was the inability to fully utilize user feedback, resulting in insufficient improvement in the accuracy of suggestions.

[0342] 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.

[0343] In this invention, the server includes a speech conversion means for receiving user speech and converting it into text data, a natural language processing means for analyzing requests and emotional states from the text data, and a data analysis means for analyzing data based on the analysis results and generating suggestions. This enables suggestions that are appropriate to the user's emotional state and allows for continuous improvement of the accuracy of the suggestions through feedback.

[0344] "Voice conversion means" refers to a function that processes audio information received from a user into text information.

[0345] A "natural language processing tool" is a function that performs processing to analyze and identify user requests and emotional states from textual information.

[0346] "Data analysis means" refers to a function that generates appropriate suggestions by referencing user behavior history and trend data based on analyzed requests and emotional states.

[0347] The "information output means" is a function that notifies the user of the generated suggestions and also receives feedback.

[0348] "Knowledge acquisition means" refers to a function that learns from user feedback and performs processing to improve the accuracy of suggestions.

[0349] The "schedule management method" is a function that acquires the user's schedule information, generates reminders, and adjusts suggestions as appropriate, taking into account the user's emotional state.

[0350] A "task management system" is a function that collects the user's task information and dynamically adjusts priorities according to their emotional state.

[0351] This invention relates to a system that processes user voice and text information to identify the user's emotional state and generate optimal suggestions. To realize this system, the following hardware and software are utilized.

[0352] Users input voice and text data into the system using devices such as wearable devices or smartphones. These devices are equipped with a microphone for voice input and a touchscreen for text input.

[0353] The device uses speech-to-text software such as the Google Cloud Speech-to-Text API to convert speech data into text data. Next, spaCy or a similar natural language processing library is used as a natural language analysis tool to analyze the user's requests and emotional state from the text data.

[0354] Subsequently, these analysis results are sent to the server. The server uses machine learning frameworks such as PyTorch and scikit-learn as data analysis tools to generate appropriate suggestions based on the user's behavior history and trend data. The generated suggestions are sent to the terminal via an information output device and notified to the user.

[0355] For example, if a user enters "I'm tired today" into their device, the emotion analysis engine identifies "fatigue." The server then suggests relaxing music to the device via services like Spotify and provides advice on adjusting the next day's schedule based on this emotional state.

[0356] Furthermore, as a means of acquiring knowledge by receiving user feedback, the server continuously learns the AI ​​model and improves the accuracy of its suggestions. This feedback is received, for example, through comments entered via a touchscreen or voice comments.

[0357] An example of a prompt message would be, "What kind of support would you offer if the user is experiencing fatigue?"

[0358] Thus, the present invention is a flexible and dynamic suggestion system capable of providing optimal support according to the user's emotional state.

[0359] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0360] Step 1:

[0361] The device receives the user's voice. At this time, it uses the microphone to collect voice data and temporarily stores it within the device. The voice data is the input, and this data is formatted for the next processing step.

[0362] Step 2:

[0363] The terminal converts audio data into text data. This process uses speech conversion software (e.g., a speech recognition API). The input is audio data, and the output is text data. The specific operation involves detecting phonemes from the audio waveform and converting them into text.

[0364] Step 3:

[0365] The terminal analyzes the user's requests and emotional state using the converted text data. This process utilizes a natural language processing library. The input is text data, and the output is the analyzed request and emotional state data. This involves analyzing keywords and context within the text data to extract emotions and intentions.

[0366] Step 4:

[0367] The terminal sends the analyzed data to the server. Here, the analysis results are securely transferred via HTTPS communication. The input is the analyzed request and sentiment state data, and the output is the secure transmission of data to the server.

[0368] Step 5:

[0369] The server uses the received analysis data to match user behavior history and trend data and generate appropriate suggestions. A machine learning framework is used for this process. The input is the user's requests and emotional state, and the output is the generated suggestions. The suggestion generation operation is based on predictive calculations by the machine learning model.

[0370] Step 6:

[0371] The server sends the generated suggestions to the terminal and notifies the user. Here, the terminal's notification system is used to display prompts. The input is the generated suggestions, and the output is a visual or audible notification to the user. This includes actions such as generating notification pop-ups and outputting audio guidance.

[0372] Step 7:

[0373] The user acts according to the received suggestions and provides feedback on the results. Feedback is entered via the device as text or voice. The input is the user's feedback, and the output is the transmission of feedback data to the server. The action of filling out the feedback form is the concrete action.

[0374] Step 8:

[0375] The server updates its AI model using knowledge acquisition methods based on feedback, improving the accuracy of its suggestions. The input is feedback data, and the output is the improved AI model. This includes running a data learning algorithm to retrain the model.

[0376] (Application Example 2)

[0377] 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."

[0378] In today's living environment, there is a need for systems that can accurately understand users' emotional states and provide personalized care based on those states. In particular, in caregiving settings, it is crucial to respond flexibly and appropriately to the emotional states of the elderly and patients, but the technology to effectively achieve this is limited. This problem necessitates a system that can detect emotional changes and propose appropriate care in real time.

[0379] 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.

[0380] In this invention, the server includes: speech recognition means for receiving user voice and converting the voice into text data; natural language processing means for analyzing the user's requests from the text data; data learning means for generating suggestions based on the analyzed requests and using the user's behavioral history and preference data; emotion recognition means for identifying the user's emotional state using an emotion recognition engine; suggestion generation means for generating personalized care suggestions based on the identified emotional state; and output means for notifying the user of the suggestions. This makes it possible to grasp the user's emotional changes in real time, improve the quality of care, and improve the quality of life.

[0381] "Speech recognition means" refers to technology that receives speech signals from a user and converts them into text data.

[0382] "Natural language processing" refers to technologies that analyze text data to understand user requests and intentions.

[0383] "Data learning methods" are technologies that use user behavior history and preference data to generate suggestions that respond to analyzed requests.

[0384] "Emotion recognition means" refers to a technology that uses an emotion recognition engine to identify the user's emotional state from their voice or text data.

[0385] The "proposal generation means" is a technology that generates personalized care suggestions to be provided to the user based on the identified emotional state.

[0386] "Output means" refers to technology for notifying the user of the generated suggestions and providing them with information.

[0387] This invention provides a system for understanding the emotional state of elderly people and patients in care settings and providing appropriate care. The server performs emotion identification and care suggestions according to the following procedure.

[0388] First, smart glasses are used as the terminal to receive the voices of elderly people and patients. The smart glasses acquire voice data via a built-in microphone and convert that data into text using a speech recognition system. High-precision speech recognition software is used for this purpose.

[0389] Next, the text data is analyzed on the server using natural language processing tools to extract user requests and intentions. A general-purpose natural language processing library is used for this process. Based on the analyzed information, a data learning tool references the user's behavioral history and preference data to generate appropriate care suggestions. This incorporates machine learning algorithms that utilize historical data.

[0390] Furthermore, a key feature of this system is its emotion recognition mechanism, which allows the emotion recognition engine to analyze audio data and identify subtle emotional states. The emotion recognition engine used here utilizes major APIs to determine emotions in real time.

[0391] Based on the identified emotional state, the server uses suggestion generation means to provide personalized care suggestions to the user. Specific care and suggestions are communicated to the smart glasses via output means. The output means includes the ability to visually display instructions on the display.

[0392] For example, if a resident in a care facility says, "I'm not feeling well today," the system immediately identifies that emotion and suggests light exercise or rest as a countermeasure to address the "discomfort." By providing care suggestions that are adapted to such emotional states, the quality of life for the elderly is improved.

