system

Abstract

We provide the system. [Solution] Interface means for receiving voice or text input from a user, A means for analyzing the input and interpreting the user's intent using natural language processing technology, A database access means for identifying specific dates and medical services and checking their availability, A means for generating a response to notify the user that the reservation has been confirmed, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern times, hospital reservation systems mainly via the Internet are increasing, but there is a problem that it is difficult for elderly people or users unfamiliar with technology to make a reservation for necessary medical services quickly and surely because of the high hurdle. Therefore, it is required to enable users to easily reserve a hospital and improve access to medical services.

Means for Solving the Problems

[0005] The present invention provides an interface means for receiving voice or text input from a user, analyzing the input, and interpreting the user's intent using natural language processing technology. It then identifies a specific date, time, and medical service, and checks its availability using a database access means. When a reservation is confirmed, a response generation means notifies the user of the reservation confirmation and generates a reservation reminder as needed, thereby providing a system that allows users to complete hospital reservations easily and efficiently.

[0006] "Interface means" refers to a component of a system for receiving input from a user in the form of voice or text.

[0007] "Natural language processing technology" is a technology that analyzes input language data to enable computers to understand the user's intentions and requests.

[0008] "Database access means" refers to a method of accessing a database that manages hospital appointment schedules and checking the availability of medical services for a specific date and time.

[0009] The "response generation means" is part of a system that generates a confirmation message necessary to notify the user that the reservation has been confirmed.

[0010] A "reservation reminder" is information used to notify the user in advance of the date, time, and details of a reservation. [Brief explanation of the drawing]

[0011] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4]This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0012] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0013] First, let's explain the terminology used in the following explanation.

[0014] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0015] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0017] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0018] 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."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] 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.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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".

[0032] The system of the present invention is designed to allow users to easily complete medical facility reservations using voice or text input. Embodiments of the present invention are described below.

[0033] The device first receives voice input from the user. In this case, it obtains information in voice or text format using a phone, text messaging service, or instant messaging service. When voice input is received, the device's voice recognition function is used to convert the input into text.

[0034] The server receives text data sent from the terminal. Next, it uses natural language processing technology to analyze the user's intent and identify the desired date and time for the appointment and the medical department. Through this analysis, it understands the user's request, "I would like to make an appointment with the internal medicine department next Monday morning," and extracts the necessary information.

[0035] Next, the server accesses a database of medical facilities to check for availability that matches the user's preferences. The database contains records of available appointment slots for various medical departments and dates, and the server refers to this database to identify the most suitable appointment slot.

[0036] If a reservation slot matching the user's preferences is found, the server sends that information to the terminal to notify the user. The terminal receives the information from the server and either displays a confirmation message or provides an audio notification to the user. For example, the user might receive feedback such as, "Your internal medicine appointment has been confirmed for 10:00 AM next Monday."

[0037] This system also generates reservation reminders and automatically sends notifications to users before the specified date and time to help them remember their reservation details. These notifications are again sent via voice or text through the device.

[0038] In this way, users can easily make hospital appointments via voice or text message. The design of this system significantly improves access to medical facilities and is user-friendly for the elderly and technophobic users.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] Users make appointment requests via telephone, text messaging services, or instant messaging services. For voice input, users verbally specify their desired department and date / time.

[0042] Step 2:

[0043] The device receives voice input from the user. Using its voice recognition function, it converts the input voice into text and sends that data to the server.

[0044] Step 3:

[0045] The server analyzes the user's intent based on the text data received from the terminal. It uses natural language processing technology to understand the user's request. For example, it interprets an intent such as, "I would like to make an eye doctor appointment for next Tuesday."

[0046] Step 4:

[0047] The server accesses the reservation database based on the user's requested date, time, and medical department. It searches for available appointment slots for the specific date and time and checks their availability.

[0048] Step 5:

[0049] If the server finds an available slot, it confirms the reservation and generates a response with that information. Specifically, it creates a confirmation message that includes the reserved date and time, and information about the medical department.

[0050] Step 6:

[0051] The server sends the generated confirmation message to the terminal.

[0052] Step 7:

[0053] The terminal notifies the user of the confirmation message received from the server. In the case of a text messaging service, it is displayed; in the case of a phone call, it is read aloud.

[0054] Step 8:

[0055] The user reviews the reservation confirmation information they received. If any corrections are needed, they can submit another request.

[0056] Step 9:

[0057] To improve service to users, the server automatically generates a reservation reminder before the scheduled date and time and notifies the user via their device.

[0058] (Example 1)

[0059] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0060] To provide a system that allows for efficient and easy booking of medical facilities, it is necessary to support a variety of user input formats, accurately interpret user intent, quickly find the optimal booking slot, and notify the user without fail. A system that achieves this process and is easy to use, even for the elderly and those unfamiliar with technology, is essential.

[0061] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0062] In this invention, the server includes communication means for receiving voice or text input from a user, processing means for analyzing the input and interpreting the user's intent using language recognition technology, and recording device access means for identifying a specified date and time and medical activity, and searching for availability information. This enables users to quickly and accurately make reservations at medical facilities through various input methods and to receive reservation confirmations and reminders.

[0063] A "user" refers to an individual or group that uses the system to make a reservation at a medical facility.

[0064] "Voice or text input" refers to voice or text data used by a user to provide information or instructions to the system.

[0065] "Communication means" refers to devices and services used to transmit user input to a system, such as telephones and messaging services.

[0066] "Language recognition technology" refers to technology that interprets voice and text data entered by a user and analyzes their intent.

[0067] "Processing means" refers to the function in which the system uses programs and logic to analyze user input and derive the information necessary for making a reservation.

[0068] "Recording device access means" refers to a means of accessing a database that stores reservation status and searching for available time slots that match the user's preferences.

[0069] "Response generation means" refers to a function that creates and provides a message to inform the user that the reservation has been completed.

[0070] A "reservation reminder" refers to a reminder function that sends a notification to the user when the reservation date and time are approaching, so that they do not forget their reservation details.

[0071] This invention relates to a system that allows users to efficiently complete medical facility reservations using voice or text input. This system allows users to input information via a device they use on a daily basis.

[0072] First, the device receives voice or text input from the user. In this case, devices such as smartphones and personal computers obtain input through means of communication such as telephone calls, text messaging services, and instant messaging services. In the case of voice input, the device converts the voice into text data using a speech recognition function (for example, a general-purpose speech recognition API).

[0073] Next, the server receives the text data sent from the terminal. The server uses language recognition technology (for example, a general-purpose natural language processing API) to analyze the user's intent. This technology makes it possible to identify specific desired appointment dates and times, as well as medical-related activities.

[0074] The server then accesses the database to search for availability information for the specified date, time, and medical activity. The recording device manages various appointment slots for medical facilities, and the server searches for and identifies an available slot that matches the user's intentions.

[0075] Once a reservation is confirmed, the server uses a response generation mechanism to generate reservation confirmation information and sends it to the terminal. The terminal then notifies the user of a confirmation message, such as "Your reservation is complete," either verbally or in text. Furthermore, it generates a reservation reminder and automatically notifies the user as the scheduled date and time approaches.

[0076] As a concrete example, consider a case where a user voice-inputs, "I would like to make an eye doctor appointment for next Tuesday afternoon." An example of a prompt in this case would be, "I would like to make an eye doctor appointment for next Tuesday afternoon." In this way, the system provides users with an easy way to make appointments at medical facilities, offering convenience especially to the elderly and users who are not tech-savvy.

[0077] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0078] Step 1:

[0079] Users enter their requests for medical facility appointments via voice or text through their device. Input is done via telephone, text messaging service, or instant messaging service. For voice input, the device utilizes its built-in speech recognition function to convert the input voice into text data. This data forms the basis for extracting detailed information about the user's intentions.

[0080] Step 2:

[0081] The terminal sends the converted text data to the server. The server performs natural language processing based on the received text data. Using language recognition technology, the server analyzes the user's desired appointment date and time and medical activities to clarify their intentions. In this process, keywords are extracted from the data and used to accurately understand the user's requests.

[0082] Step 3:

[0083] The server accesses the recording device and searches for available appointment slots that match the user's request. The database records available appointment times for each medical department, and the server processes the data to determine the most suitable appointment slot based on the specified date, time, and medical activity. As a result, available slots are identified.

[0084] Step 4:

[0085] Once a reservation slot is determined, the server generates a response based on that information. The server creates a text or voice message to notify the user that the reservation is confirmed and sends it to the terminal. For example, the message might be in the format, "Your ophthalmology appointment has been confirmed for next Tuesday at 2pm."

[0086] Step 5:

[0087] The terminal transmits the response message received from the server to the user. The user receives confirmation of the reservation via voice or text, thereby knowing that the reservation was made correctly.

[0088] Step 6:

[0089] The server also generates a reservation reminder to automatically notify the user as the reservation date approaches. This reminder has the function of being sent to the user via the device before the specified date and time, helping the user not to forget their reservation.

[0090] (Application Example 1)

[0091] 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."

[0092] In modern society, it is crucial for elderly people and those requiring care to be able to easily make appointments at medical facilities in order to reduce physical and mental burdens and improve access to healthcare. However, current appointment systems are complex for users unfamiliar with information technology, and the booking process is time-consuming and cumbersome. Therefore, there is a need for a system that allows for easy and intuitive booking of medical facilities and efficiently shares necessary information with caregivers.

[0093] 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.

[0094] In this invention, the server includes information input / output means for receiving voice or text input from a user; information processing means for analyzing the input and interpreting the user's intent using natural language processing technology; information retrieval means for identifying a specific date and time and medical service and verifying its availability; and information distribution means for notifying the user that the reservation has been confirmed and providing information to caregivers. This makes it possible to easily make reservations at medical facilities via voice or text and to efficiently notify users and caregivers of the reservation information.

[0095] "User" refers to an individual or their assistant who provides input in voice or text format to make a reservation at a medical facility.

[0096] "Information input / output means" refers to interface technologies for receiving user input through voice recognition functions and messaging services.

[0097] "Information processing means" refers to technologies that utilize natural language processing techniques to analyze and interpret the user's input intent.

[0098] "Information retrieval means" refers to technology for identifying specific dates, times, and medical services, and checking their availability to meet the user's requirements.

[0099] "Information distribution means" refers to technology used to notify users and caregivers of confirmation and reminder information when a reservation is confirmed.

[0100] A "care support provider" refers to a person responsible for managing reservation information and receiving messages to provide support to individuals who require care.

[0101] To implement this invention, the terminal used by the user is a device such as a smartphone or a caregiving robot. The terminal receives the request for a medical appointment when the user inputs it via voice or text. In particular, in the case of voice input, the terminal is equipped with a speech recognition function that converts speech to text. Technologies such as Google® Cloud Speech-to-Text API can be used.

[0102] The server receives text data sent from the terminal. Next, it analyzes this text data using natural language processing techniques to understand the user's intent. Natural language processing libraries such as NLTK and spaCy are utilized. This allows the server to identify the date and time the user wants to specify, as well as the details of the medical service.

[0103] The server then accesses the database to check for the user's desired date and time and the availability of medical services. It retrieves information through database management systems such as MySQL® or PostgreSQL. If the necessary information is found, the server confirms the reservation and issues a confirmation notice to the user.

[0104] Furthermore, reservation information is also notified to caregivers using an information distribution method. Notifications are sent in voice or text format using the Twilio SMS API or Firebase Cloud Messaging. The introduction of this system will enable elderly people to intuitively make reservations at medical facilities and will enable efficient information dissemination to caregivers.

[0105] A concrete example of its use is when an elderly person, Ms. A, tells a care robot, "I would like to book an appointment with the orthopedics department next Monday afternoon." Based on this instruction, the system automatically makes the optimal appointment and notifies Ms. A and her caregiver. An example of a prompt to the generating AI model is, "Please explain the process of making a hospital appointment by voice for an elderly person. Please describe in detail how the input data is processed and the steps until the appointment is completed."

[0106] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0107] Step 1:

[0108] The user enters their medical appointment request into the device via voice or text. The entered information is converted to text using the device's voice recognition function (in the case of voice). This converts unstructured voice data into text data.

[0109] Step 2:

[0110] The terminal sends the converted text data to the server. This data transfer delivers the speech-recognized information to the server. Here, the input is text data, and the output is the data sent to the server.

[0111] Step 3:

[0112] The server analyzes the user's intent based on the received text data using natural language processing techniques. Specifically, it uses NLTK and spaCy to extract information about specific dates, times, and medical services from the text data. The input is text data, and the output is structured data related to the user's intent.

