System

Abstract

A system is provided.SOLUTION: The system includes an interface means in charge of voice communication with a patient, a voice recognition means for converting received voice data into text data, a natural language processing means for analyzing the text data and extracting important information, a record update means for reflecting the extracted information on a medical record, and an advice generation means for generating advice to the patient on the basis of the extracted information.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] In today's medical field, the burden on medical professionals is increasing, especially when prolonged communication with patients is required. This makes it difficult for medical professionals to work efficiently within limited time and resources, resulting in difficulties in providing adequate medical care to patients. They also lack the time to provide appropriate advice to patients and encourage them to improve their lifestyle habits. This could lead to the collapse of regional medical care and a decline in patient satisfaction. To address this situation, a system is needed that can reliably extract and record important medical information while efficiently communicating with patients and reducing the burden on medical professionals. [Means for solving the problem]

[0005] The present invention provides a system that includes an interface means for handling voice communication with patients, a voice recognition means for converting received voice data into text data, a natural language processing means for analyzing the text data and extracting important information, a record updating means for reflecting the extracted information in medical records, and an advice generation means for generating advice for patients based on the extracted information.

[0006] Specifically, the patient's voice is captured by the interface means and converted into text data by the speech recognition means. Next, the text data is analyzed using the natural language processing means to extract important medical information. The extracted information is reflected in the patient's medical record through the record update means. Furthermore, the advice generation means generates and provides appropriate advice to the patient based on the extracted information. This configuration reduces the communication burden on medical professionals and enables efficient management of important medical information.

[0007] An "interface means" is a device or system that is responsible for audio communication with a patient and captures audio data.

[0008] The "voice recognition means" is a technology or device that converts voice data received from the interface means into text data.

[0009] "Natural language processing means" refers to technology or equipment that analyzes text data and extracts important information related to medical care.

[0010] A "record updater" is a technique or system that updates a patient's medical record with the extracted medical information.

[0011] The "advice generation means" is a technology or device that generates advice on appropriate lifestyle habits and treatment for the patient based on the extracted information. [Brief explanation of the drawings]

[0012] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0013] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

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

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

[0017] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

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

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0020] [First embodiment]

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

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

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

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

[0025] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0029] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

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

[0031] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

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

[0033] The present invention provides a system for communicating with patients through voice, analyzing the content of the communication, and efficiently managing medical information. This system is implemented with the following configuration.

[0034] System configuration

[0035] 1. Interface Method

[0036] Terminal: Responsible for voice communication with the patient, capturing the patient's voice and sending it to the server. It can take the form of a landline phone or a smartphone app.

[0037] 2. Voice Recognition Method

[0038] Server: Receives voice data sent from the device and converts it into text data using a voice recognition engine. For example, if a patient says, "I often have trouble sleeping at night recently," the server converts the voice data into text as, "I often have trouble sleeping at night recently."

[0039] 3. Natural Language Processing Methods

[0040] Server: Analyzes the converted text data and extracts important medical information. Specifically, it extracts the keyword "can't sleep" from the text data and recognizes that it corresponds to the symptom of "insomnia."

[0041] 4. Record-updating methods

[0042] Server: Reflects the extracted medical information in the patient's medical record. For example, the symptom "insomnia" is added to the patient's chart.

[0043] 5. Advice Generation Methods

[0044] Server: Based on the extracted information, the server generates appropriate lifestyle and treatment advice for the patient. For example, if "insomnia" information is extracted, the server generates advice to improve the quality of sleep, such as "Improve your sleeping environment and try to exercise regularly," and provides this to the patient via their device.

[0045] Example of a system

[0046] 1. Capture and transmit audio

[0047] User: The patient uses the device to start a conversation with the AI. For example, the patient might say, "I haven't had much of an appetite lately."

[0048] Device: Captures this conversation and sends the audio data to the server.

[0049] 2. Audio data conversion

[0050] Server: The received voice data is converted into text data using a voice recognition engine, such as "I haven't had much of an appetite lately."

[0051] 3. Text Data Analysis

[0052] Server: The converted text data is analyzed using a natural language processing engine to extract the symptom "loss of appetite."

[0053] 4. Updating medical records

[0054] Server: The extracted information "no appetite" is reflected in the patient's medical record.

[0055] 5. Generating and Providing Advice

[0056] Server: Based on the information that the patient has no appetite, the server generates appropriate advice for the patient. For example, the server generates advice such as "Try to regulate your eating habits" and provides this to the patient via a terminal.

[0057] By using this system, it will be possible to reduce the workload of medical professionals while enabling them to manage medical information and provide advice to patients quickly and appropriately, thereby improving the efficiency and quality of regional medical care.

[0058] The processing flow will be explained below.

[0059] Step 1:

[0060] User: The patient initiates a conversation with the AI ​​using a device. For example, the patient picks up the phone and says, "I often have trouble sleeping at night these days."

[0061] Step 2:

[0062] Terminal: Captures the patient's voice and transmits the voice data to the server in real time.

[0063] Step 3:

[0064] Server: Passes the received voice data to a voice recognition engine and converts it into text data. The text data becomes "I often have trouble sleeping at night these days."

[0065] Step 4:

[0066] Server: The converted text data is passed to a natural language processing engine, which analyzes the text content. Through the analysis, medically relevant information such as "I can't sleep at night" is extracted.

[0067] Step 5:

[0068] Server: Summarizes the extracted important medical information and adds it to the patient's medical record in the database as relevant information. For example, the information "insomnia" is added to the patient's medical record.

[0069] Step 6:

[0070] Server: Generates appropriate advice based on the keyword "insomnia." For example, it generates a message such as "Improve your sleeping environment and exercise regularly."

[0071] Step 7:

[0072] Server: Sends the generated advice to the terminal and sends instructions to provide to the patient.

[0073] Step 8:

[0074] Terminal: The advice received from the server is conveyed to the patient. In the case of a telephone call, it is played as a voice message.

[0075] Step 9:

[0076] User: The patient accepts the advice and indicates their intention to end the conversation (e.g., hang up the phone, enter an end command).

[0077] Step 10:

[0078] Terminal: Sends an intention to end the conversation to the server.

[0079] Step 11:

[0080] Server: Ends the conversation and closes the session, optionally logging and resetting the system.

[0081] ---

[0082] The above is the flow of the specific processing steps of the "AI that is always helpful" system, and an explanation of the specific operations at each step.

[0083] Example 1

[0084] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0085] In conventional medical systems, medical professionals manually manage information about patients' symptoms and lifestyle habits, which requires a great deal of time and effort. There is also a high risk of information leaks and input errors. Furthermore, it is difficult to provide appropriate advice to each patient.

[0086] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0087] In this invention, the server includes an interface means for voice communication with patients, a voice recognition means for converting received voice data into text data using a natural language processing engine, and a natural language processing means for analyzing the converted text data and extracting medical information. This makes it possible to efficiently manage patients' medical information and provide appropriate advice in real time.

[0088] 1. "Interface means" means a device or software that is responsible for voice communication with the patient, capturing voice data and transmitting it to the server.

[0089] 2. "Speech recognition means" means a device or software that converts received voice data into text data using a natural language processing engine.

[0090] 3. "Natural language processing means" means a device or software that analyzes the converted text data and extracts important medical information.

[0091] 4. "Record updating device" means a device or software that updates extracted medical information into a patient's medical record.

[0092] 5. "Advice generation means" refers to a device or software that generates and provides advice regarding lifestyle habits and treatment based on extracted medical information.

[0093] 6. "Voice data" means voice information collected from a patient via an interface means.

[0094] 7. "Text data" means character information converted from voice data by voice recognition means.

[0095] 8. "Medical information" means information about a patient's symptoms and lifestyle habits extracted from text data using natural language processing means.

[0096] The present invention is a system for communicating with patients through voice, analyzing the content of the communication, and efficiently managing medical information. Specific embodiments of the present invention will be described below.

[0097] System configuration

[0098] 1. Interface Method

[0099] The device, which can take the form of a landline phone or a smartphone app, handles voice communication with the patient, captures the voice data, and transmits it to a server.

[0100] 2. Voice Recognition Method

[0101] The server receives the voice data sent from the device and converts the voice into text data using a speech recognition engine (e.g., Google Speech-to-Text API).

[0102] For example, if a patient says, "Recently, I've often had trouble sleeping at night," the voice data is converted into text data that reads, "Recently, I've often had trouble sleeping at night."

[0103] 3. Natural Language Processing Methods

[0104] The server analyzes the text data generated by speech recognition and extracts important medical information using natural language processing engines such as spaCy and the BERT model.

[0105] As a specific example, the keyword "can't sleep" is extracted from the text data "Recently, I often can't sleep at night" and it is recognized that this corresponds to the symptom of "insomnia."

[0106] 4. Record-updating methods

[0107] The server reflects the extracted medical information in the patient's medical record. For example, the extracted information on "insomnia" is added to the patient's chart.

[0108] 5. Advice Generation Methods

[0109] The server generates appropriate lifestyle and treatment advice for the patient based on the extracted medical information, using a generative AI model (e.g., GPT-4).

[0110] For example, if information about "insomnia" is extracted, a message will be generated saying, "It would be a good idea to improve your sleeping environment and exercise regularly," and this will be provided to the patient via the terminal.

[0111] Specific examples of programs

[0112] User operation

[0113] The user uses the device to start a conversation with the AI. For example, a patient might say, "I haven't had much of an appetite lately."

[0114] Processing by the terminal

[0115] The device captures the audio and sends the audio data to the server.

[0116] Server processing

[0117] The server uses a speech recognition engine to convert the received voice data into text data such as "I haven't had much of an appetite lately." It then analyzes the data using a natural language processing engine to extract the symptom "lack of appetite." Based on this information, the server updates the patient's medical record and uses a generative AI model to generate advice such as "Try to regulate your eating habits," which is then provided to the patient via their device.

[0118] Prompt Sentence Examples

[0119] Here is an example of a prompt to be fed to a generative AI model:

[0120] Example prompt:

[0121] "A patient has recently complained of a lack of appetite. Please add the appropriate information to the medical record and generate appropriate advice."

[0122] This system will reduce the workload of medical professionals while enabling them to manage medical information and provide prompt and appropriate advice to patients, thereby improving the efficiency and quality of regional medical care.

[0123] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0124] Step 1:

[0125] The user operates the device to start a conversation with the AI. The input is the patient's voice (e.g., "I haven't had much of an appetite lately."). The output is the captured voice data on the device. Specifically, the patient opens the smartphone app, taps the "voice input" button, and speaks the voice message.

[0126] Step 2:

[0127] The terminal captures the patient's voice and sends the voice data to the server. The input is the voice data captured in step 1. The output is the voice data sent to the server. Specifically, the terminal captures voice using the built-in microphone and uploads the voice data to the server in real time. HTTPS is used as the communication protocol, and data is encrypted.

[0128] Step 3:

[0129] The server converts the received voice data into text data using a voice recognition engine. The input is the voice data sent from the device. The output is the text data converted from the voice. Specifically, the server sends the voice data to a voice recognition engine (e.g., Google Speech-to-Text API), and the API converts the voice data into text data such as "I haven't had much of an appetite lately." The server then saves the converted text data.

[0130] Step 4:

[0131] The server analyzes the converted text data using a natural language processing engine to extract important medical information. The input is the text data converted in step 3. The output is the extracted medical information. Specifically, the server inputs the text data into a natural language processing engine (e.g., spaCy, BERT model), and the engine extracts the keyword "no appetite" and recognizes it as a symptom of "loss of appetite." The extracted information is temporarily stored.

[0132] Step 5:

[0133] The server reflects the extracted medical information in the patient's medical record. The input is the medical information extracted in step 4. The output is the updated medical record. Specifically, the server retrieves the medical record based on the patient's ID, adds the new information "loss of appetite" to the existing record, and saves the updated medical record in the database.

[0134] Step 6:

[0135] The server generates appropriate lifestyle and treatment advice for the patient based on the extracted medical information. The input is the medical information extracted in step 4. The output is the generated advice message. Specifically, the server inputs a prompt to the generative AI model (e.g., GPT-4), and the AI ​​model generates advice such as "Try to regulate your eating habits." The server then sends the generated advice to the device.

[0136] Step 7:

[0137] The terminal displays the advice received from the server to the patient. The input is the advice message sent from the server. The output is the advice displayed on the terminal. Specifically, the advice received by the terminal is displayed on the screen so that the patient can check it. For example, "Try to regulate your eating habits" is displayed.

[0138] (Application example 1)

[0139] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0140] While conventional speech recognition and natural language processing systems are primarily used in the medical field, their application in other fields such as food delivery has not been fully explored. Furthermore, there is a lack of systems that can efficiently process orders and provide specific advice and product recommendations through voice communication with users, creating a need for an improved user experience.

[0141] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0142] In this invention, the server includes an interface means for voice communication with the patient, a voice recognition means for converting received voice data into text data, a natural language processing means for analyzing the text data and extracting important information, a record updating means for updating the medical record with the extracted information, an advice generating means for generating advice for the patient based on the extracted information, a means for converting order details into text data through voice communication with the user, a natural language processing means for analyzing the text data and extracting the order details, a means for storing the extracted order details in a database, and a means for generating additional recommended products and advice based on the extracted order details. This makes it possible to streamline the food delivery ordering process and provide users with recommended products and advice that are appropriate for them.

[0143] "Interface means" refers to devices or software that are responsible for voice communication with patients or users, and have the function of capturing voice data and sending it to a server.

[0144] "Speech recognition means" refers to a technology that converts received voice data into text data, and uses a voice recognition engine.

[0145] "Natural language processing means" refers to technology that analyzes text data and extracts important information and order details, and uses a natural language processing engine.

[0146] "Record updating means" refers to the function that updates extracted information into medical records and databases, keeping patient charts and user order histories up to date.

[0147] The "advice generation means" is a function that generates appropriate advice and recommended products for patients and users based on the extracted information, and generates messages based on lifestyle habits and order details.

[0148] The "means for converting the order contents into text data" refers to a function for converting the user's voice order into text data, and uses voice recognition technology.

[0149] "Means for analyzing and extracting order details" refers to a function that analyzes order details from text data and extracts necessary information, and uses natural language processing technology.

[0150] "Means for saving to a database" refers to the function of saving the extracted order details to a database, which serves as the basis for managing order history and reordering.

[0151] "Means for generating additional product recommendations and advice" refers to the functionality for generating additional product recommendations and specific advice based on the user's order, which is used to enhance the user experience.

[0152] This invention is a system for communicating with users through voice, analyzing the content of the communication, and efficiently managing order information. The system is implemented with the following specific configuration and procedures.

[0153] System configuration

[0154] 1. Interface Method

[0155] Terminal: Responsible for voice communication with the user, capturing the user's voice and sending it to the server. It can take the form of a smartphone or smart speaker.

[0156] 2. Voice Recognition Method

[0157] Server: Receives the voice data sent from the device and converts it into text data using a speech recognition engine (e.g., Google Cloud Speech-to-Text).

[0158] 3. Natural Language Processing Methods

[0159] Server: Analyzes the converted text data and extracts order details and important information (e.g., Google Cloud Natural Language API).

[0160] 4. Record-updating methods

[0161] Server: Save the extracted order details to a database (e.g., Firebase Realtime Database) and update the user's order history.

[0162] 5. Advice Generation Methods

[0163] Server: Generates additional product recommendations and specific advice appropriate for the user based on the extracted order details.

[0164] Example of a system

[0165] 1. Capture and transmit audio

[0166] User: The user uses the device to place an order by voice. For example, the user might say, "I'd like one pizza and two salads, please."

[0167] Device: Captures this conversation and sends the audio data to the server.

[0168] 2. Audio data conversion

[0169] Server: The received voice data is converted into text data using a voice recognition engine, such as "One pizza and two salads, please."

[0170] 3. Text Data Analysis

[0171] Server: The converted text data is analyzed using a natural language processing engine, and the order details, "one pizza" and "two salads," are extracted.