[0393] An example of a prompt message is: "What kind of flexible care is best to provide when the user is not feeling well today? Example: When the emotion recognition engine detects discomfort, what relaxation suggestions should be presented to the care staff?"

[0394] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0395] Step 1:

[0396] The device acquires the user's voice through smart glasses. A microphone converts the audio signal from analog to digital and collects it as audio data. This data is then input into subsequent processing steps.

[0397] Step 2:

[0398] The server converts the audio data acquired using speech recognition into text data. Dedicated speech recognition software analyzes the waveform of the audio signal and converts it into a corresponding string. This process outputs the user's spoken words as text.

[0399] Step 3:

[0400] The server uses natural language processing to analyze user requests and intentions from text data. It divides the text data into tokens, performs grammatical analysis, and then extracts semantic information. The analysis results are used as input for data learning tools.

[0401] Step 4:

[0402] The server mobilizes data learning tools and references the user's behavioral history and preference data to generate appropriate suggestions. Machine learning algorithms are applied to identify patterns from past data, and predictive models determine the content of the suggestions. These suggestions are output as customized care information for the user.

[0403] Step 5:

[0404] The server identifies emotional states from voice data using emotion recognition means. An emotion analysis engine analyzes the intonation and pitch of the voice to identify the user's emotions. These analysis results are then used as input for the suggestion generation means.

[0405] Step 6:

[0406] The server, using a suggestion generation mechanism, concretizes care suggestions that take into account the identified emotional state. For example, if a high stress level is detected, it recommends providing relaxation techniques. These care suggestions are presented in a viewable format by an output mechanism.

[0407] Step 7:

[0408] The device notifies the user of generated care suggestions through the smart glasses' display. A visual UI is configured to allow the user to easily understand the suggestions. The notified information can be immediately applied to the situation the user is facing.

[0409] 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.

[0410] 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.

[0411] 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.

[0412] [Third Embodiment]

[0413] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0414] 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.

[0415] 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).

[0416] 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.

[0417] 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.

[0418] 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).

[0419] 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.

[0420] 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.

[0421] 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.

[0422] 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.

[0423] 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.

[0424] 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".

[0425] This invention is a digital butler system that uses a wearable device to efficiently support the busy lives of users. The system functions by combining voice recognition means, natural language processing means, data learning means, output means, schedule management means, and task management means. Its specific operation is described below.

[0426] This system's speech recognition mechanism receives user voice input through a microphone built into the terminal and converts the voice data into digital format. Next, the server receives the voice data, converts it into text using natural language processing technology, and analyzes its content. This identifies the user's requests and questions and prepares an appropriate response.

[0427] Based on the analyzed information, the server uses data learning tools to learn the user's daily patterns and preferences. This learning enables the server to generate personalized suggestions and information for the user and deliver them through output tools. For example, if the server learns that a user tends to set an alarm at 7:00 AM, it will continuously set an alarm at that time.

[0428] Furthermore, the system automatically retrieves the user's schedule using a scheduling tool and creates reminders. For example, if there is a meeting scheduled, it can be set to send a notification at the appropriate time. The task management tool organizes and prioritizes the tasks that the user must manage. By prioritizing important and urgent tasks, the system enables efficient task management.

[0429] As a concrete example, if a user uses voice input to say, "Tell me what my schedule is for tomorrow," the device picks up the voice and sends it to the server. The server analyzes the request through natural language processing, and, referring to the data learning results, generates information based on the user's schedule. Finally, the device conveys that information to the user via voice.

[0430] This system allows users to receive support in all aspects of their daily lives, enabling them to make more effective use of their time.

[0431] The following describes the processing flow.

[0432] Step 1:

[0433] User: Gives a voice command to the wearable device saying, "Tell me the weather for tomorrow."

[0434] Step 2:

[0435] Terminal: The built-in microphone captures the user's voice and converts it into a digital signal. This signal is then sent to the server as digital data.

[0436] Step 3:

[0437] Server: Converts received audio data into text data using a speech recognition engine.

[0438] Step 4:

[0439] Server: Uses natural language processing (NLP) techniques to analyze text data to determine if it is a request for a "weather forecast".

[0440] Step 5:

[0441] Server: Based on the analysis results, retrieves necessary weather data from the weather information API.

[0442] Step 6:

[0443] Server: Formats acquired weather data into a user-friendly format and generates voice response messages.

[0444] Step 7:

[0445] Terminal: Performs speech synthesis to convey the generated voice response message to the user, and plays the result as audio.

[0446] Step 8:

[0447] User: Listen to the voice response from the device and give the following instructions by voice as needed.

[0448] (Example 1)

[0449] 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."

[0450] There is a challenge in providing support to help users make better use of their time by streamlining the busy schedule management and task processing in their daily lives. In particular, there is a need for automated information management with a natural interface that utilizes voice input.

[0451] 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.

[0452] In this invention, the server includes an acoustic information recognition means for receiving user voice and converting the voice into text information, a natural language processing means for analyzing the user's requests from the text information, and an information learning means for generating suggestions based on the analyzed requests and using the user's behavioral history and preference information. This makes it possible to efficiently manage daily tasks and schedules and to quickly provide personalized suggestions to the user.

[0453] "Acoustic information recognition means" refers to a device or process for receiving voice input from a user and converting it into text information.

[0454] "Natural language processing means" refers to a technology or method for analyzing textual information converted from speech and understanding user requests.

[0455] "Information learning means" refers to technologies or methods for generating appropriate suggestions and responses for users by utilizing their behavioral history and preference information.

[0456] "Information output means" refers to a device or process for notifying the user of generated proposals or responses.

[0457] A "task management method" is a technique or system for organizing, prioritizing, and managing a user's task information.

[0458] A "schedule management system" is a method or system for collecting a user's schedule information and automatically generating reminders.

[0459] "Audio output means" refers to a device or process for converting a generated proposal into an audio format using speech synthesis and conveying it audibly to the user.

[0460] The system for implementing this invention consists of a wearable device used by the user and a server operating in a cloud environment. The hardware and software used, as well as the details of the processing, are described below.

[0461] First, the device is equipped with a microphone to receive the user's voice. For voice recognition, the recorded voice data is converted into a digital format. Examples of usable devices include smartphones and smartwatches. The voice data is then transmitted to a server via a communication network.

[0462] After receiving audio data, the server converts it into text using the Google Cloud Speech-to-Text API. Next, natural language processing techniques are used to analyze the converted text. This process utilizes natural language processing libraries such as NLTK and spaCy to accurately extract the user's requests and intentions.

[0463] Based on the analyzed information, the server uses machine learning frameworks such as TensorFlow and PyTorch to train the data and generate personalized suggestions based on the user's behavior patterns and preferences. This allows, for example, the system to automatically adjust alarm settings according to the user's usual schedule and preferences.

[0464] The generated suggestions are converted into speech format using speech synthesis technology and sent to the terminal. The terminal then outputs back to the user. For example, open-source speech synthesis libraries such as Festival or commercial engines can be used as speech synthesis engines.

[0465] As a concrete example, when a user asks the device by voice, "Tell me what I have to do tomorrow," the device sends the voice input to the server, which then analyzes the request using natural language processing. Based on the user's calendar information, the server then generates content such as, "You have a meeting at 10 o'clock," converts it into speech using speech synthesis, and plays it back to the user. This allows the user to efficiently check their daily schedule.

[0466] Examples of prompts generated using the AI ​​model in this system include "Tell me my schedule for tomorrow" and "Set an alarm." This allows users to receive support from the system in various situations in their daily lives.

