system

Abstract

We provide the system. [Solution] A means for collecting past record data, A means for analyzing the aforementioned past recorded data and generating a user dialogue model and voice model, Means for controlling a terminal that converses with a user using the generated dialogue model and voice model, A means for recording the content of the aforementioned conversation and generating a summary, Means for providing the summary and conversation log to the user or a third party, 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 steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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] With the progress of an aging society, the number of dementia patients is increasing. As a result, the burden on family members and care providers is growing. In particular, dementia patients seek a sense of security and communication in their daily lives, but the corresponding measures are very time-consuming. To solve this problem, there is a need for a system that allows dementia patients to receive personalized care based on their past memories and reduces the burden on family members and care providers.

Means for Solving the Problems

[0005] To solve the above-mentioned problems, the present invention provides the following means: means for collecting past recorded data, including letters, videos, text messages, photographs, and manually entered data; means for analyzing the past recorded data and generating a user dialogue model and a voice model; this analysis includes natural language processing technology and speech generation technology; means for controlling a terminal that converses with the user using the generated dialogue model and voice model, recording the conversation content, and generating a summary; and finally, means for providing the summary and conversation log to the user or a third party. This enables personalized care for dementia patients and reduces the burden on families and caregivers.

[0006] "Past records" refers to a general term for data containing information about past events and experiences, such as letters, videos, text messages, photographs, and manually entered data, that have been saved by dementia patients or their families.

[0007] "Means of collection" refers to the mechanisms and methods for collecting and storing historical record data within a system.

[0008] "Analysis" refers to the process of processing collected historical data to extract user characteristics, language patterns, preferences, emotional tendencies, and so on.

[0009] A "dialogue model" refers to an algorithm or program that simulates natural conversations with a specific user based on analyzed data.

[0010] A "voice model" refers to an algorithm or program that is generated from a user's past voice data or text to mimic the user's specific voice characteristics.

[0011] The term "terminal" refers to a device used to converse with a user using generated dialogue models and voice models, such as a robot or a tablet device.

[0012] "Conversation content" refers to text and audio data that includes the specific details of communication between the user and the device, such as statements and responses.

[0013] A "summary" refers to data that has been compiled by extracting important information and key points from a conversation.

[0014] "Third party" refers to an individual or group other than the user themselves, such as family members or care providers. [Brief explanation of the drawing]

[0015] [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] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be one 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.

[0019] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] 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."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] This invention is a system that provides fully personalized care for the elderly and dementia patients. The program processing of this system will be explained below, including specific examples.

[0037] System Configuration

[0038] This system consists of the following main components:

[0039] 1. Data collection means: Means for collecting the user's past record data.

[0040] 2. Data analysis means: Means for analyzing collected data to generate a user dialogue model and a voice model.

[0041] 3. Terminal: A device that uses the generated dialogue model and voice model to converse with the user.

[0042] 4. Conversation recording means: A means for recording conversation content and generating and providing a summary.

[0043] System operation

[0044] User: First, upload past records (letters, videos, text messages, photos, manually entered data, etc.) to the system using a smartphone or PC. This allows the system to collect information about the user's past events and experiences.

[0045] As a concrete example, a user could scan and upload photos from an old family album, along with any related letters or video messages.

[0046] Server: Receives uploaded data and stores it in a database. Then, it analyzes this data using natural language processing and speech generation technologies. The analysis includes a process of extracting the user's language patterns, preferences, and emotional tendencies.

[0047] As a concrete example, the server analyzes the content of uploaded letters to identify frequently used vocabulary and expressions. It also analyzes video messages to extract the intonation and tone of the user's voice.

[0048] Terminal: Next, the generated dialogue model and voice model are used to converse with the user. The terminal is a robot or a tablet device, and it simulates natural conversation with the user through these devices.

[0049] As a concrete example, the robot might say, "Good morning, which photo would you like to see today?" and the user might reply, "I'd like to see this family photo."

[0050] Server: Furthermore, it records conversations in real time, extracts important information, and generates summaries. The summaries and conversation logs are provided to the user and their family.

[0051] As a concrete example, the server generates a summary stating, "The topic the user most wanted to talk about in today's conversation was family travel," and periodically notifies the family of this information.

[0052] This system not only enables personalized care for dementia patients but also significantly reduces the burden on families and caregivers. Dementia patients can gain a sense of security and satisfaction by enjoying conversations based on their own lives and memories. Furthermore, the system constantly adapts and learns based on the latest data and feedback, improving the quality of care.

[0053] The following describes the processing flow.

[0054] Step 1:

[0055] User: Upload past record data to the system. The procedure involves using a smartphone or PC to select files such as letters, videos, text messages, photos, and manually entered data, and then sending them to the server using a dedicated app or web portal.

[0056] Step 2:

[0057] Server: Receives uploaded data and saves it to the database. It verifies the data format upon receipt and saves it to the appropriate storage path. For example, scanned images of letters are saved to the images folder, and video files are saved to the videos folder.

[0058] Step 3:

[0059] Server: Analyzes stored data. Extracts language patterns and sentiment tendencies from text data using natural language processing techniques. Generates speech models from speech and text data using speech generation techniques. This creates user dialogue models and speech models.

[0060] Step 4:

[0061] Server: Stores the generated dialogue and speech models in the cloud. Performs model validation and optimization as needed to improve accuracy.

[0062] Step 5:

[0063] Terminal: The user instructs the terminal to start the conversation simulation. The terminal (robot or tablet) downloads the model generated from the server and sets up the conversation environment.

[0064] Step 6:

[0065] Terminal: Speaks to the user. For example, it uses phrases such as "Hello, how was your day?" and engages in natural conversation through a generated voice model.

[0066] Step 7:

[0067] User: Responds to questions and comments presented by the device. The device understands the user's statements through speech recognition and proceeds with the conversation.

[0068] Step 8:

[0069] Terminal: Records conversation content in real time. Generates conversation logs as text and audio data and sends them to the server periodically.

[0070] Step 9:

[0071] Server: Analyzes received conversation logs, extracts important information and key points, generates summaries, and evaluates the user's health and psychological state.

[0072] Step 10:

[0073] Server: Provides generated summaries and conversation logs to users, families, and caregivers. It also provides regular reports and gathers necessary feedback.

[0074] Through this series of steps, the system can provide effective dementia care and reduce the burden on families and caregivers.

[0075] (Example 1)

[0076] 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."

[0077] When providing personalized care to dementia patients and the elderly, there is a challenge in understanding each individual user's past experiences and preferences and engaging in conversations based on this. Furthermore, there is a lack of systems that allow families and care providers to accurately understand the patient's condition without causing them burden.

[0078] 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.

[0079] In this invention, the server includes means for collecting past recorded data from the user and uploading it to the system; means for analyzing the collected past recorded data and generating a user dialogue model and voice model; means for conversing with the user using the generated dialogue model and voice model; means for recording the conversation content in real time, extracting important information, and generating and providing a summary; and means for providing the summary and conversation log to the user or a third party. This makes it possible to achieve natural conversations based on the user's past experiences and preferences, thereby improving the user's sense of security and satisfaction. It also reduces the burden on family members and caregivers and allows them to grasp important information.

[0080] A "user" refers to an individual who provides data and utilizes the system.

[0081] "Past recorded data" refers to information including the user's past images, documents, videos, messages, and input data.

[0082] "Collection means" refers to devices and software that allow users to upload past recorded data to the system.

[0083] "Analysis means" refers to devices or software that analyze collected historical record data and generate user dialogue models and voice models.

[0084] A "dialogue model" refers to a language model designed to mimic conversations with users.

[0085] A "voice model" refers to a model used to generate speech during conversations with users.

[0086] "Conversational means" refers to devices or software that engage in conversation with a user using generated dialogue models and voice models.

[0087] "Recording means" refers to devices or software that record conversation content in real time, extract important information, and generate and provide summaries.

[0088] A "summary" refers to a compilation of the most important information from a conversation.

[0089] "Conversation log" refers to data that records the content of conversations with users.

[0090] "Third parties" refer to individuals or organizations other than the user, including family members and care providers.

[0091] This invention is a system that provides fully personalized care for the elderly and dementia patients. This system has the function of collecting and analyzing past recorded data, generating a user dialogue model and voice model, using these to converse with the user, and recording the content of the conversation. The following describes embodiments of this system.

[0092] System Configuration

[0093] 1. Data collection means: These are devices or software that allow users to upload past recorded data (images, documents, videos, messages, input data, etc.) to the system. Specific examples include the file upload function of smartphones and personal computers.

[0094] 2. Data Analysis Means: These are devices and software for analyzing uploaded data. They use natural language processing technology (e.g., Google® Cloud Natural Language API) and speech generation technology (e.g., Amazon Polly) to generate user dialogue models and speech models.

[0095] 3. Terminal: A device or software that engages in conversation with a user using the generated dialogue model and voice model. Specific examples include robots (e.g., Pepper) and tablet devices (e.g., iPad®).

[0096] 4. Conversation recording means: Devices or software that record conversation content in real time, extract important information, and generate and provide a summary.

[0097] System operation

[0098] Users collect historical data using smartphones or personal computers. For example, they scan family photo albums and collect related letters and video messages. They then upload this data to the system.

[0099] Server: Upon receiving uploaded data, it stores it in a secure database. The data is then analyzed using natural language processing and speech generation technologies. This analysis extracts the user's language patterns, preferences, and emotional tendencies, generating dialogue and voice models tailored to the user. For example, the server analyzes the text of a travel diary to identify frequently occurring vocabulary and phrases. It also extracts the pitch and intonation of the user's voice through audio analysis of video messages.

[0100] Terminal: The robot and tablet terminal use generated dialogue and voice models to converse with the user. For example, the robot might say, "Good morning, which photos would you like to see today?" and the user might reply, "I'd like to see photos from our family trip."

[0101] Server: Records conversations in real time, extracts important information, and generates summaries. The generated summaries and conversation logs are provided to the user themselves or third parties such as their family. For example, the server might generate a summary stating, "The topic the user was most interested in today was family travel," and send that information to the family via email.

[0102] Specific examples and prompt statements

[0103] Specific example:

[0104] 1. Users scan family trip photos and travel diaries and upload them to the system.

[0105] 2. The server receives this data, analyzes frequently occurring vocabulary and intonation, and generates a dialogue model and a speech model.

[0106] 3. The robot asks the user, "Which photos would you like to see today?" and the user replies, "I'd like to see photos from our family trip."

[0107] 4. The server records the conversation in real time and generates a summary stating, "The topic the user most wanted to talk about was family travel," and notifies the family.

[0108] Example of a prompt:

[0109] "Please talk about past memories related to family photos."

[0110] "What kind of music would you like to listen to today?"

[0111] In this way, a system that provides fully personalized care for the elderly and dementia patients is realized. This system can provide a sense of security and satisfaction through natural conversations based on the user's past experiences and preferences, and can reduce the burden on families and caregivers.

[0112] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0113] Step 1: Data Collection

[0114] User:

[0115] The user prepares past recorded data (e.g., images, documents, videos, messages, input data). Specifically, this involves scanning family album photos and collecting related letters and video messages.

[0116] Input: Scanned images, documents, video files

[0117] Output: Uploaded data file

[0118] Specific actions: The user takes photos for an album, scans letters, and records video messages using their smartphone. These files are then prepared in the system.

[0119] Step 2: Upload your registration

[0120] User:

[0121] Users upload their prepared historical record data to the system using the upload function of their smartphone or personal computer.

[0122] Input: Prepared data file

[0123] Output: Data files saved on the system

[0124] Specific operation: The user clicks the upload button on their smartphone, selects files such as "family trip photos" or "travel diary," and sends them to the system.

[0125] Step 3: Save data

[0126] server:

[0127] The server receives the uploaded data and stores it in a secure database.

[0128] Input: Uploaded data file

[0129] Output: Data stored in the database

[0130] Specific operation: The server parses the received file and saves it to the appropriate section of the database.

[0131] Step 4: Data analysis and model generation

[0132] server:

[0133] The stored data is analyzed. Text data is analyzed using natural language processing technology (e.g., Google Cloud Natural Language API), and audio data is analyzed using speech generation technology (e.g., Amazon Polly). This extracts the user's language patterns, preferences, and emotional tendencies, and generates dialogue models and speech models.

[0134] Input: Data stored in the database

[0135] Output: Generated dialogue model and voice model

[0136] Specific operation: The server analyzes the text of the travel diary to identify frequently occurring vocabulary and phrases. It also extracts the pitch and intonation of the user's voice through audio analysis of video messages.

[0137] Step 5: Generating and executing dialogue

[0138] Terminal:

[0139] The system uses generated dialogue and voice models to engage in conversations with users. It simulates natural conversations using robots (e.g., Pepper) or tablet devices (e.g., iPad).

[0140] Input: Generated dialogue model and voice model

[0141] Output: User interaction content

[0142] Specific action: The robot says, "Good morning, which photos would you like to see today?" and the user replies, "I'd like to see photos from our family trip."

[0143] Step 6: Record the conversation and generate a summary.

[0144] server:

[0145] The system records conversations in real time, extracts important information, and generates summaries. The generated summaries and conversation logs are provided to the user themselves or third parties such as their family.

[0146] Input: Content of the conversation between the user and the device.

[0147] Output: Generated summary and conversation log

[0148] Specific operation: The server records the conversation content, generates a summary stating, "The topic the user was most interested in today was family travel," and notifies the family via email.

[0149] Step 7: Feedback and Learning

[0150] server:

[0151] The system's learning model is updated based on the acquired conversation content and feedback. This improves the quality of subsequent conversations.

[0152] Input: Conversation log and feedback information

[0153] Output: Updated dialogue model and voice model

[0154] Specific operation: The server analyzes the conversation record, reflects the user's new interests and concerns in the model, and adjusts the system for the next interaction.

[0155] (Application Example 1)

[0156] 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."

[0157] Providing meals to the elderly and dementia patients requires personalized menu suggestions based on individual eating habits and medical information, but this is difficult to achieve with typical food delivery services. Furthermore, there is a need for a system that incorporates user feedback to provide optimal meal suggestions and records this information to offer a better dining experience.

[0158] 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.

[0159] In this invention, the server includes means for collecting past recorded data and the user's eating habits and medical information; means for analyzing the past recorded data and the user's eating habits and medical information to generate a user dialogue model and a voice model; means for controlling a terminal that converses with the user using the generated dialogue model and voice model and proposes a meal menu; means for the user to confirm an order based on the proposed meal menu; means for recording the conversation content and order history, collecting feedback on the meal menu, and generating a summary; and means for providing the summary and conversation log to the user or a third party. This makes it possible to propose the most suitable meal menu for each individual user and to provide personalized services that are tailored to the user's health condition and preferences.

[0160] "Past recorded data" refers to information about the user's previous activities and experiences, including letters, videos, text messages, photographs, handwritten data, and food photos.

[0161] "User eating habits" refers to information such as the types, frequency, and preferences of the foods that the user usually eats.

[0162] "Medical information" refers to information such as the user's health status, medical precautions, and allergy information.

[0163] A "dialogue model" is a model of a dialogue system that is generated by learning the user's language patterns and preferences in order to have a natural conversation with the user.

[0164] A "voice model" is a model of a voice generation system created to mimic the tone and intonation of a user's voice.

[0165] "Meal menu suggestion technology" is a technology that personalizes and suggests the optimal meal menu based on the user's eating habits and medical information.

[0166] A "terminal" is a hardware device used to interact with the user and to suggest and confirm meal menus, and includes smartphones, tablets, and other similar devices.

[0167] "Order history" is a record of the food menus that the user has ordered in the past.

[0168] A "summary" is a record that summarizes the content of conversations with users and their feedback on meal menus.

[0169] A "third party" refers to any person or organization other than the user who has the right to receive information, such as the user's family or caregivers.

[0170] This invention is a system that proposes personalized meal menus and provides food delivery services for the elderly and dementia patients. The system consists of the following main components:

[0171] System Configuration

[0172] 1. Data acquisition methods

[0173] The server collects users' past records, eating habits, and medical information. This includes methods of uploading letters, videos, text messages, photos, handwritten data, and food photos using smartphones or PCs. This allows the server to collect information about the user's past activities and health status.

[0174] 2. Data Analysis Methods

[0175] The server stores the collected data in a cloud database (e.g., Firebase, AWS® DynamoDB) and analyzes this data using natural language processing models (e.g., GPT-4®, BERT). During the analysis process, it extracts preferences for food menus and medical considerations, and generates user dialogue models and voice models.

[0176] 3. Proposals via devices

[0177] The generated dialogue and voice models are installed on devices such as smartphones and tablets, and the system proposes meal menus in a conversational format with the user. The device uses speech recognition technologies such as Google Speech-to-Text and Amazon Transcribe to understand the user's voice instructions and propose appropriate menu items.

[0178] 4. Ordering and Delivery

[0179] The user reviews the suggested menu and confirms their order via their device. The order data is sent to a partner food delivery service, and the user can check the delivery status on the app.

[0180] 5. Conversation records and feedback

[0181] The server records conversations and order history conducted through the terminal and collects feedback on the meal menu. This feedback can then be used to improve menu suggestions for future visits. Specifically, it checks user satisfaction through conversations such as, "Did you enjoy yesterday's fish dish?"

[0182] Specific example

[0183] The user uploads past meal photos and medical information using their smartphone. The server receives this data and analyzes their dietary preferences and health status using a natural language processing model. Through the generated voice model, the device suggests to the user, "Fish dishes are recommended today. They are rich in protein and good for your health." Once the user confirms the order, the order data is sent to a food delivery service, and the meal is delivered at the specified time. After the meal, the device displays a prompt message, "How was yesterday's fish dish?", allowing the user to provide feedback.

[0184] Hardware and software to be used

[0185] Cloud databases: Firebase, AWS DynamoDB

[0186] Natural language processing models: GPT-4, BERT

[0187] Speech recognition technology: Google Speech-to-Text, Amazon Transcribe

[0188] Application framework: React Native (iOS / ANDROID® compatible)

[0189] This system will enable personalized meal menu suggestions tailored to the user's health condition and preferences, which is expected to improve user satisfaction.

[0190] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0191] Step 1:

[0192] The server collects past records, eating habits, and medical information uploaded by users using their smartphones or PCs. Specifically, this includes letters, videos, text messages, photos, handwritten data, and food photos. Once this data is collected, it is stored in a cloud database (e.g., Firebase, AWS DynamoDB).

[0193] Input: User's recorded data, eating habits, medical information

[0194] Output: Data stored in a cloud database

[0195] Step 2:

[0196] The server analyzes the collected data using natural language processing models (e.g., GPT-4, BERT). During the analysis, it extracts information about the user's language patterns, food preferences, and health status, and generates a user dialogue model and a voice model.