[0172] 4. Storage of order data

[0173] Server: Saves the extracted order details to the database and updates the user's order history.

[0174] 5. Generating and Providing Advice

[0175] Server: Based on the order, the server generates additional product recommendations and specific advice appropriate for the user. For example, it generates a message such as "How about a Margherita pizza and a green salad?" and delivers this to the user via the device.

[0176] Specific prompt examples

[0177] The user initiates a voice order using the following prompt:

[0178] "One pizza and two salads, please."

[0179] In this way, this system can streamline the food delivery ordering process and improve the user experience. Specifically, by combining voice recognition technology and natural language processing technology, it is possible to accurately understand and manage order details, as well as provide appropriate product recommendations and advice.

[0180] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0181] Step 1:

[0182] The user places an order by voice. Specifically, the user launches the smartphone app and voice-records their order, such as "One pizza and two salads, please." This voice data becomes the input for the system.

[0183] Step 2:

[0184] The device sends the captured voice data to the server. Specifically, the device records the user's voice and sends the data to the Google Cloud Speech-to-Text API, requesting that the voice data be converted to text. In this case, the input is voice data and the output is text data.

[0185] Step 3:

[0186] The server converts the received voice data into text data using a speech recognition engine. Specifically, the server sends the voice data to the Google Cloud Speech-to-Text API and receives the text data as a result. At this stage, the input is voice data, and the output is text data obtained by speech recognition.

[0187] Step 4:

[0188] The server analyzes the text data using a natural language processing engine to extract the order details and important information. Specifically, the server sends the text data to the Google Cloud Natural Language API, which extracts the order items (e.g., one pizza, two salads). In this case, the input is text data, and the output is the specific order details and quantity.

[0189] Step 5:

[0190] The server saves the extracted order details in a database. Specifically, it makes a request to Firebase Realtime Database to save the order details (e.g., "1 pizza" and "2 salads"). The input at this stage is the order data, and the output is the updated database results.

[0191] Step 6:

[0192] The server generates additional product recommendations and specific advice based on the order details. Specifically, the server references the user's past order history and current order details, and uses the corresponding generative AI model to generate advice and recommendations such as "How about a Margherita pizza and a green salad?" The input at this stage is the order details and history data, and the output is the generated advice and recommendation message.

[0193] Step 7:

[0194] The server sends the generated advice and recommendation messages to the terminal. Specifically, the server uses a communication protocol to send the generated messages to the terminal. In this case, the input is the generated message, and the output is the data to be sent to the terminal.

[0195] Step 8:

[0196] The device notifies the user of the received advice or recommendation message. Specifically, it displays the message to the user using the smartphone's notification function. At this stage, the input is the message sent from the server, and the output is the notification content to the user.

[0197] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0198] The present invention is a system that extracts important medical information through voice communication with patients, updates the patient's medical record based on that information, and provides appropriate advice. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to respond based on the patient's emotional state and provide more personalized care. This system has the following components:

[0199] System configuration

[0200] 1. Interface Method

[0201] Terminal: Responsible for voice communication with the patient, capturing the patient's voice and sending it to the server. This can be a phone, a dedicated application, or a device with a microphone.

[0202] 2. Voice Recognition Method

[0203] Server: Receives voice data sent from the device and converts it into text data using a voice recognition engine. For example, if a patient says, "I often have trouble sleeping at night recently," the voice data is converted into text data saying, "I often have trouble sleeping at night recently."

[0204] 3. Natural Language Processing Methods

[0205] Server: Analyzes the converted text data and extracts important medical information. In this process, it identifies the keyword "can't sleep" from the text and recognizes that this corresponds to the medical information "insomnia."

[0206] 4. Emotion Engine

[0207] Server: Identifies emotions from the patient's voice and text data. For example, it analyzes elements such as the tone, speed, and pitch of the patient's voice to recognize emotions such as anxiety, tension, or relief.

[0208] 5. Record-updating methods

[0209] Server: Reflects the extracted important medical and emotional information in the patient's medical record. For example, the symptom information "insomnia" and the emotional information "anxiety" are added to the medical record.

[0210] 6. Advice Generation Methods

[0211] Server: Based on the extracted information and emotional information, the server generates advice on appropriate lifestyle habits and treatment for the patient. For example, for a patient with insomnia and anxiety, the server generates specific advice such as, "It would be good to improve your sleeping environment and try to relax. Also, if you feel anxious, try taking deep breaths."

[0212] Example of a system

[0213] 1. Capture and transmit audio

[0214] User: The patient uses the device to start a conversation with the AI, for example, saying, "I'm worried because I've lost my appetite recently."

[0215] Device: Captures this conversation and sends the audio data to the server.

[0216] 2. Audio data conversion

[0217] Server: The received voice data is converted into text data by a voice recognition engine. For example, it may be converted into "I'm worried because I've lost my appetite recently."

[0218] 3. Text Data Analysis

[0219] Server: The converted text data is analyzed using a natural language processing engine to extract symptom information such as "loss of appetite." It also uses an emotion engine to extract emotional information recognized as "worry."

[0220] 4. Updating medical records

[0221] Server: The extracted symptom information of "no appetite" and emotional information of "worry" are reflected in the patient's medical record.

[0222] 5. Generating and Providing Advice

[0223] Server: Based on the symptom information of "loss of appetite" and the emotional information of "worry," the server generates appropriate advice for the patient. For example, the server generates advice such as, "Try to maintain a regular lifestyle and gradually incorporate your favorite foods into your diet. If you continue to feel anxious, we recommend that you try relaxation therapy or seek counseling," and provides this advice to the patient via a device.

[0224] This system efficiently manages important medical information through voice communication with patients, and by combining it with an emotion engine, enables personalized responses based on the patient's emotional state, ultimately reducing the workload of medical professionals and enabling higher quality medical services to be provided to patients.

[0225] The processing flow will be explained below.

[0226] Step 1:

[0227] User: The patient uses the device to initiate a conversation with the AI, for example, saying, "I've lost my appetite recently and I'm very worried."

[0228] Step 2:

[0229] Terminal: Captures the patient's voice and transmits the voice data to the server in real time.

[0230] Step 3:

[0231] Server: The received voice data is passed to a voice recognition engine and converted into text data. The text data becomes, "I've lost my appetite recently and I'm very worried."

[0232] Step 4:

[0233] Server: The converted text data is passed to a natural language processing engine, which analyzes the text content. Through the analysis, medically relevant information such as "no appetite" is extracted.

[0234] Step 5:

[0235] Server: Using an emotion engine, identify the patient's emotion from the converted text and voice data. In this case, the emotion "worry" is recognized.

[0236] Step 6:

[0237] Server: Combines and summarizes the analyzed medical information and the recognized emotional information, and reflects this information in the patient's medical record. Specifically, the symptom information of "loss of appetite" and the emotional information of "worry" are added to the medical record.

[0238] Step 7:

[0239] Server: Generates appropriate advice for the patient based on the symptom information of "loss of appetite" and the emotion information of "worry." For example, it generates a message such as, "Try to maintain a regular lifestyle and gradually incorporate your favorite foods into your diet. Also, if you continue to feel anxious, we recommend relaxation and counseling."

[0240] Step 8:

[0241] Server: Sends the generated advice to the terminal and issues instructions to provide to the patient.

[0242] Step 9:

[0243] Terminal: Provides advice received from the server to the patient. In the case of a telephone call, a synthesized voice is generated and the advice is played back as a voice message.

[0244] Step 10:

[0245] User: The patient accepts the advice and indicates their intention to end the conversation (e.g., hang up the phone, enter an end command).

[0246] Step 11:

[0247] Terminal: Sends an intention to end the conversation to the server.

[0248] Step 12:

[0249] Server: Ends the conversation and closes the session, optionally logging and resetting the system.

[0250] ---

[0251] The above is the flow of specific processing steps for the "AI that is always kind" system that combines an emotion engine, and an explanation of the specific operations at each step.

[0252] Example 2

[0253] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0254] Conventional patient care systems have the problem that the information obtained from patients through voice communication is limited, making it difficult to fully grasp the patient's emotional state. Furthermore, the process of analyzing the obtained information in real time and providing advice is often inefficient. This increases the workload of medical professionals and risks reducing the quality of care provided to patients. Therefore, there was a need for the development of a system that can simultaneously extract important medical information and emotional information from voice data and provide prompt and appropriate advice.

[0255] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an interface means for voice communication with the patient, a voice recognition means for converting received voice data into text data, a natural language processing means for analyzing the text data and extracting important information, an emotion recognition means for identifying emotions from the extracted voice and text data, a record updating means for reflecting the extracted information in the medical record, and an advice generation means for generating advice for the patient based on the extracted information. This makes it possible to simultaneously extract important medical information and emotional information from the voice data and provide prompt and appropriate advice.

[0256] The "interface means" is a means for taking charge of voice communication with the patient, capturing the patient's voice, and transmitting it to the server.

[0257] The "voice recognition means" is a means for converting received voice data into text data.

[0258] "Natural language processing means" is a means for analyzing text data and extracting important information.

[0259] The "emotion recognition means" is a means for identifying emotions from extracted speech and text data.

[0260] The "record updating means" is a means for updating the extracted information in the patient's medical record.

[0261] The "advice generation means" is a means for generating advice for the patient based on the extracted information.

[0262] The present invention is a system that efficiently extracts important medical information and emotional information of patients through voice communication with them and provides appropriate advice. This system includes the following main components:

[0263] 1. Interface Method

[0264] Terminal: Responsible for voice communication with the patient, capturing the patient's voice and sending it to the server. The terminal can be a smartphone, tablet, PC, etc. Specifically, it collects voice using a microphone and sends the voice data to the server via an internet connection.

[0265] 2. Voice Recognition Method

[0266] Server: Receives voice data sent from the device and converts it into text data using a speech recognition engine. Google Cloud Speech-to-Text and Microsoft Azure Cognitive Services are used as speech recognition engines. For example, the server receives voice data and converts a patient's speech, such as "I've lost my appetite recently and I'm worried," into text.

[0267] 3. Natural Language Processing Methods

[0268] Server: Analyzes the converted text data and extracts important medical information. During this process, it automatically identifies keywords and phrases (e.g., "no appetite") and determines whether they correspond to symptoms. Apache OpenNLP and spaCy are used as natural language processing engines.

[0269] 4. Emotion recognition means

[0270] Server: Identifies the patient's emotion from the received voice and converted text data. IBM Watson Tone Analyzer and Affectiva SDK are used as emotion engines. For example, if a patient says "I'm worried," the server recognizes this as the emotion "worried."

[0271] 5. Record-updating methods

[0272] Server: The extracted important medical and emotional information is reflected in the patient's medical record. Epic Systems or Cerner is used as the medical record management system, and Oracle Database or PostgreSQL is used as the database.

[0273] 6. Advice Generation Methods

[0274] Server: Based on the extracted information, the server generates appropriate lifestyle and treatment advice for the patient. Generative AI models such as GPT (Generative Pre-trained Transformer) and BERT (Bidirectional Encoder Representations from Transformers) are used. For example, the server might generate advice such as, "Try to maintain a healthy lifestyle and gradually incorporate your favorite foods into your diet. If you continue to feel anxious, we recommend relaxation and counseling."

[0275] Examples:

[0276] If the user says, "I'm worried because I haven't had much of an appetite lately," the system operates as follows.

[0277] 1. Interface method: The user speaks through the smartphone microphone, saying, "I'm worried because I haven't had much of an appetite lately."

[0278] 2. Speech recognition: The device captures the voice and sends it to the server, which converts the voice into text using a speech recognition engine.

[0279] 3. Natural language processing: Analyze the converted text "I'm worried because I've had no appetite lately" and extract important information. Specifically, extract the symptom information of "no appetite."

[0280] 4. Emotion recognition means: The server identifies the emotional information "worry" from the text and voice.

[0281] 5. Record updating method: The extracted symptom information of "loss of appetite" and emotional information of "worry" are added to the medical record.

[0282] 6. Advice generation method: Using the generative AI model, advice such as "Try to maintain a regular lifestyle and gradually incorporate your favorite foods into your diet. Also, if you continue to feel anxious, we recommend that you seek relaxation and counseling" is generated and provided to the patient via their device.

[0283] Example prompt sentence:

[0284] Patient symptoms: Loss of appetite

[0285] Patient Emotions: Anxiety

[0286] Good advice:

[0287] Try to maintain a regular lifestyle and gradually incorporate your favorite foods into your diet. If you continue to feel anxious, we recommend seeking relaxation and counseling.

[0288] The above is a detailed description of an embodiment of the present invention. This system quickly and accurately extracts important medical and emotional information from speech data, enabling personalized advice to be provided to patients.

[0289] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0290] Step 1:

[0291] User: The patient uses the device to start a conversation with the AI, for example, saying, "I'm worried because I've lost my appetite recently."

[0292] Input: Patient's voice

[0293] Output: Captured audio data

[0294] Specific operation: A user speaks into the microphone of a smartphone or tablet. An application on the device captures the voice data and converts it into a voice data format.

[0295] Step 2:

[0296] Terminal: Sends captured audio data to the server.

[0297] Input: Captured audio data

[0298] Output: Audio data sent to the server

[0299] What it does: The device uses an internet connection to send audio data to the server, using HTTPS as the communication protocol to ensure secure data transfer.

[0300] Step 3:

[0301] Server: Receives the voice data sent from the terminal.

[0302] Input: Transmitted audio data

[0303] Output: Received audio data

[0304] Specific operation: The server receives the voice data and stores it in temporary storage.

[0305] Step 4:

[0306] Server: The received voice data is converted into text data using a voice recognition engine.

[0307] Input: Received audio data

[0308] Output: Text data

[0309] Specific operation: The server calls a speech recognition engine (for example, Google Cloud Speech-to-Text), analyzes the voice signal, and converts it into text data such as "I'm worried because I've lost my appetite lately."

[0310] Step 5:

[0311] Server: The converted text data is analyzed using a natural language processing engine.

[0312] Input: Converted text data

[0313] Output: Extracted symptom information and emotion information

[0314] Specific operation: The server uses a natural language processing engine (e.g., spaCy) to extract symptom information such as "no appetite" from the text data, and simultaneously uses an emotion engine (e.g., IBM Watson Tone Analyzer) to extract emotion information such as "worry."

[0315] Step 6:

[0316] Server: Reflects the extracted information in the patient's medical record.

[0317] Input: Extracted symptom information and emotion information

[0318] Output: Updated medical record

[0319] Specific operation: The server accesses a medical record management system (e.g., Epic Systems) and updates the patient's medical record database (e.g., Oracle Database). New information is added: the symptom "loss of appetite" and the emotion "anxiety."

[0320] Step 7:

[0321] Server: Generates advice for the patient based on the extracted information.

[0322] Input: Updated medical record

[0323] Output: Generated advice

[0324] Specific operation: The server uses an advice generation engine (e.g., GPT-3) to generate advice such as, "Try to maintain a regular lifestyle and incorporate your favorite foods little by little. Also, if you continue to feel anxious, we recommend relaxation and counseling."

[0325] Step 8:

[0326] Server: Sends the generated advice to the device.

[0327] Input: Generated advice

[0328] Output: Advice sent

[0329] Specific operation: The server generates advice and sends it to the device. HTTPS is used as the communication protocol to transfer data securely.

[0330] Step 9:

[0331] Terminal: Receives advice and provides it to the user by display or voice.

[0332] Input: Submitted advice

[0333] Output: Advice given to the user

[0334] Specific behavior: The device displays the advice received from the server, alerts the user with a notification sound or a pop-up message, and, if necessary, reads the advice aloud via the voice assistant.

[0335] (Application example 2)

[0336] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0337] Conventional medical information systems equipped with voice recognition and emotion recognition technologies have difficulty responding in real time to patients' emotional states. Furthermore, there is a lack of systems that can take appropriate measures immediately in emergency situations. Therefore, there is a need to ensure patient safety and respond quickly and efficiently.