[0467] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0468] Step 1:

[0469] The terminal receives the user's voice input through the microphone. The received voice data is digitally converted into an audio data format. The digital audio data generated through this conversion undergoes pre-processing such as noise reduction and is then transmitted to the server via the communication network.

[0470] Step 2:

[0471] The server passes the digital audio data received from the terminal to the speech recognition API, which converts the audio into text information. Based on the input audio data, the speech recognition API performs phoneme analysis and generates text data. The output text data is used in the next step to analyze the user's intent.

[0472] Step 3:

[0473] The server analyzes text data generated using a natural language processing library. The input text data undergoes processing such as tokenization, part-of-speech tagging, and dependency analysis to be transformed into structured data that helps understand user requests. As a result of this analysis, the server identifies the information and instructions the user is seeking.

[0474] Step 4:

[0475] The server retrieves necessary information from the database based on the analyzed user requests and generates personalized suggestions using an information learning algorithm. Here, user behavior history and preference information are used as input, and data calculations are performed by a machine learning model. The output is a suggestion optimized for the user.

[0476] Step 5:

[0477] The generated suggestions are converted into audio data by the server. By inputting the text information into a speech synthesis engine and generating natural-sounding audio data, this audio data is ready to be sent to the terminal. The audio data, as output, functions as a response to the user.

[0478] Step 6:

[0479] The terminal plays audio data received from the server and outputs it through the speaker so that the user can hear it. Specifically, it uses the terminal's built-in audio playback function to output the audio. By listening to the audio guidance, the user can take action based on the information and suggestions received from the system.

[0480] (Application Example 1)

[0481] 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."

[0482] In today's busy lifestyle, users face many challenges in efficiently managing their daily lives and maintaining a comfortable home environment. Manually managing schedules and tasks is time-consuming and laborious, and operating various household appliances is also cumbersome. This invention aims to solve these problems and provide a system that improves the efficiency and comfort of users' daily lives.

[0483] 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.

[0484] In this invention, the server includes: speech recognition means for receiving user voice and converting said voice into text data; natural language processing means for analyzing the user's requests from the text data; data learning means for generating suggestions based on the analyzed requests and using the user's behavioral history and preference data; output means for notifying the user of the suggestions; and control means for coordinating with the user's environment control device to automatically adjust home environment settings based on the presented information. This makes it possible to improve the user's lifestyle efficiency and home comfort.

[0485] "Speech recognition means" refers to an element that has the function of receiving the user's voice and converting said voice into text data.

[0486] A "natural language processing tool" is an element that analyzes user requests from text data and performs processing to understand their content.

[0487] A "data learning tool" is an element that generates user-optimized suggestions based on analyzed requests, using the user's behavioral history and preference data.

[0488] An "output mechanism" is an element that has the function of notifying and providing the generated proposal to the user.

[0489] A "control device" is an element that works in conjunction with the user's environmental control device to automatically adjust home environment settings based on the information provided.

[0490] This invention is a digital butler system designed to efficiently manage a user's life and improve their comfort. Specific embodiments are described below.

[0491] The server receives the user's voice using speech recognition and converts the voice into text data. Commercially available speech recognition software can be used for this process; for example, Google Cloud Speech-to-Text is available. The converted text data is then analyzed by natural language processing to understand the user's request. Here, a platform such as Dialogflow is utilized for natural language processing.

[0492] Based on the analysis results, the server activates a data learning mechanism, referencing the user's past behavioral history and preference data to generate suggestions. This data learning utilizes a machine learning model to learn the user's patterns. As a result, personalized suggestions are generated for the user.

[0493] The generated suggestions are notified to the user via an output device. For example, information is provided through a voice assistant or a screen display device. Furthermore, the server, through a control device, interacts with environmental control systems in the user's home and automatically adjusts settings such as lighting and air conditioning based on the obtained information. Smart home devices and IoT platforms are used for this process.

[0494] For example, if a user asks, "Tell me about my plans for this weekend," the system quickly converts the voice into text and analyzes it. Based on the analyzed information, it searches for the user's schedule and provides information via voice or display, such as, "You have plans for lunch with a friend on Saturday."

[0495] As an example of a prompt, a user can ask the voice assistant, "What's the next task?", and information based on the task list's priority will be provided immediately.

[0496] As described above, the present invention makes it possible to provide a practical system that improves the efficiency and comfort of users' daily lives.

[0497] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0498] Step 1:

[0499] The terminal receives voice input from the user via its microphone. The input is captured as compressed audio data, and this audio data is sent to the server.

[0500] Step 2:

[0501] The server converts the received audio data into text data using speech recognition. This process uses speech recognition software to analyze the audio signal and convert it into text based on a language model. The output is then sent as text data to the next processing step.

[0502] Step 3:

[0503] The server analyzes the converted text data using natural language processing techniques. It extracts keywords and intent from the input text to understand the user's request. The output is the analyzed request information.

[0504] Step 4:

[0505] The server generates suggestions based on requests analyzed using data learning tools. It references past behavioral history and user profiles, and uses machine learning algorithms to construct personalized suggestions. The output is the suggestion information to be presented to the user.

[0506] Step 5:

[0507] The server transmits the generated suggestion information to the terminal using an output device. The user can then review the suggestion via audio or display. The output here is information provided to the user visually or audibly.

[0508] Step 6:

[0509] The server interacts with the user's environmental control device through a control mechanism. Based on the proposed information, it automatically adjusts settings such as lighting and temperature. The input is the user's current environmental settings, and the output is the new, adjusted settings.

[0510] 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.

[0511] This invention is a system that utilizes an emotion recognition engine embedded in a wearable device to provide personalized support based on the user's emotional state. In addition to conventional speech recognition means, natural language processing means, data learning means, and output means, this system improves the user experience by using an emotion recognition engine.

[0512] The emotion recognition engine analyzes the user's voice and text data collected through the device to identify subtle emotional states. The server receives this data and adjusts suggestions and notification methods to match the user's emotional state. For example, if a user types "I'm tired today," the emotion recognition engine identifies "fatigue," and the server suggests relaxing music or adjusts the user's schedule for the next day.

[0513] Furthermore, the emotion recognition engine continuously learns the user's emotional data and integrates it with data learning methods to understand the user's long-term trends. This allows the server to respond immediately to changes in the user's emotions, for example, by providing recommendations for meditation or rest through output methods if stress levels are rising.

[0514] For example, if a user urgently says in the morning that they might be late for a meeting, the system will sense their anxiety and suggest the shortest route, while also offering a breathing exercise video to help them calm down upon arrival. By incorporating emotion recognition in this way, flexible responses tailored to the user's emotional needs become possible. This allows users to receive more comprehensive support, ultimately improving their quality of life.

[0515] The following describes the processing flow.

[0516] Step 1:

[0517] User: Speaks to the wearable device, saying, "The project isn't going well."

[0518] Step 2:

[0519] Terminal: The microphone captures audio and converts it into a digital signal. This is then sent to the server as digital data.

[0520] Step 3:

[0521] Server: Converts received audio data into text data using a speech recognition engine.

[0522] Step 4:

[0523] Server: Using natural language processing (NLP) technology, it analyzes user requests from text data and infers emotions such as "feeling stressed."

[0524] Step 5:

[0525] Server: The emotion recognition engine evaluates the emotional state in detail and generates emotional parameters such as "stress" and "anxiety."

[0526] Step 6:

[0527] Server: Based on emotional parameters, it plans to suggest relaxation methods and stress-relief activities recommended for the user.

[0528] Step 7:

[0529] Server: Generates suggestions and selects specific examples such as "5-minute deep breathing exercises" and "relaxation music."