[0197] Input: Data stored in a cloud database

[0198] Output: User dialogue model and voice model

[0199] Step 3:

[0200] The device interacts with the user using generated dialogue and voice models to suggest meal options. It utilizes speech recognition technologies such as Google Speech-to-Text and Amazon Transcribe to understand the user's voice commands and suggest appropriate menu items. For example, it might suggest, "Today, I recommend a fish dish. It's rich in protein and good for you."

[0201] Input: User's dialogue model and voice model

[0202] Output: Menu suggestions for the user

[0203] Step 4:

[0204] The user reviews the suggested menu and confirms their order via their device. The order data is sent to the partner food delivery service via the server. The user can check the delivery status on the app.

[0205] Input: User's order information

[0206] Output: Sending order data to food delivery service

[0207] Step 5:

[0208] The server records conversations and order history via the terminal in real time and collects feedback on the meal menu. For example, it displays a prompt message such as, "How was yesterday's fish dish?" to elicit feedback from the user. This feedback can then be used to improve future menu suggestions.

[0209] Input: User feedback

[0210] Output: Updated dialogue and voice models incorporating feedback.

[0211] 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.

[0212] This invention is a system that provides fully personalized care for the elderly and dementia patients, and in particular, integrates an emotion engine that recognizes the user's emotions. The processing of this system's program will be explained below, including specific examples.

[0213] System Configuration

[0214] This system consists of the following main components:

[0215] 1. Data collection means: Means for collecting the user's past record data.

[0216] 2. Data analysis means: Means for analyzing collected data to generate a user dialogue model and a voice model.

[0217] 3. Emotion Engine: An engine that recognizes the user's emotions and reflects them in the conversation.

[0218] 4. Terminal: A device that uses the generated dialogue model and voice model to converse with the user.

[0219] 5. Conversation recording means: A means for recording conversation content and generating and providing a summary.

[0220] System operation

[0221] User: First, upload past records (letters, videos, text messages, photos, manually entered data, etc.) to the system using a smartphone or PC. This allows the system to collect information about the user's past events and experiences.

[0222] As a concrete example, a user could scan and upload photos from an old family album, along with any related letters or video messages.

[0223] Server: Receives uploaded data and stores it in a database. Next, it analyzes this data using natural language processing and speech generation technologies. The analysis includes a process to extract the user's language patterns, preferences, and emotional tendencies. It also generates a speech model from the user's voice and text data.

[0224] As a concrete example, the server analyzes the content of uploaded letters to identify frequently used vocabulary and expressions. It also analyzes video messages to extract the intonation and tone of the user's voice.

[0225] Emotion Engine: Based on this data, it analyzes generated audio and text data to identify the user's emotional state. The emotion engine recognizes the user's emotions with high accuracy and reflects that information in the conversational dialogue model.

[0226] For example, if a user looks at a family photo and says, "This photo brings back so many memories," the emotion engine recognizes the emotion of "joy" from the tone and expression of the user's voice and incorporates that information into the next conversation.

[0227] Terminal: Next, the generated dialogue model and voice model are used to converse with the user. The terminal is a robot or a tablet device, and it simulates natural conversation with the user through these devices.

[0228] As a concrete example, the robot says, "Good morning, which photo would you like to see today?" and the user replies, "I'd like to see this family photo." Based on the information from its emotion engine, the robot continues, "That's wonderful. Tell me more about that photo."

[0229] Server: Furthermore, it records conversations in real time, extracts important information, and generates summaries. The summaries and conversation logs are provided to the user and their family.

[0230] As a concrete example, the server generates a summary stating, "The topic the user most wanted to talk about in today's conversation was family travel," and periodically notifies the family of this information.

[0231] This system not only enables personalized care for dementia patients but also significantly reduces the burden on families and caregivers. Dementia patients can gain a sense of security and satisfaction by enjoying conversations based on their own lives and memories. Furthermore, the system constantly learns and adapts based on the latest data and feedback, improving the quality of care. The introduction of an emotion engine allows for real-time understanding of the user's emotional state, enabling more appropriate responses.

[0232] The following describes the processing flow.

[0233] Step 1:

[0234] User: Upload past record data to the system. The procedure involves using a smartphone or PC to select files such as letters, videos, text messages, photos, and manually entered data, and then sending them to the server using a dedicated app or web portal.

[0235] Step 2:

[0236] Server: Receives uploaded data, verifies its format, and stores it in the database. For example, letters and photos are saved in the image folder, and video files are saved in the video folder.

[0237] Step 3:

[0238] Server: Analyzes stored data. Uses natural language processing techniques to extract language patterns and emotional tendencies from text data, and analyzes audio data to generate a speech model. It also uses an emotion engine to recognize user emotions from audio and text data.

[0239] Step 4:

[0240] Server: Saves the generated dialogue and speech models to the cloud. During this process, the models are optimized, including the results of emotion recognition by the emotion engine.

[0241] Step 5:

[0242] Terminal: Takes action at specified times or triggers to allow the user to start a conversation simulation. Downloads dialogue and voice models from the server and builds the conversation environment.

[0243] Step 6:

[0244] Terminal: Speaks to the user. For example, it might say, "Hello, how was your day?" and uses a generated voice model and emotion engine to conduct a natural conversation.

[0245] Step 7:

[0246] User: Responds to questions and comments presented by the device. The device records these responses in real time and saves them as audio data.

[0247] Step 8:

[0248] Terminal: Analyzes recorded audio data and converts it into text data. This text data is then subjected to emotion recognition by an emotion engine.

[0249] Step 9:

[0250] Server: Receives conversation logs and sentiment recognition data sent from terminals. Analyzes this data, extracts important information, and generates a summary.

[0251] Step 10:

[0252] Server: Provides generated summaries to the user, their family, and care providers. Uses a notification system to periodically send summaries and conversation logs and receive feedback.

[0253] Through this step, the system can provide personalized dementia care, including highly accurate emotion recognition, improving the user's quality of life and reducing the burden on family members and caregivers.

[0254] (Example 2)

[0255] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0256] When providing personalized care to the elderly and dementia patients, it is crucial to engage in dialogue that accurately reflects the user's emotions and individual preferences. However, conventional technology has struggled to recognize user emotions in real time and adjust dialogue accordingly. Solving this challenge has been essential to improving the quality of care and reducing the burden on families and caregivers.

[0257] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting past data, means for analyzing the past data and generating a user dialogue model and a voice model, means for controlling a terminal that interacts with the user using the generated dialogue model and voice model, means for recording the dialogue content and generating a summary, means for providing the summary and dialogue log to the user or a third party, and means for recognizing the user's emotions using an emotion engine and reflecting them in the dialogue model. This makes it possible to recognize the user's emotions in real time and to conduct appropriate dialogue based on that information.

[0258] "Past data" refers to past records provided by the user (such as letters, videos, text messages, images, and manually entered data).

[0259] A "dialogue model" refers to a model based on language patterns and context that has been generated to enable natural conversations with users.

[0260] A "voice model" refers to a model of voice data generated to reproduce the characteristics and intonation of a user's voice.

[0261] A "terminal" refers to a device used for interacting with a user (e.g., a robot or a tablet).

[0262] A "summary" refers to information that extracts the most important parts of a dialogue and presents them concisely.

[0263] "Dialogue log" refers to data that records the history of conversations with users.

[0264] An "emotion engine" refers to an analytical engine that recognizes the user's emotional state and reflects that information in the content of the conversation.

[0265] "Natural language processing technology" refers to technologies aimed at understanding and generating natural language (e.g., text analysis, syntactic analysis).

[0266] "Speech generation technology" refers to technologies for generating natural-sounding speech from text data (e.g., text-to-speech, speech synthesis).

[0267] A "server" refers to a central computing system that performs data analysis, storage, and processing for the entire system.

[0268] "User" refers to an individual, including elderly people and those with dementia, who uses this system.

[0269] "Third party" refers to any party other than the user (e.g., family members, care providers).

[0270] This invention is a system that provides personalized care for the elderly and dementia patients, and in particular has the function of recognizing the user's emotions by integrating an emotion engine. A specific description of an embodiment of this system is given below.

[0271] System Configuration

[0272] This system consists of three components: a server, a terminal, and a user. The hardware and software used in the system include the following:

[0273] Server: A central computing system for analyzing, storing, and processing data. Specifically, this would involve using services like Amazon RDS or MongoDB.

[0274] Terminal: A device used for interacting with the user. Specifically, this could be a Pepper robot or a tablet device (e.g., an iPad).

[0275] Emotion Engine: An engine that recognizes user emotions and reflects that information in the dialogue model. It uses the Microsoft® Azure® Emotion API.

[0276] Natural language processing techniques: Text analysis is performed using NLTK and spaCy.

[0277] Speech generation technology: Speech data is generated using Google Text-to-Speech.

[0278] Operation Description

[0279] User: First, the user uploads past recorded data (letters, videos, text messages, images, manually entered data, etc.) to the system using a smartphone or PC. This uploaded data is sent to the server as information about the user's past events and experiences.

[0280] As a specific example, the user scans and uploads photos of a family album and attaches relevant letters and videos.

[0281] Server: The server receives the uploaded data and stores it in the database. Next, it analyzes the data using natural language processing techniques (e.g., NLTK, spaCy) and speech generation techniques (e.g., Google Text-to-Speech). The analysis includes a process of extracting the user's language patterns, preferences, and emotional tendencies. Furthermore, it generates a speech model from the user's speech data and text data.

[0282] As a specific example, the server analyzes the content of the uploaded letter to identify frequently occurring vocabulary and expressions. It also analyzes the video message to extract the tone and intonation of the user's voice.

[0283] Emotion Engine: The emotion engine identifies the user's emotional state based on the analyzed speech and text data. This information is reflected in the dialogue model of the conversation.

[0284] As a specific example, when the user says "This photo is really nostalgic," the emotion engine recognizes the emotion of "joy" from the tone and expression of the voice.

[0285] Terminal: Using the generated dialogue model and speech model, the terminal conducts a natural conversation with the user. This enables a conversation according to the user's emotions and preferences.

[0286] As a specific example, when the robot says "Good morning. Which photo would you like to see today?" and the user replies "I would like to see this family photo," the robot continues with "That's wonderful. Please tell me more about that photo."

[0287] Server: The server records the content of the conversation in real time, extracts important information, and generates a summary. This summary and the conversation log are provided to the user himself or his family.

[0288] As a concrete example, the server generates a summary stating, "The topic the user most wanted to talk about in today's conversation was family travel," and periodically notifies the family.

[0289] Examples of prompts for generative AI models

[0290] Examples of specific prompt messages are as follows:

[0291] 1. "How are you doing?" "I'm feeling good this morning. I want to look at some family photos."

[0292] 2. "What topics have users wanted to talk about in the past?" "They've been talking a lot about family trips lately."

[0293] 3. "What should I talk about with the user next?" "You could start by talking about movies or music."

[0294] Using these prompts enables more personalized responses from generative AI models.

[0295] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0296] Step 1: Data Collection

[0297] User: Users upload past recorded data (letters, videos, text messages, images, manually entered data, etc.) to the system using their smartphones or PCs.

[0298] Input: Letters, videos, text messages, images, manually entered data

[0299] Output: Uploaded data is sent to the server.

[0300] Specific operation: The user scans and uploads photos from a family album, and attaches related letters and videos.

[0301] Step 2: Data Storage and Analysis

[0302] Server: The server receives the uploaded data and stores it in the database. Then, it analyzes the data using natural language processing technology and voice generation technology.

[0303] Input: Uploaded letters, videos, text messages, images, manually entered data

[0304] Output: The analyzed data is generated as the user's dialogue model and voice model

[0305] Specific operations: The server analyzes the content of the letter to identify frequently used vocabulary and expressions. It also analyzes video messages to extract the tone and intonation of the user's voice.

[0306] Step 3: Emotion Recognition

[0307] Emotion Engine: The emotion engine uses the analyzed voice and text data to identify the user's emotional state.

[0308] Input: Analyzed voice and text data

[0309] Output: Information reflecting the user's emotional state

[0310] Specific operations: When the user says "This photo is really nostalgic", the emotion engine recognizes the emotion of "joy" from the tone and expression of the voice.

[0311] Step 4: Dialogue Generation

[0312] Server: Based on the results of emotion recognition, the server generates an appropriate dialogue model. In this process, a machine learning model is used.

[0313] Input: Results of the emotion engine and the user's profile data

[0314] Output: Emotion-responsive dialogue model

[0315] Specific operation: The server applies the generated "emotion" tag to the dialog and produces a response such as, "That's great. Tell me more about that photo."

[0316] Step 5: Execute the conversation

[0317] Terminal: The terminal uses the generated dialogue model and voice model to engage in natural conversations with the user.

[0318] Input: Dialogue model and voice model

[0319] Output: Natural conversation with the device

[0320] Specific operation: The device says, "Good morning, which photo would you like to see today?" and when the user replies, "I'd like to see this family photo," the device continues, "That's wonderful. Tell me more about that photo."

[0321] Step 6: Conversation recording and summary generation

[0322] Server: The server records the content of the conversation in real time, extracts important information, and generates a summary.

[0323] Input: Real-time dialogue data

[0324] Output: Dialogue summary and log

[0325] Specific operation: The server generates a summary stating, "The topic the user most wanted to talk about in today's conversation was family travel," and periodically notifies the family.

[0326] (Application Example 2)

[0327] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0328] Current systems that provide personalized care for the elderly and dementia patients lack sufficient collection and analysis of historical data, making it difficult to accurately understand the emotional state of individual users and provide appropriate responses. Furthermore, systems that analyze emotional states in real time and provide conversations based on that analysis are inadequate. Solving these challenges is essential to improving the quality of care for the elderly and dementia patients.

[0329] 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.

[0330] In this invention, the server includes means for collecting historical recorded data, means for analyzing the historical recorded data and generating a user dialogue model and voice model, and means for analyzing the user's voice and facial expression data in real time and identifying their emotional state. This enables personalized dialogue based on the user's historical data and natural conversation based on real-time emotion analysis.

[0331] "Past recorded data" refers to letters, videos, text messages, photos, and manually entered data that the user has generated in the past.

[0332] A "dialogue model" is a model used to simulate natural conversations with users based on historical recorded data.

[0333] A "voice model" is a model of voice patterns generated from a user's past voice data.

[0334] A "terminal" is a device that uses the generated dialogue model and voice model to converse with the user, and specifically refers to robots, tablet devices, etc.

[0335] A "summary" is information that extracts and summarizes the main points of a recorded conversation.

[0336] A "conversation log" refers to a record of the entire conversation with a user.

[0337] "Emotional state" refers to the state of a user's emotions, such as joy, sadness, or surprise, which is identified from their facial expressions and voice.

[0338] "Emotion analysis technology" is a technology that identifies and analyzes emotions from a user's voice and facial expression data.

[0339] "Natural language processing technology" refers to algorithms and techniques that enable computers to understand and generate human language.

[0340] "Speech generation technology" is a technology that synthesizes natural, human-like speech from text data.

[0341] This invention is a system that provides personalized care to the elderly and dementia patients, and in particular utilizes an emotion engine that recognizes the user's emotions. The program processing of this system is described below.

[0342] System Configuration

[0343] The system consists of the following main components:

[0344] 1. Data collection methods: Means for collecting the user's past recorded data (letters, videos, text messages, photos, manually entered data, etc.).

[0345] 2. Data analysis means: Means for analyzing collected data and generating user dialogue models and voice models.

[0346] 3. Emotion analysis technology: A technology that analyzes the user's voice and facial expression data to identify their emotional state.

[0347] 4. Terminal: A device that uses the generated dialogue model and voice model to converse with the user.

[0348] 5. Conversation recording means: A means for recording conversation content and generating and providing a summary.

[0349] Hardware and software used

[0350] Hardware: Smartphones, tablets, robots.

[0351] Software: Python, SpeechRecognition library, TextBlob library, Natural Language Processing (NLP), Text-to-Speech (TTS).

[0352] Program processing

[0353] The server first collects past recorded data uploaded by users via smartphones or tablets. Next, it stores the collected data in a database and performs analysis using natural language processing (NLP) and text-to-speech (TTS) technologies. The analysis generates a user dialogue model and a voice model.

[0354] Using emotion analysis technology, the system identifies the user's emotional state from their voice and facial expression data. Based on this information, it simulates natural conversation and provides appropriate reactions for the user. For example, when a user is talking about a past family trip, the system identifies the emotional state of "joy" from their voice and responds with, "That's wonderful, tell me more about that trip."

[0355] Specific example

[0356] Specifically, the following processes are performed.

[0357] 1. Collect user voice data using the smartphone's microphone.

[0358] 2. Convert speech to text (using Google Cloud Speech-to-Text).

[0359] 3. Analyze text data using TextBlob to identify emotions.

[0360] 4. Generate and provide appropriate feedback to the user based on their emotions.

[0361] Example of a prompt

[0362] "Imagine a user is talking in more detail about a family trip they mentioned in a previous conversation. How would you respond to a situation where the user is expressing positive emotions?"

[0363] This prompt helps the generative AI model generate an appropriate response based on positive sentiment analysis results.

[0364] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0365] Step 1:

[0366] Users upload past data:

[0367] Users upload past records (letters, videos, text messages, photos, and manually entered data) to the system using their smartphones or tablets.

[0368] Inputs: Letters, videos, text messages, photos, hand-entered data.

[0369] Output: Data stored on a cloud server.

[0370] Step 2:

[0371] The server receives and stores the data:

[0372] The server receives the uploaded data and stores it in a database. Natural language processing (NLP) and text-to-speech (TTS) technologies are then used to analyze this data.

[0373] Input: Data stored on a cloud server.

[0374] Output: Analyzed text data and audio data.

[0375] Step 3:

[0376] The server generates the dialogue model and the voice model:

[0377] The server generates a user dialogue model and a voice model based on the analyzed data. This includes a process of extracting the user's language patterns, preferences, and emotional tendencies.

[0378] Input: Analyzed text data and audio data.

[0379] Output: Dialogue model and speech model.

[0380] Step 4:

[0381] The device analyzes the user's voice and facial expressions in real time:

[0382] The device (smartphone, tablet, or robot) uses a microphone and camera to collect the user's voice and facial expressions in real time, and uses emotion analysis technology to identify their emotional state.

[0383] Input: User's real-time voice data and facial expression data.

[0384] Output: Identified emotional state.

[0385] Step 5:

[0386] The device engages in conversations based on emotions:

[0387] The device engages in natural conversation with the user based on the generated dialogue model, voice model, and identified emotional state. For example, if the user talks about a past family trip, the system recognizes the emotion of joy from the voice and responds, "That's wonderful, tell me more about that trip."

[0388] Input: Dialogue model, voice model, identified emotional state.

[0389] Output: The content of the conversation with the user.

[0390] Step 6:

[0391] The server records the conversation and generates a summary:

[0392] The server records conversations in real time, extracts important information, and generates summaries. These summaries and conversation logs are provided to the user and their family.

[0393] Input: The content of the conversation with the user.

[0394] Output: Summary and conversation log.