[0338] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0339] In this invention, the server includes an interface means for voice communication with the patient, a voice recognition means for converting received voice data into text data, a natural language processing means for analyzing the text data and extracting important information, a record updating means for updating the extracted information in the medical record, an advice generation means for generating advice for the patient based on the extracted information and emotional information, an emotion recognition means for identifying emotional information from the voice data, and an emergency response means for detecting an emergency based on the extracted information and emotional information and sending an alert as necessary. This enables the provision of personalized care according to the patient's emotional state and a rapid response in the event of an emergency.

[0340] The "interface means" is a device that is responsible for voice communication with the patient, captures the patient's voice, and transmits it to the server.

[0341] The "voice recognition means" is an engine that converts received voice data into text data.

[0342] A "natural language processing tool" is an engine that analyzes text data and extracts important medical and other information from it.

[0343] The "record updating means" is a system for updating extracted information into the patient's medical record and security log.

[0344] The "advice generation means" is an engine that generates appropriate advice for the patient based on the extracted information and emotional information.

[0345] The "emotion recognition means" is an engine that identifies the patient's emotional information from the voice data.

[0346] The "emergency response tool" is a system for detecting emergency situations based on extracted information and emotion information and sending alerts as needed.

[0347] The system for implementing the present invention comprises an interface means, a speech recognition means, a natural language processing means, a record updating means, an advice generation means, an emotion recognition means, and an emergency response means. The following is a detailed description of each means and how they work together.

[0348] Interface Means

[0349] The server manages the interface means for voice communication with the patient, which has the function of capturing the patient's voice using a smartphone with a microphone or a dedicated application and transmitting it to the server.

[0350] Voice recognition means

[0351] The server converts the voice data sent from the device into text data using Google's speech recognition API, etc. For example, if a patient says, "Help me, someone has broken into my house," the server converts the voice data into text data.

[0352] Natural language processing tools

[0353] The server then analyzes the converted text data using HuggingFace's natural language processing engine to extract important information, identifying the keyword "home intrusion" from the text and recognizing that this is an emergency.

[0354] Record updating method

[0355] The server then updates the patient's security log with the extracted information, for example adding an emergency event such as "home intrusion" to the security log.

[0356] Advice Generation Method

[0357] The server generates appropriate advice for the patient based on the extracted information and emotion information. For example, in the event of an intrusion, the server generates specific advice such as "Evacuate to a safe place and immediately contact your emergency contact."

[0358] emotion recognition means

[0359] The server identifies the patient's emotions from the voice data by analyzing factors such as tone, speed, and pitch of the voice to assess whether the patient is feeling anxious or scared.

[0360] Emergency response measures

[0361] Based on the extracted information and emotion information, the server detects emergencies and sends alerts to emergency contacts as needed. For example, if an intruder occurs, an email is sent immediately to emergency contacts (family members or a security company).

[0362] Specific examples

[0363] Example speech input: "Help, someone is breaking into my house."

[0364] Emergency Alert: "Emergency. Please help, someone has broken into my house."

[0365] Email recipients: Emergency contacts (e.g., family, security company)

[0366] Prompt Sentence Examples

[0367] If a user says, "Help me, someone's broken into my house," the system captures that speech, converts it to text, and then runs a sentiment analysis on that text. If the emotion of fear is recognized, an email alert is sent to emergency contacts.

[0368] The system allows for personalized care according to the patient's emotional state and rapid response in emergency situations.

[0369] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0370] Step 1:

[0371] The user inputs voice using the terminal. The terminal captures the voice and sends this voice data to the server. The input is the user's voice data, and the output is the voice data sent to the server.

[0372] Step 2:

[0373] The server converts the received voice data into text data using Google's speech recognition API. The input is voice data, and the output is text data. For example, this conversion converts a voice message like "Help me, someone has broken into my house" into text data.

[0374] Step 3:

[0375] The server then analyzes the converted text data using HuggingFace's natural language processing engine to extract important information. The input is text data, and the output is the extracted important information. During this analysis, the keyword "house intrusion" is identified, and it is recognized that this is an emergency.

[0376] Step 4:

[0377] The server analyzes emotional information from the voice data. It analyzes the tone, speed, and pitch of the voice to identify emotional states such as anxiety or fear. The input is voice data, and the output is emotional information.

[0378] Step 5:

[0379] The server reflects the extracted important information and emotional information in the patient's security log. The input is the extracted important information and emotional information, and the output is the updated security log. Here, the information "house intrusion" and the user's feeling of fear are recorded in the log.

[0380] Step 6:

[0381] The server generates appropriate advice for the patient based on the extracted information. For example, advice such as "Evacuate to a safe place and immediately contact your emergency contacts" is generated. The input is the extracted information and emotion information, and the output is the generated advice.

[0382] Step 7:

[0383] If the server determines that an emergency has occurred, it will send an alert to the emergency contact as needed. The input is the emergency information and emotion information, and the output is an alert email to the emergency contact. For example, a message such as "An emergency has occurred. Please help, someone has broken into my house" is sent.

[0384] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0385] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0386] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0387] [Second embodiment]

[0388] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0389] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0390] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0391] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0392] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0393] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0394] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0395] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0396] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0397] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0398] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0399] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0400] The present invention provides a system for communicating with patients through voice, analyzing the content of the communication, and efficiently managing medical information. This system is implemented with the following configuration.

[0401] System configuration

[0402] 1. Interface Method

[0403] Terminal: Responsible for voice communication with the patient, capturing the patient's voice and sending it to the server. It can take the form of a landline phone or a smartphone app.

[0404] 2. Voice Recognition Method

[0405] Server: Receives voice data sent from the device and converts it into text data using a voice recognition engine. For example, if a patient says, "I often have trouble sleeping at night recently," the server converts the voice data into text as, "I often have trouble sleeping at night recently."

[0406] 3. Natural Language Processing Methods

[0407] Server: Analyzes the converted text data and extracts important medical information. Specifically, it extracts the keyword "can't sleep" from the text data and recognizes that it corresponds to the symptom of "insomnia."

[0408] 4. Record-updating methods

[0409] Server: Reflects the extracted medical information in the patient's medical record. For example, the symptom "insomnia" is added to the patient's chart.

[0410] 5. Advice Generation Methods

[0411] Server: Based on the extracted information, the server generates appropriate lifestyle and treatment advice for the patient. For example, if "insomnia" information is extracted, the server generates advice to improve the quality of sleep, such as "Improve your sleeping environment and try to exercise regularly," and provides this to the patient via their device.

[0412] Example of a system

[0413] 1. Capture and transmit audio

[0414] User: The patient uses the device to start a conversation with the AI. For example, the patient might say, "I haven't had much of an appetite lately."

[0415] Device: Captures this conversation and sends the audio data to the server.

[0416] 2. Audio data conversion

[0417] Server: The received voice data is converted into text data using a voice recognition engine, such as "I haven't had much of an appetite lately."

[0418] 3. Text Data Analysis

[0419] Server: The converted text data is analyzed using a natural language processing engine to extract the symptom "loss of appetite."

[0420] 4. Updating medical records

[0421] Server: The extracted information "no appetite" is reflected in the patient's medical record.

[0422] 5. Generating and Providing Advice

[0423] Server: Based on the information that the patient has no appetite, the server generates appropriate advice for the patient. For example, the server generates advice such as "Try to regulate your eating habits" and provides this to the patient via a terminal.

[0424] By using this system, it will be possible to reduce the workload of medical professionals while enabling them to manage medical information and provide advice to patients quickly and appropriately, thereby improving the efficiency and quality of regional medical care.

[0425] The processing flow will be explained below.

[0426] Step 1:

[0427] User: The patient initiates a conversation with the AI ​​using a device. For example, the patient picks up the phone and says, "I often have trouble sleeping at night these days."

[0428] Step 2:

[0429] Terminal: Captures the patient's voice and transmits the voice data to the server in real time.

[0430] Step 3:

[0431] Server: Passes the received voice data to a voice recognition engine and converts it into text data. The text data becomes "I often have trouble sleeping at night these days."

[0432] Step 4:

[0433] Server: The converted text data is passed to a natural language processing engine, which analyzes the text content. Through the analysis, medically relevant information such as "I can't sleep at night" is extracted.

[0434] Step 5:

[0435] Server: Summarizes the extracted important medical information and adds it to the patient's medical record in the database as relevant information. For example, the information "insomnia" is added to the patient's medical record.

[0436] Step 6:

[0437] Server: Generates appropriate advice based on the keyword "insomnia." For example, it generates a message such as "Improve your sleeping environment and exercise regularly."

[0438] Step 7:

[0439] Server: Sends the generated advice to the terminal and sends instructions to provide to the patient.

[0440] Step 8:

[0441] Terminal: The advice received from the server is conveyed to the patient. In the case of a telephone call, it is played as a voice message.

[0442] Step 9:

[0443] User: The patient accepts the advice and indicates their intention to end the conversation (e.g., hang up the phone, enter an end command).

[0444] Step 10:

[0445] Terminal: Sends an intention to end the conversation to the server.

[0446] Step 11:

[0447] Server: Ends the conversation and closes the session, optionally logging and resetting the system.

[0448] ---

[0449] The above is the flow of the specific processing steps of the "AI that is always helpful" system, and an explanation of the specific operations at each step.

[0450] Example 1

[0451] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0452] In conventional medical systems, medical professionals manually manage information about patients' symptoms and lifestyle habits, which requires a great deal of time and effort. There is also a high risk of information leaks and input errors. Furthermore, it is difficult to provide appropriate advice to each patient.

[0453] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0454] In this invention, the server includes an interface means for voice communication with patients, a voice recognition means for converting received voice data into text data using a natural language processing engine, and a natural language processing means for analyzing the converted text data and extracting medical information. This makes it possible to efficiently manage patients' medical information and provide appropriate advice in real time.

[0455] 1. "Interface means" means a device or software that is responsible for voice communication with the patient, capturing voice data and transmitting it to the server.

[0456] 2. "Speech recognition means" means a device or software that converts received voice data into text data using a natural language processing engine.

[0457] 3. "Natural language processing means" means a device or software that analyzes the converted text data and extracts important medical information.

[0458] 4. "Record updating device" means a device or software that updates extracted medical information into a patient's medical record.

[0459] 5. "Advice generation means" refers to a device or software that generates and provides advice regarding lifestyle habits and treatment based on extracted medical information.

[0460] 6. "Voice data" means voice information collected from a patient via an interface means.

[0461] 7. "Text data" means character information converted from voice data by voice recognition means.

[0462] 8. "Medical information" means information about a patient's symptoms and lifestyle habits extracted from text data using natural language processing means.

[0463] The present invention is a system for communicating with patients through voice, analyzing the content of the communication, and efficiently managing medical information. Specific embodiments of the present invention will be described below.

[0464] System configuration

[0465] 1. Interface Method

[0466] The device, which can take the form of a landline phone or a smartphone app, handles voice communication with the patient, captures the voice data, and transmits it to a server.

[0467] 2. Voice Recognition Method

[0468] The server receives the voice data sent from the device and converts the voice into text data using a speech recognition engine (e.g., Google Speech-to-Text API).

[0469] For example, if a patient says, "Recently, I've often had trouble sleeping at night," the voice data is converted into text data that reads, "Recently, I've often had trouble sleeping at night."

[0470] 3. Natural Language Processing Methods

[0471] The server analyzes the text data generated by speech recognition and extracts important medical information using natural language processing engines such as spaCy and the BERT model.

[0472] As a specific example, the keyword "can't sleep" is extracted from the text data "Recently, I often can't sleep at night" and it is recognized that this corresponds to the symptom of "insomnia."

[0473] 4. Record-updating methods

[0474] The server reflects the extracted medical information in the patient's medical record. For example, the extracted information on "insomnia" is added to the patient's chart.

[0475] 5. Advice Generation Methods

[0476] The server generates appropriate lifestyle and treatment advice for the patient based on the extracted medical information, using a generative AI model (e.g., GPT-4).

[0477] For example, if information about "insomnia" is extracted, a message will be generated saying, "It would be a good idea to improve your sleeping environment and exercise regularly," and this will be provided to the patient via the terminal.

[0478] Specific examples of programs

[0479] User operation

[0480] The user uses the device to start a conversation with the AI. For example, a patient might say, "I haven't had much of an appetite lately."

[0481] Processing by the terminal

[0482] The device captures the audio and sends the audio data to the server.

[0483] Server processing

[0484] The server uses a speech recognition engine to convert the received voice data into text data such as "I haven't had much of an appetite lately." It then analyzes the data using a natural language processing engine to extract the symptom "lack of appetite." Based on this information, the server updates the patient's medical record and uses a generative AI model to generate advice such as "Try to regulate your eating habits," which is then provided to the patient via their device.

[0485] Prompt Sentence Examples

[0486] Here is an example of a prompt to be fed to a generative AI model:

[0487] Example prompt:

[0488] "A patient has recently complained of a lack of appetite. Please add the appropriate information to the medical record and generate appropriate advice."

[0489] This system will reduce the workload of medical professionals while enabling them to manage medical information and provide prompt and appropriate advice to patients, thereby improving the efficiency and quality of regional medical care.

[0490] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0491] Step 1:

[0492] The user operates the device to start a conversation with the AI. The input is the patient's voice (e.g., "I haven't had much of an appetite lately."). The output is the captured voice data on the device. Specifically, the patient opens the smartphone app, taps the "voice input" button, and speaks the voice message.

[0493] Step 2:

[0494] The terminal captures the patient's voice and sends the voice data to the server. The input is the voice data captured in step 1. The output is the voice data sent to the server. Specifically, the terminal captures voice using the built-in microphone and uploads the voice data to the server in real time. HTTPS is used as the communication protocol, and data is encrypted.

[0495] Step 3:

[0496] The server converts the received voice data into text data using a voice recognition engine. The input is the voice data sent from the device. The output is the text data converted from the voice. Specifically, the server sends the voice data to a voice recognition engine (e.g., Google Speech-to-Text API), and the API converts the voice data into text data such as "I haven't had much of an appetite lately." The server then saves the converted text data.

[0497] Step 4:

[0498] The server analyzes the converted text data using a natural language processing engine to extract important medical information. The input is the text data converted in step 3. The output is the extracted medical information. Specifically, the server inputs the text data into a natural language processing engine (e.g., spaCy, BERT model), and the engine extracts the keyword "no appetite" and recognizes it as a symptom of "loss of appetite." The extracted information is temporarily stored.

[0499] Step 5:

[0500] The server reflects the extracted medical information in the patient's medical record. The input is the medical information extracted in step 4. The output is the updated medical record. Specifically, the server retrieves the medical record based on the patient's ID, adds the new information "loss of appetite" to the existing record, and saves the updated medical record in the database.

[0501] Step 6:

[0502] The server generates appropriate lifestyle and treatment advice for the patient based on the extracted medical information. The input is the medical information extracted in step 4. The output is the generated advice message. Specifically, the server inputs a prompt to the generative AI model (e.g., GPT-4), and the AI ​​model generates advice such as "Try to regulate your eating habits." The server then sends the generated advice to the device.

[0503] Step 7:

[0504] The terminal displays the advice received from the server to the patient. The input is the advice message sent from the server. The output is the advice displayed on the terminal. Specifically, the advice received by the terminal is displayed on the screen so that the patient can check it. For example, "Try to regulate your eating habits" is displayed.

[0505] (Application example 1)

[0506] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0507] While conventional speech recognition and natural language processing systems are primarily used in the medical field, their application in other fields such as food delivery has not been fully explored. Furthermore, there is a lack of systems that can efficiently process orders and provide specific advice and product recommendations through voice communication with users, creating a need for an improved user experience.

[0508] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0509] In this invention, the server includes an interface means for voice communication with the patient, a voice recognition means for converting received voice data into text data, a natural language processing means for analyzing the text data and extracting important information, a record updating means for updating the medical record with the extracted information, an advice generating means for generating advice for the patient based on the extracted information, a means for converting order details into text data through voice communication with the user, a natural language processing means for analyzing the text data and extracting the order details, a means for storing the extracted order details in a database, and a means for generating additional recommended products and advice based on the extracted order details. This makes it possible to streamline the food delivery ordering process and provide users with recommended products and advice that are appropriate for them.