[0113] Step 4:

[0114] The server uses structured intent data to access the database and check available dates, times, and service availability. It utilizes database systems such as MySQL or PostgreSQL for this search. The input is data related to the user's request, and the output is a set of available reservation options.

[0115] Step 5:

[0116] If a reservable option is found, the server confirms it and sends a confirmation notification to the device. The information is then communicated to the user via voice or text using the Twilio SMS API or Firebase Cloud Messaging. The input is the reservation option, and the output is the confirmation message.

[0117] Step 6:

[0118] Furthermore, the server notifies caregivers of the reservation information. This notification is also done via Twilio or Firebase, either in voice or text format. The input is the final confirmed reservation information, and the output is the notification to the caregiver.

[0119] Through the steps described above, users can easily make reservations at medical facilities, and this information is also appropriately communicated to caregivers.

[0120] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0121] The system of the present invention aims to provide more personalized responses by receiving voice or text input from the user and performing not only reservation but also emotion recognition. Specific embodiments of this invention are described below.

[0122] The device receives voice or text data entered by the user via telephone, text messaging service, or instant messaging service. In the case of voice, the device converts the voice to text and sends that data to the server.

[0123] The server receives data from the terminal and first analyzes the user's intent using natural language processing technology. Next, it uses an emotion engine to analyze the emotional elements of the input voice and text and recognize emotions. For example, if the user's voice sounds tense, the server will detect this and consider appropriate measures.

[0124] Once the emotions are analyzed, the server identifies the user's preferred date, time, and medical department, and accesses the hospital's database to check for available appointments. If the emotion engine detects high levels of stress or anxiety, the server will either connect the user to an operator or adjust its response to indicate that special support is needed.

[0125] If the reservation is successful, the server will generate a reservation confirmation along with a customized message and health advice tailored to the recognized emotions. This response will be sent to the terminal and notified to the user. Specifically, it may include something like, "Your internal medicine appointment has been confirmed for next Monday at 10:00 AM. You seem nervous, but please don't worry. Please contact us anytime if you have any problems."

[0126] This feature allows users to feel more at ease and receive personalized suggestions and support. This system provides an advanced medical appointment system that takes user emotions into consideration, making it easy to use even for users unfamiliar with technology or the elderly.

[0127] The following describes the processing flow.

[0128] Step 1:

[0129] Users enter appointment requests via telephone, text messaging services, or instant messaging services. If using voice input, users dictate the medical department and preferred date and time.

[0130] Step 2:

[0131] The terminal receives the user's voice input and converts it to text using speech recognition technology. In the case of text messages, it sends them to the server in their original format.

[0132] Step 3:

[0133] The server receives data sent from the terminal and first uses natural language processing technology to analyze the user's intent. This identifies the user's request and determines the desired medical department and date / time.

[0134] Step 4:

[0135] The server uses an emotion engine to analyze the emotions contained in the user's voice or text. For example, it can detect tension, stress, anxiety, etc., from the tone of voice and word choice.

[0136] Step 5:

[0137] The server accesses the hospital's database based on the specified medical department and date / time to check availability. If an appointment is possible, it confirms the reservation based on that information.

[0138] Step 6:

[0139] If the emotion engine detects high levels of stress or anxiety, the server will either connect the user to an operator or prepare a customized message to promote reassurance.

[0140] Step 7:

[0141] The server generates and sends a reservation confirmation message and a personalized message based on the user's emotions to the terminal. The message includes information such as the date and time of the reservation and the medical department.

[0142] Step 8:

[0143] The terminal receives messages from the server and notifies the user or reads them aloud.

[0144] Step 9:

[0145] Users review the messages they receive and request corrections if there are any problems with their reservations. In some cases, they may follow the server's advice to gain peace of mind.

[0146] (Example 2)

[0147] 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".

[0148] Conventional reservation systems have struggled to accurately understand user intent and facilitate smooth reservations. Furthermore, they fail to consider user emotions, thus lacking a sense of security and placing a burden on users, especially those unfamiliar with technology or the elderly. Therefore, this invention aims to provide personalized reservation responses by analyzing user input information, recognizing emotions, and thereby providing users with a sense of security.

[0149] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0150] In this invention, the server includes an input device for receiving information from a user in voice or text format, a device for analyzing the information and interpreting the user's intent using natural language processing technology, and an emotion recognition device for analyzing the emotional elements of the input information and recognizing emotions. This enables accurate understanding of the user's intent and personalized responses that take their emotions into consideration.

[0151] An "input device" is hardware or software that properly receives information from a user in voice or text format.

[0152] "Natural language processing technology" refers to technologies that enable computers to understand, interpret, and generate human language.

[0153] An "emotion recognition device" is a system that analyzes emotional elements from user input information and recognizes specific emotions.

[0154] A "data storage device" is a storage medium that stores information related to specific dates and times or medical services, and makes it accessible as needed.

[0155] A "notification generator" is a device that generates and provides users with reservation confirmation notifications and personalized responses based on their emotions.

[0156] This invention is a system that receives voice or text input from a user, analyzes it, makes the reservation the user requested, and recognizes the user's emotions to provide a personalized response. The user sends information to the terminal via telephone, messaging service, or instant messaging service. In the case of voice input, the terminal uses speech recognition software to convert the voice to text. Specifically, a speech conversion API may be used for speech recognition.

[0157] The converted text data is sent to the server via a secure communication protocol. The server uses natural language processing techniques to analyze the user's intent. For example, a natural language analysis tool is used in this process. Based on the analysis results, the server identifies the date and time of the entered medical service and accesses the database to check the availability of the appointment. Furthermore, the server uses an emotion recognition engine to analyze the user's emotions. In this system, the functionality provided by the emotion analysis tool is crucial.

[0158] Based on the emotion recognition results, the server generates a reservation confirmation response appropriate to the user's emotional state. For example, if the user is feeling stressed, the server may generate a message such as, "Please relax and wait for your appointment." This message is sent to the terminal and notified to the user.

[0159] For example, if a user types "I want to make an appointment with an orthopedic surgeon this Saturday" into a messaging app and signs of anxiety are detected, the server will make the appointment and return a message saying, "Your appointment is complete. Please come without worry."

[0160] An example of a prompt for a generative AI model might be: "Please tell me what kind of emotionally sensitive message I should provide if a user wants to make an appointment for a specific medical service and is also expressing anxiety."

[0161] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0162] Step 1:

[0163] The user enters the appointment request into the device via phone or messaging service in voice or text format. For example, the user might use a smartphone messaging app to send a request such as, "I would like to make an internal medicine appointment for next Tuesday." The input can be voice or text; if voice, the device performs speech recognition and converts it to text. The output of this step is either the text data converted from the voice or the directly entered text data.

[0164] Step 2:

[0165] The device converts speech to text via a speech recognition API and sends the result to the server. The input is the text data from the previous step, and the output is a reservation request formatted as text. Specifically, the user's voice request is sent to the server as "I would like to make an appointment with the internal medicine department next Tuesday."

[0166] Step 3:

[0167] The server analyzes the received text information using natural language processing technology to clarify the user's reservation intention. A natural language processing engine is used for this purpose. The input is converted text data, and the data processing involves extracting the user's intention. The output is the identification result of the reservation information, medical department, and date desired by the user. Specifically, "Internal Medicine" and "Next Tuesday" are extracted as reservation details.

[0168] Step 4:

[0169] The server uses an emotion recognition engine to analyze the user's emotions from text data. The input is naturally language processed text, and emotion analysis is included in the data's calculations. The output is an emotional judgment of whether the user is tense or relaxed. Specifically, if the analysis indicates a 70% probability of "expressions indicating relaxation," the user is judged to be calm.

[0170] Step 5:

[0171] The server accesses the database and checks the availability of appointment slots based on the extracted reservation details. The input is interpreted reservation information, and the verification process is performed by matching it with the database. The output is confirmed information about available time slots. Specifically, it is confirmed that an appointment slot for internal medicine is available "next Tuesday at 10:00 AM".

[0172] Step 6:

[0173] The server, upon processing the reservation, takes recognized emotions into account and generates a personalized response message. The inputs are reservation confirmation information and emotion assessment, while the output is a customized message. Data processing involves combining reservation details with emotional responses. For example, a message like, "Your internal medicine appointment has been confirmed for next Tuesday at 10:00 AM. Please relax when you come," might be generated.

[0174] Step 7:

[0175] The server notifies the user by sending a generated message to the terminal. The input is the generated response message, and the output is the notification displayed on the user's terminal. Specifically, a notification saying "Reservation complete." is displayed on the user's smartphone.

[0176] (Application Example 2)

[0177] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0178] Traditional reservation systems often fail to take user emotions into account, resulting in users making reservations while experiencing stress and anxiety. This leads to a poor user experience and makes the system difficult to use for the elderly and those unfamiliar with technology. Furthermore, the provision of customized information that addresses emotional needs after a reservation is insufficient.

[0179] 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.

[0180] In this invention, the server includes information exchange means for receiving voice or text input from a user, means for analyzing the input and interpreting the user's intent using natural language processing technology, and analysis means for analyzing the emotional elements of the input and recognizing emotions. This enables the provision of optimal reservation services and related information that take the user's emotions into consideration.

[0181] An "information exchange mechanism" is a function that receives input from users in voice or text format and exchanges information.

[0182] "Natural language processing technology" is a technique that allows computers to interpret human language, understand its intent, and analyze it.

[0183] "Analysis means" refers to the process of detecting the emotional elements of input information, analyzing them, and recognizing them.

[0184] "Data retention means" refers to functions or systems for storing specific date and time and service information, and for verifying their availability.

[0185] A "response generation means" is a technology for communicating bidirectionally with the user and generating appropriate information and responses.

[0186] To implement this invention, the user first inputs information via an information exchange means in either voice or text format. In the case of voice input, the terminal uses a speech recognition engine to convert the voice into text data. This process utilizes speech recognition software such as Google Speech-to-Text. The converted text data is then sent from the terminal to the server.

[0187] The server analyzes the received text data using natural language processing (NLP) techniques. Specifically, it utilizes NLP libraries such as spaCy and NLTK to interpret the user's intent. Next, it uses an emotion analysis engine as an analysis tool to extract the user's emotions from the input data. Software such as IBM Watson® Tone Analyzer is commonly used for this emotion analysis.

[0188] The server uses extracted emotional and intent information to access various databases for reservations using data retention mechanisms, checking the availability of specific dates and times, as well as the required medical services. A SQL-based database system supports this process.

[0189] As a response generation method, the server generates messages confirming the reservation and personalized messages based on the user's emotions. For example, a message such as, "Your internal medicine appointment has been confirmed for next Monday at 10:00 AM. You seem nervous, but please contact us anytime if you have any problems," is generated and sent to the terminal. This provides an environment where users can make reservations with peace of mind.

[0190] As a concrete example, when a user makes a rehabilitation appointment by voice, they might input, "I'd like to book a rehabilitation appointment for next week," and the AI ​​could respond, "You seem nervous, but we'll be waiting for you in good spirits." An example of a prompt to the generative AI model to implement this process would be: "Generate sample code for an application that analyzes the user's emotions from their voice input and generates appropriate suggestions and reassuring messages."

[0191] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0192] Step 1:

[0193] The user inputs either voice or text. The input voice data is received by the terminal and converted into text data via a speech recognition engine. The generated text is then sent to the server.

[0194] Step 2:

[0195] The server receives text data obtained through speech recognition and interprets the user's intent using natural language processing technology. The input text is analyzed, and data processing is performed to understand the user's request. As a result, the user's intent is identified.

[0196] Step 3:

[0197] The server extracts emotions from the analyzed text data using an emotion analysis engine. Based on the text data as input, the emotion engine identifies emotional elements and determines the user's emotional state as output.

[0198] Step 4:

[0199] The server queries the database using data storage methods based on the user's intent and emotional information. Inputs include the date, time, and medical service request, and data calculations are performed to check the availability in the database. As a result, available reservation times are identified.

[0200] Step 5:

[0201] The server determines whether the reservation is confirmed based on availability and uses a response generation mechanism to create a response for the user. Date, time, and sentiment information are provided as input, and a customized message is generated as output. Specifically, the message "Your internal medicine appointment has been confirmed for next Monday at 10:00 AM." is generated.

[0202] Step 6:

[0203] The server sends the generated response message to the terminal, notifying the user. A mechanism operates that directly outputs the message prepared as input to the terminal, ensuring that the user receives the appropriate information.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] [Second Embodiment]

[0208] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0209] 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.

[0210] 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).

[0211] 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.

[0212] 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.

[0213] 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).

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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".

[0220] The system of the present invention is designed to allow users to easily complete medical facility reservations using voice or text input. Embodiments of the present invention are described below.