[0530] Step 8:

[0531] Terminal: Outputs the suggestion to the user via voice, and displays further visual instructions on the device's display if needed.

[0532] Step 9:

[0533] User: Perform the provided relaxation techniques to regain a relaxed state of mind.

[0534] This entire process allows the system to provide information tailored to the user's emotions, enabling efficient and effective responses.

[0535] (Example 2)

[0536] 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."

[0537] Conventional systems could only offer suggestions based on simple history and preferences in response to user requests, making it difficult to provide flexible support that took into account the user's emotional state. Furthermore, a challenge was the inability to fully utilize user feedback, resulting in insufficient improvement in the accuracy of suggestions.

[0538] 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.

[0539] In this invention, the server includes a speech conversion means for receiving user speech and converting it into text data, a natural language processing means for analyzing requests and emotional states from the text data, and a data analysis means for analyzing data based on the analysis results and generating suggestions. This enables suggestions that are appropriate to the user's emotional state and allows for continuous improvement of the accuracy of the suggestions through feedback.

[0540] "Voice conversion means" refers to a function that processes audio information received from a user into text information.

[0541] A "natural language processing tool" is a function that performs processing to analyze and identify user requests and emotional states from textual information.

[0542] "Data analysis means" refers to a function that generates appropriate suggestions by referencing user behavior history and trend data based on analyzed requests and emotional states.

[0543] The "information output means" is a function that notifies the user of the generated suggestions and also receives feedback.

[0544] "Knowledge acquisition means" refers to a function that learns from user feedback and performs processing to improve the accuracy of suggestions.

[0545] The "schedule management method" is a function that acquires the user's schedule information, generates reminders, and adjusts suggestions as appropriate, taking into account the user's emotional state.

[0546] A "task management system" is a function that collects the user's task information and dynamically adjusts priorities according to their emotional state.

[0547] This invention relates to a system that processes user voice and text information to identify the user's emotional state and generate optimal suggestions. To realize this system, the following hardware and software are utilized.

[0548] Users input voice and text data into the system using devices such as wearable devices or smartphones. These devices are equipped with a microphone for voice input and a touchscreen for text input.

[0549] The device uses speech-to-text software such as the Google Cloud Speech-to-Text API to convert speech data into text data. Next, spaCy or a similar natural language processing library is used as a natural language analysis tool to analyze the user's requests and emotional state from the text data.

[0550] Subsequently, these analysis results are sent to the server. The server uses machine learning frameworks such as PyTorch and scikit-learn as data analysis tools to generate appropriate suggestions based on the user's behavior history and trend data. The generated suggestions are sent to the terminal via an information output device and notified to the user.

[0551] For example, if a user enters "I'm tired today" into their device, the emotion analysis engine identifies "fatigue." The server then suggests relaxing music to the device via services like Spotify and provides advice on adjusting the next day's schedule based on this emotional state.

[0552] Furthermore, as a means of acquiring knowledge by receiving user feedback, the server continuously learns the AI ​​model and improves the accuracy of its suggestions. This feedback is received, for example, through comments entered via a touchscreen or voice comments.

[0553] An example of a prompt message would be, "What kind of support would you offer if the user is experiencing fatigue?"

[0554] Thus, the present invention is a flexible and dynamic suggestion system capable of providing optimal support according to the user's emotional state.

[0555] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0556] Step 1:

[0557] The device receives the user's voice. At this time, it uses the microphone to collect voice data and temporarily stores it within the device. The voice data is the input, and this data is formatted for the next processing step.

[0558] Step 2:

[0559] The terminal converts audio data into text data. This process uses speech conversion software (e.g., a speech recognition API). The input is audio data, and the output is text data. The specific operation involves detecting phonemes from the audio waveform and converting them into text.

[0560] Step 3:

[0561] The terminal analyzes the user's requests and emotional state using the converted text data. This process utilizes a natural language processing library. The input is text data, and the output is the analyzed request and emotional state data. This involves analyzing keywords and context within the text data to extract emotions and intentions.

[0562] Step 4:

[0563] The terminal sends the analyzed data to the server. Here, the analysis results are securely transferred via HTTPS communication. The input is the analyzed request and sentiment state data, and the output is the secure transmission of data to the server.

[0564] Step 5:

[0565] The server uses the received analysis data to match user behavior history and trend data and generate appropriate suggestions. A machine learning framework is used for this process. The input is the user's requests and emotional state, and the output is the generated suggestions. The suggestion generation operation is based on predictive calculations by the machine learning model.

[0566] Step 6:

[0567] The server sends the generated suggestions to the terminal and notifies the user. Here, the terminal's notification system is used to display prompts. The input is the generated suggestions, and the output is a visual or audible notification to the user. This includes actions such as generating notification pop-ups and outputting audio guidance.

[0568] Step 7:

[0569] The user acts according to the received suggestions and provides feedback on the results. Feedback is entered via the device as text or voice. The input is the user's feedback, and the output is the transmission of feedback data to the server. The action of filling out the feedback form is the concrete action.

[0570] Step 8:

[0571] The server updates its AI model using knowledge acquisition methods based on feedback, improving the accuracy of its suggestions. The input is feedback data, and the output is the improved AI model. This includes running a data learning algorithm to retrain the model.

[0572] (Application Example 2)

[0573] 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."

[0574] In today's living environment, there is a need for systems that can accurately understand users' emotional states and provide personalized care based on those states. In particular, in caregiving settings, it is crucial to respond flexibly and appropriately to the emotional states of the elderly and patients, but the technology to effectively achieve this is limited. This problem necessitates a system that can detect emotional changes and propose appropriate care in real time.

[0575] 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.

[0576] In this invention, the server includes: speech recognition means for receiving user voice and converting the voice into text data; natural language processing means for analyzing the user's requests from the text data; data learning means for generating suggestions based on the analyzed requests and using the user's behavioral history and preference data; emotion recognition means for identifying the user's emotional state using an emotion recognition engine; suggestion generation means for generating personalized care suggestions based on the identified emotional state; and output means for notifying the user of the suggestions. This makes it possible to grasp the user's emotional changes in real time, improve the quality of care, and improve the quality of life.

[0577] "Speech recognition means" refers to technology that receives speech signals from a user and converts them into text data.

[0578] "Natural language processing" refers to technologies that analyze text data to understand user requests and intentions.

[0579] "Data learning methods" are technologies that use user behavior history and preference data to generate suggestions that respond to analyzed requests.

[0580] "Emotion recognition means" refers to a technology that uses an emotion recognition engine to identify the user's emotional state from their voice or text data.

[0581] The "proposal generation means" is a technology that generates personalized care suggestions to be provided to the user based on the identified emotional state.

[0582] "Output means" refers to technology for notifying the user of the generated suggestions and providing them with information.

[0583] This invention provides a system for understanding the emotional state of elderly people and patients in care settings and providing appropriate care. The server performs emotion identification and care suggestions according to the following procedure.

[0584] First, smart glasses are used as the terminal to receive the voices of elderly people and patients. The smart glasses acquire voice data via a built-in microphone and convert that data into text using a speech recognition system. High-precision speech recognition software is used for this purpose.

[0585] Next, the text data is analyzed on the server using natural language processing tools to extract user requests and intentions. A general-purpose natural language processing library is used for this process. Based on the analyzed information, a data learning tool references the user's behavioral history and preference data to generate appropriate care suggestions. This incorporates machine learning algorithms that utilize historical data.

[0586] Furthermore, a key feature of this system is its emotion recognition mechanism, which allows the emotion recognition engine to analyze audio data and identify subtle emotional states. The emotion recognition engine used here utilizes major APIs to determine emotions in real time.