[0510] "Interface means" refers to devices or software that are responsible for voice communication with patients or users, and have the function of capturing voice data and sending it to a server.

[0511] "Speech recognition means" refers to a technology that converts received voice data into text data, and uses a voice recognition engine.

[0512] "Natural language processing means" refers to technology that analyzes text data and extracts important information and order details, and uses a natural language processing engine.

[0513] "Record updating means" refers to the function that updates extracted information into medical records and databases, keeping patient charts and user order histories up to date.

[0514] The "advice generation means" is a function that generates appropriate advice and recommended products for patients and users based on the extracted information, and generates messages based on lifestyle habits and order details.

[0515] The "means for converting the order contents into text data" refers to a function for converting the user's voice order into text data, and uses voice recognition technology.

[0516] "Means for analyzing and extracting order details" refers to a function that analyzes order details from text data and extracts necessary information, and uses natural language processing technology.

[0517] "Means for saving to a database" refers to the function of saving the extracted order details to a database, which serves as the basis for managing order history and reordering.

[0518] "Means for generating additional product recommendations and advice" refers to the functionality for generating additional product recommendations and specific advice based on the user's order, which is used to enhance the user experience.

[0519] This invention is a system for communicating with users through voice, analyzing the content of the communication, and efficiently managing order information. The system is implemented with the following specific configuration and procedures.

[0520] System configuration

[0521] 1. Interface Method

[0522] Terminal: Responsible for voice communication with the user, capturing the user's voice and sending it to the server. It can take the form of a smartphone or smart speaker.

[0523] 2. Voice Recognition Method

[0524] Server: Receives the voice data sent from the device and converts it into text data using a speech recognition engine (e.g., Google Cloud Speech-to-Text).

[0525] 3. Natural Language Processing Methods

[0526] Server: Analyzes the converted text data and extracts order details and important information (e.g., Google Cloud Natural Language API).

[0527] 4. Record-updating methods

[0528] Server: Save the extracted order details to a database (e.g., Firebase Realtime Database) and update the user's order history.

[0529] 5. Advice Generation Methods

[0530] Server: Generates additional product recommendations and specific advice appropriate for the user based on the extracted order details.

[0531] Example of a system

[0532] 1. Capture and transmit audio

[0533] User: The user uses the device to place an order by voice. For example, the user might say, "I'd like one pizza and two salads, please."

[0534] Device: Captures this conversation and sends the audio data to the server.

[0535] 2. Audio data conversion

[0536] Server: The received voice data is converted into text data using a voice recognition engine, such as "One pizza and two salads, please."

[0537] 3. Text Data Analysis

[0538] Server: The converted text data is analyzed using a natural language processing engine, and the order details, "one pizza" and "two salads," are extracted.

[0539] 4. Storage of order data

[0540] Server: Saves the extracted order details to the database and updates the user's order history.

[0541] 5. Generating and Providing Advice

[0542] Server: Based on the order, the server generates additional product recommendations and specific advice appropriate for the user. For example, it generates a message such as "How about a Margherita pizza and a green salad?" and delivers this to the user via the device.

[0543] Specific prompt examples

[0544] The user initiates a voice order using the following prompt:

[0545] "One pizza and two salads, please."

[0546] In this way, this system can streamline the food delivery ordering process and improve the user experience. Specifically, by combining voice recognition technology and natural language processing technology, it is possible to accurately understand and manage order details, as well as provide appropriate product recommendations and advice.

[0547] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0548] Step 1:

[0549] The user places an order by voice. Specifically, the user launches the smartphone app and voice-records their order, such as "One pizza and two salads, please." This voice data becomes the input for the system.

[0550] Step 2:

[0551] The device sends the captured voice data to the server. Specifically, the device records the user's voice and sends the data to the Google Cloud Speech-to-Text API, requesting that the voice data be converted to text. In this case, the input is voice data and the output is text data.

[0552] Step 3:

[0553] The server converts the received voice data into text data using a speech recognition engine. Specifically, the server sends the voice data to the Google Cloud Speech-to-Text API and receives the text data as a result. At this stage, the input is voice data, and the output is text data obtained by speech recognition.

[0554] Step 4:

[0555] The server analyzes the text data using a natural language processing engine to extract the order details and important information. Specifically, the server sends the text data to the Google Cloud Natural Language API, which extracts the order items (e.g., one pizza, two salads). In this case, the input is text data, and the output is the specific order details and quantity.

[0556] Step 5:

[0557] The server saves the extracted order details in a database. Specifically, it makes a request to Firebase Realtime Database to save the order details (e.g., "1 pizza" and "2 salads"). The input at this stage is the order data, and the output is the updated database results.

[0558] Step 6:

[0559] The server generates additional product recommendations and specific advice based on the order details. Specifically, the server references the user's past order history and current order details, and uses the corresponding generative AI model to generate advice and recommendations such as "How about a Margherita pizza and a green salad?" The input at this stage is the order details and history data, and the output is the generated advice and recommendation message.

[0560] Step 7:

[0561] The server sends the generated advice and recommendation messages to the terminal. Specifically, the server uses a communication protocol to send the generated messages to the terminal. In this case, the input is the generated message, and the output is the data to be sent to the terminal.

[0562] Step 8:

[0563] The device notifies the user of the received advice or recommendation message. Specifically, it displays the message to the user using the smartphone's notification function. At this stage, the input is the message sent from the server, and the output is the notification content to the user.

[0564] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0565] The present invention is a system that extracts important medical information through voice communication with patients, updates the patient's medical record based on that information, and provides appropriate advice. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to respond based on the patient's emotional state and provide more personalized care. This system has the following components:

[0566] System configuration

[0567] 1. Interface Method

[0568] Terminal: Responsible for voice communication with the patient, capturing the patient's voice and sending it to the server. This can be a phone, a dedicated application, or a device with a microphone.

[0569] 2. Voice Recognition Method

[0570] Server: Receives voice data sent from the device and converts it into text data using a voice recognition engine. For example, if a patient says, "I often have trouble sleeping at night recently," the voice data is converted into text data saying, "I often have trouble sleeping at night recently."

[0571] 3. Natural Language Processing Methods

[0572] Server: Analyzes the converted text data and extracts important medical information. In this process, it identifies the keyword "can't sleep" from the text and recognizes that this corresponds to the medical information "insomnia."

[0573] 4. Emotion Engine

[0574] Server: Identifies emotions from the patient's voice and text data. For example, it analyzes elements such as the tone, speed, and pitch of the patient's voice to recognize emotions such as anxiety, tension, or relief.

[0575] 5. Record-updating methods

[0576] Server: Reflects the extracted important medical and emotional information in the patient's medical record. For example, the symptom information "insomnia" and the emotional information "anxiety" are added to the medical record.

[0577] 6. Advice Generation Methods

[0578] Server: Based on the extracted information and emotional information, the server generates advice on appropriate lifestyle habits and treatment for the patient. For example, for a patient with insomnia and anxiety, the server generates specific advice such as, "It would be good to improve your sleeping environment and try to relax. Also, if you feel anxious, try taking deep breaths."

[0579] Example of a system

[0580] 1. Capture and transmit audio

[0581] User: The patient uses the device to start a conversation with the AI, for example, saying, "I'm worried because I've lost my appetite recently."

[0582] Device: Captures this conversation and sends the audio data to the server.

[0583] 2. Audio data conversion

[0584] Server: The received voice data is converted into text data by a voice recognition engine. For example, it may be converted into "I'm worried because I've lost my appetite recently."

[0585] 3. Text Data Analysis

[0586] Server: The converted text data is analyzed using a natural language processing engine to extract symptom information such as "loss of appetite." It also uses an emotion engine to extract emotional information recognized as "worry."

[0587] 4. Updating medical records

[0588] Server: The extracted symptom information of "no appetite" and emotional information of "worry" are reflected in the patient's medical record.

[0589] 5. Generating and Providing Advice

[0590] Server: Based on the symptom information of "loss of appetite" and the emotional information of "worry," the server generates appropriate advice for the patient. For example, the server generates advice such as, "Try to maintain a regular lifestyle and gradually incorporate your favorite foods into your diet. If you continue to feel anxious, we recommend that you try relaxation therapy or seek counseling," and provides this advice to the patient via a device.

[0591] This system efficiently manages important medical information through voice communication with patients, and by combining it with an emotion engine, enables personalized responses based on the patient's emotional state, ultimately reducing the workload of medical professionals and enabling higher quality medical services to be provided to patients.

[0592] The processing flow will be explained below.

[0593] Step 1:

[0594] User: The patient uses the device to initiate a conversation with the AI, for example, saying, "I've lost my appetite recently and I'm very worried."

[0595] Step 2:

[0596] Terminal: Captures the patient's voice and transmits the voice data to the server in real time.

[0597] Step 3:

[0598] Server: The received voice data is passed to a voice recognition engine and converted into text data. The text data becomes, "I've lost my appetite recently and I'm very worried."

[0599] Step 4:

[0600] Server: The converted text data is passed to a natural language processing engine, which analyzes the text content. Through the analysis, medically relevant information such as "no appetite" is extracted.

[0601] Step 5:

[0602] Server: Using an emotion engine, identify the patient's emotion from the converted text and voice data. In this case, the emotion "worry" is recognized.

[0603] Step 6:

[0604] Server: Combines and summarizes the analyzed medical information and the recognized emotional information, and reflects this information in the patient's medical record. Specifically, the symptom information of "loss of appetite" and the emotional information of "worry" are added to the medical record.

[0605] Step 7:

[0606] Server: Generates appropriate advice for the patient based on the symptom information of "loss of appetite" and the emotion information of "worry." For example, it generates a message such as, "Try to maintain a regular lifestyle and gradually incorporate your favorite foods into your diet. Also, if you continue to feel anxious, we recommend relaxation and counseling."

[0607] Step 8:

[0608] Server: Sends the generated advice to the terminal and issues instructions to provide to the patient.

[0609] Step 9:

[0610] Terminal: Provides advice received from the server to the patient. In the case of a telephone call, a synthesized voice is generated and the advice is played back as a voice message.

[0611] Step 10:

[0612] User: The patient accepts the advice and indicates their intention to end the conversation (e.g., hang up the phone, enter an end command).

[0613] Step 11:

[0614] Terminal: Sends an intention to end the conversation to the server.

[0615] Step 12:

[0616] Server: Ends the conversation and closes the session, optionally logging and resetting the system.

[0617] ---

[0618] The above is the flow of specific processing steps for the "AI that is always kind" system that combines an emotion engine, and an explanation of the specific operations at each step.

[0619] Example 2

[0620] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0621] Conventional patient care systems have the problem that the information obtained from patients through voice communication is limited, making it difficult to fully grasp the patient's emotional state. Furthermore, the process of analyzing the obtained information in real time and providing advice is often inefficient. This increases the workload of medical professionals and risks reducing the quality of care provided to patients. Therefore, there was a need for the development of a system that can simultaneously extract important medical information and emotional information from voice data and provide prompt and appropriate advice.

[0622] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an interface means for voice communication with the patient, a voice recognition means for converting received voice data into text data, a natural language processing means for analyzing the text data and extracting important information, an emotion recognition means for identifying emotions from the extracted voice and text data, a record updating means for reflecting the extracted information in the medical record, and an advice generation means for generating advice for the patient based on the extracted information. This makes it possible to simultaneously extract important medical information and emotional information from the voice data and provide prompt and appropriate advice.

[0623] The "interface means" is a means for taking charge of voice communication with the patient, capturing the patient's voice, and transmitting it to the server.

[0624] The "voice recognition means" is a means for converting received voice data into text data.

[0625] "Natural language processing means" is a means for analyzing text data and extracting important information.

[0626] The "emotion recognition means" is a means for identifying emotions from extracted speech and text data.

[0627] The "record updating means" is a means for updating the extracted information in the patient's medical record.

[0628] The "advice generation means" is a means for generating advice for the patient based on the extracted information.

[0629] The present invention is a system that efficiently extracts important medical information and emotional information of patients through voice communication with them and provides appropriate advice. This system includes the following main components:

[0630] 1. Interface Method

[0631] Terminal: Responsible for voice communication with the patient, capturing the patient's voice and sending it to the server. The terminal can be a smartphone, tablet, PC, etc. Specifically, it collects voice using a microphone and sends the voice data to the server via an internet connection.

[0632] 2. Voice Recognition Method

[0633] Server: Receives voice data sent from the device and converts it into text data using a speech recognition engine. Google Cloud Speech-to-Text and Microsoft Azure Cognitive Services are used as speech recognition engines. For example, the server receives voice data and converts a patient's speech, such as "I've lost my appetite recently and I'm worried," into text.

[0634] 3. Natural Language Processing Methods

[0635] Server: Analyzes the converted text data and extracts important medical information. During this process, it automatically identifies keywords and phrases (e.g., "no appetite") and determines whether they correspond to symptoms. Apache OpenNLP and spaCy are used as natural language processing engines.

[0636] 4. Emotion recognition means

[0637] Server: Identifies the patient's emotion from the received voice and converted text data. IBM Watson Tone Analyzer and Affectiva SDK are used as emotion engines. For example, if a patient says "I'm worried," the server recognizes this as the emotion "worried."

[0638] 5. Record-updating methods

[0639] Server: The extracted important medical and emotional information is reflected in the patient's medical record. Epic Systems or Cerner is used as the medical record management system, and Oracle Database or PostgreSQL is used as the database.

[0640] 6. Advice Generation Methods

[0641] Server: Based on the extracted information, the server generates appropriate lifestyle and treatment advice for the patient. Generative AI models such as GPT (Generative Pre-trained Transformer) and BERT (Bidirectional Encoder Representations from Transformers) are used. For example, the server might generate advice such as, "Try to maintain a healthy lifestyle and gradually incorporate your favorite foods into your diet. If you continue to feel anxious, we recommend relaxation and counseling."

[0642] Examples:

[0643] If the user says, "I'm worried because I haven't had much of an appetite lately," the system operates as follows.

[0644] 1. Interface method: The user speaks through the smartphone microphone, saying, "I'm worried because I haven't had much of an appetite lately."

[0645] 2. Speech recognition: The device captures the voice and sends it to the server, which converts the voice into text using a speech recognition engine.

[0646] 3. Natural language processing: Analyze the converted text "I'm worried because I've had no appetite lately" and extract important information. Specifically, extract the symptom information of "no appetite."

[0647] 4. Emotion recognition means: The server identifies the emotional information "worry" from the text and voice.

[0648] 5. Record updating method: The extracted symptom information of "loss of appetite" and emotional information of "worry" are added to the medical record.

[0649] 6. Advice generation method: Using the generative AI model, advice such as "Try to maintain a regular lifestyle and gradually incorporate your favorite foods into your diet. Also, if you continue to feel anxious, we recommend that you seek relaxation and counseling" is generated and provided to the patient via their device.

[0650] Example prompt sentence:

[0651] Patient symptoms: Loss of appetite

[0652] Patient Emotions: Anxiety

[0653] Good advice:

[0654] Try to maintain a regular lifestyle and gradually incorporate your favorite foods into your diet. If you continue to feel anxious, we recommend seeking relaxation and counseling.

[0655] The above is a detailed description of an embodiment of the present invention. This system quickly and accurately extracts important medical and emotional information from speech data, enabling personalized advice to be provided to patients.

[0656] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0657] Step 1:

[0658] User: The patient uses the device to start a conversation with the AI, for example, saying, "I'm worried because I've lost my appetite recently."

[0659] Input: Patient's voice

[0660] Output: Captured audio data

[0661] Specific operation: A user speaks into the microphone of a smartphone or tablet. An application on the device captures the voice data and converts it into a voice data format.

[0662] Step 2:

[0663] Terminal: Sends captured audio data to the server.