[0221] The device first receives voice input from the user. In this case, it obtains information in voice or text format using a phone, text messaging service, or instant messaging service. When voice input is received, the device's voice recognition function is used to convert the input into text.

[0222] The server receives text data sent from the terminal. Next, it uses natural language processing technology to analyze the user's intent and identify the desired date and time for the appointment and the medical department. Through this analysis, it understands the user's request, "I would like to make an appointment with the internal medicine department next Monday morning," and extracts the necessary information.

[0223] Next, the server accesses a database of medical facilities to check for availability that matches the user's preferences. The database contains records of available appointment slots for various medical departments and dates, and the server refers to this database to identify the most suitable appointment slot.

[0224] If a reservation slot matching the user's preferences is found, the server sends that information to the terminal to notify the user. The terminal receives the information from the server and either displays a confirmation message or provides an audio notification to the user. For example, the user might receive feedback such as, "Your internal medicine appointment has been confirmed for 10:00 AM next Monday."

[0225] This system also generates reservation reminders and automatically sends notifications to users before the specified date and time to help them remember their reservation details. These notifications are again sent via voice or text through the device.

[0226] In this way, users can easily make hospital appointments via voice or text message. The design of this system significantly improves access to medical facilities and is user-friendly for the elderly and technophobic users.

[0227] The following describes the processing flow.

[0228] Step 1:

[0229] Users make appointment requests via telephone, text messaging services, or instant messaging services. For voice input, users verbally specify their desired department and date / time.

[0230] Step 2:

[0231] The device receives voice input from the user. Using its voice recognition function, it converts the input voice into text and sends that data to the server.

[0232] Step 3:

[0233] The server analyzes the user's intent based on the text data received from the terminal. It uses natural language processing technology to understand the user's request. For example, it interprets an intent such as, "I would like to make an eye doctor appointment for next Tuesday."

[0234] Step 4:

[0235] The server accesses the reservation database based on the user's requested date, time, and medical department. It searches for available appointment slots for the specific date and time and checks their availability.

[0236] Step 5:

[0237] If the server finds an available slot, it confirms the reservation and generates a response with that information. Specifically, it creates a confirmation message that includes the reserved date and time, and information about the medical department.

[0238] Step 6:

[0239] The server sends the generated confirmation message to the terminal.

[0240] Step 7:

[0241] The terminal notifies the user of the confirmation message received from the server. In the case of a text messaging service, it is displayed; in the case of a phone call, it is read aloud.

[0242] Step 8:

[0243] The user reviews the reservation confirmation information they received. If any corrections are needed, they can submit another request.

[0244] Step 9:

[0245] To improve service to users, the server automatically generates a reservation reminder before the scheduled date and time and notifies the user via their device.

[0246] (Example 1)

[0247] 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."

[0248] To provide a system that allows for efficient and easy booking of medical facilities, it is necessary to support a variety of user input formats, accurately interpret user intent, quickly find the optimal booking slot, and notify the user without fail. A system that achieves this process and is easy to use, even for the elderly and those unfamiliar with technology, is essential.

[0249] 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.

[0250] In this invention, the server includes communication means for receiving voice or text input from a user, processing means for analyzing the input and interpreting the user's intent using language recognition technology, and recording device access means for identifying a specified date and time and medical activity, and searching for availability information. This enables users to quickly and accurately make reservations at medical facilities through various input methods and to receive reservation confirmations and reminders.

[0251] A "user" refers to an individual or group that uses the system to make a reservation at a medical facility.

[0252] "Voice or text input" refers to voice or text data used by a user to provide information or instructions to the system.

[0253] "Communication means" refers to devices and services used to transmit user input to a system, such as telephones and messaging services.

[0254] "Language recognition technology" refers to technology that interprets voice and text data entered by a user and analyzes their intent.

[0255] "Processing means" refers to the function in which the system uses programs and logic to analyze user input and derive the information necessary for making a reservation.

[0256] "Recording device access means" refers to a means of accessing a database that stores reservation status and searching for available time slots that match the user's preferences.

[0257] "Response generation means" refers to a function that creates and provides a message to inform the user that the reservation has been completed.

[0258] A "reservation reminder" refers to a reminder function that sends a notification to the user when the reservation date and time are approaching, so that they do not forget their reservation details.

[0259] This invention relates to a system that allows users to efficiently complete medical facility reservations using voice or text input. This system allows users to input information via a device they use on a daily basis.

[0260] First, the device receives voice or text input from the user. In this case, devices such as smartphones and personal computers obtain input through means of communication such as telephone calls, text messaging services, and instant messaging services. In the case of voice input, the device converts the voice into text data using a speech recognition function (for example, a general-purpose speech recognition API).

[0261] Next, the server receives the text data sent from the terminal. The server uses language recognition technology (for example, a general-purpose natural language processing API) to analyze the user's intent. This technology makes it possible to identify specific desired appointment dates and times, as well as medical-related activities.

[0262] The server then accesses the database to search for availability information for the specified date, time, and medical activity. The recording device manages various appointment slots for medical facilities, and the server searches for and identifies an available slot that matches the user's intentions.

[0263] Once a reservation is confirmed, the server uses a response generation mechanism to generate reservation confirmation information and sends it to the terminal. The terminal then notifies the user of a confirmation message, such as "Your reservation is complete," either verbally or in text. Furthermore, it generates a reservation reminder and automatically notifies the user as the scheduled date and time approaches.

[0264] As a concrete example, consider a case where a user voice-inputs, "I would like to make an eye doctor appointment for next Tuesday afternoon." An example of a prompt in this case would be, "I would like to make an eye doctor appointment for next Tuesday afternoon." In this way, the system provides users with an easy way to make appointments at medical facilities, offering convenience especially to the elderly and users who are not tech-savvy.

[0265] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0266] Step 1:

[0267] Users enter their requests for medical facility appointments via voice or text through their device. Input is done via telephone, text messaging service, or instant messaging service. For voice input, the device utilizes its built-in speech recognition function to convert the input voice into text data. This data forms the basis for extracting detailed information about the user's intentions.

[0268] Step 2:

[0269] The terminal sends the converted text data to the server. The server performs natural language processing based on the received text data. Using language recognition technology, the server analyzes the user's desired appointment date and time and medical activities to clarify their intentions. In this process, keywords are extracted from the data and used to accurately understand the user's requests.

[0270] Step 3:

[0271] The server accesses the recording device and searches for available appointment slots that match the user's request. The database records available appointment times for each medical department, and the server processes the data to determine the most suitable appointment slot based on the specified date, time, and medical activity. As a result, available slots are identified.

[0272] Step 4:

[0273] Once a reservation slot is determined, the server generates a response based on that information. The server creates a text or voice message to notify the user that the reservation is confirmed and sends it to the terminal. For example, the message might be in the format, "Your ophthalmology appointment has been confirmed for next Tuesday at 2pm."

[0274] Step 5:

[0275] The terminal transmits the response message received from the server to the user. The user receives confirmation of the reservation via voice or text, thereby knowing that the reservation was made correctly.

[0276] Step 6:

[0277] The server also generates a reservation reminder to automatically notify the user as the reservation date approaches. This reminder has the function of being sent to the user via the device before the specified date and time, helping the user not to forget their reservation.

[0278] (Application Example 1)

[0279] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0280] In modern society, it is particularly important for the elderly and those who require care to smoothly make reservations at medical facilities in order to reduce physical and mental burdens and improve medical access. However, the current reservation system is complex for users who are not familiar with information technology, and there is a problem that the reservation process takes a lot of time and effort. Therefore, there is a demand for a system that can make reservations at medical facilities in a simple and intuitive way and efficiently share the necessary information with care providers.

[0281] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0282] In this invention, the server includes information input / output means for receiving input in the form of voice or text from a user, information processing means for analyzing the input and interpreting the user's intention using natural language processing technology, information search means for identifying a specific date and time and a medical service and checking its availability, and information distribution means for notifying the user that the reservation has been confirmed and providing information to care providers as well. As a result, it is possible to easily make a reservation at a medical facility via voice or text and efficiently notify the user and care providers of the reservation information.

[0283] The "user" refers to an individual who provides input in the form of voice or text and makes a reservation at a medical facility or their supporter.

[0284] The "information input / output means" refers to interface technology for receiving input from a user through a voice recognition function or a messaging service.

[0285] The "information processing means" refers to a technology that performs a process of analyzing and interpreting the input intention of a user by making full use of natural language processing technology.

[0286] The "information retrieval means" refers to a technology for identifying a specific date and time and medical services, and checking the available status that meets the user's requirements among them.

[0287] The "information distribution means" refers to a technology for notifying the user and the care support person of confirmation and reminder information when a reservation is confirmed.

[0288] The "care support person" refers to a person who has the responsibility of managing reservation information and receiving and supporting messages for an individual who needs care.

[0289] To implement this invention, the terminal used by the user is a device such as a smartphone or a care robot. When the user inputs a medical reservation request in voice or text, the terminal receives it. Especially in the case of voice input, the terminal is equipped with a voice recognition function for converting voice into text. Technologies such as Google Cloud Speech-to-Text API can be used.

[0290] The server receives the text data sent from the terminal. Next, it analyzes this text data using natural language processing technology to grasp the user's intention. Natural language processing libraries such as NLTK and spaCy are utilized. Thereby, the date and time and the content of the medical service that the user wants to specify are specified.

[0291] After that, the server accesses the database to check the available slots for the date and time and medical service intended by the user. Information retrieval is performed through a database management system such as MySQL or PostgreSQL. If the necessary information is found, the server confirms the reservation and issues a confirmation notice to the user.

[0292] Furthermore, reservation information is also notified to caregivers using an information distribution method. Notifications are sent in voice or text format using the Twilio SMS API or Firebase Cloud Messaging. The introduction of this system will enable elderly people to intuitively make reservations at medical facilities and will enable efficient information dissemination to caregivers.

[0293] A concrete example of its use is when an elderly person, Ms. A, tells a care robot, "I would like to book an appointment with the orthopedics department next Monday afternoon." Based on this instruction, the system automatically makes the optimal appointment and notifies Ms. A and her caregiver. An example of a prompt to the generating AI model is, "Please explain the process of making a hospital appointment by voice for an elderly person. Please describe in detail how the input data is processed and the steps until the appointment is completed."

[0294] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0295] Step 1:

[0296] The user enters their medical appointment request into the device via voice or text. The entered information is converted to text using the device's voice recognition function (in the case of voice). This converts unstructured voice data into text data.

[0297] Step 2:

[0298] The terminal sends the converted text data to the server. This data transfer delivers the speech-recognized information to the server. Here, the input is text data, and the output is the data sent to the server.

[0299] Step 3:

[0300] Based on the received text data, the server analyzes the user's intention using natural language processing technology. Specifically, NLTK or spaCy is utilized to extract information regarding specific dates and times or medical services from the text data. The input is the text data, and the output is structured data regarding the user's intention.

[0301] Step 4:

[0302] The server uses the structured intention data to access the database and check the availability of reservable dates and services. At this time, a database system such as MySQL or PostgreSQL is utilized for the search. The input is data regarding the user's request, and the output is a set of reservable options.

[0303] Step 5:

[0304] If reservable options are found, the server confirms them and sends a confirmation notice to the terminal. Using the Twilio SMS API or Firebase Cloud Messaging, information is conveyed to the user in voice or text. The input is the reservation option, and the output is the confirmation message.

[0305] Step 6:

[0306] Furthermore, the server notifies the caregiver of the reservation information. This is also done via Twilio or Firebase in the form of a voice or text notification. The input is the finally confirmed reservation information, and the output is the notification to the caregiver.

[0307] Through the above steps, the user can easily make a reservation at a medical facility, and furthermore, the information is appropriately conveyed to the caregiver.

[0308] 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.

[0309] The system of the present invention aims to provide more personalized responses by receiving voice or text input from the user and performing not only reservation but also emotion recognition. Specific embodiments of this invention are described below.

[0310] The device receives voice or text data entered by the user via telephone, text messaging service, or instant messaging service. In the case of voice, the device converts the voice to text and sends that data to the server.

[0311] The server receives data from the terminal and first analyzes the user's intent using natural language processing technology. Next, it uses an emotion engine to analyze the emotional elements of the input voice and text and recognize emotions. For example, if the user's voice sounds tense, the server will detect this and consider appropriate measures.

[0312] Once the emotions are analyzed, the server identifies the user's preferred date, time, and medical department, and accesses the hospital's database to check for available appointments. If the emotion engine detects high levels of stress or anxiety, the server will either connect the user to an operator or adjust its response to indicate that special support is needed.