[0587] Based on the identified emotional state, the server uses suggestion generation means to provide personalized care suggestions to the user. Specific care and suggestions are communicated to the smart glasses via output means. The output means includes the ability to visually display instructions on the display.

[0588] For example, if a resident in a care facility says, "I'm not feeling well today," the system immediately identifies that emotion and suggests light exercise or rest as a countermeasure to address the "discomfort." By providing care suggestions that are adapted to such emotional states, the quality of life for the elderly is improved.

[0589] An example of a prompt message is: "What kind of flexible care is best to provide when the user is not feeling well today? Example: When the emotion recognition engine detects discomfort, what relaxation suggestions should be presented to the care staff?"

[0590] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0591] Step 1:

[0592] The device acquires the user's voice through smart glasses. A microphone converts the audio signal from analog to digital and collects it as audio data. This data is then input into subsequent processing steps.

[0593] Step 2:

[0594] The server converts the audio data acquired using speech recognition into text data. Dedicated speech recognition software analyzes the waveform of the audio signal and converts it into a corresponding string. This process outputs the user's spoken words as text.

[0595] Step 3:

[0596] The server uses natural language processing to analyze user requests and intentions from text data. It divides the text data into tokens, performs grammatical analysis, and then extracts semantic information. The analysis results are used as input for data learning tools.

[0597] Step 4:

[0598] The server mobilizes data learning tools and references the user's behavioral history and preference data to generate appropriate suggestions. Machine learning algorithms are applied to identify patterns from past data, and predictive models determine the content of the suggestions. These suggestions are output as customized care information for the user.

[0599] Step 5:

[0600] The server identifies emotional states from voice data using emotion recognition means. An emotion analysis engine analyzes the intonation and pitch of the voice to identify the user's emotions. These analysis results are then used as input for the suggestion generation means.

[0601] Step 6:

[0602] The server, using a suggestion generation mechanism, concretizes care suggestions that take into account the identified emotional state. For example, if a high stress level is detected, it recommends providing relaxation techniques. These care suggestions are presented in a viewable format by an output mechanism.

[0603] Step 7:

[0604] The device notifies the user of generated care suggestions through the smart glasses' display. A visual UI is configured to allow the user to easily understand the suggestions. The notified information can be immediately applied to the situation the user is facing.

[0605] 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.

[0606] 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.

[0607] 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.

[0608] [Fourth Embodiment]

[0609] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0610] 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.

[0611] 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).

[0612] 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.

[0613] 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.

[0614] 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).

[0615] 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.

[0616] 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.

[0617] 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.

[0618] 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.

[0619] 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.

[0620] 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.

[0621] 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".

[0622] This invention is a digital butler system that uses a wearable device to efficiently support the busy lives of users. The system functions by combining voice recognition means, natural language processing means, data learning means, output means, schedule management means, and task management means. Its specific operation is described below.

[0623] This system's speech recognition mechanism receives user voice input through a microphone built into the terminal and converts the voice data into digital format. Next, the server receives the voice data, converts it into text using natural language processing technology, and analyzes its content. This identifies the user's requests and questions and prepares an appropriate response.

[0624] Based on the analyzed information, the server uses data learning tools to learn the user's daily patterns and preferences. This learning enables the server to generate personalized suggestions and information for the user and deliver them through output tools. For example, if the server learns that a user tends to set an alarm at 7:00 AM, it will continuously set an alarm at that time.

[0625] Furthermore, the system automatically retrieves the user's schedule using a scheduling tool and creates reminders. For example, if there is a meeting scheduled, it can be set to send a notification at the appropriate time. The task management tool organizes and prioritizes the tasks that the user must manage. By prioritizing important and urgent tasks, the system enables efficient task management.

[0626] As a concrete example, if a user uses voice input to say, "Tell me what my schedule is for tomorrow," the device picks up the voice and sends it to the server. The server analyzes the request through natural language processing, and, referring to the data learning results, generates information based on the user's schedule. Finally, the device conveys that information to the user via voice.

[0627] This system allows users to receive support in all aspects of their daily lives, enabling them to make more effective use of their time.

[0628] The following describes the processing flow.

[0629] Step 1:

[0630] User: Gives a voice command to the wearable device saying, "Tell me the weather for tomorrow."

[0631] Step 2:

[0632] Terminal: The built-in microphone captures the user's voice and converts it into a digital signal. This signal is then sent to the server as digital data.

[0633] Step 3:

[0634] Server: Converts received audio data into text data using a speech recognition engine.

[0635] Step 4:

[0636] Server: Uses natural language processing (NLP) techniques to analyze text data to determine if it is a request for a "weather forecast".

[0637] Step 5:

[0638] Server: Based on the analysis results, retrieves necessary weather data from the weather information API.

[0639] Step 6:

[0640] Server: Formats acquired weather data into a user-friendly format and generates voice response messages.

[0641] Step 7:

[0642] Terminal: Performs speech synthesis to convey the generated voice response message to the user, and plays the result as audio.

[0643] Step 8:

[0644] User: Listen to the voice response from the device and give the following instructions by voice as needed.

[0645] (Example 1)

[0646] 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".

[0647] There is a challenge in providing support to help users make better use of their time by streamlining the busy schedule management and task processing in their daily lives. In particular, there is a need for automated information management with a natural interface that utilizes voice input.

[0648] 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.

[0649] In this invention, the server includes an acoustic information recognition means for receiving user voice and converting the voice into text information, a natural language processing means for analyzing the user's requests from the text information, and an information learning means for generating suggestions based on the analyzed requests and using the user's behavioral history and preference information. This makes it possible to efficiently manage daily tasks and schedules and to quickly provide personalized suggestions to the user.

[0650] "Acoustic information recognition means" refers to a device or process for receiving voice input from a user and converting it into text information.

[0651] "Natural language processing means" refers to a technology or method for analyzing textual information converted from speech and understanding user requests.

[0652] "Information learning means" refers to technologies or methods for generating appropriate suggestions and responses for users by utilizing their behavioral history and preference information.

[0653] "Information output means" refers to a device or process for notifying the user of generated proposals or responses.

[0654] A "task management method" is a technique or system for organizing, prioritizing, and managing a user's task information.

[0655] A "schedule management system" is a method or system for collecting a user's schedule information and automatically generating reminders.

[0656] "Audio output means" refers to a device or process for converting a generated proposal into an audio format using speech synthesis and conveying it audibly to the user.

[0657] The system for implementing this invention consists of a wearable device used by the user and a server operating in a cloud environment. The hardware and software used, as well as the details of the processing, are described below.

[0658] First, the device is equipped with a microphone to receive the user's voice. For voice recognition, the recorded voice data is converted into a digital format. Examples of usable devices include smartphones and smartwatches. The voice data is then transmitted to a server via a communication network.

[0659] After receiving audio data, the server converts it into text using the Google Cloud Speech-to-Text API. Next, natural language processing techniques are used to analyze the converted text. This process utilizes natural language processing libraries such as NLTK and spaCy to accurately extract the user's requests and intentions.

[0660] Based on the analyzed information, the server uses machine learning frameworks such as TensorFlow and PyTorch to train the data and generate personalized suggestions based on the user's behavior patterns and preferences. This allows, for example, the system to automatically adjust alarm settings according to the user's usual schedule and preferences.

[0661] The generated suggestions are converted into speech format using speech synthesis technology and sent to the terminal. The terminal then outputs back to the user. For example, open-source speech synthesis libraries such as Festival or commercial engines can be used as speech synthesis engines.