[0395] Step 7:

[0396] The server provides summaries and conversation logs to the user or a third party:

[0397] The server periodically notifies the user or a third party, such as a family member, of the generated summary and conversation logs.

[0398] Input: Summary and conversation log.

[0399] Output: Summary and conversation log provided to the user or a third party.

[0400] 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.

[0401] 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.

[0402] 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.

[0403] [Second Embodiment]

[0404] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0405] 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.

[0406] 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).

[0407] 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.

[0408] 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.

[0409] 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).

[0410] 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.

[0411] 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.

[0412] 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.

[0413] 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.

[0414] 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.

[0415] 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".

[0416] This invention is a system that provides fully personalized care for the elderly and dementia patients. The program processing of this system will be explained below, including specific examples.

[0417] System Configuration

[0418] This system consists of the following main components:

[0419] 1. Data collection means: Means for collecting the user's past record data.

[0420] 2. Data analysis means: Means for analyzing collected data to generate a user dialogue model and a voice model.

[0421] 3. Terminal: A device that uses the generated dialogue model and voice model to converse with the user.

[0422] 4. Conversation recording means: A means for recording conversation content and generating and providing a summary.

[0423] System operation

[0424] User: First, upload past records (letters, videos, text messages, photos, manually entered data, etc.) to the system using a smartphone or PC. This allows the system to collect information about the user's past events and experiences.

[0425] As a concrete example, a user could scan and upload photos from an old family album, along with any related letters or video messages.

[0426] Server: Receives uploaded data and stores it in a database. Then, it analyzes this data using natural language processing and speech generation technologies. The analysis includes a process of extracting the user's language patterns, preferences, and emotional tendencies.

[0427] As a concrete example, the server analyzes the content of uploaded letters to identify frequently used vocabulary and expressions. It also analyzes video messages to extract the intonation and tone of the user's voice.

[0428] Terminal: Next, the generated dialogue model and voice model are used to converse with the user. The terminal is a robot or a tablet device, and it simulates natural conversation with the user through these devices.

[0429] As a concrete example, the robot might say, "Good morning, which photo would you like to see today?" and the user might reply, "I'd like to see this family photo."

[0430] Server: Furthermore, it records conversations in real time, extracts important information, and generates summaries. The summaries and conversation logs are provided to the user and their family.

[0431] As a concrete example, the server generates a summary stating, "The topic the user most wanted to talk about in today's conversation was family travel," and periodically notifies the family of this information.

[0432] This system not only enables personalized care for dementia patients but also significantly reduces the burden on families and caregivers. Dementia patients can gain a sense of security and satisfaction by enjoying conversations based on their own lives and memories. Furthermore, the system constantly adapts and learns based on the latest data and feedback, improving the quality of care.

[0433] The following describes the processing flow.

[0434] Step 1:

[0435] User: Upload past record data to the system. The procedure involves using a smartphone or PC to select files such as letters, videos, text messages, photos, and manually entered data, and then sending them to the server using a dedicated app or web portal.

[0436] Step 2:

[0437] Server: Receives uploaded data and saves it to the database. It verifies the data format upon receipt and saves it to the appropriate storage path. For example, scanned images of letters are saved to the images folder, and video files are saved to the videos folder.

[0438] Step 3:

[0439] Server: Analyzes stored data. Extracts language patterns and sentiment tendencies from text data using natural language processing techniques. Generates speech models from speech and text data using speech generation techniques. This creates user dialogue models and speech models.

[0440] Step 4:

[0441] Server: Stores the generated dialogue and speech models in the cloud. Performs model validation and optimization as needed to improve accuracy.

[0442] Step 5:

[0443] Terminal: The user instructs the terminal to start the conversation simulation. The terminal (robot or tablet) downloads the model generated from the server and sets up the conversation environment.

[0444] Step 6:

[0445] Terminal: Speaks to the user. For example, it uses phrases such as "Hello, how was your day?" and engages in natural conversation through a generated voice model.

[0446] Step 7:

[0447] User: Responds to questions and comments presented by the device. The device understands the user's statements through speech recognition and proceeds with the conversation.

[0448] Step 8:

[0449] Terminal: Records conversation content in real time. Generates conversation logs as text and audio data and sends them to the server periodically.

[0450] Step 9:

[0451] Server: Analyzes received conversation logs, extracts important information and key points, generates summaries, and evaluates the user's health and psychological state.

[0452] Step 10:

[0453] Server: Provides generated summaries and conversation logs to users, families, and caregivers. It also provides regular reports and gathers necessary feedback.

[0454] Through this series of steps, the system can provide effective dementia care and reduce the burden on families and caregivers.

[0455] (Example 1)

[0456] 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".

[0457] When providing personalized care to dementia patients and the elderly, there is a challenge in understanding each individual user's past experiences and preferences and engaging in conversations based on this. Furthermore, there is a lack of systems that allow families and care providers to accurately understand the patient's condition without causing them burden.

[0458] 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.

[0459] In this invention, the server includes means for collecting past recorded data from the user and uploading it to the system; means for analyzing the collected past recorded data and generating a user dialogue model and voice model; means for conversing with the user using the generated dialogue model and voice model; means for recording the conversation content in real time, extracting important information, and generating and providing a summary; and means for providing the summary and conversation log to the user or a third party. This makes it possible to achieve natural conversations based on the user's past experiences and preferences, thereby improving the user's sense of security and satisfaction. It also reduces the burden on family members and caregivers and allows them to grasp important information.

[0460] A "user" refers to an individual who provides data and utilizes the system.

[0461] "Past recorded data" refers to information including the user's past images, documents, videos, messages, and input data.

[0462] "Collection means" refers to devices and software that allow users to upload past recorded data to the system.

[0463] "Analysis means" refers to devices or software that analyze collected historical record data and generate user dialogue models and voice models.

[0464] A "dialogue model" refers to a language model designed to mimic conversations with users.

[0465] A "voice model" refers to a model used to generate speech during conversations with users.

[0466] "Conversational means" refers to devices or software that engage in conversation with a user using generated dialogue models and voice models.

[0467] "Recording means" refers to devices or software that record conversation content in real time, extract important information, and generate and provide summaries.

[0468] A "summary" refers to a compilation of the most important information from a conversation.

[0469] "Conversation log" refers to data that records the content of conversations with users.

[0470] "Third parties" refer to individuals or organizations other than the user, including family members and care providers.

[0471] This invention is a system that provides fully personalized care for the elderly and dementia patients. This system has the function of collecting and analyzing past recorded data, generating a user dialogue model and voice model, using these to converse with the user, and recording the content of the conversation. The following describes embodiments of this system.

[0472] System Configuration

[0473] 1. Data collection means: These are devices or software that allow users to upload past recorded data (images, documents, videos, messages, input data, etc.) to the system. Specific examples include the file upload function of smartphones and personal computers.

[0474] 2. Data Analysis Means: These are devices and software for analyzing uploaded data. They generate user dialogue models and voice models using natural language processing technology (e.g., Google Cloud Natural Language API) and speech generation technology (e.g., Amazon Polly).

[0475] 3. Terminal: A device or software that engages in conversation with the user using the generated dialogue model and voice model. Specific examples include robots (e.g., Pepper) and tablet devices (e.g., iPad).

[0476] 4. Conversation recording means: Devices or software that record conversation content in real time, extract important information, and generate and provide a summary.

[0477] System operation

[0478] Users collect historical data using smartphones or personal computers. For example, they scan family photo albums and collect related letters and video messages. They then upload this data to the system.

[0479] Server: Upon receiving uploaded data, it stores it in a secure database. The data is then analyzed using natural language processing and speech generation technologies. This analysis extracts the user's language patterns, preferences, and emotional tendencies, generating dialogue and voice models tailored to the user. For example, the server analyzes the text of a travel diary to identify frequently occurring vocabulary and phrases. It also extracts the pitch and intonation of the user's voice through audio analysis of video messages.

[0480] Terminal: The robot and tablet terminal use generated dialogue and voice models to converse with the user. For example, the robot might say, "Good morning, which photos would you like to see today?" and the user might reply, "I'd like to see photos from our family trip."

[0481] Server: Records conversations in real time, extracts important information, and generates summaries. The generated summaries and conversation logs are provided to the user themselves or third parties such as their family. For example, the server might generate a summary stating, "The topic the user was most interested in today was family travel," and send that information to the family via email.

[0482] Specific examples and prompt statements

[0483] Specific example:

[0484] 1. Users scan family trip photos and travel diaries and upload them to the system.

[0485] 2. The server receives this data, analyzes frequently occurring vocabulary and intonation, and generates a dialogue model and a speech model.

[0486] 3. The robot asks the user, "Which photos would you like to see today?" and the user replies, "I'd like to see photos from our family trip."

[0487] 4. The server records the conversation in real time and generates a summary stating, "The topic the user most wanted to talk about was family travel," and notifies the family.

[0488] Example of a prompt:

[0489] "Please talk about past memories related to family photos."

[0490] "What kind of music would you like to listen to today?"

[0491] In this way, a system that provides fully personalized care for the elderly and dementia patients is realized. This system can provide a sense of security and satisfaction through natural conversations based on the user's past experiences and preferences, and can reduce the burden on families and caregivers.

[0492] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0493] Step 1: Data Collection

[0494] User:

[0495] The user prepares past recorded data (e.g., images, documents, videos, messages, input data). Specifically, this involves scanning family album photos and collecting related letters and video messages.

[0496] Input: Scanned images, documents, video files

[0497] Output: Uploaded data file

[0498] Specific actions: The user takes photos for an album, scans letters, and records video messages using their smartphone. These files are then prepared in the system.

[0499] Step 2: Upload your registration

[0500] User:

[0501] Users upload their prepared historical record data to the system using the upload function of their smartphone or personal computer.

[0502] Input: Prepared data file

[0503] Output: Data files saved on the system

[0504] Specific operation: The user clicks the upload button on their smartphone, selects files such as "family trip photos" or "travel diary," and sends them to the system.

[0505] Step 3: Save data

[0506] server:

[0507] The server receives the uploaded data and stores it in a secure database.

[0508] Input: Uploaded data file

[0509] Output: Data stored in the database

[0510] Specific operation: The server parses the received file and saves it to the appropriate section of the database.

[0511] Step 4: Data analysis and model generation

[0512] server:

[0513] The stored data is analyzed. Text data is analyzed using natural language processing technology (e.g., Google Cloud Natural Language API), and audio data is analyzed using speech generation technology (e.g., Amazon Polly). This extracts the user's language patterns, preferences, and emotional tendencies, and generates dialogue models and speech models.

[0514] Input: Data stored in the database

[0515] Output: Generated dialogue model and voice model

[0516] Specific operation: The server analyzes the text of the travel diary to identify frequently occurring vocabulary and phrases. It also extracts the pitch and intonation of the user's voice through audio analysis of video messages.

[0517] Step 5: Generating and executing dialogue

[0518] Terminal:

[0519] The system uses generated dialogue and voice models to engage in conversations with users. It simulates natural conversations using robots (e.g., Pepper) or tablet devices (e.g., iPad).

[0520] Input: Generated dialogue model and voice model

[0521] Output: User interaction content

[0522] Specific action: The robot says, "Good morning, which photos would you like to see today?" and the user replies, "I'd like to see photos from our family trip."

[0523] Step 6: Record the conversation and generate a summary.

[0524] server:

[0525] The system records conversations in real time, extracts important information, and generates summaries. The generated summaries and conversation logs are provided to the user themselves or third parties such as their family.

[0526] Input: Content of the conversation between the user and the device.

[0527] Output: Generated summary and conversation log

[0528] Specific operation: The server records the conversation content, generates a summary stating, "The topic the user was most interested in today was family travel," and notifies the family via email.

[0529] Step 7: Feedback and Learning

[0530] server:

[0531] The system's learning model is updated based on the acquired conversation content and feedback. This improves the quality of subsequent conversations.

[0532] Input: Conversation log and feedback information

[0533] Output: Updated dialogue model and voice model

[0534] Specific operation: The server analyzes the conversation record, reflects the user's new interests and concerns in the model, and adjusts the system for the next interaction.

[0535] (Application Example 1)

[0536] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0537] Providing meals to the elderly and dementia patients requires personalized menu suggestions based on individual eating habits and medical information, but this is difficult to achieve with typical food delivery services. Furthermore, there is a need for a system that incorporates user feedback to provide optimal meal suggestions and records this information to offer a better dining experience.

[0538] 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.

[0539] In this invention, the server includes means for collecting past recorded data and the user's eating habits and medical information; means for analyzing the past recorded data and the user's eating habits and medical information to generate a user dialogue model and a voice model; means for controlling a terminal that converses with the user using the generated dialogue model and voice model and proposes a meal menu; means for the user to confirm an order based on the proposed meal menu; means for recording the conversation content and order history, collecting feedback on the meal menu, and generating a summary; and means for providing the summary and conversation log to the user or a third party. This makes it possible to propose the most suitable meal menu for each individual user and to provide personalized services that are tailored to the user's health condition and preferences.

[0540] "Past recorded data" refers to information about the user's previous activities and experiences, including letters, videos, text messages, photographs, handwritten data, and food photos.

[0541] "User eating habits" refers to information such as the types, frequency, and preferences of the foods that the user usually eats.

[0542] "Medical information" refers to information such as the user's health status, medical precautions, and allergy information.

[0543] A "dialogue model" is a model of a dialogue system that is generated by learning the user's language patterns and preferences in order to have a natural conversation with the user.

[0544] A "voice model" is a model of a voice generation system created to mimic the tone and intonation of a user's voice.

[0545] "Meal menu suggestion technology" is a technology that personalizes and suggests the optimal meal menu based on the user's eating habits and medical information.

[0546] A "terminal" is a hardware device used to interact with the user and to suggest and confirm meal menus, and includes smartphones, tablets, and other similar devices.

[0547] "Order history" is a record of the food menus that the user has ordered in the past.

[0548] A "summary" is a record that summarizes the content of conversations with users and their feedback on meal menus.

[0549] A "third party" refers to any person or organization other than the user who has the right to receive information, such as the user's family or caregivers.

[0550] This invention is a system that proposes personalized meal menus and provides food delivery services for the elderly and dementia patients. The system consists of the following main components:

[0551] System Configuration

[0552] 1. Data acquisition methods

[0553] The server collects users' past records, eating habits, and medical information. This includes methods of uploading letters, videos, text messages, photos, handwritten data, and food photos using smartphones or PCs. This allows the server to collect information about the user's past activities and health status.

[0554] 2. Data Analysis Methods

[0555] The server stores the collected data in a cloud database (e.g., Firebase, AWS DynamoDB) and analyzes this data using natural language processing models (e.g., GPT-4, BERT). During the analysis process, it extracts food menu preferences and medical considerations, and generates user dialogue models and voice models.

[0556] 3. Proposals via devices

[0557] The generated dialogue and voice models are installed on devices such as smartphones and tablets, and the system proposes meal menus in a conversational format with the user. The device uses speech recognition technologies such as Google Speech-to-Text and Amazon Transcribe to understand the user's voice instructions and propose appropriate menu items.

[0558] 4. Ordering and Delivery

[0559] The user reviews the suggested menu and confirms their order via their device. The order data is sent to a partner food delivery service, and the user can check the delivery status on the app.

[0560] 5. Conversation records and feedback

[0561] The server records conversations and order history conducted through the terminal and collects feedback on the meal menu. This feedback can then be used to improve menu suggestions for future visits. Specifically, it checks user satisfaction through conversations such as, "Did you enjoy yesterday's fish dish?"

[0562] Specific example

[0563] The user uploads past meal photos and medical information using their smartphone. The server receives this data and analyzes their dietary preferences and health status using a natural language processing model. Through the generated voice model, the device suggests to the user, "Fish dishes are recommended today. They are rich in protein and good for your health." Once the user confirms the order, the order data is sent to a food delivery service, and the meal is delivered at the specified time. After the meal, the device displays a prompt message, "How was yesterday's fish dish?", allowing the user to provide feedback.

[0564] Hardware and software to be used

[0565] Cloud databases: Firebase, AWS DynamoDB

[0566] Natural language processing models: GPT-4, BERT

[0567] Speech recognition technology: Google Speech-to-Text, Amazon Transcribe

[0568] Application framework: React Native (iOS / Android compatible)

[0569] This system will enable personalized meal menu suggestions tailored to the user's health condition and preferences, which is expected to improve user satisfaction.

[0570] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0571] Step 1:

[0572] The server collects past records, eating habits, and medical information uploaded by users using their smartphones or PCs. Specifically, this includes letters, videos, text messages, photos, handwritten data, and food photos. Once this data is collected, it is stored in a cloud database (e.g., Firebase, AWS DynamoDB).

[0573] Input: User's recorded data, eating habits, medical information

[0574] Output: Data stored in a cloud database

[0575] Step 2:

[0576] The server analyzes the collected data using natural language processing models (e.g., GPT-4, BERT). During the analysis, it extracts information about the user's language patterns, food preferences, and health status, and generates a user dialogue model and a voice model.

[0577] Input: Data stored in a cloud database

[0578] Output: User dialogue model and voice model

[0579] Step 3:

[0580] The device interacts with the user using generated dialogue and voice models to suggest meal options. It utilizes speech recognition technologies such as Google Speech-to-Text and Amazon Transcribe to understand the user's voice commands and suggest appropriate menu items. For example, it might suggest, "Today, I recommend a fish dish. It's rich in protein and good for you."

[0581] Input: User's dialogue model and voice model

[0582] Output: Menu suggestions for the user

[0583] Step 4:

[0584] The user reviews the suggested menu and confirms their order via their device. The order data is sent to the partner food delivery service via the server. The user can check the delivery status on the app.

[0585] Input: User's order information

[0586] Output: Sending order data to food delivery service

[0587] Step 5:

[0588] The server records conversations and order history via the terminal in real time and collects feedback on the meal menu. For example, it displays a prompt message such as, "How was yesterday's fish dish?" to elicit feedback from the user. This feedback can then be used to improve future menu suggestions.

[0589] Input: User feedback

[0590] Output: Updated dialogue and voice models incorporating feedback.

[0591] 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.

[0592] This invention is a system that provides fully personalized care for the elderly and dementia patients, and in particular, integrates an emotion engine that recognizes the user's emotions. The processing of this system's program will be explained below, including specific examples.

[0593] System Configuration

[0594] This system consists of the following main components:

[0595] 1. Data collection means: Means for collecting the user's past record data.

[0596] 2. Data analysis means: Means for analyzing collected data to generate a user dialogue model and a voice model.

[0597] 3. Emotion Engine: An engine that recognizes the user's emotions and reflects them in the conversation.

[0598] 4. Terminal: A device that uses the generated dialogue model and voice model to converse with the user.

[0599] 5. Conversation recording means: A means for recording conversation content and generating and providing a summary.

[0600] System operation

[0601] User: First, upload past records (letters, videos, text messages, photos, manually entered data, etc.) to the system using a smartphone or PC. This allows the system to collect information about the user's past events and experiences.