[0313] If the reservation is successful, the server will generate a reservation confirmation along with a customized message and health advice tailored to the recognized emotions. This response will be sent to the terminal and notified to the user. Specifically, it may include something like, "Your internal medicine appointment has been confirmed for next Monday at 10:00 AM. You seem nervous, but please don't worry. Please contact us anytime if you have any problems."

[0314] This feature allows users to feel more at ease and receive personalized suggestions and support. This system provides an advanced medical appointment system that takes user emotions into consideration, making it easy to use even for users unfamiliar with technology or the elderly.

[0315] The following describes the processing flow.

[0316] Step 1:

[0317] Users enter appointment requests via telephone, text messaging services, or instant messaging services. If using voice input, users dictate the medical department and preferred date and time.

[0318] Step 2:

[0319] The terminal receives the user's voice input and converts it to text using speech recognition technology. In the case of text messages, it sends them to the server in their original format.

[0320] Step 3:

[0321] The server receives data sent from the terminal and first uses natural language processing technology to analyze the user's intent. This identifies the user's request and determines the desired medical department and date / time.

[0322] Step 4:

[0323] The server uses an emotion engine to analyze the emotions contained in the user's voice or text. For example, it can detect tension, stress, anxiety, etc., from the tone of voice and word choice.

[0324] Step 5:

[0325] The server accesses the hospital's database based on the specified medical department and date / time to check availability. If an appointment is possible, it confirms the reservation based on that information.

[0326] Step 6:

[0327] If the emotion engine detects high levels of stress or anxiety, the server will either connect the user to an operator or prepare a customized message to promote reassurance.

[0328] Step 7:

[0329] The server generates and sends a reservation confirmation message and a personalized message based on the user's emotions to the terminal. The message includes information such as the date and time of the reservation and the medical department.

[0330] Step 8:

[0331] The terminal receives messages from the server and notifies the user or reads them aloud.

[0332] Step 9:

[0333] Users review the messages they receive and request corrections if there are any problems with their reservations. In some cases, they may follow the server's advice to gain peace of mind.

[0334] (Example 2)

[0335] 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".

[0336] Conventional reservation systems have struggled to accurately understand user intent and facilitate smooth reservations. Furthermore, they fail to consider user emotions, thus lacking a sense of security and placing a burden on users, especially those unfamiliar with technology or the elderly. Therefore, this invention aims to provide personalized reservation responses by analyzing user input information, recognizing emotions, and thereby providing users with a sense of security.

[0337] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0338] In this invention, the server includes an input device for receiving information from a user in voice or text format, a device for analyzing the information and interpreting the user's intent using natural language processing technology, and an emotion recognition device for analyzing the emotional elements of the input information and recognizing emotions. This enables accurate understanding of the user's intent and personalized responses that take their emotions into consideration.

[0339] An "input device" is hardware or software that properly receives information from a user in voice or text format.

[0340] "Natural language processing technology" refers to technologies that enable computers to understand, interpret, and generate human language.

[0341] An "emotion recognition device" is a system that analyzes emotional elements from user input information and recognizes specific emotions.

[0342] A "data storage device" is a storage medium that stores information related to specific dates and times or medical services, and makes it accessible as needed.

[0343] A "notification generator" is a device that generates and provides users with reservation confirmation notifications and personalized responses based on their emotions.

[0344] This invention is a system that receives voice or text input from a user, analyzes it, makes the reservation the user requested, and recognizes the user's emotions to provide a personalized response. The user sends information to the terminal via telephone, messaging service, or instant messaging service. In the case of voice input, the terminal uses speech recognition software to convert the voice to text. Specifically, a speech conversion API may be used for speech recognition.

[0345] The converted text data is sent to the server via a secure communication protocol. The server uses natural language processing techniques to analyze the user's intent. For example, a natural language analysis tool is used in this process. Based on the analysis results, the server identifies the date and time of the entered medical service and accesses the database to check the availability of the appointment. Furthermore, the server uses an emotion recognition engine to analyze the user's emotions. In this system, the functionality provided by the emotion analysis tool is crucial.

[0346] Based on the emotion recognition results, the server generates a reservation confirmation response appropriate to the user's emotional state. For example, if the user is feeling stressed, the server may generate a message such as, "Please relax and wait for your appointment." This message is sent to the terminal and notified to the user.

[0347] For example, if a user types "I want to make an appointment with an orthopedic surgeon this Saturday" into a messaging app and signs of anxiety are detected, the server will make the appointment and return a message saying, "Your appointment is complete. Please come without worry."

[0348] An example of a prompt for a generative AI model might be: "Please tell me what kind of emotionally sensitive message I should provide if a user wants to make an appointment for a specific medical service and is also expressing anxiety."

[0349] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0350] Step 1:

[0351] The user enters the appointment request into the device via phone or messaging service in voice or text format. For example, the user might use a smartphone messaging app to send a request such as, "I would like to make an internal medicine appointment for next Tuesday." The input can be voice or text; if voice, the device performs speech recognition and converts it to text. The output of this step is either the text data converted from the voice or the directly entered text data.

[0352] Step 2:

[0353] The device converts speech to text via a speech recognition API and sends the result to the server. The input is the text data from the previous step, and the output is a reservation request formatted as text. Specifically, the user's voice request is sent to the server as "I would like to make an appointment with the internal medicine department next Tuesday."

[0354] Step 3:

[0355] The server analyzes the received text information using natural language processing technology to clarify the user's reservation intention. A natural language processing engine is used for this purpose. The input is converted text data, and the data processing involves extracting the user's intention. The output is the identification result of the reservation information, medical department, and date desired by the user. Specifically, "Internal Medicine" and "Next Tuesday" are extracted as reservation details.

[0356] Step 4:

[0357] The server uses an emotion recognition engine to analyze the user's emotions from text data. The input is naturally language processed text, and emotion analysis is included in the data's calculations. The output is an emotional judgment of whether the user is tense or relaxed. Specifically, if the analysis indicates a 70% probability of "expressions indicating relaxation," the user is judged to be calm.

[0358] Step 5:

[0359] The server accesses the database and checks the availability of appointment slots based on the extracted reservation details. The input is interpreted reservation information, and the verification process is performed by matching it with the database. The output is confirmed information about available time slots. Specifically, it is confirmed that an appointment slot for internal medicine is available "next Tuesday at 10:00 AM".

[0360] Step 6:

[0361] The server, upon processing the reservation, takes recognized emotions into account and generates a personalized response message. The inputs are reservation confirmation information and emotion assessment, while the output is a customized message. Data processing involves combining reservation details with emotional responses. For example, a message like, "Your internal medicine appointment has been confirmed for next Tuesday at 10:00 AM. Please relax when you come," might be generated.

[0362] Step 7:

[0363] The server notifies the user by sending a generated message to the terminal. The input is the generated response message, and the output is the notification displayed on the user's terminal. Specifically, a notification saying "Reservation complete." is displayed on the user's smartphone.

[0364] (Application Example 2)

[0365] 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."

[0366] Traditional reservation systems often fail to take user emotions into account, resulting in users making reservations while experiencing stress and anxiety. This leads to a poor user experience and makes the system difficult to use for the elderly and those unfamiliar with technology. Furthermore, the provision of customized information that addresses emotional needs after a reservation is insufficient.

[0367] 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.

[0368] In this invention, the server includes information exchange means for receiving voice or text input from a user, means for analyzing the input and interpreting the user's intent using natural language processing technology, and analysis means for analyzing the emotional elements of the input and recognizing emotions. This enables the provision of optimal reservation services and related information that take the user's emotions into consideration.

[0369] An "information exchange mechanism" is a function that receives input from users in voice or text format and exchanges information.

[0370] "Natural language processing technology" is a technique that allows computers to interpret human language, understand its intent, and analyze it.

[0371] "Analysis means" refers to the process of detecting the emotional elements of input information, analyzing them, and recognizing them.

[0372] "Data retention means" refers to functions or systems for storing specific date and time and service information, and for verifying their availability.

[0373] A "response generation means" is a technology for communicating bidirectionally with the user and generating appropriate information and responses.

[0374] To implement this invention, the user first inputs information via an information exchange means in either voice or text format. In the case of voice input, the terminal uses a speech recognition engine to convert the voice into text data. This process utilizes speech recognition software such as Google Speech-to-Text. The converted text data is then sent from the terminal to the server.

[0375] The server analyzes the received text data using natural language processing (NLP) techniques. Specifically, it utilizes NLP libraries such as spaCy and NLTK to interpret the user's intent. Next, it uses a sentiment analysis engine as an analysis tool to extract the user's emotions from the input data. Software such as IBM Watson Tone Analyzer is commonly used for this sentiment analysis.

[0376] The server uses extracted emotional and intent information to access various databases for reservations using data retention mechanisms, checking the availability of specific dates and times, as well as the required medical services. A SQL-based database system supports this process.

[0377] As a response generation method, the server generates messages confirming the reservation and personalized messages based on the user's emotions. For example, a message such as, "Your internal medicine appointment has been confirmed for next Monday at 10:00 AM. You seem nervous, but please contact us anytime if you have any problems," is generated and sent to the terminal. This provides an environment where users can make reservations with peace of mind.

[0378] As a concrete example, when a user makes a rehabilitation appointment by voice, they might input, "I'd like to book a rehabilitation appointment for next week," and the AI ​​could respond, "You seem nervous, but we'll be waiting for you in good spirits." An example of a prompt to the generative AI model to implement this process would be: "Generate sample code for an application that analyzes the user's emotions from their voice input and generates appropriate suggestions and reassuring messages."

[0379] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0380] Step 1:

[0381] The user inputs either voice or text. The input voice data is received by the terminal and converted into text data via a speech recognition engine. The generated text is then sent to the server.

[0382] Step 2:

[0383] The server receives text data obtained through speech recognition and interprets the user's intent using natural language processing technology. The input text is analyzed, and data processing is performed to understand the user's request. As a result, the user's intent is identified.

[0384] Step 3:

[0385] The server extracts emotions from the analyzed text data using an emotion analysis engine. Based on the text data as input, the emotion engine identifies emotional elements and determines the user's emotional state as output.

[0386] Step 4:

[0387] The server queries the database using data storage methods based on the user's intent and emotional information. Inputs include the date, time, and medical service request, and data calculations are performed to check the availability in the database. As a result, available reservation times are identified.

[0388] Step 5:

[0389] The server determines whether the reservation is confirmed based on availability and uses a response generation mechanism to create a response for the user. Date, time, and sentiment information are provided as input, and a customized message is generated as output. Specifically, the message "Your internal medicine appointment has been confirmed for next Monday at 10:00 AM." is generated.

[0390] Step 6:

[0391] The server sends the generated response message to the terminal, notifying the user. A mechanism operates that directly outputs the message prepared as input to the terminal, ensuring that the user receives the appropriate information.

[0392] 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.

[0393] 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.

[0394] 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.

[0395] [Third Embodiment]

[0396] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0397] 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.

[0398] 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).

[0399] 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.

[0400] 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.

[0401] 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).

[0402] 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.

[0403] 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.

[0404] 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.

[0405] 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.

[0406] 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.

[0407] 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".

[0408] The system of the present invention is designed to allow users to easily complete medical facility reservations using voice or text input. Embodiments of the present invention are described below.

[0409] The device first receives voice input from the user. In this case, it obtains information in voice or text format using a phone, text messaging service, or instant messaging service. When voice input is received, the device's voice recognition function is used to convert the input into text.

[0410] The server receives text data sent from the terminal. Next, it uses natural language processing technology to analyze the user's intent and identify the desired date and time for the appointment and the medical department. Through this analysis, it understands the user's request, "I would like to make an appointment with the internal medicine department next Monday morning," and extracts the necessary information.

[0411] Next, the server accesses a database of medical facilities to check for availability that matches the user's preferences. The database contains records of available appointment slots for various medical departments and dates, and the server refers to this database to identify the most suitable appointment slot.

[0412] If a reservation slot matching the user's preferences is found, the server sends that information to the terminal to notify the user. The terminal receives the information from the server and either displays a confirmation message or provides an audio notification to the user. For example, the user might receive feedback such as, "Your internal medicine appointment has been confirmed for 10:00 AM next Monday."

[0413] This system also generates reservation reminders and automatically sends notifications to users before the specified date and time to help them remember their reservation details. These notifications are again sent via voice or text through the device.

[0414] In this way, users can easily make hospital appointments via voice or text message. The design of this system significantly improves access to medical facilities and is user-friendly for the elderly and technophobic users.

[0415] The following describes the processing flow.