[0662] As a concrete example, when a user asks the device by voice, "Tell me what I have to do tomorrow," the device sends the voice input to the server, which then analyzes the request using natural language processing. Based on the user's calendar information, the server then generates content such as, "You have a meeting at 10 o'clock," converts it into speech using speech synthesis, and plays it back to the user. This allows the user to efficiently check their daily schedule.

[0663] Examples of prompts generated using the AI ​​model in this system include "Tell me my schedule for tomorrow" and "Set an alarm." This allows users to receive support from the system in various situations in their daily lives.

[0664] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0665] Step 1:

[0666] The terminal receives the user's voice input through the microphone. The received voice data is digitally converted into an audio data format. The digital audio data generated through this conversion undergoes pre-processing such as noise reduction and is then transmitted to the server via the communication network.

[0667] Step 2:

[0668] The server passes the digital audio data received from the terminal to the speech recognition API, which converts the audio into text information. Based on the input audio data, the speech recognition API performs phoneme analysis and generates text data. The output text data is used in the next step to analyze the user's intent.

[0669] Step 3:

[0670] The server analyzes text data generated using a natural language processing library. The input text data undergoes processing such as tokenization, part-of-speech tagging, and dependency analysis to be transformed into structured data that helps understand user requests. As a result of this analysis, the server identifies the information and instructions the user is seeking.

[0671] Step 4:

[0672] The server retrieves necessary information from the database based on the analyzed user requests and generates personalized suggestions using an information learning algorithm. Here, user behavior history and preference information are used as input, and data calculations are performed by a machine learning model. The output is a suggestion optimized for the user.

[0673] Step 5:

[0674] The generated suggestions are converted into audio data by the server. By inputting the text information into a speech synthesis engine and generating natural-sounding audio data, this audio data is ready to be sent to the terminal. The audio data, as output, functions as a response to the user.

[0675] Step 6:

[0676] The terminal plays audio data received from the server and outputs it through the speaker so that the user can hear it. Specifically, it uses the terminal's built-in audio playback function to output the audio. By listening to the audio guidance, the user can take action based on the information and suggestions received from the system.

[0677] (Application Example 1)

[0678] 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".

[0679] In today's busy lifestyle, users face many challenges in efficiently managing their daily lives and maintaining a comfortable home environment. Manually managing schedules and tasks is time-consuming and laborious, and operating various household appliances is also cumbersome. This invention aims to solve these problems and provide a system that improves the efficiency and comfort of users' daily lives.

[0680] 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.

[0681] In this invention, the server includes: speech recognition means for receiving user voice and converting said voice into text data; natural language processing means for analyzing the user's requests from the text data; data learning means for generating suggestions based on the analyzed requests and using the user's behavioral history and preference data; output means for notifying the user of the suggestions; and control means for coordinating with the user's environment control device to automatically adjust home environment settings based on the presented information. This makes it possible to improve the user's lifestyle efficiency and home comfort.

[0682] "Speech recognition means" refers to an element that has the function of receiving the user's voice and converting said voice into text data.

[0683] A "natural language processing tool" is an element that analyzes user requests from text data and performs processing to understand their content.

[0684] A "data learning tool" is an element that generates user-optimized suggestions based on analyzed requests, using the user's behavioral history and preference data.

[0685] An "output mechanism" is an element that has the function of notifying and providing the generated proposal to the user.

[0686] A "control device" is an element that works in conjunction with the user's environmental control device to automatically adjust home environment settings based on the information provided.

[0687] This invention is a digital butler system designed to efficiently manage a user's life and improve their comfort. Specific embodiments are described below.

[0688] The server receives the user's voice using speech recognition and converts the voice into text data. Commercially available speech recognition software can be used for this process; for example, Google Cloud Speech-to-Text is available. The converted text data is then analyzed by natural language processing to understand the user's request. Here, a platform such as Dialogflow is utilized for natural language processing.

[0689] Based on the analysis results, the server activates a data learning mechanism, referencing the user's past behavioral history and preference data to generate suggestions. This data learning utilizes a machine learning model to learn the user's patterns. As a result, personalized suggestions are generated for the user.

[0690] The generated suggestions are notified to the user via an output device. For example, information is provided through a voice assistant or a screen display device. Furthermore, the server, through a control device, interacts with environmental control systems in the user's home and automatically adjusts settings such as lighting and air conditioning based on the obtained information. Smart home devices and IoT platforms are used for this process.

[0691] For example, if a user asks, "Tell me about my plans for this weekend," the system quickly converts the voice into text and analyzes it. Based on the analyzed information, it searches for the user's schedule and provides information via voice or display, such as, "You have plans for lunch with a friend on Saturday."

[0692] As an example of a prompt, a user can ask the voice assistant, "What's the next task?", and information based on the task list's priority will be provided immediately.

[0693] As described above, the present invention makes it possible to provide a practical system that improves the efficiency and comfort of users' daily lives.

[0694] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0695] Step 1:

[0696] The terminal receives voice input from the user via its microphone. The input is captured as compressed audio data, and this audio data is sent to the server.

[0697] Step 2:

[0698] The server converts the received audio data into text data using speech recognition. This process uses speech recognition software to analyze the audio signal and convert it into text based on a language model. The output is then sent as text data to the next processing step.

[0699] Step 3:

[0700] The server analyzes the converted text data using natural language processing techniques. It extracts keywords and intent from the input text to understand the user's request. The output is the analyzed request information.

[0701] Step 4:

[0702] The server generates suggestions based on requests analyzed using data learning tools. It references past behavioral history and user profiles, and uses machine learning algorithms to construct personalized suggestions. The output is the suggestion information to be presented to the user.

[0703] Step 5:

[0704] The server transmits the generated suggestion information to the terminal using an output device. The user can then review the suggestion via audio or display. The output here is information provided to the user visually or audibly.

[0705] Step 6:

[0706] The server interacts with the user's environmental control device through a control mechanism. Based on the proposed information, it automatically adjusts settings such as lighting and temperature. The input is the user's current environmental settings, and the output is the new, adjusted settings.

[0707] 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.

[0708] This invention is a system that utilizes an emotion recognition engine embedded in a wearable device to provide personalized support based on the user's emotional state. In addition to conventional speech recognition means, natural language processing means, data learning means, and output means, this system improves the user experience by using an emotion recognition engine.

[0709] The emotion recognition engine analyzes the user's voice and text data collected through the device to identify subtle emotional states. The server receives this data and adjusts suggestions and notification methods to match the user's emotional state. For example, if a user types "I'm tired today," the emotion recognition engine identifies "fatigue," and the server suggests relaxing music or adjusts the user's schedule for the next day.

[0710] Furthermore, the emotion recognition engine continuously learns the user's emotional data and integrates it with data learning methods to understand the user's long-term trends. This allows the server to respond immediately to changes in the user's emotions, for example, by providing recommendations for meditation or rest through output methods if stress levels are rising.

[0711] For example, if a user urgently says in the morning that they might be late for a meeting, the system will sense their anxiety and suggest the shortest route, while also offering a breathing exercise video to help them calm down upon arrival. By incorporating emotion recognition in this way, flexible responses tailored to the user's emotional needs become possible. This allows users to receive more comprehensive support, ultimately improving their quality of life.

[0712] The following describes the processing flow.

[0713] Step 1:

[0714] User: Speaks to the wearable device, saying, "The project isn't going well."

[0715] Step 2:

[0716] Terminal: The microphone captures audio and converts it into a digital signal. This is then sent to the server as digital data.

[0717] Step 3:

[0718] Server: Converts received audio data into text data using a speech recognition engine.