[0602] As a concrete example, a user could scan and upload photos from an old family album, along with any related letters or video messages.

[0603] Server: Receives uploaded data and stores it in a database. Next, it analyzes this data using natural language processing and speech generation technologies. The analysis includes a process to extract the user's language patterns, preferences, and emotional tendencies. It also generates a speech model from the user's voice and text data.

[0604] As a concrete example, the server analyzes the content of uploaded letters to identify frequently used vocabulary and expressions. It also analyzes video messages to extract the intonation and tone of the user's voice.

[0605] Emotion Engine: Based on this data, it analyzes generated audio and text data to identify the user's emotional state. The emotion engine recognizes the user's emotions with high accuracy and reflects that information in the conversational dialogue model.

[0606] For example, if a user looks at a family photo and says, "This photo brings back so many memories," the emotion engine recognizes the emotion of "joy" from the tone and expression of the user's voice and incorporates that information into the next conversation.

[0607] Terminal: Next, the generated dialogue model and voice model are used to converse with the user. The terminal is a robot or a tablet device, and it simulates natural conversation with the user through these devices.

[0608] As a concrete example, the robot says, "Good morning, which photo would you like to see today?" and the user replies, "I'd like to see this family photo." Based on the information from its emotion engine, the robot continues, "That's wonderful. Tell me more about that photo."

[0609] Server: Furthermore, it records conversations in real time, extracts important information, and generates summaries. The summaries and conversation logs are provided to the user and their family.

[0610] As a concrete example, the server generates a summary stating, "The topic the user most wanted to talk about in today's conversation was family travel," and periodically notifies the family of this information.

[0611] This system not only enables personalized care for dementia patients but also significantly reduces the burden on families and caregivers. Dementia patients can gain a sense of security and satisfaction by enjoying conversations based on their own lives and memories. Furthermore, the system constantly learns and adapts based on the latest data and feedback, improving the quality of care. The introduction of an emotion engine allows for real-time understanding of the user's emotional state, enabling more appropriate responses.

[0612] The following describes the processing flow.

[0613] Step 1:

[0614] User: Upload past record data to the system. The procedure involves using a smartphone or PC to select files such as letters, videos, text messages, photos, and manually entered data, and then sending them to the server using a dedicated app or web portal.

[0615] Step 2:

[0616] Server: Receives uploaded data, verifies its format, and stores it in the database. For example, letters and photos are saved in the image folder, and video files are saved in the video folder.

[0617] Step 3:

[0618] Server: Analyzes stored data. Uses natural language processing techniques to extract language patterns and emotional tendencies from text data, and analyzes audio data to generate a speech model. It also uses an emotion engine to recognize user emotions from audio and text data.

[0619] Step 4:

[0620] Server: Saves the generated dialogue and speech models to the cloud. During this process, the models are optimized, including the results of emotion recognition by the emotion engine.

[0621] Step 5:

[0622] Terminal: Takes action at specified times or triggers to allow the user to start a conversation simulation. Downloads dialogue and voice models from the server and builds the conversation environment.

[0623] Step 6:

[0624] Terminal: Speaks to the user. For example, it might say, "Hello, how was your day?" and uses a generated voice model and emotion engine to conduct a natural conversation.

[0625] Step 7:

[0626] User: Responds to questions and comments presented by the device. The device records these responses in real time and saves them as audio data.

[0627] Step 8:

[0628] Terminal: Analyzes recorded audio data and converts it into text data. This text data is then subjected to emotion recognition by an emotion engine.

[0629] Step 9:

[0630] Server: Receives conversation logs and sentiment recognition data sent from terminals. Analyzes this data, extracts important information, and generates a summary.

[0631] Step 10:

[0632] Server: Provides generated summaries to the user, their family, and care providers. Uses a notification system to periodically send summaries and conversation logs and receive feedback.

[0633] Through this step, the system can provide personalized dementia care, including highly accurate emotion recognition, improving the user's quality of life and reducing the burden on family members and caregivers.

[0634] (Example 2)

[0635] 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".

[0636] When providing personalized care to the elderly and dementia patients, it is crucial to engage in dialogue that accurately reflects the user's emotions and individual preferences. However, conventional technology has struggled to recognize user emotions in real time and adjust dialogue accordingly. Solving this challenge has been essential to improving the quality of care and reducing the burden on families and caregivers.

[0637] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting past data, means for analyzing the past data and generating a user dialogue model and a voice model, means for controlling a terminal that interacts with the user using the generated dialogue model and voice model, means for recording the dialogue content and generating a summary, means for providing the summary and dialogue log to the user or a third party, and means for recognizing the user's emotions using an emotion engine and reflecting them in the dialogue model. This makes it possible to recognize the user's emotions in real time and to conduct appropriate dialogue based on that information.

[0638] "Past data" refers to past records provided by the user (such as letters, videos, text messages, images, and manually entered data).

[0639] A "dialogue model" refers to a model based on language patterns and context that has been generated to enable natural conversations with users.

[0640] A "voice model" refers to a model of voice data generated to reproduce the characteristics and intonation of a user's voice.

[0641] A "terminal" refers to a device used for interacting with a user (e.g., a robot or a tablet).

[0642] A "summary" refers to information that extracts the most important parts of a dialogue and presents them concisely.

[0643] "Dialogue log" refers to data that records the history of conversations with users.

[0644] An "emotion engine" refers to an analytical engine that recognizes the user's emotional state and reflects that information in the content of the conversation.

[0645] "Natural language processing technology" refers to technologies aimed at understanding and generating natural language (e.g., text analysis, syntactic analysis).

[0646] "Speech generation technology" refers to technologies for generating natural-sounding speech from text data (e.g., text-to-speech, speech synthesis).

[0647] A "server" refers to a central computing system that performs data analysis, storage, and processing for the entire system.

[0648] "User" refers to an individual, including elderly people and those with dementia, who uses this system.

[0649] "Third party" refers to any party other than the user (e.g., family members, care providers).

[0650] This invention is a system that provides personalized care for the elderly and dementia patients, and in particular has the function of recognizing the user's emotions by integrating an emotion engine. A specific description of an embodiment of this system is given below.

[0651] System Configuration

[0652] This system consists of three components: a server, a terminal, and a user. The hardware and software used in the system include the following:

[0653] Server: A central computing system for analyzing, storing, and processing data. Specifically, this would involve using services like Amazon RDS or MongoDB.

[0654] Terminal: A device used for interacting with the user. Specifically, this could be a Pepper robot or a tablet device (e.g., an iPad).

[0655] Emotion Engine: An engine that recognizes user emotions and reflects that information in the dialogue model. It uses the Microsoft Azure Emotion API.

[0656] Natural language processing techniques: Text analysis is performed using NLTK and spaCy.

[0657] Speech generation technology: Speech data is generated using Google Text-to-Speech.

[0658] Operation Description

[0659] User: First, the user uploads past recorded data (letters, videos, text messages, images, manually entered data, etc.) to the system using a smartphone or PC. This uploaded data is sent to the server as information about the user's past events and experiences.

[0660] For example, a user could scan and upload photos from a family album, and attach related letters or videos.

[0661] Server: The server receives uploaded data and stores it in a database. Next, it analyzes the data using natural language processing techniques (e.g., NLTK, spaCy) and speech generation techniques (e.g., Google Text-to-Speech). This analysis includes extracting the user's language patterns, preferences, and emotional tendencies. Furthermore, it generates a speech model from the user's voice and text data.

[0662] As a concrete example, the server analyzes the content of uploaded letters to identify frequently occurring vocabulary and expressions. It also analyzes video messages to extract the tone and intonation of the user's voice.

[0663] Emotion Engine: The emotion engine identifies the user's emotional state based on analyzed voice and text data. This information is then reflected in the dialogue model of the conversation.

[0664] For example, if a user says, "This photo brings back so many memories," the emotion engine recognizes the emotion of "joy" from the tone and expression of their voice.

[0665] Terminal: Using the generated dialogue and voice models, the terminal engages in natural conversations with the user. This enables conversations that are tailored to the user's emotions and preferences.

[0666] As a concrete example, the robot might say, "Good morning, which photo would you like to see today?" and when the user replies, "I'd like to see this family photo," the robot might continue, "That's wonderful. Tell me more about that photo."

[0667] Server: The server records the content of the conversation in real time, extracts important information, and generates a summary. This summary and conversation log are provided to the user and their family.

[0668] As a concrete example, the server generates a summary stating, "The topic the user most wanted to talk about in today's conversation was family travel," and periodically notifies the family.

[0669] Examples of prompts for generative AI models

[0670] Examples of specific prompt messages are as follows:

[0671] 1. "How are you doing?" "I'm feeling good this morning. I want to look at some family photos."

[0672] 2. "What topics have users wanted to talk about in the past?" "They've been talking a lot about family trips lately."

[0673] 3. "What should I talk about with the user next?" "You could start by talking about movies or music."

[0674] Using these prompts enables more personalized responses from generative AI models.

[0675] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0676] Step 1: Data Collection

[0677] User: Users upload past recorded data (letters, videos, text messages, images, manually entered data, etc.) to the system using their smartphones or PCs.

[0678] Input: Letters, videos, text messages, images, manually entered data

[0679] Output: Uploaded data is sent to the server.

[0680] Specific operation: The user scans and uploads photos from a family album, and attaches related letters and videos.

[0681] Step 2: Data storage and analysis

[0682] Server: The server receives the uploaded data and stores it in the database. It then analyzes the data using natural language processing and speech generation technologies.

[0683] Input: Uploaded letters, videos, text messages, images, handwritten data

[0684] Output: The analyzed data is generated as a user dialogue model and a voice model.

[0685] Specific operations: The server analyzes the content of the letter to identify frequently occurring vocabulary and expressions. It also analyzes video messages to extract the user's voice tone and intonation.

[0686] Step 3: Emotion Recognition

[0687] Emotion Engine: The emotion engine uses analyzed voice and text data to identify the user's emotional state.

[0688] Input: Analyzed speech and text data

[0689] Output: Information reflecting the user's emotional state.

[0690] Specific operation: When a user says, "This photo brings back so many memories," the emotion engine recognizes the emotion of "joy" from the tone and expression of their voice.

[0691] Step 4: Generate Dialog

[0692] Server: The server generates an appropriate dialogue model based on the emotion recognition results. This process utilizes machine learning models.

[0693] Input: Emotion engine results and user profile data

[0694] Output: Emotion-responsive dialogue model

[0695] Specific operation: The server applies the generated "emotion" tag to the dialog and produces a response such as, "That's great. Tell me more about that photo."

[0696] Step 5: Execute the conversation

[0697] Terminal: The terminal uses the generated dialogue model and voice model to engage in natural conversations with the user.

[0698] Input: Dialogue model and voice model

[0699] Output: Natural conversation with the device

[0700] Specific operation: The device says, "Good morning, which photo would you like to see today?" and when the user replies, "I'd like to see this family photo," the device continues, "That's wonderful. Tell me more about that photo."

[0701] Step 6: Conversation recording and summary generation

[0702] Server: The server records the content of the conversation in real time, extracts important information, and generates a summary.

[0703] Input: Real-time dialogue data

[0704] Output: Dialogue summary and log

[0705] Specific operation: The server generates a summary stating, "The topic the user most wanted to talk about in today's conversation was family travel," and periodically notifies the family.

[0706] (Application Example 2)

[0707] 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."

[0708] Current systems that provide personalized care for the elderly and dementia patients lack sufficient collection and analysis of historical data, making it difficult to accurately understand the emotional state of individual users and provide appropriate responses. Furthermore, systems that analyze emotional states in real time and provide conversations based on that analysis are inadequate. Solving these challenges is essential to improving the quality of care for the elderly and dementia patients.

[0709] 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.

[0710] In this invention, the server includes means for collecting historical recorded data, means for analyzing the historical recorded data and generating a user dialogue model and voice model, and means for analyzing the user's voice and facial expression data in real time and identifying their emotional state. This enables personalized dialogue based on the user's historical data and natural conversation based on real-time emotion analysis.

[0711] "Past recorded data" refers to letters, videos, text messages, photos, and manually entered data that the user has generated in the past.

[0712] A "dialogue model" is a model used to simulate natural conversations with users based on historical recorded data.

[0713] A "voice model" is a model of voice patterns generated from a user's past voice data.

[0714] A "terminal" is a device that uses the generated dialogue model and voice model to converse with the user, and specifically refers to robots, tablet devices, etc.

[0715] A "summary" is information that extracts and summarizes the main points of a recorded conversation.

[0716] A "conversation log" refers to a record of the entire conversation with a user.

[0717] "Emotional state" refers to the state of a user's emotions, such as joy, sadness, or surprise, which is identified from their facial expressions and voice.

[0718] "Emotion analysis technology" is a technology that identifies and analyzes emotions from a user's voice and facial expression data.

[0719] "Natural language processing technology" refers to algorithms and techniques that enable computers to understand and generate human language.

[0720] "Speech generation technology" is a technology that synthesizes natural, human-like speech from text data.

[0721] This invention is a system that provides personalized care to the elderly and dementia patients, and in particular utilizes an emotion engine that recognizes the user's emotions. The program processing of this system is described below.

[0722] System Configuration

[0723] The system consists of the following main components:

[0724] 1. Data collection methods: Means for collecting the user's past recorded data (letters, videos, text messages, photos, manually entered data, etc.).

[0725] 2. Data analysis means: Means for analyzing collected data and generating user dialogue models and voice models.

[0726] 3. Emotion analysis technology: A technology that analyzes the user's voice and facial expression data to identify their emotional state.

[0727] 4. Terminal: A device that uses the generated dialogue model and voice model to converse with the user.

[0728] 5. Conversation recording means: A means for recording conversation content and generating and providing a summary.

[0729] Hardware and software used

[0730] Hardware: Smartphones, tablets, robots.

[0731] Software: Python, SpeechRecognition library, TextBlob library, Natural Language Processing (NLP), Text-to-Speech (TTS).

[0732] Program processing

[0733] The server first collects past recorded data uploaded by users via smartphones or tablets. Next, it stores the collected data in a database and performs analysis using natural language processing (NLP) and text-to-speech (TTS) technologies. The analysis generates a user dialogue model and a voice model.

[0734] Using emotion analysis technology, the system identifies the user's emotional state from their voice and facial expression data. Based on this information, it simulates natural conversation and provides appropriate reactions for the user. For example, when a user is talking about a past family trip, the system identifies the emotional state of "joy" from their voice and responds with, "That's wonderful, tell me more about that trip."

[0735] Specific example

[0736] Specifically, the following processes are performed.

[0737] 1. Collect user voice data using the smartphone's microphone.

[0738] 2. Convert speech to text (using Google Cloud Speech-to-Text).

[0739] 3. Analyze text data using TextBlob to identify emotions.

[0740] 4. Generate and provide appropriate feedback to the user based on their emotions.

[0741] Example of a prompt

[0742] "Imagine a user is talking in more detail about a family trip they mentioned in a previous conversation. How would you respond to a situation where the user is expressing positive emotions?"

[0743] This prompt helps the generative AI model generate an appropriate response based on positive sentiment analysis results.

[0744] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0745] Step 1:

[0746] Users upload past data:

[0747] Users upload past records (letters, videos, text messages, photos, and manually entered data) to the system using their smartphones or tablets.

[0748] Inputs: Letters, videos, text messages, photos, hand-entered data.

[0749] Output: Data stored on a cloud server.

[0750] Step 2:

[0751] The server receives and stores the data:

[0752] The server receives the uploaded data and stores it in a database. Natural language processing (NLP) and text-to-speech (TTS) technologies are then used to analyze this data.

[0753] Input: Data stored on a cloud server.

[0754] Output: Analyzed text data and audio data.

[0755] Step 3:

[0756] The server generates the dialogue model and the voice model:

[0757] The server generates a user dialogue model and a voice model based on the analyzed data. This includes a process of extracting the user's language patterns, preferences, and emotional tendencies.

[0758] Input: Analyzed text data and audio data.

[0759] Output: Dialogue model and speech model.

[0760] Step 4:

[0761] The device analyzes the user's voice and facial expressions in real time:

[0762] The device (smartphone, tablet, or robot) uses a microphone and camera to collect the user's voice and facial expressions in real time, and uses emotion analysis technology to identify their emotional state.

[0763] Input: User's real-time voice data and facial expression data.

[0764] Output: Identified emotional state.

[0765] Step 5:

[0766] The device engages in conversations based on emotions:

[0767] The device engages in natural conversation with the user based on the generated dialogue model, voice model, and identified emotional state. For example, if the user talks about a past family trip, the system recognizes the emotion of joy from the voice and responds, "That's wonderful, tell me more about that trip."

[0768] Input: Dialogue model, voice model, identified emotional state.

[0769] Output: The content of the conversation with the user.

[0770] Step 6:

[0771] The server records the conversation and generates a summary:

[0772] The server records conversations in real time, extracts important information, and generates summaries. These summaries and conversation logs are provided to the user and their family.

[0773] Input: The content of the conversation with the user.

[0774] Output: Summary and conversation log.

[0775] Step 7:

[0776] The server provides summaries and conversation logs to the user or a third party:

[0777] The server periodically notifies the user or a third party, such as a family member, of the generated summary and conversation logs.

[0778] Input: Summary and conversation log.

[0779] Output: Summary and conversation log provided to the user or a third party.

[0780] 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.

[0781] 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.

[0782] 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.

[0783] [Third Embodiment]

[0784] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0785] 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.

[0786] 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).

[0787] 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.

[0788] 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.

[0789] 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).

[0790] 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.

[0791] 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.

[0792] 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.

[0793] 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.

[0794] 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.

[0795] 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".

[0796] This invention is a system that provides fully personalized care for the elderly and dementia patients. The program processing of this system will be explained below, including specific examples.

[0797] System Configuration

[0798] This system consists of the following main components:

[0799] 1. Data collection means: Means for collecting the user's past record data.

[0800] 2. Data analysis means: Means for analyzing collected data to generate a user dialogue model and a voice model.

[0801] 3. Terminal: A device that uses the generated dialogue model and voice model to converse with the user.

[0802] 4. Conversation recording means: A means for recording conversation content and generating and providing a summary.

[0803] System operation

[0804] User: First, upload past records (letters, videos, text messages, photos, manually entered data, etc.) to the system using a smartphone or PC. This allows the system to collect information about the user's past events and experiences.

[0805] As a concrete example, a user could scan and upload photos from an old family album, along with any related letters or video messages.

[0806] Server: Receives uploaded data and stores it in a database. Then, it analyzes this data using natural language processing and speech generation technologies. The analysis includes a process of extracting the user's language patterns, preferences, and emotional tendencies.

[0807] As a concrete example, the server analyzes the content of uploaded letters to identify frequently used vocabulary and expressions. It also analyzes video messages to extract the intonation and tone of the user's voice.