[0664] Input: Captured audio data

[0665] Output: Audio data sent to the server

[0666] What it does: The device uses an internet connection to send audio data to the server, using HTTPS as the communication protocol to ensure secure data transfer.

[0667] Step 3:

[0668] Server: Receives the voice data sent from the terminal.

[0669] Input: Transmitted audio data

[0670] Output: Received audio data

[0671] Specific operation: The server receives the voice data and stores it in temporary storage.

[0672] Step 4:

[0673] Server: The received voice data is converted into text data using a voice recognition engine.

[0674] Input: Received audio data

[0675] Output: Text data

[0676] Specific operation: The server calls a speech recognition engine (for example, Google Cloud Speech-to-Text), analyzes the voice signal, and converts it into text data such as "I'm worried because I've lost my appetite lately."

[0677] Step 5:

[0678] Server: The converted text data is analyzed using a natural language processing engine.

[0679] Input: Converted text data

[0680] Output: Extracted symptom information and emotion information

[0681] Specific operation: The server uses a natural language processing engine (e.g., spaCy) to extract symptom information such as "no appetite" from the text data, and simultaneously uses an emotion engine (e.g., IBM Watson Tone Analyzer) to extract emotion information such as "worry."

[0682] Step 6:

[0683] Server: Reflects the extracted information in the patient's medical record.

[0684] Input: Extracted symptom information and emotion information

[0685] Output: Updated medical record

[0686] Specific operation: The server accesses a medical record management system (e.g., Epic Systems) and updates the patient's medical record database (e.g., Oracle Database). New information is added: the symptom "loss of appetite" and the emotion "anxiety."

[0687] Step 7:

[0688] Server: Generates advice for the patient based on the extracted information.

[0689] Input: Updated medical record

[0690] Output: Generated advice

[0691] Specific operation: The server uses an advice generation engine (e.g., GPT-3) to generate advice such as, "Try to maintain a regular lifestyle and incorporate your favorite foods little by little. Also, if you continue to feel anxious, we recommend relaxation and counseling."

[0692] Step 8:

[0693] Server: Sends the generated advice to the device.

[0694] Input: Generated advice

[0695] Output: Advice sent

[0696] Specific operation: The server generates advice and sends it to the device. HTTPS is used as the communication protocol to transfer data securely.

[0697] Step 9:

[0698] Terminal: Receives advice and provides it to the user by display or voice.

[0699] Input: Submitted advice

[0700] Output: Advice given to the user

[0701] Specific behavior: The device displays the advice received from the server, alerts the user with a notification sound or a pop-up message, and, if necessary, reads the advice aloud via the voice assistant.

[0702] (Application example 2)

[0703] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0704] Conventional medical information systems equipped with voice recognition and emotion recognition technologies have difficulty responding in real time to patients' emotional states. Furthermore, there is a lack of systems that can take appropriate measures immediately in emergency situations. Therefore, there is a need to ensure patient safety and respond quickly and efficiently.

[0705] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0706] In this invention, the server includes an interface means for voice communication with the patient, a voice recognition means for converting received voice data into text data, a natural language processing means for analyzing the text data and extracting important information, a record updating means for updating the extracted information in the medical record, an advice generation means for generating advice for the patient based on the extracted information and emotional information, an emotion recognition means for identifying emotional information from the voice data, and an emergency response means for detecting an emergency based on the extracted information and emotional information and sending an alert as necessary. This enables the provision of personalized care according to the patient's emotional state and a rapid response in the event of an emergency.

[0707] The "interface means" is a device that is responsible for voice communication with the patient, captures the patient's voice, and transmits it to the server.

[0708] The "voice recognition means" is an engine that converts received voice data into text data.

[0709] A "natural language processing tool" is an engine that analyzes text data and extracts important medical and other information from it.

[0710] The "record updating means" is a system for updating extracted information into the patient's medical record and security log.

[0711] The "advice generation means" is an engine that generates appropriate advice for the patient based on the extracted information and emotional information.

[0712] The "emotion recognition means" is an engine that identifies the patient's emotional information from the voice data.

[0713] The "emergency response tool" is a system for detecting emergency situations based on extracted information and emotion information and sending alerts as needed.

[0714] The system for implementing the present invention comprises an interface means, a speech recognition means, a natural language processing means, a record updating means, an advice generation means, an emotion recognition means, and an emergency response means. The following is a detailed description of each means and how they work together.

[0715] Interface Means

[0716] The server manages the interface means for voice communication with the patient, which has the function of capturing the patient's voice using a smartphone with a microphone or a dedicated application and transmitting it to the server.

[0717] Voice recognition means

[0718] The server converts the voice data sent from the device into text data using Google's speech recognition API, etc. For example, if a patient says, "Help me, someone has broken into my house," the server converts the voice data into text data.

[0719] Natural language processing tools

[0720] The server then analyzes the converted text data using HuggingFace's natural language processing engine to extract important information, identifying the keyword "home intrusion" from the text and recognizing that this is an emergency.

[0721] Record updating method

[0722] The server then updates the patient's security log with the extracted information, for example adding an emergency event such as "home intrusion" to the security log.

[0723] Advice Generation Method

[0724] The server generates appropriate advice for the patient based on the extracted information and emotion information. For example, in the event of an intrusion, the server generates specific advice such as "Evacuate to a safe place and immediately contact your emergency contact."

[0725] emotion recognition means

[0726] The server identifies the patient's emotions from the voice data by analyzing factors such as tone, speed, and pitch of the voice to assess whether the patient is feeling anxious or scared.

[0727] Emergency response measures

[0728] Based on the extracted information and emotion information, the server detects emergencies and sends alerts to emergency contacts as needed. For example, if an intruder occurs, an email is sent immediately to emergency contacts (family members or a security company).

[0729] Specific examples

[0730] Example speech input: "Help, someone is breaking into my house."

[0731] Emergency Alert: "Emergency. Please help, someone has broken into my house."

[0732] Email recipients: Emergency contacts (e.g., family, security company)

[0733] Prompt Sentence Examples

[0734] If a user says, "Help me, someone's broken into my house," the system captures that speech, converts it to text, and then runs a sentiment analysis on that text. If the emotion of fear is recognized, an email alert is sent to emergency contacts.

[0735] The system allows for personalized care according to the patient's emotional state and rapid response in emergency situations.

[0736] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0737] Step 1:

[0738] The user inputs voice using the terminal. The terminal captures the voice and sends this voice data to the server. The input is the user's voice data, and the output is the voice data sent to the server.

[0739] Step 2:

[0740] The server converts the received voice data into text data using Google's speech recognition API. The input is voice data, and the output is text data. For example, this conversion converts a voice message like "Help me, someone has broken into my house" into text data.

[0741] Step 3:

[0742] The server then analyzes the converted text data using HuggingFace's natural language processing engine to extract important information. The input is text data, and the output is the extracted important information. During this analysis, the keyword "house intrusion" is identified, and it is recognized that this is an emergency.

[0743] Step 4:

[0744] The server analyzes emotional information from the voice data. It analyzes the tone, speed, and pitch of the voice to identify emotional states such as anxiety or fear. The input is voice data, and the output is emotional information.

[0745] Step 5:

[0746] The server reflects the extracted important information and emotional information in the patient's security log. The input is the extracted important information and emotional information, and the output is the updated security log. Here, the information "house intrusion" and the user's feeling of fear are recorded in the log.

[0747] Step 6:

[0748] The server generates appropriate advice for the patient based on the extracted information. For example, advice such as "Evacuate to a safe place and immediately contact your emergency contacts" is generated. The input is the extracted information and emotion information, and the output is the generated advice.

[0749] Step 7:

[0750] If the server determines that an emergency has occurred, it will send an alert to the emergency contact as needed. The input is the emergency information and emotion information, and the output is an alert email to the emergency contact. For example, a message such as "An emergency has occurred. Please help, someone has broken into my house" is sent.

[0751] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0752] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0753] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0754] [Third embodiment]

[0755] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0756] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0757] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0758] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0759] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0760] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0761] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0762] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0763] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0764] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0765] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0766] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0767] The present invention provides a system for communicating with patients through voice, analyzing the content of the communication, and efficiently managing medical information. This system is implemented with the following configuration.

[0768] System configuration

[0769] 1. Interface Method

[0770] Terminal: Responsible for voice communication with the patient, capturing the patient's voice and sending it to the server. It can take the form of a landline phone or a smartphone app.

[0771] 2. Voice Recognition Method

[0772] Server: Receives voice data sent from the device and converts it into text data using a voice recognition engine. For example, if a patient says, "I often have trouble sleeping at night recently," the server converts the voice data into text as, "I often have trouble sleeping at night recently."

[0773] 3. Natural Language Processing Methods

[0774] Server: Analyzes the converted text data and extracts important medical information. Specifically, it extracts the keyword "can't sleep" from the text data and recognizes that it corresponds to the symptom of "insomnia."

[0775] 4. Record-updating methods

[0776] Server: Reflects the extracted medical information in the patient's medical record. For example, the symptom "insomnia" is added to the patient's chart.

[0777] 5. Advice Generation Methods

[0778] Server: Based on the extracted information, the server generates appropriate lifestyle and treatment advice for the patient. For example, if "insomnia" information is extracted, the server generates advice to improve the quality of sleep, such as "Improve your sleeping environment and try to exercise regularly," and provides this to the patient via their device.

[0779] Example of a system

[0780] 1. Capture and transmit audio

[0781] User: The patient uses the device to start a conversation with the AI. For example, the patient might say, "I haven't had much of an appetite lately."

[0782] Device: Captures this conversation and sends the audio data to the server.

[0783] 2. Audio data conversion

[0784] Server: The received voice data is converted into text data using a voice recognition engine, such as "I haven't had much of an appetite lately."

[0785] 3. Text Data Analysis

[0786] Server: The converted text data is analyzed using a natural language processing engine to extract the symptom "loss of appetite."

[0787] 4. Updating medical records

[0788] Server: The extracted information "no appetite" is reflected in the patient's medical record.

[0789] 5. Generating and Providing Advice

[0790] Server: Based on the information that the patient has no appetite, the server generates appropriate advice for the patient. For example, the server generates advice such as "Try to regulate your eating habits" and provides this to the patient via a terminal.

[0791] By using this system, it will be possible to reduce the workload of medical professionals while enabling them to manage medical information and provide advice to patients quickly and appropriately, thereby improving the efficiency and quality of regional medical care.

[0792] The processing flow will be explained below.

[0793] Step 1:

[0794] User: The patient initiates a conversation with the AI ​​using a device. For example, the patient picks up the phone and says, "I often have trouble sleeping at night these days."

[0795] Step 2:

[0796] Terminal: Captures the patient's voice and transmits the voice data to the server in real time.

[0797] Step 3:

[0798] Server: Passes the received voice data to a voice recognition engine and converts it into text data. The text data becomes "I often have trouble sleeping at night these days."

[0799] Step 4:

[0800] Server: The converted text data is passed to a natural language processing engine, which analyzes the text content. Through the analysis, medically relevant information such as "I can't sleep at night" is extracted.

[0801] Step 5:

[0802] Server: Summarizes the extracted important medical information and adds it to the patient's medical record in the database as relevant information. For example, the information "insomnia" is added to the patient's medical record.

[0803] Step 6:

[0804] Server: Generates appropriate advice based on the keyword "insomnia." For example, it generates a message such as "Improve your sleeping environment and exercise regularly."

[0805] Step 7:

[0806] Server: Sends the generated advice to the terminal and sends instructions to provide to the patient.

[0807] Step 8:

[0808] Terminal: The advice received from the server is conveyed to the patient. In the case of a telephone call, it is played as a voice message.

[0809] Step 9:

[0810] User: The patient accepts the advice and indicates their intention to end the conversation (e.g., hang up the phone, enter an end command).

[0811] Step 10:

[0812] Terminal: Sends an intention to end the conversation to the server.

[0813] Step 11:

[0814] Server: Ends the conversation and closes the session, optionally logging and resetting the system.

[0815] ---

[0816] The above is the flow of the specific processing steps of the "AI that is always helpful" system, and an explanation of the specific operations at each step.

[0817] Example 1

[0818] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0819] In conventional medical systems, medical professionals manually manage information about patients' symptoms and lifestyle habits, which requires a great deal of time and effort. There is also a high risk of information leaks and input errors. Furthermore, it is difficult to provide appropriate advice to each patient.

[0820] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0821] In this invention, the server includes an interface means for voice communication with patients, a voice recognition means for converting received voice data into text data using a natural language processing engine, and a natural language processing means for analyzing the converted text data and extracting medical information. This makes it possible to efficiently manage patients' medical information and provide appropriate advice in real time.

[0822] 1. "Interface means" means a device or software that is responsible for voice communication with the patient, capturing voice data and transmitting it to the server.

[0823] 2. "Speech recognition means" means a device or software that converts received voice data into text data using a natural language processing engine.

[0824] 3. "Natural language processing means" means a device or software that analyzes the converted text data and extracts important medical information.

[0825] 4. "Record updating device" means a device or software that updates extracted medical information into a patient's medical record.

[0826] 5. "Advice generation means" refers to a device or software that generates and provides advice regarding lifestyle habits and treatment based on extracted medical information.

[0827] 6. "Voice data" means voice information collected from a patient via an interface means.

[0828] 7. "Text data" means character information converted from voice data by voice recognition means.

[0829] 8. "Medical information" means information about a patient's symptoms and lifestyle habits extracted from text data using natural language processing means.

[0830] The present invention is a system for communicating with patients through voice, analyzing the content of the communication, and efficiently managing medical information. Specific embodiments of the present invention will be described below.

[0831] System configuration

[0832] 1. Interface Method

[0833] The device, which can take the form of a landline phone or a smartphone app, handles voice communication with the patient, captures the voice data, and transmits it to a server.

[0834] 2. Voice Recognition Method

[0835] The server receives the voice data sent from the device and converts the voice into text data using a speech recognition engine (e.g., Google Speech-to-Text API).

[0836] For example, if a patient says, "Recently, I've often had trouble sleeping at night," the voice data is converted into text data that reads, "Recently, I've often had trouble sleeping at night."

[0837] 3. Natural Language Processing Methods

[0838] The server analyzes the text data generated by speech recognition and extracts important medical information using natural language processing engines such as spaCy and the BERT model.

[0839] As a specific example, the keyword "can't sleep" is extracted from the text data "Recently, I often can't sleep at night" and it is recognized that this corresponds to the symptom of "insomnia."

[0840] 4. Record-updating methods

[0841] The server reflects the extracted medical information in the patient's medical record. For example, the extracted information on "insomnia" is added to the patient's chart.

[0842] 5. Advice Generation Methods

[0843] The server generates appropriate lifestyle and treatment advice for the patient based on the extracted medical information, using a generative AI model (e.g., GPT-4).

[0844] For example, if information about "insomnia" is extracted, a message will be generated saying, "It would be a good idea to improve your sleeping environment and exercise regularly," and this will be provided to the patient via the terminal.

[0845] Specific examples of programs

[0846] User operation

[0847] The user uses the device to start a conversation with the AI. For example, a patient might say, "I haven't had much of an appetite lately."

[0848] Processing by the terminal

[0849] The device captures the audio and sends the audio data to the server.

[0850] Server processing

[0851] The server uses a speech recognition engine to convert the received voice data into text data such as "I haven't had much of an appetite lately." It then analyzes the data using a natural language processing engine to extract the symptom "lack of appetite." Based on this information, the server updates the patient's medical record and uses a generative AI model to generate advice such as "Try to regulate your eating habits," which is then provided to the patient via their device.

[0852] Prompt Sentence Examples

[0853] Here is an example of a prompt to be fed to a generative AI model:

[0854] Example prompt:

[0855] "A patient has recently complained of a lack of appetite. Please add the appropriate information to the medical record and generate appropriate advice."

[0856] This system will reduce the workload of medical professionals while enabling them to manage medical information and provide prompt and appropriate advice to patients, thereby improving the efficiency and quality of regional medical care.