[0416] Step 1:

[0417] Users make appointment requests via telephone, text messaging services, or instant messaging services. For voice input, users verbally specify their desired department and date / time.

[0418] Step 2:

[0419] The device receives voice input from the user. Using its voice recognition function, it converts the input voice into text and sends that data to the server.

[0420] Step 3:

[0421] The server analyzes the user's intent based on the text data received from the terminal. It uses natural language processing technology to understand the user's request. For example, it interprets an intent such as, "I would like to make an eye doctor appointment for next Tuesday."

[0422] Step 4:

[0423] The server accesses the reservation database based on the user's requested date, time, and medical department. It searches for available appointment slots for the specific date and time and checks their availability.

[0424] Step 5:

[0425] If the server finds an available slot, it confirms the reservation and generates a response with that information. Specifically, it creates a confirmation message that includes the reserved date and time, and information about the medical department.

[0426] Step 6:

[0427] The server sends the generated confirmation message to the terminal.

[0428] Step 7:

[0429] The terminal notifies the user of the confirmation message received from the server. In the case of a text messaging service, it is displayed; in the case of a phone call, it is read aloud.

[0430] Step 8:

[0431] The user reviews the reservation confirmation information they received. If any corrections are needed, they can submit another request.

[0432] Step 9:

[0433] To improve service to users, the server automatically generates a reservation reminder before the scheduled date and time and notifies the user via their device.

[0434] (Example 1)

[0435] 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."

[0436] To provide a system that allows for efficient and easy booking of medical facilities, it is necessary to support a variety of user input formats, accurately interpret user intent, quickly find the optimal booking slot, and notify the user without fail. A system that achieves this process and is easy to use, even for the elderly and those unfamiliar with technology, is essential.

[0437] 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.

[0438] In this invention, the server includes communication means for receiving voice or text input from a user, processing means for analyzing the input and interpreting the user's intent using language recognition technology, and recording device access means for identifying a specified date and time and medical activity, and searching for availability information. This enables users to quickly and accurately make reservations at medical facilities through various input methods and to receive reservation confirmations and reminders.

[0439] A "user" refers to an individual or group that uses the system to make a reservation at a medical facility.

[0440] "Voice or text input" refers to voice or text data used by a user to provide information or instructions to the system.

[0441] "Communication means" refers to devices and services used to transmit user input to a system, such as telephones and messaging services.

[0442] "Language recognition technology" refers to technology that interprets voice and text data entered by a user and analyzes their intent.

[0443] "Processing means" refers to the function in which the system uses programs and logic to analyze user input and derive the information necessary for making a reservation.

[0444] "Recording device access means" refers to a means of accessing a database that stores reservation status and searching for available time slots that match the user's preferences.

[0445] "Response generation means" refers to a function that creates and provides a message to inform the user that the reservation has been completed.

[0446] A "reservation reminder" refers to a reminder function that sends a notification to the user when the reservation date and time are approaching, so that they do not forget their reservation details.

[0447] This invention relates to a system that allows users to efficiently complete medical facility reservations using voice or text input. This system allows users to input information via a device they use on a daily basis.

[0448] First, the device receives voice or text input from the user. In this case, devices such as smartphones and personal computers obtain input through means of communication such as telephone calls, text messaging services, and instant messaging services. In the case of voice input, the device converts the voice into text data using a speech recognition function (for example, a general-purpose speech recognition API).

[0449] Next, the server receives the text data sent from the terminal. The server uses language recognition technology (for example, a general-purpose natural language processing API) to analyze the user's intent. This technology makes it possible to identify specific desired appointment dates and times, as well as medical-related activities.

[0450] The server then accesses the database to search for availability information for the specified date, time, and medical activity. The recording device manages various appointment slots for medical facilities, and the server searches for and identifies an available slot that matches the user's intentions.

[0451] Once a reservation is confirmed, the server uses a response generation mechanism to generate reservation confirmation information and sends it to the terminal. The terminal then notifies the user of a confirmation message, such as "Your reservation is complete," either verbally or in text. Furthermore, it generates a reservation reminder and automatically notifies the user as the scheduled date and time approaches.

[0452] As a concrete example, consider a case where a user voice-inputs, "I would like to make an eye doctor appointment for next Tuesday afternoon." An example of a prompt in this case would be, "I would like to make an eye doctor appointment for next Tuesday afternoon." In this way, the system provides users with an easy way to make appointments at medical facilities, offering convenience especially to the elderly and users who are not tech-savvy.

[0453] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0454] Step 1:

[0455] Users enter their requests for medical facility appointments via voice or text through their device. Input is done via telephone, text messaging service, or instant messaging service. For voice input, the device utilizes its built-in speech recognition function to convert the input voice into text data. This data forms the basis for extracting detailed information about the user's intentions.

[0456] Step 2:

[0457] The terminal sends the converted text data to the server. The server performs natural language processing based on the received text data. Using language recognition technology, the server analyzes the user's desired appointment date and time and medical activities to clarify their intentions. In this process, keywords are extracted from the data and used to accurately understand the user's requests.

[0458] Step 3:

[0459] The server accesses the recording device and searches for available appointment slots that match the user's request. The database records available appointment times for each medical department, and the server processes the data to determine the most suitable appointment slot based on the specified date, time, and medical activity. As a result, available slots are identified.

[0460] Step 4:

[0461] Once a reservation slot is determined, the server generates a response based on that information. The server creates a text or voice message to notify the user that the reservation is confirmed and sends it to the terminal. For example, the message might be in the format, "Your ophthalmology appointment has been confirmed for next Tuesday at 2pm."

[0462] Step 5:

[0463] The terminal transmits the response message received from the server to the user. The user receives confirmation of the reservation via voice or text, thereby knowing that the reservation was made correctly.

[0464] Step 6:

[0465] The server also generates a reservation reminder to automatically notify the user as the reservation date approaches. This reminder has the function of being sent to the user via the device before the specified date and time, helping the user not to forget their reservation.

[0466] (Application Example 1)

[0467] 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."

[0468] In modern society, it is crucial for elderly people and those requiring care to be able to easily make appointments at medical facilities in order to reduce physical and mental burdens and improve access to healthcare. However, current appointment systems are complex for users unfamiliar with information technology, and the booking process is time-consuming and cumbersome. Therefore, there is a need for a system that allows for easy and intuitive booking of medical facilities and efficiently shares necessary information with caregivers.

[0469] 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.

[0470] In this invention, the server includes information input / output means for receiving voice or text input from a user; information processing means for analyzing the input and interpreting the user's intent using natural language processing technology; information retrieval means for identifying a specific date and time and medical service and verifying its availability; and information distribution means for notifying the user that the reservation has been confirmed and providing information to caregivers. This makes it possible to easily make reservations at medical facilities via voice or text and to efficiently notify users and caregivers of the reservation information.

[0471] "User" refers to an individual or their assistant who provides input in voice or text format to make a reservation at a medical facility.

[0472] "Information input / output means" refers to interface technologies for receiving user input through voice recognition functions and messaging services.

[0473] "Information processing means" refers to technologies that utilize natural language processing techniques to analyze and interpret the user's input intent.

[0474] "Information retrieval means" refers to technology for identifying specific dates, times, and medical services, and checking their availability to meet the user's requirements.

[0475] "Information distribution means" refers to technology used to notify users and caregivers of confirmation and reminder information when a reservation is confirmed.

[0476] A "care support provider" refers to a person responsible for managing reservation information and receiving messages to provide support to individuals who require care.

[0477] To implement this invention, the terminal used by the user is a device such as a smartphone or a caregiving robot. The terminal receives the request for a medical appointment when the user inputs it via voice or text. In particular, in the case of voice input, the terminal is equipped with a speech recognition function that converts speech to text. Technologies such as the Google Cloud Speech-to-Text API can be used.

[0478] The server receives text data sent from the terminal. Next, it analyzes this text data using natural language processing techniques to understand the user's intent. Natural language processing libraries such as NLTK and spaCy are utilized. This allows the server to identify the date and time the user wants to specify, as well as the details of the medical service.

[0479] The server then accesses the database to check for the user's desired date and time and the availability of medical services. It searches for information through database management systems such as MySQL or PostgreSQL. If the necessary information is found, the server confirms the reservation and issues a confirmation notice to the user.

[0480] Furthermore, reservation information is also notified to caregivers using an information distribution method. Notifications are sent in voice or text format using the Twilio SMS API or Firebase Cloud Messaging. The introduction of this system will enable elderly people to intuitively make reservations at medical facilities and will enable efficient information dissemination to caregivers.

[0481] A concrete example of its use is when an elderly person, Ms. A, tells a care robot, "I would like to book an appointment with the orthopedics department next Monday afternoon." Based on this instruction, the system automatically makes the optimal appointment and notifies Ms. A and her caregiver. An example of a prompt to the generating AI model is, "Please explain the process of making a hospital appointment by voice for an elderly person. Please describe in detail how the input data is processed and the steps until the appointment is completed."

[0482] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0483] Step 1:

[0484] The user enters their medical appointment request into the device via voice or text. The entered information is converted to text using the device's voice recognition function (in the case of voice). This converts unstructured voice data into text data.

[0485] Step 2:

[0486] The terminal sends the converted text data to the server. This data transfer delivers the speech-recognized information to the server. Here, the input is text data, and the output is the data sent to the server.

[0487] Step 3:

[0488] The server analyzes the user's intent based on the received text data using natural language processing techniques. Specifically, it uses NLTK and spaCy to extract information about specific dates, times, and medical services from the text data. The input is text data, and the output is structured data related to the user's intent.

[0489] Step 4:

[0490] The server uses structured intent data to access the database and check available dates, times, and service availability. It utilizes database systems such as MySQL or PostgreSQL for this search. The input is data related to the user's request, and the output is a set of available reservation options.

[0491] Step 5:

[0492] If a reservable option is found, the server confirms it and sends a confirmation notification to the device. The information is then communicated to the user via voice or text using the Twilio SMS API or Firebase Cloud Messaging. The input is the reservation option, and the output is the confirmation message.

[0493] Step 6:

[0494] Furthermore, the server notifies caregivers of the reservation information. This notification is also done via Twilio or Firebase, either in voice or text format. The input is the final confirmed reservation information, and the output is the notification to the caregiver.

[0495] Through the steps described above, users can easily make reservations at medical facilities, and this information is also appropriately communicated to caregivers.

[0496] 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.

[0497] The system of the present invention aims to provide more personalized responses by receiving voice or text input from the user and performing not only reservation but also emotion recognition. Specific embodiments of this invention are described below.

[0498] The device receives voice or text data entered by the user via telephone, text messaging service, or instant messaging service. In the case of voice, the device converts the voice to text and sends that data to the server.

[0499] The server receives data from the terminal and first analyzes the user's intent using natural language processing technology. Next, it uses an emotion engine to analyze the emotional elements of the input voice and text and recognize emotions. For example, if the user's voice sounds tense, the server will detect this and consider appropriate measures.

[0500] Once the emotions are analyzed, the server identifies the user's preferred date, time, and medical department, and accesses the hospital's database to check for available appointments. If the emotion engine detects high levels of stress or anxiety, the server will either connect the user to an operator or adjust its response to indicate that special support is needed.

[0501] If the reservation is successful, the server will generate a reservation confirmation along with a customized message and health advice tailored to the recognized emotions. This response will be sent to the terminal and notified to the user. Specifically, it may include something like, "Your internal medicine appointment has been confirmed for next Monday at 10:00 AM. You seem nervous, but please don't worry. Please contact us anytime if you have any problems."

[0502] This feature allows users to feel more at ease and receive personalized suggestions and support. This system provides an advanced medical appointment system that takes user emotions into consideration, making it easy to use even for users unfamiliar with technology or the elderly.

[0503] The following describes the processing flow.

[0504] Step 1:

[0505] Users enter appointment requests via telephone, text messaging services, or instant messaging services. If using voice input, users dictate the medical department and preferred date and time.

[0506] Step 2:

[0507] The terminal receives the user's voice input and converts it to text using speech recognition technology. In the case of text messages, it sends them to the server in their original format.

[0508] Step 3:

[0509] The server receives data sent from the terminal and first uses natural language processing technology to analyze the user's intent. This identifies the user's request and determines the desired medical department and date / time.

[0510] Step 4:

[0511] The server uses an emotion engine to analyze the emotions contained in the user's voice or text. For example, it can detect tension, stress, anxiety, etc., from the tone of voice and word choice.

[0512] Step 5:

[0513] The server accesses the hospital's database based on the specified medical department and date / time to check availability. If an appointment is possible, it confirms the reservation based on that information.