[0808] Terminal: Next, the generated dialogue model and voice model are used to converse with the user. The terminal is a robot or a tablet device, and it simulates natural conversation with the user through these devices.

[0809] As a concrete example, the robot might say, "Good morning, which photo would you like to see today?" and the user might reply, "I'd like to see this family photo."

[0810] Server: Furthermore, it records conversations in real time, extracts important information, and generates summaries. The summaries and conversation logs are provided to the user and their family.

[0811] As a concrete example, the server generates a summary stating, "The topic the user most wanted to talk about in today's conversation was family travel," and periodically notifies the family of this information.

[0812] This system not only enables personalized care for dementia patients but also significantly reduces the burden on families and caregivers. Dementia patients can gain a sense of security and satisfaction by enjoying conversations based on their own lives and memories. Furthermore, the system constantly adapts and learns based on the latest data and feedback, improving the quality of care.

[0813] The following describes the processing flow.

[0814] Step 1:

[0815] User: Upload past record data to the system. The procedure involves using a smartphone or PC to select files such as letters, videos, text messages, photos, and manually entered data, and then sending them to the server using a dedicated app or web portal.

[0816] Step 2:

[0817] Server: Receives uploaded data and saves it to the database. It verifies the data format upon receipt and saves it to the appropriate storage path. For example, scanned images of letters are saved to the images folder, and video files are saved to the videos folder.

[0818] Step 3:

[0819] Server: Analyzes stored data. Extracts language patterns and sentiment tendencies from text data using natural language processing techniques. Generates speech models from speech and text data using speech generation techniques. This creates user dialogue models and speech models.

[0820] Step 4:

[0821] Server: Stores the generated dialogue and speech models in the cloud. Performs model validation and optimization as needed to improve accuracy.

[0822] Step 5:

[0823] Terminal: The user instructs the terminal to start the conversation simulation. The terminal (robot or tablet) downloads the model generated from the server and sets up the conversation environment.

[0824] Step 6:

[0825] Terminal: Speaks to the user. For example, it uses phrases such as "Hello, how was your day?" and engages in natural conversation through a generated voice model.

[0826] Step 7:

[0827] User: Responds to questions and comments presented by the device. The device understands the user's statements through speech recognition and proceeds with the conversation.

[0828] Step 8:

[0829] Terminal: Records conversation content in real time. Generates conversation logs as text and audio data and sends them to the server periodically.

[0830] Step 9:

[0831] Server: Analyzes received conversation logs, extracts important information and key points, generates summaries, and evaluates the user's health and psychological state.

[0832] Step 10:

[0833] Server: Provides generated summaries and conversation logs to users, families, and caregivers. It also provides regular reports and gathers necessary feedback.

[0834] Through this series of steps, the system can provide effective dementia care and reduce the burden on families and caregivers.

[0835] (Example 1)

[0836] 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."

[0837] When providing personalized care to dementia patients and the elderly, there is a challenge in understanding each individual user's past experiences and preferences and engaging in conversations based on this. Furthermore, there is a lack of systems that allow families and care providers to accurately understand the patient's condition without causing them burden.

[0838] 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.

[0839] In this invention, the server includes means for collecting past recorded data from the user and uploading it to the system; means for analyzing the collected past recorded data and generating a user dialogue model and voice model; means for conversing with the user using the generated dialogue model and voice model; means for recording the conversation content in real time, extracting important information, and generating and providing a summary; and means for providing the summary and conversation log to the user or a third party. This makes it possible to achieve natural conversations based on the user's past experiences and preferences, thereby improving the user's sense of security and satisfaction. It also reduces the burden on family members and caregivers and allows them to grasp important information.

[0840] A "user" refers to an individual who provides data and utilizes the system.

[0841] "Past recorded data" refers to information including the user's past images, documents, videos, messages, and input data.

[0842] "Collection means" refers to devices and software that allow users to upload past recorded data to the system.

[0843] "Analysis means" refers to devices or software that analyze collected historical record data and generate user dialogue models and voice models.

[0844] A "dialogue model" refers to a language model designed to mimic conversations with users.

[0845] A "voice model" refers to a model used to generate speech during conversations with users.

[0846] "Conversational means" refers to devices or software that engage in conversation with a user using generated dialogue models and voice models.

[0847] "Recording means" refers to devices or software that record conversation content in real time, extract important information, and generate and provide summaries.

[0848] A "summary" refers to a compilation of the most important information from a conversation.

[0849] "Conversation log" refers to data that records the content of conversations with users.

[0850] "Third parties" refer to individuals or organizations other than the user, including family members and care providers.

[0851] This invention is a system that provides fully personalized care for the elderly and dementia patients. This system has the function of collecting and analyzing past recorded data, generating a user dialogue model and voice model, using these to converse with the user, and recording the content of the conversation. The following describes embodiments of this system.

[0852] System Configuration

[0853] 1. Data collection means: These are devices or software that allow users to upload past recorded data (images, documents, videos, messages, input data, etc.) to the system. Specific examples include the file upload function of smartphones and personal computers.

[0854] 2. Data Analysis Means: These are devices and software for analyzing uploaded data. They generate user dialogue models and voice models using natural language processing technology (e.g., Google Cloud Natural Language API) and speech generation technology (e.g., Amazon Polly).

[0855] 3. Terminal: A device or software that engages in conversation with the user using the generated dialogue model and voice model. Specific examples include robots (e.g., Pepper) and tablet devices (e.g., iPad).

[0856] 4. Conversation recording means: Devices or software that record conversation content in real time, extract important information, and generate and provide a summary.

[0857] System operation

[0858] Users collect historical data using smartphones or personal computers. For example, they scan family photo albums and collect related letters and video messages. They then upload this data to the system.

[0859] Server: Upon receiving uploaded data, it stores it in a secure database. The data is then analyzed using natural language processing and speech generation technologies. This analysis extracts the user's language patterns, preferences, and emotional tendencies, generating dialogue and voice models tailored to the user. For example, the server analyzes the text of a travel diary to identify frequently occurring vocabulary and phrases. It also extracts the pitch and intonation of the user's voice through audio analysis of video messages.

[0860] Terminal: The robot and tablet terminal use generated dialogue and voice models to converse with the user. For example, the robot might say, "Good morning, which photos would you like to see today?" and the user might reply, "I'd like to see photos from our family trip."

[0861] Server: Records conversations in real time, extracts important information, and generates summaries. The generated summaries and conversation logs are provided to the user themselves or third parties such as their family. For example, the server might generate a summary stating, "The topic the user was most interested in today was family travel," and send that information to the family via email.

[0862] Specific examples and prompt statements

[0863] Specific example:

[0864] 1. Users scan family trip photos and travel diaries and upload them to the system.

[0865] 2. The server receives this data, analyzes frequently occurring vocabulary and intonation, and generates a dialogue model and a speech model.

[0866] 3. The robot asks the user, "Which photos would you like to see today?" and the user replies, "I'd like to see photos from our family trip."

[0867] 4. The server records the conversation in real time and generates a summary stating, "The topic the user most wanted to talk about was family travel," and notifies the family.

[0868] Example of a prompt:

[0869] "Please talk about past memories related to family photos."

[0870] "What kind of music would you like to listen to today?"

[0871] In this way, a system that provides fully personalized care for the elderly and dementia patients is realized. This system can provide a sense of security and satisfaction through natural conversations based on the user's past experiences and preferences, and can reduce the burden on families and caregivers.

[0872] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0873] Step 1: Data Collection

[0874] User:

[0875] The user prepares past recorded data (e.g., images, documents, videos, messages, input data). Specifically, this involves scanning family album photos and collecting related letters and video messages.

[0876] Input: Scanned images, documents, video files

[0877] Output: Uploaded data file

[0878] Specific actions: The user takes photos for an album, scans letters, and records video messages using their smartphone. These files are then prepared in the system.

[0879] Step 2: Upload your registration

[0880] User:

[0881] Users upload their prepared historical record data to the system using the upload function of their smartphone or personal computer.

[0882] Input: Prepared data file

[0883] Output: Data files saved on the system

[0884] Specific operation: The user clicks the upload button on their smartphone, selects files such as "family trip photos" or "travel diary," and sends them to the system.

[0885] Step 3: Save data

[0886] server:

[0887] The server receives the uploaded data and stores it in a secure database.

[0888] Input: Uploaded data file

[0889] Output: Data stored in the database

[0890] Specific operation: The server parses the received file and saves it to the appropriate section of the database.

[0891] Step 4: Data analysis and model generation

[0892] server:

[0893] The stored data is analyzed. Text data is analyzed using natural language processing technology (e.g., Google Cloud Natural Language API), and audio data is analyzed using speech generation technology (e.g., Amazon Polly). This extracts the user's language patterns, preferences, and emotional tendencies, and generates dialogue models and speech models.

[0894] Input: Data stored in the database

[0895] Output: Generated dialogue model and voice model

[0896] Specific operation: The server analyzes the text of the travel diary to identify frequently occurring vocabulary and phrases. It also extracts the pitch and intonation of the user's voice through audio analysis of video messages.

[0897] Step 5: Generating and executing dialogue

[0898] Terminal:

[0899] The system uses generated dialogue and voice models to engage in conversations with users. It simulates natural conversations using robots (e.g., Pepper) or tablet devices (e.g., iPad).

[0900] Input: Generated dialogue model and voice model

[0901] Output: User interaction content

[0902] Specific action: The robot says, "Good morning, which photos would you like to see today?" and the user replies, "I'd like to see photos from our family trip."

[0903] Step 6: Record the conversation and generate a summary.

[0904] server:

[0905] The system records conversations in real time, extracts important information, and generates summaries. The generated summaries and conversation logs are provided to the user themselves or third parties such as their family.

[0906] Input: Content of the conversation between the user and the device.

[0907] Output: Generated summary and conversation log

[0908] Specific operation: The server records the conversation content, generates a summary stating, "The topic the user was most interested in today was family travel," and notifies the family via email.

[0909] Step 7: Feedback and Learning

[0910] server:

[0911] The system's learning model is updated based on the acquired conversation content and feedback. This improves the quality of subsequent conversations.

[0912] Input: Conversation log and feedback information

[0913] Output: Updated dialogue model and voice model

[0914] Specific operation: The server analyzes the conversation record, reflects the user's new interests and concerns in the model, and adjusts the system for the next interaction.

[0915] (Application Example 1)

[0916] 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."

[0917] Providing meals to the elderly and dementia patients requires personalized menu suggestions based on individual eating habits and medical information, but this is difficult to achieve with typical food delivery services. Furthermore, there is a need for a system that incorporates user feedback to provide optimal meal suggestions and records this information to offer a better dining experience.

[0918] 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.

[0919] In this invention, the server includes means for collecting past recorded data and the user's eating habits and medical information; means for analyzing the past recorded data and the user's eating habits and medical information to generate a user dialogue model and a voice model; means for controlling a terminal that converses with the user using the generated dialogue model and voice model and proposes a meal menu; means for the user to confirm an order based on the proposed meal menu; means for recording the conversation content and order history, collecting feedback on the meal menu, and generating a summary; and means for providing the summary and conversation log to the user or a third party. This makes it possible to propose the most suitable meal menu for each individual user and to provide personalized services that are tailored to the user's health condition and preferences.

[0920] "Past recorded data" refers to information about the user's previous activities and experiences, including letters, videos, text messages, photographs, handwritten data, and food photos.

[0921] "User eating habits" refers to information such as the types, frequency, and preferences of the foods that the user usually eats.

[0922] "Medical information" refers to information such as the user's health status, medical precautions, and allergy information.

[0923] A "dialogue model" is a model of a dialogue system that is generated by learning the user's language patterns and preferences in order to have a natural conversation with the user.

[0924] A "voice model" is a model of a voice generation system created to mimic the tone and intonation of a user's voice.

[0925] "Meal menu suggestion technology" is a technology that personalizes and suggests the optimal meal menu based on the user's eating habits and medical information.

[0926] A "terminal" is a hardware device used to interact with the user and to suggest and confirm meal menus, and includes smartphones, tablets, and other similar devices.

[0927] "Order history" is a record of the food menus that the user has ordered in the past.

[0928] A "summary" is a record that summarizes the content of conversations with users and their feedback on meal menus.

[0929] A "third party" refers to any person or organization other than the user who has the right to receive information, such as the user's family or caregivers.

[0930] This invention is a system that proposes personalized meal menus and provides food delivery services for the elderly and dementia patients. The system consists of the following main components:

[0931] System Configuration

[0932] 1. Data acquisition methods

[0933] The server collects users' past records, eating habits, and medical information. This includes methods of uploading letters, videos, text messages, photos, handwritten data, and food photos using smartphones or PCs. This allows the server to collect information about the user's past activities and health status.

[0934] 2. Data Analysis Methods

[0935] The server stores the collected data in a cloud database (e.g., Firebase, AWS DynamoDB) and analyzes this data using natural language processing models (e.g., GPT-4, BERT). During the analysis process, it extracts food menu preferences and medical considerations, and generates user dialogue models and voice models.

[0936] 3. Proposals via devices

[0937] The generated dialogue and voice models are installed on devices such as smartphones and tablets, and the system proposes meal menus in a conversational format with the user. The device uses speech recognition technologies such as Google Speech-to-Text and Amazon Transcribe to understand the user's voice instructions and propose appropriate menu items.

[0938] 4. Ordering and Delivery

[0939] The user reviews the suggested menu and confirms their order via their device. The order data is sent to a partner food delivery service, and the user can check the delivery status on the app.

[0940] 5. Conversation records and feedback

[0941] The server records conversations and order history conducted through the terminal and collects feedback on the meal menu. This feedback can then be used to improve menu suggestions for future visits. Specifically, it checks user satisfaction through conversations such as, "Did you enjoy yesterday's fish dish?"

[0942] Specific example

[0943] The user uploads past meal photos and medical information using their smartphone. The server receives this data and analyzes their dietary preferences and health status using a natural language processing model. Through the generated voice model, the device suggests to the user, "Fish dishes are recommended today. They are rich in protein and good for your health." Once the user confirms the order, the order data is sent to a food delivery service, and the meal is delivered at the specified time. After the meal, the device displays a prompt message, "How was yesterday's fish dish?", allowing the user to provide feedback.

[0944] Hardware and software to be used

[0945] Cloud databases: Firebase, AWS DynamoDB

[0946] Natural language processing models: GPT-4, BERT

[0947] Speech recognition technology: Google Speech-to-Text, Amazon Transcribe

[0948] Application framework: React Native (iOS / Android compatible)

[0949] This system will enable personalized meal menu suggestions tailored to the user's health condition and preferences, which is expected to improve user satisfaction.

[0950] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0951] Step 1:

[0952] The server collects past records, eating habits, and medical information uploaded by users using their smartphones or PCs. Specifically, this includes letters, videos, text messages, photos, handwritten data, and food photos. Once this data is collected, it is stored in a cloud database (e.g., Firebase, AWS DynamoDB).

[0953] Input: User's recorded data, eating habits, medical information

[0954] Output: Data stored in a cloud database

[0955] Step 2:

[0956] The server analyzes the collected data using natural language processing models (e.g., GPT-4, BERT). During the analysis, it extracts information about the user's language patterns, food preferences, and health status, and generates a user dialogue model and a voice model.

[0957] Input: Data stored in a cloud database

[0958] Output: User dialogue model and voice model

[0959] Step 3:

[0960] The device interacts with the user using generated dialogue and voice models to suggest meal options. It utilizes speech recognition technologies such as Google Speech-to-Text and Amazon Transcribe to understand the user's voice commands and suggest appropriate menu items. For example, it might suggest, "Today, I recommend a fish dish. It's rich in protein and good for you."

[0961] Input: User's dialogue model and voice model

[0962] Output: Menu suggestions for the user

[0963] Step 4:

[0964] The user reviews the suggested menu and confirms their order via their device. The order data is sent to the partner food delivery service via the server. The user can check the delivery status on the app.

[0965] Input: User's order information

[0966] Output: Sending order data to food delivery service

[0967] Step 5:

[0968] The server records conversations and order history via the terminal in real time and collects feedback on the meal menu. For example, it displays a prompt message such as, "How was yesterday's fish dish?" to elicit feedback from the user. This feedback can then be used to improve future menu suggestions.

[0969] Input: User feedback

[0970] Output: Updated dialogue and voice models incorporating feedback.

[0971] 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.

[0972] This invention is a system that provides fully personalized care for the elderly and dementia patients, and in particular, integrates an emotion engine that recognizes the user's emotions. The processing of this system's program will be explained below, including specific examples.

[0973] System Configuration

[0974] This system consists of the following main components:

[0975] 1. Data collection means: Means for collecting the user's past record data.

[0976] 2. Data analysis means: Means for analyzing collected data to generate a user dialogue model and a voice model.

[0977] 3. Emotion Engine: An engine that recognizes the user's emotions and reflects them in the conversation.

[0978] 4. Terminal: A device that uses the generated dialogue model and voice model to converse with the user.

[0979] 5. Conversation recording means: A means for recording conversation content and generating and providing a summary.

[0980] System operation

[0981] User: First, upload past records (letters, videos, text messages, photos, manually entered data, etc.) to the system using a smartphone or PC. This allows the system to collect information about the user's past events and experiences.

[0982] As a concrete example, a user could scan and upload photos from an old family album, along with any related letters or video messages.

[0983] Server: Receives uploaded data and stores it in a database. Next, it analyzes this data using natural language processing and speech generation technologies. The analysis includes a process to extract the user's language patterns, preferences, and emotional tendencies. It also generates a speech model from the user's voice and text data.

[0984] As a concrete example, the server analyzes the content of uploaded letters to identify frequently used vocabulary and expressions. It also analyzes video messages to extract the intonation and tone of the user's voice.

[0985] Emotion Engine: Based on this data, it analyzes generated audio and text data to identify the user's emotional state. The emotion engine recognizes the user's emotions with high accuracy and reflects that information in the conversational dialogue model.

[0986] For example, if a user looks at a family photo and says, "This photo brings back so many memories," the emotion engine recognizes the emotion of "joy" from the tone and expression of the user's voice and incorporates that information into the next conversation.

[0987] Terminal: Next, the generated dialogue model and voice model are used to converse with the user. The terminal is a robot or a tablet device, and it simulates natural conversation with the user through these devices.

[0988] As a concrete example, the robot says, "Good morning, which photo would you like to see today?" and the user replies, "I'd like to see this family photo." Based on the information from its emotion engine, the robot continues, "That's wonderful. Tell me more about that photo."

[0989] Server: Furthermore, it records conversations in real time, extracts important information, and generates summaries. The summaries and conversation logs are provided to the user and their family.

[0990] As a concrete example, the server generates a summary stating, "The topic the user most wanted to talk about in today's conversation was family travel," and periodically notifies the family of this information.