[0719] Step 4:

[0720] Server: Using natural language processing (NLP) technology, it analyzes user requests from text data and infers emotions such as "feeling stressed."

[0721] Step 5:

[0722] Server: The emotion recognition engine evaluates the emotional state in detail and generates emotional parameters such as "stress" and "anxiety."

[0723] Step 6:

[0724] Server: Based on emotional parameters, it plans to suggest relaxation methods and stress-relief activities recommended for the user.

[0725] Step 7:

[0726] Server: Generates suggestions and selects specific examples such as "5-minute deep breathing exercises" and "relaxation music."

[0727] Step 8:

[0728] Terminal: Outputs the suggestion to the user via voice, and displays further visual instructions on the device's display if needed.

[0729] Step 9:

[0730] User: Perform the provided relaxation techniques to regain a relaxed state of mind.

[0731] This entire process allows the system to provide information tailored to the user's emotions, enabling efficient and effective responses.

[0732] (Example 2)

[0733] 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".

[0734] Conventional systems could only offer suggestions based on simple history and preferences in response to user requests, making it difficult to provide flexible support that took into account the user's emotional state. Furthermore, a challenge was the inability to fully utilize user feedback, resulting in insufficient improvement in the accuracy of suggestions.

[0735] 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.

[0736] In this invention, the server includes a speech conversion means for receiving user speech and converting it into text data, a natural language processing means for analyzing requests and emotional states from the text data, and a data analysis means for analyzing data based on the analysis results and generating suggestions. This enables suggestions that are appropriate to the user's emotional state and allows for continuous improvement of the accuracy of the suggestions through feedback.

[0737] "Voice conversion means" refers to a function that processes audio information received from a user into text information.

[0738] A "natural language processing tool" is a function that performs processing to analyze and identify user requests and emotional states from textual information.

[0739] "Data analysis means" refers to a function that generates appropriate suggestions by referencing user behavior history and trend data based on analyzed requests and emotional states.

[0740] The "information output means" is a function that notifies the user of the generated suggestions and also receives feedback.

[0741] "Knowledge acquisition means" refers to a function that learns from user feedback and performs processing to improve the accuracy of suggestions.

[0742] The "schedule management method" is a function that acquires the user's schedule information, generates reminders, and adjusts suggestions as appropriate, taking into account the user's emotional state.

[0743] A "task management system" is a function that collects the user's task information and dynamically adjusts priorities according to their emotional state.

[0744] This invention relates to a system that processes user voice and text information to identify the user's emotional state and generate optimal suggestions. To realize this system, the following hardware and software are utilized.

[0745] Users input voice and text data into the system using devices such as wearable devices or smartphones. These devices are equipped with a microphone for voice input and a touchscreen for text input.

[0746] The device uses speech-to-text software such as the Google Cloud Speech-to-Text API to convert speech data into text data. Next, spaCy or a similar natural language processing library is used as a natural language analysis tool to analyze the user's requests and emotional state from the text data.

[0747] Subsequently, these analysis results are sent to the server. The server uses machine learning frameworks such as PyTorch and scikit-learn as data analysis tools to generate appropriate suggestions based on the user's behavior history and trend data. The generated suggestions are sent to the terminal via an information output device and notified to the user.

[0748] For example, if a user enters "I'm tired today" into their device, the emotion analysis engine identifies "fatigue." The server then suggests relaxing music to the device via services like Spotify and provides advice on adjusting the next day's schedule based on this emotional state.

[0749] Furthermore, as a means of acquiring knowledge by receiving user feedback, the server continuously learns the AI ​​model and improves the accuracy of its suggestions. This feedback is received, for example, through comments entered via a touchscreen or voice comments.

[0750] An example of a prompt message would be, "What kind of support would you offer if the user is experiencing fatigue?"

[0751] Thus, the present invention is a flexible and dynamic suggestion system capable of providing optimal support according to the user's emotional state.

[0752] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0753] Step 1:

[0754] The device receives the user's voice. At this time, it uses the microphone to collect voice data and temporarily stores it within the device. The voice data is the input, and this data is formatted for the next processing step.

[0755] Step 2:

[0756] The terminal converts audio data into text data. This process uses speech conversion software (e.g., a speech recognition API). The input is audio data, and the output is text data. The specific operation involves detecting phonemes from the audio waveform and converting them into text.

[0757] Step 3:

[0758] The terminal analyzes the user's requests and emotional state using the converted text data. This process utilizes a natural language processing library. The input is text data, and the output is the analyzed request and emotional state data. This involves analyzing keywords and context within the text data to extract emotions and intentions.

[0759] Step 4:

[0760] The terminal sends the analyzed data to the server. Here, the analysis results are securely transferred via HTTPS communication. The input is the analyzed request and sentiment state data, and the output is the secure transmission of data to the server.

[0761] Step 5:

[0762] The server uses the received analysis data to match user behavior history and trend data and generate appropriate suggestions. A machine learning framework is used for this process. The input is the user's requests and emotional state, and the output is the generated suggestions. The suggestion generation operation is based on predictive calculations by the machine learning model.

[0763] Step 6:

[0764] The server sends the generated suggestions to the terminal and notifies the user. Here, the terminal's notification system is used to display prompts. The input is the generated suggestions, and the output is a visual or audible notification to the user. This includes actions such as generating notification pop-ups and outputting audio guidance.

[0765] Step 7:

[0766] The user acts according to the received suggestions and provides feedback on the results. Feedback is entered via the device as text or voice. The input is the user's feedback, and the output is the transmission of feedback data to the server. The action of filling out the feedback form is the concrete action.

[0767] Step 8:

[0768] The server updates its AI model using knowledge acquisition methods based on feedback, improving the accuracy of its suggestions. The input is feedback data, and the output is the improved AI model. This includes running a data learning algorithm to retrain the model.

[0769] (Application Example 2)

[0770] 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".

[0771] In today's living environment, there is a need for systems that can accurately understand users' emotional states and provide personalized care based on those states. In particular, in caregiving settings, it is crucial to respond flexibly and appropriately to the emotional states of the elderly and patients, but the technology to effectively achieve this is limited. This problem necessitates a system that can detect emotional changes and propose appropriate care in real time.

[0772] 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.

[0773] In this invention, the server includes: speech recognition means for receiving user voice and converting the voice into text data; natural language processing means for analyzing the user's requests from the text data; data learning means for generating suggestions based on the analyzed requests and using the user's behavioral history and preference data; emotion recognition means for identifying the user's emotional state using an emotion recognition engine; suggestion generation means for generating personalized care suggestions based on the identified emotional state; and output means for notifying the user of the suggestions. This makes it possible to grasp the user's emotional changes in real time, improve the quality of care, and improve the quality of life.

[0774] "Speech recognition means" refers to technology that receives speech signals from a user and converts them into text data.

[0775] "Natural language processing" refers to technologies that analyze text data to understand user requests and intentions.

[0776] "Data learning methods" are technologies that use user behavior history and preference data to generate suggestions that respond to analyzed requests.

[0777] "Emotion recognition means" refers to a technology that uses an emotion recognition engine to identify the user's emotional state from their voice or text data.

[0778] The "proposal generation means" is a technology that generates personalized care suggestions to be provided to the user based on the identified emotional state.

[0779] "Output means" refers to technology for notifying the user of the generated suggestions and providing them with information.

[0780] This invention provides a system for understanding the emotional state of elderly people and patients in care settings and providing appropriate care. The server performs emotion identification and care suggestions according to the following procedure.

[0781] First, smart glasses are used as the terminal to receive the voices of elderly people and patients. The smart glasses acquire voice data via a built-in microphone and convert that data into text using a speech recognition system. High-precision speech recognition software is used for this purpose.