[0514] Step 6:

[0515] If the emotion engine detects high levels of stress or anxiety, the server will either connect the user to an operator or prepare a customized message to promote reassurance.

[0516] Step 7:

[0517] The server generates and sends a reservation confirmation message and a personalized message based on the user's emotions to the terminal. The message includes information such as the date and time of the reservation and the medical department.

[0518] Step 8:

[0519] The terminal receives messages from the server and notifies the user or reads them aloud.

[0520] Step 9:

[0521] Users review the messages they receive and request corrections if there are any problems with their reservations. In some cases, they may follow the server's advice to gain peace of mind.

[0522] (Example 2)

[0523] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0524] Conventional reservation systems have struggled to accurately understand user intent and facilitate smooth reservations. Furthermore, they fail to consider user emotions, thus lacking a sense of security and placing a burden on users, especially those unfamiliar with technology or the elderly. Therefore, this invention aims to provide personalized reservation responses by analyzing user input information, recognizing emotions, and thereby providing users with a sense of security.

[0525] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0526] In this invention, the server includes an input device for receiving information from a user in voice or text format, a device for analyzing the information and interpreting the user's intent using natural language processing technology, and an emotion recognition device for analyzing the emotional elements of the input information and recognizing emotions. This enables accurate understanding of the user's intent and personalized responses that take their emotions into consideration.

[0527] An "input device" is hardware or software that properly receives information from a user in voice or text format.

[0528] "Natural language processing technology" refers to technologies that enable computers to understand, interpret, and generate human language.

[0529] An "emotion recognition device" is a system that analyzes emotional elements from user input information and recognizes specific emotions.

[0530] A "data storage device" is a storage medium that stores information related to specific dates and times or medical services, and makes it accessible as needed.

[0531] A "notification generator" is a device that generates and provides users with reservation confirmation notifications and personalized responses based on their emotions.

[0532] This invention is a system that receives voice or text input from a user, analyzes it, makes the reservation the user requested, and recognizes the user's emotions to provide a personalized response. The user sends information to the terminal via telephone, messaging service, or instant messaging service. In the case of voice input, the terminal uses speech recognition software to convert the voice to text. Specifically, a speech conversion API may be used for speech recognition.

[0533] The converted text data is sent to the server via a secure communication protocol. The server uses natural language processing techniques to analyze the user's intent. For example, a natural language analysis tool is used in this process. Based on the analysis results, the server identifies the date and time of the entered medical service and accesses the database to check the availability of the appointment. Furthermore, the server uses an emotion recognition engine to analyze the user's emotions. In this system, the functionality provided by the emotion analysis tool is crucial.

[0534] Based on the emotion recognition results, the server generates a reservation confirmation response appropriate to the user's emotional state. For example, if the user is feeling stressed, the server may generate a message such as, "Please relax and wait for your appointment." This message is sent to the terminal and notified to the user.

[0535] For example, if a user types "I want to make an appointment with an orthopedic surgeon this Saturday" into a messaging app and signs of anxiety are detected, the server will make the appointment and return a message saying, "Your appointment is complete. Please come without worry."

[0536] An example of a prompt for a generative AI model might be: "Please tell me what kind of emotionally sensitive message I should provide if a user wants to make an appointment for a specific medical service and is also expressing anxiety."

[0537] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0538] Step 1:

[0539] The user enters the appointment request into the device via phone or messaging service in voice or text format. For example, the user might use a smartphone messaging app to send a request such as, "I would like to make an internal medicine appointment for next Tuesday." The input can be voice or text; if voice, the device performs speech recognition and converts it to text. The output of this step is either the text data converted from the voice or the directly entered text data.

[0540] Step 2:

[0541] The device converts speech to text via a speech recognition API and sends the result to the server. The input is the text data from the previous step, and the output is a reservation request formatted as text. Specifically, the user's voice request is sent to the server as "I would like to make an appointment with the internal medicine department next Tuesday."

[0542] Step 3:

[0543] The server analyzes the received text information using natural language processing technology to clarify the user's reservation intention. A natural language processing engine is used for this purpose. The input is converted text data, and the data processing involves extracting the user's intention. The output is the identification result of the reservation information, medical department, and date desired by the user. Specifically, "Internal Medicine" and "Next Tuesday" are extracted as reservation details.

[0544] Step 4:

[0545] The server uses an emotion recognition engine to analyze the user's emotions from text data. The input is naturally language processed text, and emotion analysis is included in the data's calculations. The output is an emotional judgment of whether the user is tense or relaxed. Specifically, if the analysis indicates a 70% probability of "expressions indicating relaxation," the user is judged to be calm.

[0546] Step 5:

[0547] The server accesses the database and checks the availability of appointment slots based on the extracted reservation details. The input is interpreted reservation information, and the verification process is performed by matching it with the database. The output is confirmed information about available time slots. Specifically, it is confirmed that an appointment slot for internal medicine is available "next Tuesday at 10:00 AM".

[0548] Step 6:

[0549] The server, upon processing the reservation, takes recognized emotions into account and generates a personalized response message. The inputs are reservation confirmation information and emotion assessment, while the output is a customized message. Data processing involves combining reservation details with emotional responses. For example, a message like, "Your internal medicine appointment has been confirmed for next Tuesday at 10:00 AM. Please relax when you come," might be generated.

[0550] Step 7:

[0551] The server notifies the user by sending a generated message to the terminal. The input is the generated response message, and the output is the notification displayed on the user's terminal. Specifically, a notification saying "Reservation complete." is displayed on the user's smartphone.

[0552] (Application Example 2)

[0553] 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."

[0554] Traditional reservation systems often fail to take user emotions into account, resulting in users making reservations while experiencing stress and anxiety. This leads to a poor user experience and makes the system difficult to use for the elderly and those unfamiliar with technology. Furthermore, the provision of customized information that addresses emotional needs after a reservation is insufficient.

[0555] 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.

[0556] In this invention, the server includes information exchange means for receiving voice or text input from a user, means for analyzing the input and interpreting the user's intent using natural language processing technology, and analysis means for analyzing the emotional elements of the input and recognizing emotions. This enables the provision of optimal reservation services and related information that take the user's emotions into consideration.

[0557] An "information exchange mechanism" is a function that receives input from users in voice or text format and exchanges information.

[0558] "Natural language processing technology" is a technique that allows computers to interpret human language, understand its intent, and analyze it.

[0559] "Analysis means" refers to the process of detecting the emotional elements of input information, analyzing them, and recognizing them.

[0560] "Data retention means" refers to functions or systems for storing specific date and time and service information, and for verifying their availability.

[0561] A "response generation means" is a technology for communicating bidirectionally with the user and generating appropriate information and responses.

[0562] To implement this invention, the user first inputs information via an information exchange means in either voice or text format. In the case of voice input, the terminal uses a speech recognition engine to convert the voice into text data. This process utilizes speech recognition software such as Google Speech-to-Text. The converted text data is then sent from the terminal to the server.

[0563] The server analyzes the received text data using natural language processing (NLP) techniques. Specifically, it utilizes NLP libraries such as spaCy and NLTK to interpret the user's intent. Next, it uses a sentiment analysis engine as an analysis tool to extract the user's emotions from the input data. Software such as IBM Watson Tone Analyzer is commonly used for this sentiment analysis.

[0564] The server uses extracted emotional and intent information to access various databases for reservations using data retention mechanisms, checking the availability of specific dates and times, as well as the required medical services. A SQL-based database system supports this process.

[0565] As a response generation method, the server generates messages confirming the reservation and personalized messages based on the user's emotions. For example, a message such as, "Your internal medicine appointment has been confirmed for next Monday at 10:00 AM. You seem nervous, but please contact us anytime if you have any problems," is generated and sent to the terminal. This provides an environment where users can make reservations with peace of mind.

[0566] As a concrete example, when a user makes a rehabilitation appointment by voice, they might input, "I'd like to book a rehabilitation appointment for next week," and the AI ​​could respond, "You seem nervous, but we'll be waiting for you in good spirits." An example of a prompt to the generative AI model to implement this process would be: "Generate sample code for an application that analyzes the user's emotions from their voice input and generates appropriate suggestions and reassuring messages."

[0567] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0568] Step 1:

[0569] The user inputs either voice or text. The input voice data is received by the terminal and converted into text data via a speech recognition engine. The generated text is then sent to the server.

[0570] Step 2:

[0571] The server receives text data obtained through speech recognition and interprets the user's intent using natural language processing technology. The input text is analyzed, and data processing is performed to understand the user's request. As a result, the user's intent is identified.

[0572] Step 3:

[0573] The server extracts emotions from the analyzed text data using an emotion analysis engine. Based on the text data as input, the emotion engine identifies emotional elements and determines the user's emotional state as output.

[0574] Step 4:

[0575] The server queries the database using data storage methods based on the user's intent and emotional information. Inputs include the date, time, and medical service request, and data calculations are performed to check the availability in the database. As a result, available reservation times are identified.

[0576] Step 5:

[0577] The server determines whether the reservation is confirmed based on availability and uses a response generation mechanism to create a response for the user. Date, time, and sentiment information are provided as input, and a customized message is generated as output. Specifically, the message "Your internal medicine appointment has been confirmed for next Monday at 10:00 AM." is generated.

[0578] Step 6:

[0579] The server sends the generated response message to the terminal, notifying the user. A mechanism operates that directly outputs the message prepared as input to the terminal, ensuring that the user receives the appropriate information.

[0580] 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.

[0581] 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.

[0582] 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.

[0583] [Fourth Embodiment]

[0584] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0585] 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.

[0586] 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).

[0587] 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.

[0588] 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.

[0589] 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).

[0590] 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.

[0591] 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.

[0592] 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.

[0593] 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.

[0594] 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.

[0595] 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.

[0596] 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".

[0597] The system of the present invention is designed to allow users to easily complete medical facility reservations using voice or text input. Embodiments of the present invention are described below.

[0598] The device first receives voice input from the user. In this case, it obtains information in voice or text format using a phone, text messaging service, or instant messaging service. When voice input is received, the device's voice recognition function is used to convert the input into text.

[0599] The server receives text data sent from the terminal. Next, it uses natural language processing technology to analyze the user's intent and identify the desired date and time for the appointment and the medical department. Through this analysis, it understands the user's request, "I would like to make an appointment with the internal medicine department next Monday morning," and extracts the necessary information.

[0600] Next, the server accesses a database of medical facilities to check for availability that matches the user's preferences. The database contains records of available appointment slots for various medical departments and dates, and the server refers to this database to identify the most suitable appointment slot.

[0601] If a reservation slot matching the user's preferences is found, the server sends that information to the terminal to notify the user. The terminal receives the information from the server and either displays a confirmation message or provides an audio notification to the user. For example, the user might receive feedback such as, "Your internal medicine appointment has been confirmed for 10:00 AM next Monday."

[0602] This system also generates reservation reminders and automatically sends notifications to users before the specified date and time to help them remember their reservation details. These notifications are again sent via voice or text through the device.

[0603] In this way, users can easily make hospital appointments via voice or text message. The design of this system significantly improves access to medical facilities and is user-friendly for the elderly and technophobic users.

[0604] The following describes the processing flow.

[0605] Step 1:

[0606] Users make appointment requests via telephone, text messaging services, or instant messaging services. For voice input, users verbally specify their desired department and date / time.

[0607] Step 2:

[0608] The device receives voice input from the user. Using its voice recognition function, it converts the input voice into text and sends that data to the server.

[0609] Step 3:

[0610] The server analyzes the user's intent based on the text data received from the terminal. It uses natural language processing technology to understand the user's request. For example, it interprets an intent such as, "I would like to make an eye doctor appointment for next Tuesday."

[0611] Step 4:

[0612] The server accesses the reservation database based on the user's requested date, time, and medical department. It searches for available appointment slots for the specific date and time and checks their availability.

[0613] Step 5:

[0614] If the server finds an available slot, it confirms the reservation and generates a response with that information. Specifically, it creates a confirmation message that includes the reserved date and time, and information about the medical department.

[0615] Step 6:

[0616] The server sends the generated confirmation message to the terminal.

[0617] Step 7:

[0618] The terminal notifies the user of the confirmation message received from the server. In the case of a text messaging service, it is displayed; in the case of a phone call, it is read aloud.

[0619] Step 8:

[0620] The user reviews the reservation confirmation information they received. If any corrections are needed, they can submit another request.

[0621] Step 9:

[0622] To improve service to users, the server automatically generates a reservation reminder before the scheduled date and time and notifies the user via their device.

[0623] (Example 1)

[0624] 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".