[0857] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0858] Step 1:

[0859] The user operates the device to start a conversation with the AI. The input is the patient's voice (e.g., "I haven't had much of an appetite lately."). The output is the captured voice data on the device. Specifically, the patient opens the smartphone app, taps the "voice input" button, and speaks the voice message.

[0860] Step 2:

[0861] The terminal captures the patient's voice and sends the voice data to the server. The input is the voice data captured in step 1. The output is the voice data sent to the server. Specifically, the terminal captures voice using the built-in microphone and uploads the voice data to the server in real time. HTTPS is used as the communication protocol, and data is encrypted.

[0862] Step 3:

[0863] The server converts the received voice data into text data using a voice recognition engine. The input is the voice data sent from the device. The output is the text data converted from the voice. Specifically, the server sends the voice data to a voice recognition engine (e.g., Google Speech-to-Text API), and the API converts the voice data into text data such as "I haven't had much of an appetite lately." The server then saves the converted text data.

[0864] Step 4:

[0865] The server analyzes the converted text data using a natural language processing engine to extract important medical information. The input is the text data converted in step 3. The output is the extracted medical information. Specifically, the server inputs the text data into a natural language processing engine (e.g., spaCy, BERT model), and the engine extracts the keyword "no appetite" and recognizes it as a symptom of "loss of appetite." The extracted information is temporarily stored.

[0866] Step 5:

[0867] The server reflects the extracted medical information in the patient's medical record. The input is the medical information extracted in step 4. The output is the updated medical record. Specifically, the server retrieves the medical record based on the patient's ID, adds the new information "loss of appetite" to the existing record, and saves the updated medical record in the database.

[0868] Step 6:

[0869] The server generates appropriate lifestyle and treatment advice for the patient based on the extracted medical information. The input is the medical information extracted in step 4. The output is the generated advice message. Specifically, the server inputs a prompt to the generative AI model (e.g., GPT-4), and the AI ​​model generates advice such as "Try to regulate your eating habits." The server then sends the generated advice to the device.

[0870] Step 7:

[0871] The terminal displays the advice received from the server to the patient. The input is the advice message sent from the server. The output is the advice displayed on the terminal. Specifically, the advice received by the terminal is displayed on the screen so that the patient can check it. For example, "Try to regulate your eating habits" is displayed.

[0872] (Application example 1)

[0873] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0874] While conventional speech recognition and natural language processing systems are primarily used in the medical field, their application in other fields such as food delivery has not been fully explored. Furthermore, there is a lack of systems that can efficiently process orders and provide specific advice and product recommendations through voice communication with users, creating a need for an improved user experience.

[0875] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0876] In this invention, the server includes an interface means for voice communication with the patient, a voice recognition means for converting received voice data into text data, a natural language processing means for analyzing the text data and extracting important information, a record updating means for updating the medical record with the extracted information, an advice generating means for generating advice for the patient based on the extracted information, a means for converting order details into text data through voice communication with the user, a natural language processing means for analyzing the text data and extracting the order details, a means for storing the extracted order details in a database, and a means for generating additional recommended products and advice based on the extracted order details. This makes it possible to streamline the food delivery ordering process and provide users with recommended products and advice that are appropriate for them.

[0877] "Interface means" refers to devices or software that are responsible for voice communication with patients or users, and have the function of capturing voice data and sending it to a server.

[0878] "Speech recognition means" refers to a technology that converts received voice data into text data, and uses a voice recognition engine.

[0879] "Natural language processing means" refers to technology that analyzes text data and extracts important information and order details, and uses a natural language processing engine.

[0880] "Record updating means" refers to the function that updates extracted information into medical records and databases, keeping patient charts and user order histories up to date.

[0881] The "advice generation means" is a function that generates appropriate advice and recommended products for patients and users based on the extracted information, and generates messages based on lifestyle habits and order details.

[0882] The "means for converting the order contents into text data" refers to a function for converting the user's voice order into text data, and uses voice recognition technology.

[0883] "Means for analyzing and extracting order details" refers to a function that analyzes order details from text data and extracts necessary information, and uses natural language processing technology.

[0884] "Means for saving to a database" refers to the function of saving the extracted order details to a database, which serves as the basis for managing order history and reordering.

[0885] "Means for generating additional product recommendations and advice" refers to the functionality for generating additional product recommendations and specific advice based on the user's order, which is used to enhance the user experience.

[0886] This invention is a system for communicating with users through voice, analyzing the content of the communication, and efficiently managing order information. The system is implemented with the following specific configuration and procedures.

[0887] System configuration

[0888] 1. Interface Method

[0889] Terminal: Responsible for voice communication with the user, capturing the user's voice and sending it to the server. It can take the form of a smartphone or smart speaker.

[0890] 2. Voice Recognition Method

[0891] Server: Receives the voice data sent from the device and converts it into text data using a speech recognition engine (e.g., Google Cloud Speech-to-Text).

[0892] 3. Natural Language Processing Methods

[0893] Server: Analyzes the converted text data and extracts order details and important information (e.g., Google Cloud Natural Language API).

[0894] 4. Record-updating methods

[0895] Server: Save the extracted order details to a database (e.g., Firebase Realtime Database) and update the user's order history.

[0896] 5. Advice Generation Methods

[0897] Server: Generates additional product recommendations and specific advice appropriate for the user based on the extracted order details.

[0898] Example of a system

[0899] 1. Capture and transmit audio

[0900] User: The user uses the device to place an order by voice. For example, the user might say, "I'd like one pizza and two salads, please."

[0901] Device: Captures this conversation and sends the audio data to the server.

[0902] 2. Audio data conversion

[0903] Server: The received voice data is converted into text data using a voice recognition engine, such as "One pizza and two salads, please."

[0904] 3. Text Data Analysis

[0905] Server: The converted text data is analyzed using a natural language processing engine, and the order details, "one pizza" and "two salads," are extracted.

[0906] 4. Storage of order data

[0907] Server: Saves the extracted order details to the database and updates the user's order history.

[0908] 5. Generating and Providing Advice

[0909] Server: Based on the order, the server generates additional product recommendations and specific advice appropriate for the user. For example, it generates a message such as "How about a Margherita pizza and a green salad?" and delivers this to the user via the device.

[0910] Specific prompt examples

[0911] The user initiates a voice order using the following prompt:

[0912] "One pizza and two salads, please."

[0913] In this way, this system can streamline the food delivery ordering process and improve the user experience. Specifically, by combining voice recognition technology and natural language processing technology, it is possible to accurately understand and manage order details, as well as provide appropriate product recommendations and advice.

[0914] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0915] Step 1:

[0916] The user places an order by voice. Specifically, the user launches the smartphone app and voice-records their order, such as "One pizza and two salads, please." This voice data becomes the input for the system.

[0917] Step 2:

[0918] The device sends the captured voice data to the server. Specifically, the device records the user's voice and sends the data to the Google Cloud Speech-to-Text API, requesting that the voice data be converted to text. In this case, the input is voice data and the output is text data.

[0919] Step 3:

[0920] The server converts the received voice data into text data using a speech recognition engine. Specifically, the server sends the voice data to the Google Cloud Speech-to-Text API and receives the text data as a result. At this stage, the input is voice data, and the output is text data obtained by speech recognition.

[0921] Step 4:

[0922] The server analyzes the text data using a natural language processing engine to extract the order details and important information. Specifically, the server sends the text data to the Google Cloud Natural Language API, which extracts the order items (e.g., one pizza, two salads). In this case, the input is text data, and the output is the specific order details and quantity.

[0923] Step 5:

[0924] The server saves the extracted order details in a database. Specifically, it makes a request to Firebase Realtime Database to save the order details (e.g., "1 pizza" and "2 salads"). The input at this stage is the order data, and the output is the updated database results.

[0925] Step 6:

[0926] The server generates additional product recommendations and specific advice based on the order details. Specifically, the server references the user's past order history and current order details, and uses the corresponding generative AI model to generate advice and recommendations such as "How about a Margherita pizza and a green salad?" The input at this stage is the order details and history data, and the output is the generated advice and recommendation message.

[0927] Step 7:

[0928] The server sends the generated advice and recommendation messages to the terminal. Specifically, the server uses a communication protocol to send the generated messages to the terminal. In this case, the input is the generated message, and the output is the data to be sent to the terminal.

[0929] Step 8:

[0930] The device notifies the user of the received advice or recommendation message. Specifically, it displays the message to the user using the smartphone's notification function. At this stage, the input is the message sent from the server, and the output is the notification content to the user.

[0931] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0932] The present invention is a system that extracts important medical information through voice communication with patients, updates the patient's medical record based on that information, and provides appropriate advice. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to respond based on the patient's emotional state and provide more personalized care. This system has the following components:

[0933] System configuration

[0934] 1. Interface Method

[0935] Terminal: Responsible for voice communication with the patient, capturing the patient's voice and sending it to the server. This can be a phone, a dedicated application, or a device with a microphone.

[0936] 2. Voice Recognition Method

[0937] Server: Receives voice data sent from the device and converts it into text data using a voice recognition engine. For example, if a patient says, "I often have trouble sleeping at night recently," the voice data is converted into text data saying, "I often have trouble sleeping at night recently."

[0938] 3. Natural Language Processing Methods

[0939] Server: Analyzes the converted text data and extracts important medical information. In this process, it identifies the keyword "can't sleep" from the text and recognizes that this corresponds to the medical information "insomnia."

[0940] 4. Emotion Engine

[0941] Server: Identifies emotions from the patient's voice and text data. For example, it analyzes elements such as the tone, speed, and pitch of the patient's voice to recognize emotions such as anxiety, tension, or relief.

[0942] 5. Record-updating methods

[0943] Server: Reflects the extracted important medical and emotional information in the patient's medical record. For example, the symptom information "insomnia" and the emotional information "anxiety" are added to the medical record.

[0944] 6. Advice Generation Methods

[0945] Server: Based on the extracted information and emotional information, the server generates advice on appropriate lifestyle habits and treatment for the patient. For example, for a patient with insomnia and anxiety, the server generates specific advice such as, "It would be good to improve your sleeping environment and try to relax. Also, if you feel anxious, try taking deep breaths."

[0946] Example of a system

[0947] 1. Capture and transmit audio

[0948] User: The patient uses the device to start a conversation with the AI, for example, saying, "I'm worried because I've lost my appetite recently."

[0949] Device: Captures this conversation and sends the audio data to the server.

[0950] 2. Audio data conversion

[0951] Server: The received voice data is converted into text data by a voice recognition engine. For example, it may be converted into "I'm worried because I've lost my appetite recently."

[0952] 3. Text Data Analysis

[0953] Server: The converted text data is analyzed using a natural language processing engine to extract symptom information such as "loss of appetite." It also uses an emotion engine to extract emotional information recognized as "worry."

[0954] 4. Updating medical records

[0955] Server: The extracted symptom information of "no appetite" and emotional information of "worry" are reflected in the patient's medical record.

[0956] 5. Generating and Providing Advice

[0957] Server: Based on the symptom information of "loss of appetite" and the emotional information of "worry," the server generates appropriate advice for the patient. For example, the server generates advice such as, "Try to maintain a regular lifestyle and gradually incorporate your favorite foods into your diet. If you continue to feel anxious, we recommend that you try relaxation therapy or seek counseling," and provides this advice to the patient via a device.

[0958] This system efficiently manages important medical information through voice communication with patients, and by combining it with an emotion engine, enables personalized responses based on the patient's emotional state, ultimately reducing the workload of medical professionals and enabling higher quality medical services to be provided to patients.

[0959] The processing flow will be explained below.

[0960] Step 1:

[0961] User: The patient uses the device to initiate a conversation with the AI, for example, saying, "I've lost my appetite recently and I'm very worried."

[0962] Step 2:

[0963] Terminal: Captures the patient's voice and transmits the voice data to the server in real time.

[0964] Step 3:

[0965] Server: The received voice data is passed to a voice recognition engine and converted into text data. The text data becomes, "I've lost my appetite recently and I'm very worried."

[0966] Step 4:

[0967] Server: The converted text data is passed to a natural language processing engine, which analyzes the text content. Through the analysis, medically relevant information such as "no appetite" is extracted.

[0968] Step 5:

[0969] Server: Using an emotion engine, identify the patient's emotion from the converted text and voice data. In this case, the emotion "worry" is recognized.

[0970] Step 6:

[0971] Server: Combines and summarizes the analyzed medical information and the recognized emotional information, and reflects this information in the patient's medical record. Specifically, the symptom information of "loss of appetite" and the emotional information of "worry" are added to the medical record.

[0972] Step 7:

[0973] Server: Generates appropriate advice for the patient based on the symptom information of "loss of appetite" and the emotion information of "worry." For example, it generates a message such as, "Try to maintain a regular lifestyle and gradually incorporate your favorite foods into your diet. Also, if you continue to feel anxious, we recommend relaxation and counseling."

[0974] Step 8:

[0975] Server: Sends the generated advice to the terminal and issues instructions to provide to the patient.

[0976] Step 9:

[0977] Terminal: Provides advice received from the server to the patient. In the case of a telephone call, a synthesized voice is generated and the advice is played back as a voice message.

[0978] Step 10:

[0979] User: The patient accepts the advice and indicates their intention to end the conversation (e.g., hang up the phone, enter an end command).

[0980] Step 11:

[0981] Terminal: Sends an intention to end the conversation to the server.

[0982] Step 12:

[0983] Server: Ends the conversation and closes the session, optionally logging and resetting the system.

[0984] ---

[0985] The above is the flow of specific processing steps for the "AI that is always kind" system that combines an emotion engine, and an explanation of the specific operations at each step.

[0986] Example 2

[0987] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0988] Conventional patient care systems have the problem that the information obtained from patients through voice communication is limited, making it difficult to fully grasp the patient's emotional state. Furthermore, the process of analyzing the obtained information in real time and providing advice is often inefficient. This increases the workload of medical professionals and risks reducing the quality of care provided to patients. Therefore, there was a need for the development of a system that can simultaneously extract important medical information and emotional information from voice data and provide prompt and appropriate advice.

[0989] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an interface means for voice communication with the patient, a voice recognition means for converting received voice data into text data, a natural language processing means for analyzing the text data and extracting important information, an emotion recognition means for identifying emotions from the extracted voice and text data, a record updating means for reflecting the extracted information in the medical record, and an advice generation means for generating advice for the patient based on the extracted information. This makes it possible to simultaneously extract important medical information and emotional information from the voice data and provide prompt and appropriate advice.

[0990] The "interface means" is a means for taking charge of voice communication with the patient, capturing the patient's voice, and transmitting it to the server.

[0991] The "voice recognition means" is a means for converting received voice data into text data.

[0992] "Natural language processing means" is a means for analyzing text data and extracting important information.

[0993] The "emotion recognition means" is a means for identifying emotions from extracted speech and text data.

[0994] The "record updating means" is a means for updating the extracted information in the patient's medical record.

[0995] The "advice generation means" is a means for generating advice for the patient based on the extracted information.

[0996] The present invention is a system that efficiently extracts important medical information and emotional information of patients through voice communication with them and provides appropriate advice. This system includes the following main components:

[0997] 1. Interface Method

[0998] Terminal: Responsible for voice communication with the patient, capturing the patient's voice and sending it to the server. The terminal can be a smartphone, tablet, PC, etc. Specifically, it collects voice using a microphone and sends the voice data to the server via an internet connection.

[0999] 2. Voice Recognition Method

[1000] Server: Receives voice data sent from the device and converts it into text data using a speech recognition engine. Google Cloud Speech-to-Text and Microsoft Azure Cognitive Services are used as speech recognition engines. For example, the server receives voice data and converts a patient's speech, such as "I've lost my appetite recently and I'm worried," into text.

[1001] 3. Natural Language Processing Methods

[1002] Server: Analyzes the converted text data and extracts important medical information. During this process, it automatically identifies keywords and phrases (e.g., "no appetite") and determines whether they correspond to symptoms. Apache OpenNLP and spaCy are used as natural language processing engines.