[0991] This system not only enables personalized care for dementia patients but also significantly reduces the burden on families and caregivers. Dementia patients can gain a sense of security and satisfaction by enjoying conversations based on their own lives and memories. Furthermore, the system constantly learns and adapts based on the latest data and feedback, improving the quality of care. The introduction of an emotion engine allows for real-time understanding of the user's emotional state, enabling more appropriate responses.

[0992] The following describes the processing flow.

[0993] Step 1:

[0994] User: Upload past record data to the system. The procedure involves using a smartphone or PC to select files such as letters, videos, text messages, photos, and manually entered data, and then sending them to the server using a dedicated app or web portal.

[0995] Step 2:

[0996] Server: Receives uploaded data, verifies its format, and stores it in the database. For example, letters and photos are saved in the image folder, and video files are saved in the video folder.

[0997] Step 3:

[0998] Server: Analyzes stored data. Uses natural language processing techniques to extract language patterns and emotional tendencies from text data, and analyzes audio data to generate a speech model. It also uses an emotion engine to recognize user emotions from audio and text data.

[0999] Step 4:

[1000] Server: Saves the generated dialogue and speech models to the cloud. During this process, the models are optimized, including the results of emotion recognition by the emotion engine.

[1001] Step 5:

[1002] Terminal: Takes action at specified times or triggers to allow the user to start a conversation simulation. Downloads dialogue and voice models from the server and builds the conversation environment.

[1003] Step 6:

[1004] Terminal: Speaks to the user. For example, it might say, "Hello, how was your day?" and uses a generated voice model and emotion engine to conduct a natural conversation.

[1005] Step 7:

[1006] User: Responds to questions and comments presented by the device. The device records these responses in real time and saves them as audio data.

[1007] Step 8:

[1008] Terminal: Analyzes recorded audio data and converts it into text data. This text data is then subjected to emotion recognition by an emotion engine.

[1009] Step 9:

[1010] Server: Receives conversation logs and sentiment recognition data sent from terminals. Analyzes this data, extracts important information, and generates a summary.

[1011] Step 10:

[1012] Server: Provides generated summaries to the user, their family, and care providers. Uses a notification system to periodically send summaries and conversation logs and receive feedback.

[1013] Through this step, the system can provide personalized dementia care, including highly accurate emotion recognition, improving the user's quality of life and reducing the burden on family members and caregivers.

[1014] (Example 2)

[1015] 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."

[1016] When providing personalized care to the elderly and dementia patients, it is crucial to engage in dialogue that accurately reflects the user's emotions and individual preferences. However, conventional technology has struggled to recognize user emotions in real time and adjust dialogue accordingly. Solving this challenge has been essential to improving the quality of care and reducing the burden on families and caregivers.

[1017] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting past data, means for analyzing the past data and generating a user dialogue model and a voice model, means for controlling a terminal that interacts with the user using the generated dialogue model and voice model, means for recording the dialogue content and generating a summary, means for providing the summary and dialogue log to the user or a third party, and means for recognizing the user's emotions using an emotion engine and reflecting them in the dialogue model. This makes it possible to recognize the user's emotions in real time and to conduct appropriate dialogue based on that information.

[1018] "Past data" refers to past records provided by the user (such as letters, videos, text messages, images, and manually entered data).

[1019] A "dialogue model" refers to a model based on language patterns and context that has been generated to enable natural conversations with users.

[1020] A "voice model" refers to a model of voice data generated to reproduce the characteristics and intonation of a user's voice.

[1021] A "terminal" refers to a device used for interacting with a user (e.g., a robot or a tablet).

[1022] A "summary" refers to information that extracts the most important parts of a dialogue and presents them concisely.

[1023] "Dialogue log" refers to data that records the history of conversations with users.

[1024] An "emotion engine" refers to an analytical engine that recognizes the user's emotional state and reflects that information in the content of the conversation.

[1025] "Natural language processing technology" refers to technologies aimed at understanding and generating natural language (e.g., text analysis, syntactic analysis).

[1026] "Speech generation technology" refers to technologies for generating natural-sounding speech from text data (e.g., text-to-speech, speech synthesis).

[1027] A "server" refers to a central computing system that performs data analysis, storage, and processing for the entire system.

[1028] "User" refers to an individual, including elderly people and those with dementia, who uses this system.

[1029] "Third party" refers to any party other than the user (e.g., family members, care providers).

[1030] This invention is a system that provides personalized care for the elderly and dementia patients, and in particular has the function of recognizing the user's emotions by integrating an emotion engine. A specific description of an embodiment of this system is given below.

[1031] System Configuration

[1032] This system consists of three components: a server, a terminal, and a user. The hardware and software used in the system include the following:

[1033] Server: A central computing system for analyzing, storing, and processing data. Specifically, this would involve using services like Amazon RDS or MongoDB.

[1034] Terminal: A device used for interacting with the user. Specifically, this could be a Pepper robot or a tablet device (e.g., an iPad).

[1035] Emotion Engine: An engine that recognizes user emotions and reflects that information in the dialogue model. It uses the Microsoft Azure Emotion API.

[1036] Natural language processing techniques: Text analysis is performed using NLTK and spaCy.

[1037] Speech generation technology: Speech data is generated using Google Text-to-Speech.

[1038] Operation Description

[1039] User: First, the user uploads past recorded data (letters, videos, text messages, images, manually entered data, etc.) to the system using a smartphone or PC. This uploaded data is sent to the server as information about the user's past events and experiences.

[1040] For example, a user could scan and upload photos from a family album, and attach related letters or videos.

[1041] Server: The server receives uploaded data and stores it in a database. Next, it analyzes the data using natural language processing techniques (e.g., NLTK, spaCy) and speech generation techniques (e.g., Google Text-to-Speech). This analysis includes extracting the user's language patterns, preferences, and emotional tendencies. Furthermore, it generates a speech model from the user's voice and text data.

[1042] As a concrete example, the server analyzes the content of uploaded letters to identify frequently occurring vocabulary and expressions. It also analyzes video messages to extract the tone and intonation of the user's voice.

[1043] Emotion Engine: The emotion engine identifies the user's emotional state based on analyzed voice and text data. This information is then reflected in the dialogue model of the conversation.

[1044] For example, if a user says, "This photo brings back so many memories," the emotion engine recognizes the emotion of "joy" from the tone and expression of their voice.

[1045] Terminal: Using the generated dialogue and voice models, the terminal engages in natural conversations with the user. This enables conversations that are tailored to the user's emotions and preferences.

[1046] As a concrete example, the robot might say, "Good morning, which photo would you like to see today?" and when the user replies, "I'd like to see this family photo," the robot might continue, "That's wonderful. Tell me more about that photo."

[1047] Server: The server records the content of the conversation in real time, extracts important information, and generates a summary. This summary and conversation log are provided to the user and their family.

[1048] As a concrete example, the server generates a summary stating, "The topic the user most wanted to talk about in today's conversation was family travel," and periodically notifies the family.

[1049] Examples of prompts for generative AI models

[1050] Examples of specific prompt messages are as follows:

[1051] 1. "How are you doing?" "I'm feeling good this morning. I want to look at some family photos."

[1052] 2. "What topics have users wanted to talk about in the past?" "They've been talking a lot about family trips lately."

[1053] 3. "What should I talk about with the user next?" "You could start by talking about movies or music."

[1054] Using these prompts enables more personalized responses from generative AI models.

[1055] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1056] Step 1: Data Collection

[1057] User: Users upload past recorded data (letters, videos, text messages, images, manually entered data, etc.) to the system using their smartphones or PCs.

[1058] Input: Letters, videos, text messages, images, manually entered data

[1059] Output: Uploaded data is sent to the server.

[1060] Specific operation: The user scans and uploads photos from a family album, and attaches related letters and videos.

[1061] Step 2: Data storage and analysis

[1062] Server: The server receives the uploaded data and stores it in the database. It then analyzes the data using natural language processing and speech generation technologies.

[1063] Input: Uploaded letters, videos, text messages, images, handwritten data

[1064] Output: The analyzed data is generated as a user dialogue model and a voice model.

[1065] Specific operations: The server analyzes the content of the letter to identify frequently occurring vocabulary and expressions. It also analyzes video messages to extract the user's voice tone and intonation.

[1066] Step 3: Emotion Recognition

[1067] Emotion Engine: The emotion engine uses analyzed voice and text data to identify the user's emotional state.

[1068] Input: Analyzed speech and text data

[1069] Output: Information reflecting the user's emotional state.

[1070] Specific operation: When a user says, "This photo brings back so many memories," the emotion engine recognizes the emotion of "joy" from the tone and expression of their voice.

[1071] Step 4: Generate Dialog

[1072] Server: The server generates an appropriate dialogue model based on the emotion recognition results. This process utilizes machine learning models.

[1073] Input: Emotion engine results and user profile data

[1074] Output: Emotion-responsive dialogue model

[1075] Specific operation: The server applies the generated "emotion" tag to the dialog and produces a response such as, "That's great. Tell me more about that photo."

[1076] Step 5: Execute the conversation

[1077] Terminal: The terminal uses the generated dialogue model and voice model to engage in natural conversations with the user.

[1078] Input: Dialogue model and voice model

[1079] Output: Natural conversation with the device

[1080] Specific operation: The device says, "Good morning, which photo would you like to see today?" and when the user replies, "I'd like to see this family photo," the device continues, "That's wonderful. Tell me more about that photo."

[1081] Step 6: Conversation recording and summary generation

[1082] Server: The server records the content of the conversation in real time, extracts important information, and generates a summary.

[1083] Input: Real-time dialogue data

[1084] Output: Dialogue summary and log

[1085] Specific operation: The server generates a summary stating, "The topic the user most wanted to talk about in today's conversation was family travel," and periodically notifies the family.

[1086] (Application Example 2)

[1087] 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."

[1088] Current systems that provide personalized care for the elderly and dementia patients lack sufficient collection and analysis of historical data, making it difficult to accurately understand the emotional state of individual users and provide appropriate responses. Furthermore, systems that analyze emotional states in real time and provide conversations based on that analysis are inadequate. Solving these challenges is essential to improving the quality of care for the elderly and dementia patients.

[1089] 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.

[1090] In this invention, the server includes means for collecting historical recorded data, means for analyzing the historical recorded data and generating a user dialogue model and voice model, and means for analyzing the user's voice and facial expression data in real time and identifying their emotional state. This enables personalized dialogue based on the user's historical data and natural conversation based on real-time emotion analysis.

[1091] "Past recorded data" refers to letters, videos, text messages, photos, and manually entered data that the user has generated in the past.

[1092] A "dialogue model" is a model used to simulate natural conversations with users based on historical recorded data.

[1093] A "voice model" is a model of voice patterns generated from a user's past voice data.

[1094] A "terminal" is a device that uses the generated dialogue model and voice model to converse with the user, and specifically refers to robots, tablet devices, etc.

[1095] A "summary" is information that extracts and summarizes the main points of a recorded conversation.

[1096] A "conversation log" refers to a record of the entire conversation with a user.

[1097] "Emotional state" refers to the state of a user's emotions, such as joy, sadness, or surprise, which is identified from their facial expressions and voice.

[1098] "Emotion analysis technology" is a technology that identifies and analyzes emotions from a user's voice and facial expression data.

[1099] "Natural language processing technology" refers to algorithms and techniques that enable computers to understand and generate human language.

[1100] "Speech generation technology" is a technology that synthesizes natural, human-like speech from text data.

[1101] This invention is a system that provides personalized care to the elderly and dementia patients, and in particular utilizes an emotion engine that recognizes the user's emotions. The program processing of this system is described below.

[1102] System Configuration

[1103] The system consists of the following main components:

[1104] 1. Data collection methods: Means for collecting the user's past recorded data (letters, videos, text messages, photos, manually entered data, etc.).

[1105] 2. Data analysis means: Means for analyzing collected data and generating user dialogue models and voice models.

[1106] 3. Emotion analysis technology: A technology that analyzes the user's voice and facial expression data to identify their emotional state.

[1107] 4. Terminal: A device that uses the generated dialogue model and voice model to converse with the user.

[1108] 5. Conversation recording means: A means for recording conversation content and generating and providing a summary.

[1109] Hardware and software used

[1110] Hardware: Smartphones, tablets, robots.

[1111] Software: Python, SpeechRecognition library, TextBlob library, Natural Language Processing (NLP), Text-to-Speech (TTS).

[1112] Program processing

[1113] The server first collects past recorded data uploaded by users via smartphones or tablets. Next, it stores the collected data in a database and performs analysis using natural language processing (NLP) and text-to-speech (TTS) technologies. The analysis generates a user dialogue model and a voice model.

[1114] Using emotion analysis technology, the system identifies the user's emotional state from their voice and facial expression data. Based on this information, it simulates natural conversation and provides appropriate reactions for the user. For example, when a user is talking about a past family trip, the system identifies the emotional state of "joy" from their voice and responds with, "That's wonderful, tell me more about that trip."

[1115] Specific example

[1116] Specifically, the following processes are performed.

[1117] 1. Collect user voice data using the smartphone's microphone.

[1118] 2. Convert speech to text (using Google Cloud Speech-to-Text).

[1119] 3. Analyze text data using TextBlob to identify emotions.

[1120] 4. Generate and provide appropriate feedback to the user based on their emotions.

[1121] Example of a prompt

[1122] "Imagine a user is talking in more detail about a family trip they mentioned in a previous conversation. How would you respond to a situation where the user is expressing positive emotions?"

[1123] This prompt helps the generative AI model generate an appropriate response based on positive sentiment analysis results.

[1124] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1125] Step 1:

[1126] Users upload past data:

[1127] Users upload past records (letters, videos, text messages, photos, and manually entered data) to the system using their smartphones or tablets.

[1128] Inputs: Letters, videos, text messages, photos, hand-entered data.

[1129] Output: Data stored on a cloud server.

[1130] Step 2:

[1131] The server receives and stores the data:

[1132] The server receives the uploaded data and stores it in a database. Natural language processing (NLP) and text-to-speech (TTS) technologies are then used to analyze this data.

[1133] Input: Data stored on a cloud server.

[1134] Output: Analyzed text data and audio data.

[1135] Step 3:

[1136] The server generates the dialogue model and the voice model:

[1137] The server generates a user dialogue model and a voice model based on the analyzed data. This includes a process of extracting the user's language patterns, preferences, and emotional tendencies.

[1138] Input: Analyzed text data and audio data.

[1139] Output: Dialogue model and speech model.

[1140] Step 4:

[1141] The device analyzes the user's voice and facial expressions in real time:

[1142] The device (smartphone, tablet, or robot) uses a microphone and camera to collect the user's voice and facial expressions in real time, and uses emotion analysis technology to identify their emotional state.

[1143] Input: User's real-time voice data and facial expression data.

[1144] Output: Identified emotional state.

[1145] Step 5:

[1146] The device engages in conversations based on emotions:

[1147] The device engages in natural conversation with the user based on the generated dialogue model, voice model, and identified emotional state. For example, if the user talks about a past family trip, the system recognizes the emotion of joy from the voice and responds, "That's wonderful, tell me more about that trip."

[1148] Input: Dialogue model, voice model, identified emotional state.

[1149] Output: The content of the conversation with the user.

[1150] Step 6:

[1151] The server records the conversation and generates a summary:

[1152] The server records conversations in real time, extracts important information, and generates summaries. These summaries and conversation logs are provided to the user and their family.

[1153] Input: The content of the conversation with the user.

[1154] Output: Summary and conversation log.

[1155] Step 7:

[1156] The server provides summaries and conversation logs to the user or a third party:

[1157] The server periodically notifies the user or a third party, such as a family member, of the generated summary and conversation logs.

[1158] Input: Summary and conversation log.

[1159] Output: Summary and conversation log provided to the user or a third party.

[1160] 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.

[1161] 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.

[1162] 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.

[1163] [Fourth Embodiment]

[1164] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1165] 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.

[1166] 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).

[1167] 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.

[1168] 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.

[1169] 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).

[1170] 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.

[1171] 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.

[1172] 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.

[1173] 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.

[1174] 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.

[1175] 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.

[1176] 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".

[1177] This invention is a system that provides fully personalized care for the elderly and dementia patients. The program processing of this system will be explained below, including specific examples.

[1178] System Configuration

[1179] This system consists of the following main components:

[1180] 1. Data collection means: Means for collecting the user's past record data.

[1181] 2. Data analysis means: Means for analyzing collected data to generate a user dialogue model and a voice model.

[1182] 3. Terminal: A device that uses the generated dialogue model and voice model to converse with the user.

[1183] 4. Conversation recording means: A means for recording conversation content and generating and providing a summary.

[1184] System operation

[1185] User: First, upload past records (letters, videos, text messages, photos, manually entered data, etc.) to the system using a smartphone or PC. This allows the system to collect information about the user's past events and experiences.

[1186] As a concrete example, a user could scan and upload photos from an old family album, along with any related letters or video messages.

[1187] Server: Receives uploaded data and stores it in a database. Then, it analyzes this data using natural language processing and speech generation technologies. The analysis includes a process of extracting the user's language patterns, preferences, and emotional tendencies.

[1188] As a concrete example, the server analyzes the content of uploaded letters to identify frequently used vocabulary and expressions. It also analyzes video messages to extract the intonation and tone of the user's voice.

[1189] Terminal: Next, the generated dialogue model and voice model are used to converse with the user. The terminal is a robot or a tablet device, and it simulates natural conversation with the user through these devices.

[1190] As a concrete example, the robot might say, "Good morning, which photo would you like to see today?" and the user might reply, "I'd like to see this family photo."

[1191] Server: Furthermore, it records conversations in real time, extracts important information, and generates summaries. The summaries and conversation logs are provided to the user and their family.

[1192] As a concrete example, the server generates a summary stating, "The topic the user most wanted to talk about in today's conversation was family travel," and periodically notifies the family of this information.

[1193] This system not only enables personalized care for dementia patients but also significantly reduces the burden on families and caregivers. Dementia patients can gain a sense of security and satisfaction by enjoying conversations based on their own lives and memories. Furthermore, the system constantly adapts and learns based on the latest data and feedback, improving the quality of care.

[1194] The following describes the processing flow.

[1195] Step 1:

[1196] User: Upload past record data to the system. The procedure involves using a smartphone or PC to select files such as letters, videos, text messages, photos, and manually entered data, and then sending them to the server using a dedicated app or web portal.

[1197] Step 2:

[1198] Server: Receives uploaded data and saves it to the database. It verifies the data format upon receipt and saves it to the appropriate storage path. For example, scanned images of letters are saved to the images folder, and video files are saved to the videos folder.

[1199] Step 3:

[1200] Server: Analyzes stored data. Extracts language patterns and sentiment tendencies from text data using natural language processing techniques. Generates speech models from speech and text data using speech generation techniques. This creates user dialogue models and speech models.

[1201] Step 4:

[1202] Server: Stores the generated dialogue and speech models in the cloud. Performs model validation and optimization as needed to improve accuracy.

[1203] Step 5:

[1204] Terminal: The user instructs the terminal to start the conversation simulation. The terminal (robot or tablet) downloads the model generated from the server and sets up the conversation environment.