[0625] To provide a system that allows for efficient and easy booking of medical facilities, it is necessary to support a variety of user input formats, accurately interpret user intent, quickly find the optimal booking slot, and notify the user without fail. A system that achieves this process and is easy to use, even for the elderly and those unfamiliar with technology, is essential.

[0626] 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.

[0627] In this invention, the server includes communication means for receiving voice or text input from a user, processing means for analyzing the input and interpreting the user's intent using language recognition technology, and recording device access means for identifying a specified date and time and medical activity, and searching for availability information. This enables users to quickly and accurately make reservations at medical facilities through various input methods and to receive reservation confirmations and reminders.

[0628] A "user" refers to an individual or group that uses the system to make a reservation at a medical facility.

[0629] "Voice or text input" refers to voice or text data used by a user to provide information or instructions to the system.

[0630] "Communication means" refers to devices and services used to transmit user input to a system, such as telephones and messaging services.

[0631] "Language recognition technology" refers to technology that interprets voice and text data entered by a user and analyzes their intent.

[0632] "Processing means" refers to the function in which the system uses programs and logic to analyze user input and derive the information necessary for making a reservation.

[0633] "Recording device access means" refers to a means of accessing a database that stores reservation status and searching for available time slots that match the user's preferences.

[0634] "Response generation means" refers to a function that creates and provides a message to inform the user that the reservation has been completed.

[0635] A "reservation reminder" refers to a reminder function that sends a notification to the user when the reservation date and time are approaching, so that they do not forget their reservation details.

[0636] This invention relates to a system that allows users to efficiently complete medical facility reservations using voice or text input. This system allows users to input information via a device they use on a daily basis.

[0637] First, the device receives voice or text input from the user. In this case, devices such as smartphones and personal computers obtain input through means of communication such as telephone calls, text messaging services, and instant messaging services. In the case of voice input, the device converts the voice into text data using a speech recognition function (for example, a general-purpose speech recognition API).

[0638] Next, the server receives the text data sent from the terminal. The server uses language recognition technology (for example, a general-purpose natural language processing API) to analyze the user's intent. This technology makes it possible to identify specific desired appointment dates and times, as well as medical-related activities.

[0639] The server then accesses the database to search for availability information for the specified date, time, and medical activity. The recording device manages various appointment slots for medical facilities, and the server searches for and identifies an available slot that matches the user's intentions.

[0640] Once a reservation is confirmed, the server uses a response generation mechanism to generate reservation confirmation information and sends it to the terminal. The terminal then notifies the user of a confirmation message, such as "Your reservation is complete," either verbally or in text. Furthermore, it generates a reservation reminder and automatically notifies the user as the scheduled date and time approaches.

[0641] As a concrete example, consider a case where a user voice-inputs, "I would like to make an eye doctor appointment for next Tuesday afternoon." An example of a prompt in this case would be, "I would like to make an eye doctor appointment for next Tuesday afternoon." In this way, the system provides users with an easy way to make appointments at medical facilities, offering convenience especially to the elderly and users who are not tech-savvy.

[0642] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0643] Step 1:

[0644] Users enter their requests for medical facility appointments via voice or text through their device. Input is done via telephone, text messaging service, or instant messaging service. For voice input, the device utilizes its built-in speech recognition function to convert the input voice into text data. This data forms the basis for extracting detailed information about the user's intentions.

[0645] Step 2:

[0646] The terminal sends the converted text data to the server. The server performs natural language processing based on the received text data. Using language recognition technology, the server analyzes the user's desired appointment date and time and medical activities to clarify their intentions. In this process, keywords are extracted from the data and used to accurately understand the user's requests.

[0647] Step 3:

[0648] The server accesses the recording device and searches for available appointment slots that match the user's request. The database records available appointment times for each medical department, and the server processes the data to determine the most suitable appointment slot based on the specified date, time, and medical activity. As a result, available slots are identified.

[0649] Step 4:

[0650] Once a reservation slot is determined, the server generates a response based on that information. The server creates a text or voice message to notify the user that the reservation is confirmed and sends it to the terminal. For example, the message might be in the format, "Your ophthalmology appointment has been confirmed for next Tuesday at 2pm."

[0651] Step 5:

[0652] The terminal transmits the response message received from the server to the user. The user receives confirmation of the reservation via voice or text, thereby knowing that the reservation was made correctly.

[0653] Step 6:

[0654] The server also generates a reservation reminder to automatically notify the user as the reservation date approaches. This reminder has the function of being sent to the user via the device before the specified date and time, helping the user not to forget their reservation.

[0655] (Application Example 1)

[0656] 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".

[0657] In modern society, it is crucial for elderly people and those requiring care to be able to easily make appointments at medical facilities in order to reduce physical and mental burdens and improve access to healthcare. However, current appointment systems are complex for users unfamiliar with information technology, and the booking process is time-consuming and cumbersome. Therefore, there is a need for a system that allows for easy and intuitive booking of medical facilities and efficiently shares necessary information with caregivers.

[0658] 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.

[0659] In this invention, the server includes information input / output means for receiving voice or text input from a user; information processing means for analyzing the input and interpreting the user's intent using natural language processing technology; information retrieval means for identifying a specific date and time and medical service and verifying its availability; and information distribution means for notifying the user that the reservation has been confirmed and providing information to caregivers. This makes it possible to easily make reservations at medical facilities via voice or text and to efficiently notify users and caregivers of the reservation information.

[0660] "User" refers to an individual or their assistant who provides input in voice or text format to make a reservation at a medical facility.

[0661] "Information input / output means" refers to interface technologies for receiving user input through voice recognition functions and messaging services.

[0662] "Information processing means" refers to technologies that utilize natural language processing techniques to analyze and interpret the user's input intent.

[0663] "Information retrieval means" refers to technology for identifying specific dates, times, and medical services, and checking their availability to meet the user's requirements.

[0664] "Information distribution means" refers to technology used to notify users and caregivers of confirmation and reminder information when a reservation is confirmed.

[0665] A "care support provider" refers to a person responsible for managing reservation information and receiving messages to provide support to individuals who require care.

[0666] To implement this invention, the terminal used by the user is a device such as a smartphone or a caregiving robot. The terminal receives the request for a medical appointment when the user inputs it via voice or text. In particular, in the case of voice input, the terminal is equipped with a speech recognition function that converts speech to text. Technologies such as the Google Cloud Speech-to-Text API can be used.

[0667] The server receives text data sent from the terminal. Next, it analyzes this text data using natural language processing techniques to understand the user's intent. Natural language processing libraries such as NLTK and spaCy are utilized. This allows the server to identify the date and time the user wants to specify, as well as the details of the medical service.

[0668] The server then accesses the database to check for the user's desired date and time and the availability of medical services. It searches for information through database management systems such as MySQL or PostgreSQL. If the necessary information is found, the server confirms the reservation and issues a confirmation notice to the user.

[0669] Furthermore, reservation information is also notified to caregivers using an information distribution method. Notifications are sent in voice or text format using the Twilio SMS API or Firebase Cloud Messaging. The introduction of this system will enable elderly people to intuitively make reservations at medical facilities and will enable efficient information dissemination to caregivers.

[0670] A concrete example of its use is when an elderly person, Ms. A, tells a care robot, "I would like to book an appointment with the orthopedics department next Monday afternoon." Based on this instruction, the system automatically makes the optimal appointment and notifies Ms. A and her caregiver. An example of a prompt to the generating AI model is, "Please explain the process of making a hospital appointment by voice for an elderly person. Please describe in detail how the input data is processed and the steps until the appointment is completed."

[0671] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0672] Step 1:

[0673] The user enters their medical appointment request into the device via voice or text. The entered information is converted to text using the device's voice recognition function (in the case of voice). This converts unstructured voice data into text data.

[0674] Step 2:

[0675] The terminal sends the converted text data to the server. This data transfer delivers the speech-recognized information to the server. Here, the input is text data, and the output is the data sent to the server.

[0676] Step 3:

[0677] The server analyzes the user's intent based on the received text data using natural language processing techniques. Specifically, it uses NLTK and spaCy to extract information about specific dates, times, and medical services from the text data. The input is text data, and the output is structured data related to the user's intent.

[0678] Step 4:

[0679] The server uses structured intent data to access the database and check available dates, times, and service availability. It utilizes database systems such as MySQL or PostgreSQL for this search. The input is data related to the user's request, and the output is a set of available reservation options.

[0680] Step 5:

[0681] If a reservable option is found, the server confirms it and sends a confirmation notification to the device. The information is then communicated to the user via voice or text using the Twilio SMS API or Firebase Cloud Messaging. The input is the reservation option, and the output is the confirmation message.

[0682] Step 6:

[0683] Furthermore, the server notifies caregivers of the reservation information. This notification is also done via Twilio or Firebase, either in voice or text format. The input is the final confirmed reservation information, and the output is the notification to the caregiver.

[0684] Through the steps described above, users can easily make reservations at medical facilities, and this information is also appropriately communicated to caregivers.

[0685] 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.

[0686] The system of the present invention aims to provide more personalized responses by receiving voice or text input from the user and performing not only reservation but also emotion recognition. Specific embodiments of this invention are described below.

[0687] The device receives voice or text data entered by the user via telephone, text messaging service, or instant messaging service. In the case of voice, the device converts the voice to text and sends that data to the server.

[0688] The server receives data from the terminal and first analyzes the user's intent using natural language processing technology. Next, it uses an emotion engine to analyze the emotional elements of the input voice and text and recognize emotions. For example, if the user's voice sounds tense, the server will detect this and consider appropriate measures.

[0689] Once the emotions are analyzed, the server identifies the user's preferred date, time, and medical department, and accesses the hospital's database to check for available appointments. If the emotion engine detects high levels of stress or anxiety, the server will either connect the user to an operator or adjust its response to indicate that special support is needed.

[0690] If the reservation is successful, the server will generate a reservation confirmation along with a customized message and health advice tailored to the recognized emotions. This response will be sent to the terminal and notified to the user. Specifically, it may include something like, "Your internal medicine appointment has been confirmed for next Monday at 10:00 AM. You seem nervous, but please don't worry. Please contact us anytime if you have any problems."

[0691] This feature allows users to feel more at ease and receive personalized suggestions and support. This system provides an advanced medical appointment system that takes user emotions into consideration, making it easy to use even for users unfamiliar with technology or the elderly.

[0692] The following describes the processing flow.

[0693] Step 1:

[0694] Users enter appointment requests via telephone, text messaging services, or instant messaging services. If using voice input, users dictate the medical department and preferred date and time.

[0695] Step 2:

[0696] The terminal receives the user's voice input and converts it to text using speech recognition technology. In the case of text messages, it sends them to the server in their original format.

[0697] Step 3:

[0698] The server receives data sent from the terminal and first uses natural language processing technology to analyze the user's intent. This identifies the user's request and determines the desired medical department and date / time.

[0699] Step 4:

[0700] The server uses an emotion engine to analyze the emotions contained in the user's voice or text. For example, it can detect tension, stress, anxiety, etc., from the tone of voice and word choice.

[0701] Step 5:

[0702] The server accesses the hospital's database based on the specified medical department and date / time to check availability. If an appointment is possible, it confirms the reservation based on that information.

[0703] Step 6:

[0704] If the emotion engine detects high levels of stress or anxiety, the server will either connect the user to an operator or prepare a customized message to promote reassurance.

[0705] Step 7:

[0706] The server generates and sends a reservation confirmation message and a personalized message based on the user's emotions to the terminal. The message includes information such as the date and time of the reservation and the medical department.

[0707] Step 8:

[0708] The terminal receives messages from the server and notifies the user or reads them aloud.

[0709] Step 9:

[0710] Users review the messages they receive and request corrections if there are any problems with their reservations. In some cases, they may follow the server's advice to gain peace of mind.

[0711] (Example 2)

[0712] 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".

[0713] Conventional reservation systems have struggled to accurately understand user intent and facilitate smooth reservations. Furthermore, they fail to consider user emotions, thus lacking a sense of security and placing a burden on users, especially those unfamiliar with technology or the elderly. Therefore, this invention aims to provide personalized reservation responses by analyzing user input information, recognizing emotions, and thereby providing users with a sense of security.

[0714] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0715] In this invention, the server includes an input device for receiving information from a user in voice or text format, a device for analyzing the information and interpreting the user's intent using natural language processing technology, and an emotion recognition device for analyzing the emotional elements of the input information and recognizing emotions. This enables accurate understanding of the user's intent and personalized responses that take their emotions into consideration.

[0716] An "input device" is hardware or software that properly receives information from a user in voice or text format.

[0717] "Natural language processing technology" refers to technologies that enable computers to understand, interpret, and generate human language.

[0718] An "emotion recognition device" is a system that analyzes emotional elements from user input information and recognizes specific emotions.