[1003] 4. Emotion recognition means

[1004] Server: Identifies the patient's emotion from the received voice and converted text data. IBM Watson Tone Analyzer and Affectiva SDK are used as emotion engines. For example, if a patient says "I'm worried," the server recognizes this as the emotion "worried."

[1005] 5. Record-updating methods

[1006] Server: The extracted important medical and emotional information is reflected in the patient's medical record. Epic Systems or Cerner is used as the medical record management system, and Oracle Database or PostgreSQL is used as the database.

[1007] 6. Advice Generation Methods

[1008] Server: Based on the extracted information, the server generates appropriate lifestyle and treatment advice for the patient. Generative AI models such as GPT (Generative Pre-trained Transformer) and BERT (Bidirectional Encoder Representations from Transformers) are used. For example, the server might generate advice such as, "Try to maintain a healthy lifestyle and gradually incorporate your favorite foods into your diet. If you continue to feel anxious, we recommend relaxation and counseling."

[1009] Examples:

[1010] If the user says, "I'm worried because I haven't had much of an appetite lately," the system operates as follows.

[1011] 1. Interface method: The user speaks through the smartphone microphone, saying, "I'm worried because I haven't had much of an appetite lately."

[1012] 2. Speech recognition: The device captures the voice and sends it to the server, which converts the voice into text using a speech recognition engine.

[1013] 3. Natural language processing: Analyze the converted text "I'm worried because I've had no appetite lately" and extract important information. Specifically, extract the symptom information of "no appetite."

[1014] 4. Emotion recognition means: The server identifies the emotional information "worry" from the text and voice.

[1015] 5. Record updating method: The extracted symptom information of "loss of appetite" and emotional information of "worry" are added to the medical record.

[1016] 6. Advice generation method: Using the generative AI model, advice such as "Try to maintain a regular lifestyle and gradually incorporate your favorite foods into your diet. Also, if you continue to feel anxious, we recommend that you seek relaxation and counseling" is generated and provided to the patient via their device.

[1017] Example prompt sentence:

[1018] Patient symptoms: Loss of appetite

[1019] Patient Emotions: Anxiety

[1020] Good advice:

[1021] Try to maintain a regular lifestyle and gradually incorporate your favorite foods into your diet. If you continue to feel anxious, we recommend seeking relaxation and counseling.

[1022] The above is a detailed description of an embodiment of the present invention. This system quickly and accurately extracts important medical and emotional information from speech data, enabling personalized advice to be provided to patients.

[1023] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1024] Step 1:

[1025] User: The patient uses the device to start a conversation with the AI, for example, saying, "I'm worried because I've lost my appetite recently."

[1026] Input: Patient's voice

[1027] Output: Captured audio data

[1028] Specific operation: A user speaks into the microphone of a smartphone or tablet. An application on the device captures the voice data and converts it into a voice data format.

[1029] Step 2:

[1030] Terminal: Sends captured audio data to the server.

[1031] Input: Captured audio data

[1032] Output: Audio data sent to the server

[1033] What it does: The device uses an internet connection to send audio data to the server, using HTTPS as the communication protocol to ensure secure data transfer.

[1034] Step 3:

[1035] Server: Receives the voice data sent from the terminal.

[1036] Input: Transmitted audio data

[1037] Output: Received audio data

[1038] Specific operation: The server receives the voice data and stores it in temporary storage.

[1039] Step 4:

[1040] Server: The received voice data is converted into text data using a voice recognition engine.

[1041] Input: Received audio data

[1042] Output: Text data

[1043] Specific operation: The server calls a speech recognition engine (for example, Google Cloud Speech-to-Text), analyzes the voice signal, and converts it into text data such as "I'm worried because I've lost my appetite lately."

[1044] Step 5:

[1045] Server: The converted text data is analyzed using a natural language processing engine.

[1046] Input: Converted text data

[1047] Output: Extracted symptom information and emotion information

[1048] Specific operation: The server uses a natural language processing engine (e.g., spaCy) to extract symptom information such as "no appetite" from the text data, and simultaneously uses an emotion engine (e.g., IBM Watson Tone Analyzer) to extract emotion information such as "worry."

[1049] Step 6:

[1050] Server: Reflects the extracted information in the patient's medical record.

[1051] Input: Extracted symptom information and emotion information

[1052] Output: Updated medical record

[1053] Specific operation: The server accesses a medical record management system (e.g., Epic Systems) and updates the patient's medical record database (e.g., Oracle Database). New information is added: the symptom "loss of appetite" and the emotion "anxiety."

[1054] Step 7:

[1055] Server: Generates advice for the patient based on the extracted information.

[1056] Input: Updated medical record

[1057] Output: Generated advice

[1058] Specific operation: The server uses an advice generation engine (e.g., GPT-3) to generate advice such as, "Try to maintain a regular lifestyle and incorporate your favorite foods little by little. Also, if you continue to feel anxious, we recommend relaxation and counseling."

[1059] Step 8:

[1060] Server: Sends the generated advice to the device.

[1061] Input: Generated advice

[1062] Output: Advice sent

[1063] Specific operation: The server generates advice and sends it to the device. HTTPS is used as the communication protocol to transfer data securely.

[1064] Step 9:

[1065] Terminal: Receives advice and provides it to the user by display or voice.

[1066] Input: Submitted advice

[1067] Output: Advice given to the user

[1068] Specific behavior: The device displays the advice received from the server, alerts the user with a notification sound or a pop-up message, and, if necessary, reads the advice aloud via the voice assistant.

[1069] (Application example 2)

[1070] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1071] Conventional medical information systems equipped with voice recognition and emotion recognition technologies have difficulty responding in real time to patients' emotional states. Furthermore, there is a lack of systems that can take appropriate measures immediately in emergency situations. Therefore, there is a need to ensure patient safety and respond quickly and efficiently.

[1072] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1073] In this invention, the server includes an interface means for voice communication with the patient, a voice recognition means for converting received voice data into text data, a natural language processing means for analyzing the text data and extracting important information, a record updating means for updating the extracted information in the medical record, an advice generation means for generating advice for the patient based on the extracted information and emotional information, an emotion recognition means for identifying emotional information from the voice data, and an emergency response means for detecting an emergency based on the extracted information and emotional information and sending an alert as necessary. This enables the provision of personalized care according to the patient's emotional state and a rapid response in the event of an emergency.

[1074] The "interface means" is a device that is responsible for voice communication with the patient, captures the patient's voice, and transmits it to the server.

[1075] The "voice recognition means" is an engine that converts received voice data into text data.

[1076] A "natural language processing tool" is an engine that analyzes text data and extracts important medical and other information from it.

[1077] The "record updating means" is a system for updating extracted information into the patient's medical record and security log.

[1078] The "advice generation means" is an engine that generates appropriate advice for the patient based on the extracted information and emotional information.

[1079] The "emotion recognition means" is an engine that identifies the patient's emotional information from the voice data.

[1080] The "emergency response tool" is a system for detecting emergency situations based on extracted information and emotion information and sending alerts as needed.

[1081] The system for implementing the present invention comprises an interface means, a speech recognition means, a natural language processing means, a record updating means, an advice generation means, an emotion recognition means, and an emergency response means. The following is a detailed description of each means and how they work together.

[1082] Interface Means

[1083] The server manages the interface means for voice communication with the patient, which has the function of capturing the patient's voice using a smartphone with a microphone or a dedicated application and transmitting it to the server.

[1084] Voice recognition means

[1085] The server converts the voice data sent from the device into text data using Google's speech recognition API, etc. For example, if a patient says, "Help me, someone has broken into my house," the server converts the voice data into text data.

[1086] Natural language processing tools

[1087] The server then analyzes the converted text data using HuggingFace's natural language processing engine to extract important information, identifying the keyword "home intrusion" from the text and recognizing that this is an emergency.

[1088] Record updating method

[1089] The server then updates the patient's security log with the extracted information, for example adding an emergency event such as "home intrusion" to the security log.

[1090] Advice Generation Method

[1091] The server generates appropriate advice for the patient based on the extracted information and emotion information. For example, in the event of an intrusion, the server generates specific advice such as "Evacuate to a safe place and immediately contact your emergency contact."

[1092] emotion recognition means

[1093] The server identifies the patient's emotions from the voice data by analyzing factors such as tone, speed, and pitch of the voice to assess whether the patient is feeling anxious or scared.

[1094] Emergency response measures

[1095] Based on the extracted information and emotion information, the server detects emergencies and sends alerts to emergency contacts as needed. For example, if an intruder occurs, an email is sent immediately to emergency contacts (family members or a security company).

[1096] Specific examples

[1097] Example speech input: "Help, someone is breaking into my house."

[1098] Emergency Alert: "Emergency. Please help, someone has broken into my house."

[1099] Email recipients: Emergency contacts (e.g., family, security company)

[1100] Prompt Sentence Examples

[1101] If a user says, "Help me, someone's broken into my house," the system captures that speech, converts it to text, and then runs a sentiment analysis on that text. If the emotion of fear is recognized, an email alert is sent to emergency contacts.

[1102] The system allows for personalized care according to the patient's emotional state and rapid response in emergency situations.

[1103] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1104] Step 1:

[1105] The user inputs voice using the terminal. The terminal captures the voice and sends this voice data to the server. The input is the user's voice data, and the output is the voice data sent to the server.

[1106] Step 2:

[1107] The server converts the received voice data into text data using Google's speech recognition API. The input is voice data, and the output is text data. For example, this conversion converts a voice message like "Help me, someone has broken into my house" into text data.

[1108] Step 3:

[1109] The server then analyzes the converted text data using HuggingFace's natural language processing engine to extract important information. The input is text data, and the output is the extracted important information. During this analysis, the keyword "house intrusion" is identified, and it is recognized that this is an emergency.

[1110] Step 4:

[1111] The server analyzes emotional information from the voice data. It analyzes the tone, speed, and pitch of the voice to identify emotional states such as anxiety or fear. The input is voice data, and the output is emotional information.

[1112] Step 5:

[1113] The server reflects the extracted important information and emotional information in the patient's security log. The input is the extracted important information and emotional information, and the output is the updated security log. Here, the information "house intrusion" and the user's feeling of fear are recorded in the log.

[1114] Step 6:

[1115] The server generates appropriate advice for the patient based on the extracted information. For example, advice such as "Evacuate to a safe place and immediately contact your emergency contacts" is generated. The input is the extracted information and emotion information, and the output is the generated advice.

[1116] Step 7:

[1117] If the server determines that an emergency has occurred, it will send an alert to the emergency contact as needed. The input is the emergency information and emotion information, and the output is an alert email to the emergency contact. For example, a message such as "An emergency has occurred. Please help, someone has broken into my house" is sent.

[1118] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1119] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1120] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1121] [Fourth embodiment]

[1122] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1123] 7, a 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.

[1124] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1125] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1126] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1127] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1128] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1129] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1130] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1131] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1132] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1133] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1134] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1135] The present invention provides a system for communicating with patients through voice, analyzing the content of the communication, and efficiently managing medical information. This system is implemented with the following configuration.

[1136] System configuration

[1137] 1. Interface Method

[1138] Terminal: Responsible for voice communication with the patient, capturing the patient's voice and sending it to the server. It can take the form of a landline phone or a smartphone app.

[1139] 2. Voice Recognition Method

[1140] Server: Receives voice data sent from the device and converts it into text data using a voice recognition engine. For example, if a patient says, "I often have trouble sleeping at night recently," the server converts the voice data into text as, "I often have trouble sleeping at night recently."

[1141] 3. Natural Language Processing Methods

[1142] Server: Analyzes the converted text data and extracts important medical information. Specifically, it extracts the keyword "can't sleep" from the text data and recognizes that it corresponds to the symptom of "insomnia."

[1143] 4. Record-updating methods

[1144] Server: Reflects the extracted medical information in the patient's medical record. For example, the symptom "insomnia" is added to the patient's chart.

[1145] 5. Advice Generation Methods

[1146] Server: Based on the extracted information, the server generates appropriate lifestyle and treatment advice for the patient. For example, if "insomnia" information is extracted, the server generates advice to improve the quality of sleep, such as "Improve your sleeping environment and try to exercise regularly," and provides this to the patient via their device.

[1147] Example of a system

[1148] 1. Capture and transmit audio

[1149] User: The patient uses the device to start a conversation with the AI. For example, the patient might say, "I haven't had much of an appetite lately."

[1150] Device: Captures this conversation and sends the audio data to the server.

[1151] 2. Audio data conversion

[1152] Server: The received voice data is converted into text data using a voice recognition engine, such as "I haven't had much of an appetite lately."

[1153] 3. Text Data Analysis

[1154] Server: The converted text data is analyzed using a natural language processing engine to extract the symptom "loss of appetite."

[1155] 4. Updating medical records

[1156] Server: The extracted information "no appetite" is reflected in the patient's medical record.

[1157] 5. Generating and Providing Advice

[1158] Server: Based on the information that the patient has no appetite, the server generates appropriate advice for the patient. For example, the server generates advice such as "Try to regulate your eating habits" and provides this to the patient via a terminal.

[1159] By using this system, it will be possible to reduce the workload of medical professionals while enabling them to manage medical information and provide advice to patients quickly and appropriately, thereby improving the efficiency and quality of regional medical care.

[1160] The processing flow will be explained below.

[1161] Step 1:

[1162] User: The patient initiates a conversation with the AI ​​using a device. For example, the patient picks up the phone and says, "I often have trouble sleeping at night these days."

[1163] Step 2:

[1164] Terminal: Captures the patient's voice and transmits the voice data to the server in real time.

[1165] Step 3:

[1166] Server: Passes the received voice data to a voice recognition engine and converts it into text data. The text data becomes "I often have trouble sleeping at night these days."

[1167] Step 4:

[1168] Server: The converted text data is passed to a natural language processing engine, which analyzes the text content. Through the analysis, medically relevant information such as "I can't sleep at night" is extracted.

[1169] Step 5:

[1170] Server: Summarizes the extracted important medical information and adds it to the patient's medical record in the database as relevant information. For example, the information "insomnia" is added to the patient's medical record.

[1171] Step 6:

[1172] Server: Generates appropriate advice based on the keyword "insomnia." For example, it generates a message such as "Improve your sleeping environment and exercise regularly."

[1173] Step 7:

[1174] Server: Sends the generated advice to the terminal and sends instructions to provide to the patient.

[1175] Step 8:

[1176] Terminal: The advice received from the server is conveyed to the patient. In the case of a telephone call, it is played as a voice message.

[1177] Step 9:

[1178] User: The patient accepts the advice and indicates their intention to end the conversation (e.g., hang up the phone, enter an end command).

[1179] Step 10:

[1180] Terminal: Sends an intention to end the conversation to the server.

[1181] Step 11:

[1182] Server: Ends the conversation and closes the session, optionally logging and resetting the system.

[1183] ---

[1184] The above is the flow of the specific processing steps of the "AI that is always helpful" system, and an explanation of the specific operations at each step.

[1185] Example 1

[1186] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1187] In conventional medical systems, medical professionals manually manage information about patients' symptoms and lifestyle habits, which requires a great deal of time and effort. There is also a high risk of information leaks and input errors. Furthermore, it is difficult to provide appropriate advice to each patient.

[1188] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1189] In this invention, the server includes an interface means for voice communication with patients, a voice recognition means for converting received voice data into text data using a natural language processing engine, and a natural language processing means for analyzing the converted text data and extracting medical information. This makes it possible to efficiently manage patients' medical information and provide appropriate advice in real time.

[1190] 1. "Interface means" means a device or software that is responsible for voice communication with the patient, capturing voice data and transmitting it to the server.

[1191] 2. "Speech recognition means" means a device or software that converts received voice data into text data using a natural language processing engine.

[1192] 3. "Natural language processing means" means a device or software that analyzes the converted text data and extracts important medical information.

[1193] 4. "Record updating device" means a device or software that updates extracted medical information into a patient's medical record.

[1194] 5. "Advice generation means" refers to a device or software that generates and provides advice regarding lifestyle habits and treatment based on extracted medical information.