[1205] Step 6:

[1206] Terminal: Speaks to the user. For example, it uses phrases such as "Hello, how was your day?" and engages in natural conversation through a generated voice model.

[1207] Step 7:

[1208] User: Responds to questions and comments presented by the device. The device understands the user's statements through speech recognition and proceeds with the conversation.

[1209] Step 8:

[1210] Terminal: Records conversation content in real time. Generates conversation logs as text and audio data and sends them to the server periodically.

[1211] Step 9:

[1212] Server: Analyzes received conversation logs, extracts important information and key points, generates summaries, and evaluates the user's health and psychological state.

[1213] Step 10:

[1214] Server: Provides generated summaries and conversation logs to users, families, and caregivers. It also provides regular reports and gathers necessary feedback.

[1215] Through this series of steps, the system can provide effective dementia care and reduce the burden on families and caregivers.

[1216] (Example 1)

[1217] 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".

[1218] When providing personalized care to dementia patients and the elderly, there is a challenge in understanding each individual user's past experiences and preferences and engaging in conversations based on this. Furthermore, there is a lack of systems that allow families and care providers to accurately understand the patient's condition without causing them burden.

[1219] 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.

[1220] In this invention, the server includes means for collecting past recorded data from the user and uploading it to the system; means for analyzing the collected past recorded data and generating a user dialogue model and voice model; means for conversing with the user using the generated dialogue model and voice model; means for recording the conversation content in real time, extracting important information, and generating and providing a summary; and means for providing the summary and conversation log to the user or a third party. This makes it possible to achieve natural conversations based on the user's past experiences and preferences, thereby improving the user's sense of security and satisfaction. It also reduces the burden on family members and caregivers and allows them to grasp important information.

[1221] A "user" refers to an individual who provides data and utilizes the system.

[1222] "Past recorded data" refers to information including the user's past images, documents, videos, messages, and input data.

[1223] "Collection means" refers to devices and software that allow users to upload past recorded data to the system.

[1224] "Analysis means" refers to devices or software that analyze collected historical record data and generate user dialogue models and voice models.

[1225] A "dialogue model" refers to a language model designed to mimic conversations with users.

[1226] A "voice model" refers to a model used to generate speech during conversations with users.

[1227] "Conversational means" refers to devices or software that engage in conversation with a user using generated dialogue models and voice models.

[1228] "Recording means" refers to devices or software that record conversation content in real time, extract important information, and generate and provide summaries.

[1229] A "summary" refers to a compilation of the most important information from a conversation.

[1230] "Conversation log" refers to data that records the content of conversations with users.

[1231] "Third parties" refer to individuals or organizations other than the user, including family members and care providers.

[1232] This invention is a system that provides fully personalized care for the elderly and dementia patients. This system has the function of collecting and analyzing past recorded data, generating a user dialogue model and voice model, using these to converse with the user, and recording the content of the conversation. The following describes embodiments of this system.

[1233] System Configuration

[1234] 1. Data collection means: These are devices or software that allow users to upload past recorded data (images, documents, videos, messages, input data, etc.) to the system. Specific examples include the file upload function of smartphones and personal computers.

[1235] 2. Data Analysis Means: These are devices and software for analyzing uploaded data. They generate user dialogue models and voice models using natural language processing technology (e.g., Google Cloud Natural Language API) and speech generation technology (e.g., Amazon Polly).

[1236] 3. Terminal: A device or software that engages in conversation with the user using the generated dialogue model and voice model. Specific examples include robots (e.g., Pepper) and tablet devices (e.g., iPad).

[1237] 4. Conversation recording means: Devices or software that record conversation content in real time, extract important information, and generate and provide a summary.

[1238] System operation

[1239] Users collect historical data using smartphones or personal computers. For example, they scan family photo albums and collect related letters and video messages. They then upload this data to the system.

[1240] Server: Upon receiving uploaded data, it stores it in a secure database. The data is then analyzed using natural language processing and speech generation technologies. This analysis extracts the user's language patterns, preferences, and emotional tendencies, generating dialogue and voice models tailored to the user. For example, the server analyzes the text of a travel diary to identify frequently occurring vocabulary and phrases. It also extracts the pitch and intonation of the user's voice through audio analysis of video messages.

[1241] Terminal: The robot and tablet terminal use generated dialogue and voice models to converse with the user. For example, the robot might say, "Good morning, which photos would you like to see today?" and the user might reply, "I'd like to see photos from our family trip."

[1242] Server: Records conversations in real time, extracts important information, and generates summaries. The generated summaries and conversation logs are provided to the user themselves or third parties such as their family. For example, the server might generate a summary stating, "The topic the user was most interested in today was family travel," and send that information to the family via email.

[1243] Specific examples and prompt statements

[1244] Specific example:

[1245] 1. Users scan family trip photos and travel diaries and upload them to the system.

[1246] 2. The server receives this data, analyzes frequently occurring vocabulary and intonation, and generates a dialogue model and a speech model.

[1247] 3. The robot asks the user, "Which photos would you like to see today?" and the user replies, "I'd like to see photos from our family trip."

[1248] 4. The server records the conversation in real time and generates a summary stating, "The topic the user most wanted to talk about was family travel," and notifies the family.

[1249] Example of a prompt:

[1250] "Please talk about past memories related to family photos."

[1251] "What kind of music would you like to listen to today?"

[1252] In this way, a system that provides fully personalized care for the elderly and dementia patients is realized. This system can provide a sense of security and satisfaction through natural conversations based on the user's past experiences and preferences, and can reduce the burden on families and caregivers.

[1253] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1254] Step 1: Data Collection

[1255] User:

[1256] The user prepares past recorded data (e.g., images, documents, videos, messages, input data). Specifically, this involves scanning family album photos and collecting related letters and video messages.

[1257] Input: Scanned images, documents, video files

[1258] Output: Uploaded data file

[1259] Specific actions: The user takes photos for an album, scans letters, and records video messages using their smartphone. These files are then prepared in the system.

[1260] Step 2: Upload your registration

[1261] User:

[1262] Users upload their prepared historical record data to the system using the upload function of their smartphone or personal computer.

[1263] Input: Prepared data file

[1264] Output: Data files saved on the system

[1265] Specific operation: The user clicks the upload button on their smartphone, selects files such as "family trip photos" or "travel diary," and sends them to the system.

[1266] Step 3: Save data

[1267] server:

[1268] The server receives the uploaded data and stores it in a secure database.

[1269] Input: Uploaded data file

[1270] Output: Data stored in the database

[1271] Specific operation: The server parses the received file and saves it to the appropriate section of the database.

[1272] Step 4: Data analysis and model generation

[1273] server:

[1274] The stored data is analyzed. Text data is analyzed using natural language processing technology (e.g., Google Cloud Natural Language API), and audio data is analyzed using speech generation technology (e.g., Amazon Polly). This extracts the user's language patterns, preferences, and emotional tendencies, and generates dialogue models and speech models.

[1275] Input: Data stored in the database

[1276] Output: Generated dialogue model and voice model

[1277] Specific operation: The server analyzes the text of the travel diary to identify frequently occurring vocabulary and phrases. It also extracts the pitch and intonation of the user's voice through audio analysis of video messages.

[1278] Step 5: Generating and executing dialogue

[1279] Terminal:

[1280] The system uses generated dialogue and voice models to engage in conversations with users. It simulates natural conversations using robots (e.g., Pepper) or tablet devices (e.g., iPad).

[1281] Input: Generated dialogue model and voice model

[1282] Output: User interaction content

[1283] Specific action: The robot says, "Good morning, which photos would you like to see today?" and the user replies, "I'd like to see photos from our family trip."

[1284] Step 6: Record the conversation and generate a summary.

[1285] server:

[1286] The system records conversations in real time, extracts important information, and generates summaries. The generated summaries and conversation logs are provided to the user themselves or third parties such as their family.

[1287] Input: Content of the conversation between the user and the device.

[1288] Output: Generated summary and conversation log

[1289] Specific operation: The server records the conversation content, generates a summary stating, "The topic the user was most interested in today was family travel," and notifies the family via email.

[1290] Step 7: Feedback and Learning

[1291] server:

[1292] The system's learning model is updated based on the acquired conversation content and feedback. This improves the quality of subsequent conversations.

[1293] Input: Conversation log and feedback information

[1294] Output: Updated dialogue model and voice model

[1295] Specific operation: The server analyzes the conversation record, reflects the user's new interests and concerns in the model, and adjusts the system for the next interaction.

[1296] (Application Example 1)

[1297] 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".

[1298] Providing meals to the elderly and dementia patients requires personalized menu suggestions based on individual eating habits and medical information, but this is difficult to achieve with typical food delivery services. Furthermore, there is a need for a system that incorporates user feedback to provide optimal meal suggestions and records this information to offer a better dining experience.

[1299] 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.

[1300] In this invention, the server includes means for collecting past recorded data and the user's eating habits and medical information; means for analyzing the past recorded data and the user's eating habits and medical information to generate a user dialogue model and a voice model; means for controlling a terminal that converses with the user using the generated dialogue model and voice model and proposes a meal menu; means for the user to confirm an order based on the proposed meal menu; means for recording the conversation content and order history, collecting feedback on the meal menu, and generating a summary; and means for providing the summary and conversation log to the user or a third party. This makes it possible to propose the most suitable meal menu for each individual user and to provide personalized services that are tailored to the user's health condition and preferences.

[1301] "Past recorded data" refers to information about the user's previous activities and experiences, including letters, videos, text messages, photographs, handwritten data, and food photos.

[1302] "User eating habits" refers to information such as the types, frequency, and preferences of the foods that the user usually eats.

[1303] "Medical information" refers to information such as the user's health status, medical precautions, and allergy information.

[1304] A "dialogue model" is a model of a dialogue system that is generated by learning the user's language patterns and preferences in order to have a natural conversation with the user.

[1305] A "voice model" is a model of a voice generation system created to mimic the tone and intonation of a user's voice.

[1306] "Meal menu suggestion technology" is a technology that personalizes and suggests the optimal meal menu based on the user's eating habits and medical information.

[1307] A "terminal" is a hardware device used to interact with the user and to suggest and confirm meal menus, and includes smartphones, tablets, and other similar devices.

[1308] "Order history" is a record of the food menus that the user has ordered in the past.

[1309] A "summary" is a record that summarizes the content of conversations with users and their feedback on meal menus.

[1310] A "third party" refers to any person or organization other than the user who has the right to receive information, such as the user's family or caregivers.

[1311] This invention is a system that proposes personalized meal menus and provides food delivery services for the elderly and dementia patients. The system consists of the following main components:

[1312] System Configuration

[1313] 1. Data acquisition methods

[1314] The server collects users' past records, eating habits, and medical information. This includes methods of uploading letters, videos, text messages, photos, handwritten data, and food photos using smartphones or PCs. This allows the server to collect information about the user's past activities and health status.

[1315] 2. Data Analysis Methods

[1316] The server stores the collected data in a cloud database (e.g., Firebase, AWS DynamoDB) and analyzes this data using natural language processing models (e.g., GPT-4, BERT). During the analysis process, it extracts food menu preferences and medical considerations, and generates user dialogue models and voice models.

[1317] 3. Proposals via devices

[1318] The generated dialogue and voice models are installed on devices such as smartphones and tablets, and the system proposes meal menus in a conversational format with the user. The device uses speech recognition technologies such as Google Speech-to-Text and Amazon Transcribe to understand the user's voice instructions and propose appropriate menu items.

[1319] 4. Ordering and Delivery

[1320] The user reviews the suggested menu and confirms their order via their device. The order data is sent to a partner food delivery service, and the user can check the delivery status on the app.

[1321] 5. Conversation records and feedback

[1322] The server records conversations and order history conducted through the terminal and collects feedback on the meal menu. This feedback can then be used to improve menu suggestions for future visits. Specifically, it checks user satisfaction through conversations such as, "Did you enjoy yesterday's fish dish?"

[1323] Specific example

[1324] The user uploads past meal photos and medical information using their smartphone. The server receives this data and analyzes their dietary preferences and health status using a natural language processing model. Through the generated voice model, the device suggests to the user, "Fish dishes are recommended today. They are rich in protein and good for your health." Once the user confirms the order, the order data is sent to a food delivery service, and the meal is delivered at the specified time. After the meal, the device displays a prompt message, "How was yesterday's fish dish?", allowing the user to provide feedback.

[1325] Hardware and software to be used

[1326] Cloud databases: Firebase, AWS DynamoDB

[1327] Natural language processing models: GPT-4, BERT

[1328] Speech recognition technology: Google Speech-to-Text, Amazon Transcribe

[1329] Application framework: React Native (iOS / Android compatible)

[1330] This system will enable personalized meal menu suggestions tailored to the user's health condition and preferences, which is expected to improve user satisfaction.

[1331] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1332] Step 1:

[1333] The server collects past records, eating habits, and medical information uploaded by users using their smartphones or PCs. Specifically, this includes letters, videos, text messages, photos, handwritten data, and food photos. Once this data is collected, it is stored in a cloud database (e.g., Firebase, AWS DynamoDB).

[1334] Input: User's recorded data, eating habits, medical information

[1335] Output: Data stored in a cloud database

[1336] Step 2:

[1337] The server analyzes the collected data using natural language processing models (e.g., GPT-4, BERT). During the analysis, it extracts information about the user's language patterns, food preferences, and health status, and generates a user dialogue model and a voice model.

[1338] Input: Data stored in a cloud database

[1339] Output: User dialogue model and voice model

[1340] Step 3:

[1341] The device interacts with the user using generated dialogue and voice models to suggest meal options. It utilizes speech recognition technologies such as Google Speech-to-Text and Amazon Transcribe to understand the user's voice commands and suggest appropriate menu items. For example, it might suggest, "Today, I recommend a fish dish. It's rich in protein and good for you."

[1342] Input: User's dialogue model and voice model

[1343] Output: Menu suggestions for the user

[1344] Step 4:

[1345] The user reviews the suggested menu and confirms their order via their device. The order data is sent to the partner food delivery service via the server. The user can check the delivery status on the app.

[1346] Input: User's order information

[1347] Output: Sending order data to food delivery service

[1348] Step 5:

[1349] The server records conversations and order history via the terminal in real time and collects feedback on the meal menu. For example, it displays a prompt message such as, "How was yesterday's fish dish?" to elicit feedback from the user. This feedback can then be used to improve future menu suggestions.

[1350] Input: User feedback

[1351] Output: Updated dialogue and voice models incorporating feedback.

[1352] 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.

[1353] This invention is a system that provides fully personalized care for the elderly and dementia patients, and in particular, integrates an emotion engine that recognizes the user's emotions. The processing of this system's program will be explained below, including specific examples.

[1354] System Configuration

[1355] This system consists of the following main components:

[1356] 1. Data collection means: Means for collecting the user's past record data.

[1357] 2. Data analysis means: Means for analyzing collected data to generate a user dialogue model and a voice model.

[1358] 3. Emotion Engine: An engine that recognizes the user's emotions and reflects them in the conversation.

[1359] 4. Terminal: A device that uses the generated dialogue model and voice model to converse with the user.

[1360] 5. Conversation recording means: A means for recording conversation content and generating and providing a summary.

[1361] System operation

[1362] User: First, upload past records (letters, videos, text messages, photos, manually entered data, etc.) to the system using a smartphone or PC. This allows the system to collect information about the user's past events and experiences.

[1363] As a concrete example, a user could scan and upload photos from an old family album, along with any related letters or video messages.

[1364] Server: Receives uploaded data and stores it in a database. Next, it analyzes this data using natural language processing and speech generation technologies. The analysis includes a process to extract the user's language patterns, preferences, and emotional tendencies. It also generates a speech model from the user's voice and text data.

[1365] As a concrete example, the server analyzes the content of uploaded letters to identify frequently used vocabulary and expressions. It also analyzes video messages to extract the intonation and tone of the user's voice.

[1366] Emotion Engine: Based on this data, it analyzes generated audio and text data to identify the user's emotional state. The emotion engine recognizes the user's emotions with high accuracy and reflects that information in the conversational dialogue model.

[1367] For example, if a user looks at a family photo and says, "This photo brings back so many memories," the emotion engine recognizes the emotion of "joy" from the tone and expression of the user's voice and incorporates that information into the next conversation.

[1368] Terminal: Next, the generated dialogue model and voice model are used to converse with the user. The terminal is a robot or a tablet device, and it simulates natural conversation with the user through these devices.

[1369] As a concrete example, the robot says, "Good morning, which photo would you like to see today?" and the user replies, "I'd like to see this family photo." Based on the information from its emotion engine, the robot continues, "That's wonderful. Tell me more about that photo."

[1370] Server: Furthermore, it records conversations in real time, extracts important information, and generates summaries. The summaries and conversation logs are provided to the user and their family.

[1371] As a concrete example, the server generates a summary stating, "The topic the user most wanted to talk about in today's conversation was family travel," and periodically notifies the family of this information.

[1372] This system not only enables personalized care for dementia patients but also significantly reduces the burden on families and caregivers. Dementia patients can gain a sense of security and satisfaction by enjoying conversations based on their own lives and memories. Furthermore, the system constantly learns and adapts based on the latest data and feedback, improving the quality of care. The introduction of an emotion engine allows for real-time understanding of the user's emotional state, enabling more appropriate responses.

[1373] The following describes the processing flow.

[1374] Step 1:

[1375] User: Upload past record data to the system. The procedure involves using a smartphone or PC to select files such as letters, videos, text messages, photos, and manually entered data, and then sending them to the server using a dedicated app or web portal.

[1376] Step 2:

[1377] Server: Receives uploaded data, verifies its format, and stores it in the database. For example, letters and photos are saved in the image folder, and video files are saved in the video folder.

[1378] Step 3:

[1379] Server: Analyzes stored data. Uses natural language processing techniques to extract language patterns and emotional tendencies from text data, and analyzes audio data to generate a speech model. It also uses an emotion engine to recognize user emotions from audio and text data.

[1380] Step 4:

[1381] Server: Saves the generated dialogue and speech models to the cloud. During this process, the models are optimized, including the results of emotion recognition by the emotion engine.

[1382] Step 5:

[1383] Terminal: Takes action at specified times or triggers to allow the user to start a conversation simulation. Downloads dialogue and voice models from the server and builds the conversation environment.

[1384] Step 6:

[1385] Terminal: Speaks to the user. For example, it might say, "Hello, how was your day?" and uses a generated voice model and emotion engine to conduct a natural conversation.

[1386] Step 7:

[1387] User: Responds to questions and comments presented by the device. The device records these responses in real time and saves them as audio data.

[1388] Step 8:

[1389] Terminal: Analyzes recorded audio data and converts it into text data. This text data is then subjected to emotion recognition by an emotion engine.

[1390] Step 9:

[1391] Server: Receives conversation logs and sentiment recognition data sent from terminals. Analyzes this data, extracts important information, and generates a summary.