[0719] A "data storage device" is a storage medium that stores information related to specific dates and times or medical services, and makes it accessible as needed.

[0720] A "notification generator" is a device that generates and provides users with reservation confirmation notifications and personalized responses based on their emotions.

[0721] This invention is a system that receives voice or text input from a user, analyzes it, makes the reservation the user requested, and recognizes the user's emotions to provide a personalized response. The user sends information to the terminal via telephone, messaging service, or instant messaging service. In the case of voice input, the terminal uses speech recognition software to convert the voice to text. Specifically, a speech conversion API may be used for speech recognition.

[0722] The converted text data is sent to the server via a secure communication protocol. The server uses natural language processing techniques to analyze the user's intent. For example, a natural language analysis tool is used in this process. Based on the analysis results, the server identifies the date and time of the entered medical service and accesses the database to check the availability of the appointment. Furthermore, the server uses an emotion recognition engine to analyze the user's emotions. In this system, the functionality provided by the emotion analysis tool is crucial.

[0723] Based on the emotion recognition results, the server generates a reservation confirmation response appropriate to the user's emotional state. For example, if the user is feeling stressed, the server may generate a message such as, "Please relax and wait for your appointment." This message is sent to the terminal and notified to the user.

[0724] For example, if a user types "I want to make an appointment with an orthopedic surgeon this Saturday" into a messaging app and signs of anxiety are detected, the server will make the appointment and return a message saying, "Your appointment is complete. Please come without worry."

[0725] An example of a prompt for a generative AI model might be: "Please tell me what kind of emotionally sensitive message I should provide if a user wants to make an appointment for a specific medical service and is also expressing anxiety."

[0726] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0727] Step 1:

[0728] The user enters the appointment request into the device via phone or messaging service in voice or text format. For example, the user might use a smartphone messaging app to send a request such as, "I would like to make an internal medicine appointment for next Tuesday." The input can be voice or text; if voice, the device performs speech recognition and converts it to text. The output of this step is either the text data converted from the voice or the directly entered text data.

[0729] Step 2:

[0730] The device converts speech to text via a speech recognition API and sends the result to the server. The input is the text data from the previous step, and the output is a reservation request formatted as text. Specifically, the user's voice request is sent to the server as "I would like to make an appointment with the internal medicine department next Tuesday."

[0731] Step 3:

[0732] The server analyzes the received text information using natural language processing technology to clarify the user's reservation intention. A natural language processing engine is used for this purpose. The input is converted text data, and the data processing involves extracting the user's intention. The output is the identification result of the reservation information, medical department, and date desired by the user. Specifically, "Internal Medicine" and "Next Tuesday" are extracted as reservation details.

[0733] Step 4:

[0734] The server uses an emotion recognition engine to analyze the user's emotions from text data. The input is naturally language processed text, and emotion analysis is included in the data's calculations. The output is an emotional judgment of whether the user is tense or relaxed. Specifically, if the analysis indicates a 70% probability of "expressions indicating relaxation," the user is judged to be calm.

[0735] Step 5:

[0736] The server accesses the database and checks the availability of appointment slots based on the extracted reservation details. The input is interpreted reservation information, and the verification process is performed by matching it with the database. The output is confirmed information about available time slots. Specifically, it is confirmed that an appointment slot for internal medicine is available "next Tuesday at 10:00 AM".

[0737] Step 6:

[0738] The server, upon processing the reservation, takes recognized emotions into account and generates a personalized response message. The inputs are reservation confirmation information and emotion assessment, while the output is a customized message. Data processing involves combining reservation details with emotional responses. For example, a message like, "Your internal medicine appointment has been confirmed for next Tuesday at 10:00 AM. Please relax when you come," might be generated.

[0739] Step 7:

[0740] The server notifies the user by sending a generated message to the terminal. The input is the generated response message, and the output is the notification displayed on the user's terminal. Specifically, a notification saying "Reservation complete." is displayed on the user's smartphone.

[0741] (Application Example 2)

[0742] 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".

[0743] Traditional reservation systems often fail to take user emotions into account, resulting in users making reservations while experiencing stress and anxiety. This leads to a poor user experience and makes the system difficult to use for the elderly and those unfamiliar with technology. Furthermore, the provision of customized information that addresses emotional needs after a reservation is insufficient.

[0744] 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.

[0745] In this invention, the server includes information exchange means for receiving voice or text input from a user, means for analyzing the input and interpreting the user's intent using natural language processing technology, and analysis means for analyzing the emotional elements of the input and recognizing emotions. This enables the provision of optimal reservation services and related information that take the user's emotions into consideration.

[0746] An "information exchange mechanism" is a function that receives input from users in voice or text format and exchanges information.

[0747] "Natural language processing technology" is a technique that allows computers to interpret human language, understand its intent, and analyze it.

[0748] "Analysis means" refers to the process of detecting the emotional elements of input information, analyzing them, and recognizing them.

[0749] "Data retention means" refers to functions or systems for storing specific date and time and service information, and for verifying their availability.

[0750] A "response generation means" is a technology for communicating bidirectionally with the user and generating appropriate information and responses.

[0751] To implement this invention, the user first inputs information via an information exchange means in either voice or text format. In the case of voice input, the terminal uses a speech recognition engine to convert the voice into text data. This process utilizes speech recognition software such as Google Speech-to-Text. The converted text data is then sent from the terminal to the server.

[0752] The server analyzes the received text data using natural language processing (NLP) techniques. Specifically, it utilizes NLP libraries such as spaCy and NLTK to interpret the user's intent. Next, it uses a sentiment analysis engine as an analysis tool to extract the user's emotions from the input data. Software such as IBM Watson Tone Analyzer is commonly used for this sentiment analysis.

[0753] The server uses extracted emotional and intent information to access various databases for reservations using data retention mechanisms, checking the availability of specific dates and times, as well as the required medical services. A SQL-based database system supports this process.

[0754] As a response generation method, the server generates messages confirming the reservation and personalized messages based on the user's emotions. For example, a message such as, "Your internal medicine appointment has been confirmed for next Monday at 10:00 AM. You seem nervous, but please contact us anytime if you have any problems," is generated and sent to the terminal. This provides an environment where users can make reservations with peace of mind.

[0755] As a concrete example, when a user makes a rehabilitation appointment by voice, they might input, "I'd like to book a rehabilitation appointment for next week," and the AI ​​could respond, "You seem nervous, but we'll be waiting for you in good spirits." An example of a prompt to the generative AI model to implement this process would be: "Generate sample code for an application that analyzes the user's emotions from their voice input and generates appropriate suggestions and reassuring messages."

[0756] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0757] Step 1:

[0758] The user inputs either voice or text. The input voice data is received by the terminal and converted into text data via a speech recognition engine. The generated text is then sent to the server.

[0759] Step 2:

[0760] The server receives text data obtained through speech recognition and interprets the user's intent using natural language processing technology. The input text is analyzed, and data processing is performed to understand the user's request. As a result, the user's intent is identified.

[0761] Step 3:

[0762] The server extracts emotions from the analyzed text data using an emotion analysis engine. Based on the text data as input, the emotion engine identifies emotional elements and determines the user's emotional state as output.

[0763] Step 4:

[0764] The server queries the database using data storage methods based on the user's intent and emotional information. Inputs include the date, time, and medical service request, and data calculations are performed to check the availability in the database. As a result, available reservation times are identified.

[0765] Step 5:

[0766] The server determines whether the reservation is confirmed based on availability and uses a response generation mechanism to create a response for the user. Date, time, and sentiment information are provided as input, and a customized message is generated as output. Specifically, the message "Your internal medicine appointment has been confirmed for next Monday at 10:00 AM." is generated.

[0767] Step 6:

[0768] The server sends the generated response message to the terminal, notifying the user. A mechanism operates that directly outputs the message prepared as input to the terminal, ensuring that the user receives the appropriate information.

[0769] 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.

[0770] 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.

[0771] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0772] 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.

[0773] 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.

[0774] 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.

[0775] 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.

[0776] 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.

[0777] 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."

[0778] 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.

[0779] 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.

[0780] 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.

[0781] 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.

[0782] 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.

[0783] 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.

[0784] 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.

[0785] 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.

[0786] 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.

[0787] 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.

[0788] 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.

[0789] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0790] The following is further disclosed regarding the embodiments described above.

[0791] (Claim 1)

[0792] Interface means for receiving voice or text input from a user,

[0793] A means for analyzing the input and interpreting the user's intent using natural language processing technology,

[0794] A database access means for identifying specific dates and medical services and checking their availability,

[0795] A means for generating a response to notify the user that the reservation has been confirmed,

[0796] A system that includes this.

[0797] (Claim 2)

[0798] The system according to claim 1, wherein the interface means receives user input via telephone, text messaging service, or instant messaging service.

[0799] (Claim 3)

[0800] The system according to claim 1, wherein the response generation means presents the user with a reservation confirmation in voice or text format and generates a reservation reminder.

[0801] "Example 1"

[0802] (Claim 1)

[0803] A means of communication for receiving voice or text input from a user,

[0804] A processing means for analyzing the input and interpreting the user's intent using language recognition technology,

[0805] A recording device access means for identifying a specified date and time and medical activity, and for searching for availability information,

[0806] A means for generating a response to notify the user that the reservation has been confirmed,

[0807] A means of generating a reservation reminder and notifying the user before a specified date and time,

[0808] A system that includes this.

[0809] (Claim 2)

[0810] The system according to claim 1, wherein the communication means receives user input via telephone, text message sending service, or instant messaging service.

[0811] (Claim 3)

[0812] The system according to claim 1, wherein the response generation means presents the user with a reservation confirmation in voice or text, and further provides an automatically generated reservation reminder.

[0813] "Application Example 1"

[0814] (Claim 1)

[0815] Information input / output means for receiving voice or text input from a user,

[0816] Information processing means for analyzing the input and interpreting the user's intent using natural language processing technology,

[0817] Information retrieval means for identifying specific dates and times and medical services, and for checking their availability,

[0818] A means of distributing information to notify users that their reservation has been confirmed and to provide information to caregivers,

[0819] A system that includes this.

[0820] (Claim 2)

[0821] The system according to claim 1, wherein the information input / output means receives user input via a speech recognition function or a messaging service.

[0822] (Claim 3)

[0823] The system according to claim 1, wherein the information distribution means generates reservation confirmations and reservation reminders in voice or text format, and further notifies caregivers of the reminders.

[0824] "Example 2 of combining an emotion engine"

[0825] (Claim 1)

[0826] An input device for receiving information from a user in voice or text format,

[0827] A device that analyzes the information and interprets the user's intent using natural language processing technology,

[0828] An emotion recognition device that analyzes the emotional elements of input information and recognizes emotions,

[0829] A device that connects to a data storage device for identifying specific dates and times and medical services, and for checking their availability,

[0830] A notification generator for generating a personalized response based on the confirmed reservation and recognized emotions,

[0831] A system that includes this.

[0832] (Claim 2)

[0833] The system according to claim 1, wherein the input device receives user information via voice call, messaging service, or instant communication service.

[0834] (Claim 3)

[0835] The notification generating device presents the user with a reservation confirmation in voice or text format and provides additional health advice based on recognized emotions, according to claim 1.

[0836] "Application example 2 when combining with an emotional engine"

[0837] (Claim 1)

[0838] Information exchange means for receiving voice or text input from users,

[0839] A means for analyzing the input and interpreting the user's intent using natural language processing technology,

[0840] An analytical means for analyzing the emotional elements of the input and recognizing the emotion,

[0841] A data storage means for identifying a specific date and time and medical service, and for checking its availability,

[0842] A response generation means for notifying the user that the reservation has been confirmed and for providing a customized response based on their emotions,

[0843] A system that includes this.

[0844] (Claim 2)

[0845] The system according to claim 1, wherein the information exchange means receives user input via telephone, text messaging service, or instant messaging service.

[0846] (Claim 3)

[0847] The system according to claim 1, wherein the response generation means presents the user with a reservation confirmation in voice or text format, generates a reservation reminder, and further provides emotion-based advice. [Explanation of symbols]

[0848] 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. Interface means for receiving voice or text input from a user, A means for analyzing the input and interpreting the user's intent using natural language processing technology, A database access means for identifying specific dates and medical services and checking their availability, A means for generating a response to notify the user that the reservation has been confirmed, A system that includes this.

2. The system according to claim 1, wherein the interface means receives user input via telephone, text messaging service, or instant messaging service.

3. The system according to claim 1, wherein the response generation means presents the user with a reservation confirmation in voice or text format and generates a reservation reminder.

Images