[0782] Next, the text data is analyzed on the server using natural language processing tools to extract user requests and intentions. A general-purpose natural language processing library is used for this process. Based on the analyzed information, a data learning tool references the user's behavioral history and preference data to generate appropriate care suggestions. This incorporates machine learning algorithms that utilize historical data.

[0783] Furthermore, a key feature of this system is its emotion recognition mechanism, which allows the emotion recognition engine to analyze audio data and identify subtle emotional states. The emotion recognition engine used here utilizes major APIs to determine emotions in real time.

[0784] Based on the identified emotional state, the server uses suggestion generation means to provide personalized care suggestions to the user. Specific care and suggestions are communicated to the smart glasses via output means. The output means includes the ability to visually display instructions on the display.

[0785] For example, if a resident in a care facility says, "I'm not feeling well today," the system immediately identifies that emotion and suggests light exercise or rest as a countermeasure to address the "discomfort." By providing care suggestions that are adapted to such emotional states, the quality of life for the elderly is improved.

[0786] An example of a prompt message is: "What kind of flexible care is best to provide when the user is not feeling well today? Example: When the emotion recognition engine detects discomfort, what relaxation suggestions should be presented to the care staff?"

[0787] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0788] Step 1:

[0789] The device acquires the user's voice through smart glasses. A microphone converts the audio signal from analog to digital and collects it as audio data. This data is then input into subsequent processing steps.

[0790] Step 2:

[0791] The server converts the audio data acquired using speech recognition into text data. Dedicated speech recognition software analyzes the waveform of the audio signal and converts it into a corresponding string. This process outputs the user's spoken words as text.

[0792] Step 3:

[0793] The server uses natural language processing to analyze user requests and intentions from text data. It divides the text data into tokens, performs grammatical analysis, and then extracts semantic information. The analysis results are used as input for data learning tools.

[0794] Step 4:

[0795] The server mobilizes data learning tools and references the user's behavioral history and preference data to generate appropriate suggestions. Machine learning algorithms are applied to identify patterns from past data, and predictive models determine the content of the suggestions. These suggestions are output as customized care information for the user.

[0796] Step 5:

[0797] The server identifies emotional states from voice data using emotion recognition means. An emotion analysis engine analyzes the intonation and pitch of the voice to identify the user's emotions. These analysis results are then used as input for the suggestion generation means.

[0798] Step 6:

[0799] The server, using a suggestion generation mechanism, concretizes care suggestions that take into account the identified emotional state. For example, if a high stress level is detected, it recommends providing relaxation techniques. These care suggestions are presented in a viewable format by an output mechanism.

[0800] Step 7:

[0801] The device notifies the user of generated care suggestions through the smart glasses' display. A visual UI is configured to allow the user to easily understand the suggestions. The notified information can be immediately applied to the situation the user is facing.

[0802] 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.

[0803] 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.

[0804] 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.

[0805] 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.

[0806] 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.

[0807] 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.

[0808] 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.

[0809] 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.

[0810] 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."

[0811] 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.

[0812] 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.

[0813] 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.

[0814] 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.

[0815] 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.

[0816] 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.

[0817] 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.

[0818] 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.

[0819] 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.

[0820] 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.

[0821] 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.

[0822] 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.

[0823] The following is further disclosed regarding the embodiments described above.

[0824] (Claim 1)

[0825] A speech recognition means that receives the user's voice and converts the voice into text data,

[0826] A natural language processing means for analyzing user requests from the aforementioned text data,

[0827] A data learning means that generates suggestions using user behavior history and preference data based on analyzed requests,

[0828] An output means for notifying the user of the proposal,

[0829] A system that includes this.

[0830] (Claim 2)

[0831] The system according to claim 1, further comprising a schedule management means for acquiring user schedule information and automatically generating reminders.

[0832] (Claim 3)

[0833] The system according to claim 1, further comprising a task management means for prioritizing user task information.

[0834] "Example 1"

[0835] (Claim 1)

[0836] Acoustic information recognition means that receives user voice and converts said voice into text information,

[0837] A natural language processing means for analyzing user requests from the aforementioned textual information,

[0838] An information learning means that generates suggestions based on analyzed requests using the user's behavioral history and preference information,

[0839] Information output means for notifying the user of the proposal,

[0840] A task management method for prioritizing task information,

[0841] A system that includes this.

[0842] (Claim 2)

[0843] The system according to claim 1, further comprising a schedule management means for acquiring user schedule information and automatically generating reminders.

[0844] (Claim 3)

[0845] The system according to claim 1, further comprising a voice output means for synthesizing the generated proposal's voice and notifying the user.

[0846] "Application Example 1"

[0847] (Claim 1)

[0848] A speech recognition means that receives the user's voice and converts the voice into text data,

[0849] A natural language processing means for analyzing user requests from the aforementioned text data,

[0850] A data learning means that generates suggestions using user behavior history and preference data based on analyzed requests,

[0851] An output means for notifying the user of the proposal,

[0852] A control means that works in conjunction with the user's environmental control device to automatically adjust home environment settings based on the information provided,

[0853] A system that includes this.

[0854] (Claim 2)

[0855] The system according to claim 1, further comprising a schedule management means for acquiring user schedule information and automatically generating reminders.

[0856] (Claim 3)

[0857] The system according to claim 1, further comprising a task management means for prioritizing user task information.

[0858] "Example 2 of combining an emotion engine"

[0859] (Claim 1)

[0860] A voice conversion means that receives the user's voice and converts the voice into text data,

[0861] A natural language processing means that analyzes the user's request from the aforementioned text data and identifies their emotional state,

[0862] A data analysis means that generates suggestions based on analyzed requests and emotional states, using user behavior history and trend data,

[0863] Information output means for notifying the user of the proposal and receiving feedback,

[0864] A knowledge acquisition method that continuously learns the model based on the aforementioned feedback and improves the accuracy of the proposals,

[0865] A system that includes this.

[0866] (Claim 2)

[0867] The system according to claim 1, further comprising a schedule management means for acquiring user schedule information, automatically generating reminders, and adjusting suggestions based on emotional state.

[0868] (Claim 3)

[0869] The system according to claim 1, further comprising task management means for prioritizing user task information and dynamically adjusting task priorities while taking into account the user's emotional state.

[0870] "Application example 2 when combining with an emotional engine"

[0871] (Claim 1)

[0872] A speech recognition means that receives the user's voice and converts the voice into text data,

[0873] A natural language processing means for analyzing user requests from the aforementioned text data,

[0874] A data learning means that generates suggestions using user behavior history and preference data based on analyzed requests,

[0875] An emotion recognition means that identifies the user's emotional state using an emotion recognition engine,

[0876] A proposal generation means that generates personalized care proposals based on identified emotional states,

[0877] An output means for notifying the user of the proposal,

[0878] A system that includes this.

[0879] (Claim 2)

[0880] The system according to claim 1, further comprising a schedule management means for acquiring user schedule information and automatically generating reminders.

[0881] (Claim 3)

[0882] The system according to claim 1, further comprising a task management means for prioritizing user task information. [Explanation of symbols]

[0883] 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 speech recognition means that receives the user's voice and converts the voice into text data, A natural language processing means for analyzing user requests from the aforementioned text data, A data learning means that generates suggestions using user behavior history and preference data based on analyzed requests, An output means for notifying the user of the proposal, A system that includes this.

2. The system according to claim 1, further comprising a schedule management means for acquiring user schedule information and automatically generating reminders.

3. The system according to claim 1, further comprising a task management means for prioritizing user task information.

Images