[1392] Step 10:

[1393] Server: Provides generated summaries to the user, their family, and care providers. Uses a notification system to periodically send summaries and conversation logs and receive feedback.

[1394] Through this step, the system can provide personalized dementia care, including highly accurate emotion recognition, improving the user's quality of life and reducing the burden on family members and caregivers.

[1395] (Example 2)

[1396] 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".

[1397] When providing personalized care to the elderly and dementia patients, it is crucial to engage in dialogue that accurately reflects the user's emotions and individual preferences. However, conventional technology has struggled to recognize user emotions in real time and adjust dialogue accordingly. Solving this challenge has been essential to improving the quality of care and reducing the burden on families and caregivers.

[1398] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting past data, means for analyzing the past data and generating a user dialogue model and a voice model, means for controlling a terminal that interacts with the user using the generated dialogue model and voice model, means for recording the dialogue content and generating a summary, means for providing the summary and dialogue log to the user or a third party, and means for recognizing the user's emotions using an emotion engine and reflecting them in the dialogue model. This makes it possible to recognize the user's emotions in real time and to conduct appropriate dialogue based on that information.

[1399] "Past data" refers to past records provided by the user (such as letters, videos, text messages, images, and manually entered data).

[1400] A "dialogue model" refers to a model based on language patterns and context that has been generated to enable natural conversations with users.

[1401] A "voice model" refers to a model of voice data generated to reproduce the characteristics and intonation of a user's voice.

[1402] A "terminal" refers to a device used for interacting with a user (e.g., a robot or a tablet).

[1403] A "summary" refers to information that extracts the most important parts of a dialogue and presents them concisely.

[1404] "Dialogue log" refers to data that records the history of conversations with users.

[1405] An "emotion engine" refers to an analytical engine that recognizes the user's emotional state and reflects that information in the content of the conversation.

[1406] "Natural language processing technology" refers to technologies aimed at understanding and generating natural language (e.g., text analysis, syntactic analysis).

[1407] "Speech generation technology" refers to technologies for generating natural-sounding speech from text data (e.g., text-to-speech, speech synthesis).

[1408] A "server" refers to a central computing system that performs data analysis, storage, and processing for the entire system.

[1409] "User" refers to an individual, including elderly people and those with dementia, who uses this system.

[1410] "Third party" refers to any party other than the user (e.g., family members, care providers).

[1411] This invention is a system that provides personalized care for the elderly and dementia patients, and in particular has the function of recognizing the user's emotions by integrating an emotion engine. A specific description of an embodiment of this system is given below.

[1412] System Configuration

[1413] This system consists of three components: a server, a terminal, and a user. The hardware and software used in the system include the following:

[1414] Server: A central computing system for analyzing, storing, and processing data. Specifically, this would involve using services like Amazon RDS or MongoDB.

[1415] Terminal: A device used for interacting with the user. Specifically, this could be a Pepper robot or a tablet device (e.g., an iPad).

[1416] Emotion Engine: An engine that recognizes user emotions and reflects that information in the dialogue model. It uses the Microsoft Azure Emotion API.

[1417] Natural language processing techniques: Text analysis is performed using NLTK and spaCy.

[1418] Speech generation technology: Speech data is generated using Google Text-to-Speech.

[1419] Operation Description

[1420] User: First, the user uploads past recorded data (letters, videos, text messages, images, manually entered data, etc.) to the system using a smartphone or PC. This uploaded data is sent to the server as information about the user's past events and experiences.

[1421] For example, a user could scan and upload photos from a family album, and attach related letters or videos.

[1422] Server: The server receives uploaded data and stores it in a database. Next, it analyzes the data using natural language processing techniques (e.g., NLTK, spaCy) and speech generation techniques (e.g., Google Text-to-Speech). This analysis includes extracting the user's language patterns, preferences, and emotional tendencies. Furthermore, it generates a speech model from the user's voice and text data.

[1423] As a concrete example, the server analyzes the content of uploaded letters to identify frequently occurring vocabulary and expressions. It also analyzes video messages to extract the tone and intonation of the user's voice.

[1424] Emotion Engine: The emotion engine identifies the user's emotional state based on analyzed voice and text data. This information is then reflected in the dialogue model of the conversation.

[1425] For example, if a user says, "This photo brings back so many memories," the emotion engine recognizes the emotion of "joy" from the tone and expression of their voice.

[1426] Terminal: Using the generated dialogue and voice models, the terminal engages in natural conversations with the user. This enables conversations that are tailored to the user's emotions and preferences.

[1427] As a concrete example, the robot might say, "Good morning, which photo would you like to see today?" and when the user replies, "I'd like to see this family photo," the robot might continue, "That's wonderful. Tell me more about that photo."

[1428] Server: The server records the content of the conversation in real time, extracts important information, and generates a summary. This summary and conversation log are provided to the user and their family.

[1429] As a concrete example, the server generates a summary stating, "The topic the user most wanted to talk about in today's conversation was family travel," and periodically notifies the family.

[1430] Examples of prompts for generative AI models

[1431] Examples of specific prompt messages are as follows:

[1432] 1. "How are you doing?" "I'm feeling good this morning. I want to look at some family photos."

[1433] 2. "What topics have users wanted to talk about in the past?" "They've been talking a lot about family trips lately."

[1434] 3. "What should I talk about with the user next?" "You could start by talking about movies or music."

[1435] Using these prompts enables more personalized responses from generative AI models.

[1436] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1437] Step 1: Data Collection

[1438] User: Users upload past recorded data (letters, videos, text messages, images, manually entered data, etc.) to the system using their smartphones or PCs.

[1439] Input: Letters, videos, text messages, images, manually entered data

[1440] Output: Uploaded data is sent to the server.

[1441] Specific operation: The user scans and uploads photos from a family album, and attaches related letters and videos.

[1442] Step 2: Data storage and analysis

[1443] Server: The server receives the uploaded data and stores it in the database. It then analyzes the data using natural language processing and speech generation technologies.

[1444] Input: Uploaded letters, videos, text messages, images, handwritten data

[1445] Output: The analyzed data is generated as a user dialogue model and a voice model.

[1446] Specific operations: The server analyzes the content of the letter to identify frequently occurring vocabulary and expressions. It also analyzes video messages to extract the user's voice tone and intonation.

[1447] Step 3: Emotion Recognition

[1448] Emotion Engine: The emotion engine uses analyzed voice and text data to identify the user's emotional state.

[1449] Input: Analyzed speech and text data

[1450] Output: Information reflecting the user's emotional state.

[1451] Specific operation: When a user says, "This photo brings back so many memories," the emotion engine recognizes the emotion of "joy" from the tone and expression of their voice.

[1452] Step 4: Generate Dialog

[1453] Server: The server generates an appropriate dialogue model based on the emotion recognition results. This process utilizes machine learning models.

[1454] Input: Emotion engine results and user profile data

[1455] Output: Emotion-responsive dialogue model

[1456] Specific operation: The server applies the generated "emotion" tag to the dialog and produces a response such as, "That's great. Tell me more about that photo."

[1457] Step 5: Execute the conversation

[1458] Terminal: The terminal uses the generated dialogue model and voice model to engage in natural conversations with the user.

[1459] Input: Dialogue model and voice model

[1460] Output: Natural conversation with the device

[1461] Specific operation: The device says, "Good morning, which photo would you like to see today?" and when the user replies, "I'd like to see this family photo," the device continues, "That's wonderful. Tell me more about that photo."

[1462] Step 6: Conversation recording and summary generation

[1463] Server: The server records the content of the conversation in real time, extracts important information, and generates a summary.

[1464] Input: Real-time dialogue data

[1465] Output: Dialogue summary and log

[1466] Specific operation: The server generates a summary stating, "The topic the user most wanted to talk about in today's conversation was family travel," and periodically notifies the family.

[1467] (Application Example 2)

[1468] 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".

[1469] Current systems that provide personalized care for the elderly and dementia patients lack sufficient collection and analysis of historical data, making it difficult to accurately understand the emotional state of individual users and provide appropriate responses. Furthermore, systems that analyze emotional states in real time and provide conversations based on that analysis are inadequate. Solving these challenges is essential to improving the quality of care for the elderly and dementia patients.

[1470] 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.

[1471] In this invention, the server includes means for collecting historical recorded data, means for analyzing the historical recorded data and generating a user dialogue model and voice model, and means for analyzing the user's voice and facial expression data in real time and identifying their emotional state. This enables personalized dialogue based on the user's historical data and natural conversation based on real-time emotion analysis.

[1472] "Past recorded data" refers to letters, videos, text messages, photos, and manually entered data that the user has generated in the past.

[1473] A "dialogue model" is a model used to simulate natural conversations with users based on historical recorded data.

[1474] A "voice model" is a model of voice patterns generated from a user's past voice data.

[1475] A "terminal" is a device that uses the generated dialogue model and voice model to converse with the user, and specifically refers to robots, tablet devices, etc.

[1476] A "summary" is information that extracts and summarizes the main points of a recorded conversation.

[1477] A "conversation log" refers to a record of the entire conversation with a user.

[1478] "Emotional state" refers to the state of a user's emotions, such as joy, sadness, or surprise, which is identified from their facial expressions and voice.

[1479] "Emotion analysis technology" is a technology that identifies and analyzes emotions from a user's voice and facial expression data.

[1480] "Natural language processing technology" refers to algorithms and techniques that enable computers to understand and generate human language.

[1481] "Speech generation technology" is a technology that synthesizes natural, human-like speech from text data.

[1482] This invention is a system that provides personalized care to the elderly and dementia patients, and in particular utilizes an emotion engine that recognizes the user's emotions. The program processing of this system is described below.

[1483] System Configuration

[1484] The system consists of the following main components:

[1485] 1. Data collection methods: Means for collecting the user's past recorded data (letters, videos, text messages, photos, manually entered data, etc.).

[1486] 2. Data analysis means: Means for analyzing collected data and generating user dialogue models and voice models.

[1487] 3. Emotion analysis technology: A technology that analyzes the user's voice and facial expression data to identify their emotional state.

[1488] 4. Terminal: A device that uses the generated dialogue model and voice model to converse with the user.

[1489] 5. Conversation recording means: A means for recording conversation content and generating and providing a summary.

[1490] Hardware and software used

[1491] Hardware: Smartphones, tablets, robots.

[1492] Software: Python, SpeechRecognition library, TextBlob library, Natural Language Processing (NLP), Text-to-Speech (TTS).

[1493] Program processing

[1494] The server first collects past recorded data uploaded by users via smartphones or tablets. Next, it stores the collected data in a database and performs analysis using natural language processing (NLP) and text-to-speech (TTS) technologies. The analysis generates a user dialogue model and a voice model.

[1495] Using emotion analysis technology, the system identifies the user's emotional state from their voice and facial expression data. Based on this information, it simulates natural conversation and provides appropriate reactions for the user. For example, when a user is talking about a past family trip, the system identifies the emotional state of "joy" from their voice and responds with, "That's wonderful, tell me more about that trip."

[1496] Specific example

[1497] Specifically, the following processes are performed.

[1498] 1. Collect user voice data using the smartphone's microphone.

[1499] 2. Convert speech to text (using Google Cloud Speech-to-Text).

[1500] 3. Analyze text data using TextBlob to identify emotions.

[1501] 4. Generate and provide appropriate feedback to the user based on their emotions.

[1502] Example of a prompt

[1503] "Imagine a user is talking in more detail about a family trip they mentioned in a previous conversation. How would you respond to a situation where the user is expressing positive emotions?"

[1504] This prompt helps the generative AI model generate an appropriate response based on positive sentiment analysis results.

[1505] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1506] Step 1:

[1507] Users upload past data:

[1508] Users upload past records (letters, videos, text messages, photos, and manually entered data) to the system using their smartphones or tablets.

[1509] Inputs: Letters, videos, text messages, photos, hand-entered data.

[1510] Output: Data stored on a cloud server.

[1511] Step 2:

[1512] The server receives and stores the data:

[1513] The server receives the uploaded data and stores it in a database. Natural language processing (NLP) and text-to-speech (TTS) technologies are then used to analyze this data.

[1514] Input: Data stored on a cloud server.

[1515] Output: Analyzed text data and audio data.

[1516] Step 3:

[1517] The server generates the dialogue model and the voice model:

[1518] The server generates a user dialogue model and a voice model based on the analyzed data. This includes a process of extracting the user's language patterns, preferences, and emotional tendencies.

[1519] Input: Analyzed text data and audio data.

[1520] Output: Dialogue model and speech model.

[1521] Step 4:

[1522] The device analyzes the user's voice and facial expressions in real time:

[1523] The device (smartphone, tablet, or robot) uses a microphone and camera to collect the user's voice and facial expressions in real time, and uses emotion analysis technology to identify their emotional state.

[1524] Input: User's real-time voice data and facial expression data.

[1525] Output: Identified emotional state.

[1526] Step 5:

[1527] The device engages in conversations based on emotions:

[1528] The device engages in natural conversation with the user based on the generated dialogue model, voice model, and identified emotional state. For example, if the user talks about a past family trip, the system recognizes the emotion of joy from the voice and responds, "That's wonderful, tell me more about that trip."

[1529] Input: Dialogue model, voice model, identified emotional state.

[1530] Output: The content of the conversation with the user.

[1531] Step 6:

[1532] The server records the conversation and generates a summary:

[1533] The server records conversations in real time, extracts important information, and generates summaries. These summaries and conversation logs are provided to the user and their family.

[1534] Input: The content of the conversation with the user.

[1535] Output: Summary and conversation log.

[1536] Step 7:

[1537] The server provides summaries and conversation logs to the user or a third party:

[1538] The server periodically notifies the user or a third party, such as a family member, of the generated summary and conversation logs.

[1539] Input: Summary and conversation log.

[1540] Output: Summary and conversation log provided to the user or a third party.

[1541] 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.

[1542] 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.

[1543] 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 robot 414.

[1544] 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.

[1545] 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.

[1546] 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.

[1547] 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.

[1548] 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.

[1549] 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."

[1550] 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.

[1551] 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.

[1552] 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.

[1553] 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.

[1554] 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.

[1555] 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.

[1556] 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.

[1557] 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.

[1558] 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.

[1559] 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.

[1560] 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.

[1561] 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 as being incorporated by reference.

[1562] The following is further disclosed regarding the embodiments described above.

[1563] (Claim 1)

[1564] Means for collecting historical record data,

[1565] A means for analyzing the aforementioned past recorded data and generating a user dialogue model and voice model,

[1566] Means for controlling a terminal that converses with a user using the generated dialogue model and voice model,

[1567] A means for recording the content of the aforementioned conversation and generating a summary,

[1568] Means for providing the summary and conversation log to the user or a third party,

[1569] A system that includes this.

[1570] (Claim 2)

[1571] The system according to claim 1, wherein the aforementioned past recorded data includes letters, videos, text messages, photographs, and manually entered data.

[1572] (Claim 3)

[1573] The system according to claim 1, wherein the analysis includes natural language processing technology and speech generation technology.

[1574] "Example 1"

[1575] (Claim 1)

[1576] A means for users to collect past record data and upload it to the system,

[1577] The means for analyzing the collected historical record data and generating a user dialogue model and voice model,

[1578] A means for conducting a conversation with a user using the generated dialogue model and voice model,

[1579] A means for recording the aforementioned conversation content in real time, extracting important information, and generating and providing a summary,

[1580] Means for providing the summary and conversation log to the user or a third party,

[1581] A system that includes this.

[1582] (Claim 2)

[1583] The system according to claim 1, wherein the aforementioned past recorded data includes images, documents, videos, messages, and input data.

[1584] (Claim 3)

[1585] The system according to claim 1, wherein the analysis includes information processing technology and speech synthesis technology.

[1586] "Application Example 1"

[1587] (Claim 1)

[1588] A means of collecting past record data and user dietary habits and medical information,

[1589] The means for analyzing the aforementioned past record data and the user's eating habits and medical information to generate a user dialogue model and a voice model,

[1590] A means for controlling a terminal that converses with the user and suggests a meal menu using the generated dialogue model and voice model,

[1591] A means for the user to confirm their order based on the proposed meal menu,

[1592] A means for recording the aforementioned conversation content and order history, collecting feedback on the meal menu, and generating a summary,

[1593] Means for providing the summary and conversation log to the user or a third party,

[1594] A system that includes this.

[1595] (Claim 2)

[1596] The system according to claim 1, wherein the aforementioned past record data and the user's eating habits and medical information include letters, videos, text messages, photographs, manually entered data, and food photos.

[1597] (Claim 3)

[1598] The system according to claim 1, wherein the analysis includes natural language processing technology, speech generation technology, and meal menu suggestion technology.

[1599] "Example 2 of combining an emotion engine"

[1600] (Claim 1)

[1601] Means of collecting past data,

[1602] A means for analyzing the aforementioned past data and generating a user dialogue model and a voice model,

[1603] Means for controlling a terminal that interacts with a user using the generated dialogue model and voice model,

[1604] Means for recording the content of the aforementioned dialogue and generating a summary,

[1605] Means for providing the summary and dialogue log to the user or a third party,

[1606] A means for recognizing the user's emotions using an emotion engine and reflecting them in the dialogue model,

[1607] A system that includes this.

[1608] (Claim 2)

[1609] The system according to claim 1, wherein the aforementioned past data includes letters, videos, text messages, images, and manually entered data.

[1610] (Claim 3)

[1611] The system according to claim 1, wherein the analysis includes natural language processing technology and speech generation technology.

[1612] "Application example 2 when combining with an emotional engine"

[1613] (Claim 1)

[1614] Means for collecting historical record data,

[1615] A means for analyzing the aforementioned past recorded data and generating a user dialogue model and voice model,

[1616] A means for analyzing a user's voice and facial expression data in real time to identify their emotional state,

[1617] Means for controlling a terminal that converses with a user using the generated dialogue model and voice model,

[1618] A means for recording the content of the aforementioned conversation and generating a summary,

[1619] Means for providing the summary and conversation log to the user or a third party,

[1620] A system that includes this.

[1621] (Claim 2)

[1622] The system according to claim 1, comprising means for acquiring the aforementioned past recorded data and user voice and facial expression data.

[1623] (Claim 3)

[1624] The system according to claim 1, wherein the analysis includes natural language processing technology, speech generation technology, and emotion analysis technology. [Explanation of Symbols]

[1625] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means for collecting historical record data, A means for analyzing the aforementioned past recorded data and generating a user dialogue model and voice model, Means for controlling a terminal that converses with a user using the generated dialogue model and voice model, A means for recording the content of the aforementioned conversation and generating a summary, Means for providing the summary and conversation log to the user or a third party, A system that includes this.

2. The system according to claim 1, wherein the aforementioned past recorded data includes letters, videos, text messages, photographs, and manually entered data.

3. The system according to claim 1, wherein the analysis includes natural language processing technology and speech generation technology.

Images