[1195] 6. "Voice data" means voice information collected from a patient via an interface means.

[1196] 7. "Text data" means character information converted from voice data by voice recognition means.

[1197] 8. "Medical information" means information about a patient's symptoms and lifestyle habits extracted from text data using natural language processing means.

[1198] The present invention is a system for communicating with patients through voice, analyzing the content of the communication, and efficiently managing medical information. Specific embodiments of the present invention will be described below.

[1199] System configuration

[1200] 1. Interface Method

[1201] The device, which can take the form of a landline phone or a smartphone app, handles voice communication with the patient, captures the voice data, and transmits it to a server.

[1202] 2. Voice Recognition Method

[1203] The server receives the voice data sent from the device and converts the voice into text data using a speech recognition engine (e.g., Google Speech-to-Text API).

[1204] For example, if a patient says, "Recently, I've often had trouble sleeping at night," the voice data is converted into text data that reads, "Recently, I've often had trouble sleeping at night."

[1205] 3. Natural Language Processing Methods

[1206] The server analyzes the text data generated by speech recognition and extracts important medical information using natural language processing engines such as spaCy and the BERT model.

[1207] As a specific example, the keyword "can't sleep" is extracted from the text data "Recently, I often can't sleep at night" and it is recognized that this corresponds to the symptom of "insomnia."

[1208] 4. Record-updating methods

[1209] The server reflects the extracted medical information in the patient's medical record. For example, the extracted information on "insomnia" is added to the patient's chart.

[1210] 5. Advice Generation Methods

[1211] The server generates appropriate lifestyle and treatment advice for the patient based on the extracted medical information, using a generative AI model (e.g., GPT-4).

[1212] For example, if information about "insomnia" is extracted, a message will be generated saying, "It would be a good idea to improve your sleeping environment and exercise regularly," and this will be provided to the patient via the terminal.

[1213] Specific examples of programs

[1214] User operation

[1215] The user uses the device to start a conversation with the AI. For example, a patient might say, "I haven't had much of an appetite lately."

[1216] Processing by the terminal

[1217] The device captures the audio and sends the audio data to the server.

[1218] Server processing

[1219] The server uses a speech recognition engine to convert the received voice data into text data such as "I haven't had much of an appetite lately." It then analyzes the data using a natural language processing engine to extract the symptom "lack of appetite." Based on this information, the server updates the patient's medical record and uses a generative AI model to generate advice such as "Try to regulate your eating habits," which is then provided to the patient via their device.

[1220] Prompt Sentence Examples

[1221] Here is an example of a prompt to be fed to a generative AI model:

[1222] Example prompt:

[1223] "A patient has recently complained of a lack of appetite. Please add the appropriate information to the medical record and generate appropriate advice."

[1224] This system will reduce the workload of medical professionals while enabling them to manage medical information and provide prompt and appropriate advice to patients, thereby improving the efficiency and quality of regional medical care.

[1225] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1226] Step 1:

[1227] The user operates the device to start a conversation with the AI. The input is the patient's voice (e.g., "I haven't had much of an appetite lately."). The output is the captured voice data on the device. Specifically, the patient opens the smartphone app, taps the "voice input" button, and speaks the voice message.

[1228] Step 2:

[1229] The terminal captures the patient's voice and sends the voice data to the server. The input is the voice data captured in step 1. The output is the voice data sent to the server. Specifically, the terminal captures voice using the built-in microphone and uploads the voice data to the server in real time. HTTPS is used as the communication protocol, and data is encrypted.

[1230] Step 3:

[1231] The server converts the received voice data into text data using a voice recognition engine. The input is the voice data sent from the device. The output is the text data converted from the voice. Specifically, the server sends the voice data to a voice recognition engine (e.g., Google Speech-to-Text API), and the API converts the voice data into text data such as "I haven't had much of an appetite lately." The server then saves the converted text data.

[1232] Step 4:

[1233] The server analyzes the converted text data using a natural language processing engine to extract important medical information. The input is the text data converted in step 3. The output is the extracted medical information. Specifically, the server inputs the text data into a natural language processing engine (e.g., spaCy, BERT model), and the engine extracts the keyword "no appetite" and recognizes it as a symptom of "loss of appetite." The extracted information is temporarily stored.

[1234] Step 5:

[1235] The server reflects the extracted medical information in the patient's medical record. The input is the medical information extracted in step 4. The output is the updated medical record. Specifically, the server retrieves the medical record based on the patient's ID, adds the new information "loss of appetite" to the existing record, and saves the updated medical record in the database.

[1236] Step 6:

[1237] The server generates appropriate lifestyle and treatment advice for the patient based on the extracted medical information. The input is the medical information extracted in step 4. The output is the generated advice message. Specifically, the server inputs a prompt to the generative AI model (e.g., GPT-4), and the AI ​​model generates advice such as "Try to regulate your eating habits." The server then sends the generated advice to the device.

[1238] Step 7:

[1239] The terminal displays the advice received from the server to the patient. The input is the advice message sent from the server. The output is the advice displayed on the terminal. Specifically, the advice received by the terminal is displayed on the screen so that the patient can check it. For example, "Try to regulate your eating habits" is displayed.

[1240] (Application example 1)

[1241] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1242] While conventional speech recognition and natural language processing systems are primarily used in the medical field, their application in other fields such as food delivery has not been fully explored. Furthermore, there is a lack of systems that can efficiently process orders and provide specific advice and product recommendations through voice communication with users, creating a need for an improved user experience.

[1243] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1244] In this invention, the server includes an interface means for voice communication with the patient, a voice recognition means for converting received voice data into text data, a natural language processing means for analyzing the text data and extracting important information, a record updating means for updating the medical record with the extracted information, an advice generating means for generating advice for the patient based on the extracted information, a means for converting order details into text data through voice communication with the user, a natural language processing means for analyzing the text data and extracting the order details, a means for storing the extracted order details in a database, and a means for generating additional recommended products and advice based on the extracted order details. This makes it possible to streamline the food delivery ordering process and provide users with recommended products and advice that are appropriate for them.

[1245] "Interface means" refers to devices or software that are responsible for voice communication with patients or users, and have the function of capturing voice data and sending it to a server.

[1246] "Speech recognition means" refers to a technology that converts received voice data into text data, and uses a voice recognition engine.

[1247] "Natural language processing means" refers to technology that analyzes text data and extracts important information and order details, and uses a natural language processing engine.

[1248] "Record updating means" refers to the function that updates extracted information into medical records and databases, keeping patient charts and user order histories up to date.

[1249] The "advice generation means" is a function that generates appropriate advice and recommended products for patients and users based on the extracted information, and generates messages based on lifestyle habits and order details.

[1250] The "means for converting the order contents into text data" refers to a function for converting the user's voice order into text data, and uses voice recognition technology.

[1251] "Means for analyzing and extracting order details" refers to a function that analyzes order details from text data and extracts necessary information, and uses natural language processing technology.

[1252] "Means for saving to a database" refers to the function of saving the extracted order details to a database, which serves as the basis for managing order history and reordering.

[1253] "Means for generating additional product recommendations and advice" refers to the functionality for generating additional product recommendations and specific advice based on the user's order, which is used to enhance the user experience.

[1254] This invention is a system for communicating with users through voice, analyzing the content of the communication, and efficiently managing order information. The system is implemented with the following specific configuration and procedures.

[1255] System configuration

[1256] 1. Interface Method

[1257] Terminal: Responsible for voice communication with the user, capturing the user's voice and sending it to the server. It can take the form of a smartphone or smart speaker.

[1258] 2. Voice Recognition Method

[1259] Server: Receives the voice data sent from the device and converts it into text data using a speech recognition engine (e.g., Google Cloud Speech-to-Text).

[1260] 3. Natural Language Processing Methods

[1261] Server: Analyzes the converted text data and extracts order details and important information (e.g., Google Cloud Natural Language API).

[1262] 4. Record-updating methods

[1263] Server: Save the extracted order details to a database (e.g., Firebase Realtime Database) and update the user's order history.

[1264] 5. Advice Generation Methods

[1265] Server: Generates additional product recommendations and specific advice appropriate for the user based on the extracted order details.

[1266] Example of a system

[1267] 1. Capture and transmit audio

[1268] User: The user uses the device to place an order by voice. For example, the user might say, "I'd like one pizza and two salads, please."

[1269] Device: Captures this conversation and sends the audio data to the server.

[1270] 2. Audio data conversion

[1271] Server: The received voice data is converted into text data using a voice recognition engine, such as "One pizza and two salads, please."

[1272] 3. Text Data Analysis

[1273] Server: The converted text data is analyzed using a natural language processing engine, and the order details, "one pizza" and "two salads," are extracted.

[1274] 4. Storage of order data

[1275] Server: Saves the extracted order details to the database and updates the user's order history.

[1276] 5. Generating and Providing Advice

[1277] Server: Based on the order, the server generates additional product recommendations and specific advice appropriate for the user. For example, it generates a message such as "How about a Margherita pizza and a green salad?" and delivers this to the user via the device.

[1278] Specific prompt examples

[1279] The user initiates a voice order using the following prompt:

[1280] "One pizza and two salads, please."

[1281] In this way, this system can streamline the food delivery ordering process and improve the user experience. Specifically, by combining voice recognition technology and natural language processing technology, it is possible to accurately understand and manage order details, as well as provide appropriate product recommendations and advice.

[1282] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1283] Step 1:

[1284] The user places an order by voice. Specifically, the user launches the smartphone app and voice-records their order, such as "One pizza and two salads, please." This voice data becomes the input for the system.

[1285] Step 2:

[1286] The device sends the captured voice data to the server. Specifically, the device records the user's voice and sends the data to the Google Cloud Speech-to-Text API, requesting that the voice data be converted to text. In this case, the input is voice data and the output is text data.

[1287] Step 3:

[1288] The server converts the received voice data into text data using a speech recognition engine. Specifically, the server sends the voice data to the Google Cloud Speech-to-Text API and receives the text data as a result. At this stage, the input is voice data, and the output is text data obtained by speech recognition.

[1289] Step 4:

[1290] The server analyzes the text data using a natural language processing engine to extract the order details and important information. Specifically, the server sends the text data to the Google Cloud Natural Language API, which extracts the order items (e.g., one pizza, two salads). In this case, the input is text data, and the output is the specific order details and quantity.

[1291] Step 5:

[1292] The server saves the extracted order details in a database. Specifically, it makes a request to Firebase Realtime Database to save the order details (e.g., "1 pizza" and "2 salads"). The input at this stage is the order data, and the output is the updated database results.

[1293] Step 6:

[1294] The server generates additional product recommendations and specific advice based on the order details. Specifically, the server references the user's past order history and current order details, and uses the corresponding generative AI model to generate advice and recommendations such as "How about a Margherita pizza and a green salad?" The input at this stage is the order details and history data, and the output is the generated advice and recommendation message.

[1295] Step 7:

[1296] The server sends the generated advice and recommendation messages to the terminal. Specifically, the server uses a communication protocol to send the generated messages to the terminal. In this case, the input is the generated message, and the output is the data to be sent to the terminal.

[1297] Step 8:

[1298] The device notifies the user of the received advice or recommendation message. Specifically, it displays the message to the user using the smartphone's notification function. At this stage, the input is the message sent from the server, and the output is the notification content to the user.

[1299] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1300] The present invention is a system that extracts important medical information through voice communication with patients, updates the patient's medical record based on that information, and provides appropriate advice. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to respond based on the patient's emotional state and provide more personalized care. This system has the following components:

[1301] System configuration

[1302] 1. Interface Method

[1303] Terminal: Responsible for voice communication with the patient, capturing the patient's voice and sending it to the server. This can be a phone, a dedicated application, or a device with a microphone.

[1304] 2. Voice Recognition Method

[1305] Server: Receives voice data sent from the device and converts it into text data using a voice recognition engine. For example, if a patient says, "I often have trouble sleeping at night recently," the voice data is converted into text data saying, "I often have trouble sleeping at night recently."

[1306] 3. Natural Language Processing Methods

[1307] Server: Analyzes the converted text data and extracts important medical information. In this process, it identifies the keyword "can't sleep" from the text and recognizes that this corresponds to the medical information "insomnia."

[1308] 4. Emotion Engine

[1309] Server: Identifies emotions from the patient's voice and text data. For example, it analyzes elements such as the tone, speed, and pitch of the patient's voice to recognize emotions such as anxiety, tension, or relief.

[1310] 5. Record-updating methods

[1311] Server: Reflects the extracted important medical and emotional information in the patient's medical record. For example, the symptom information "insomnia" and the emotional information "anxiety" are added to the medical record.

[1312] 6. Advice Generation Methods

[1313] Server: Based on the extracted information and emotional information, the server generates advice on appropriate lifestyle habits and treatment for the patient. For example, for a patient with insomnia and anxiety, the server generates specific advice such as, "It would be good to improve your sleeping environment and try to relax. Also, if you feel anxious, try taking deep breaths."

[1314] Example of a system

[1315] 1. Capture and transmit audio

[1316] User: The patient uses the device to start a conversation with the AI, for example, saying, "I'm worried because I've lost my appetite recently."

[1317] Device: Captures this conversation and sends the audio data to the server.

[1318] 2. Audio data conversion

[1319] Server: The received voice data is converted into text data by a voice recognition engine. For example, it may be converted into "I'm worried because I've lost my appetite recently."

[1320] 3. Text Data Analysis

[1321] Server: The converted text data is analyzed using a natural language processing engine to extract symptom information such as "loss of appetite." It also uses an emotion engine to extract emotional information recognized as "worry."

[1322] 4. Updating medical records

[1323] Server: The extracted symptom information of "no appetite" and emotional information of "worry" are reflected in the patient's medical record.

[1324] 5. Generating and Providing Advice

[1325] Server: Based on the symptom information of "loss of appetite" and the emotional information of "worry," the server generates appropriate advice for the patient. For example, the server generates advice such as, "Try to maintain a regular lifestyle and gradually incorporate your favorite foods into your diet. If you continue to feel anxious, we recommend that you try relaxation therapy or seek counseling," and provides this advice to the patient via a device.

[1326] This system efficiently manages important medical information through voice communication with patients, and by combining it with an emotion engine, enables personalized responses based on the patient's emotional state, ultimately reducing the workload of medical professionals and enabling higher quality medical services to be provided to patients.

[1327] The processing flow will be explained below.

[1328] Step 1:

[1329] User: The patient uses the device to initiate a conversation with the AI, for example, saying, "I've lost my appetite recently and I'm very worried."

[1330] Step 2:

[1331] Terminal: Captures the patient's voice and transmits the voice data to the server in real time.

[1332] Step 3:

[1333] Server: The received voice data is passed to a voice recognition engine and converted into text data. The text data becomes, "I've lost my appetite recently and I'm very worried."

[1334] Step 4:

[1335] Server: The converted text data is passed to a natural language processing engine, which analyzes the text content. Through the analysis, medically relevant information such as "no appetite" is extracted.

[1336] Step 5:

[1337] Server: Using an emotion engine, identify the patient's emotion from the converted text and voice data. In this case, the emotion "worry" is recognized.

[1338] Step 6:

[1339] Server: Combines and summarizes the analyzed medical information and the recognized emotional information, and reflects this information in the patient's medical record. Specifically, the symptom information of "loss of appetite" and the emotional information of "worry" are added to the medical record.

[1340] Step 7:

[1341] Server: Generates appropriate advice for the patient based on the symptom information of "loss of appetite" and the emotion information of "worry." For example, it generates a message such as, "Try to maintain a regular lifestyle and gradually incorporate your favorite foods into your diet. Also, if you continue to feel anxious, we recommend relaxation and counseling."

[1342] Step 8:

[1343] Server: Sends the generated advice to the terminal and issues instructions to provide to the patient.

[1344] Step 9:

[1345] Terminal: Provides advice received from the server to the patient. In the case of a telephone call, a synthesized voice is generated and the advice is played back as a voice message.

[1346] Step 10:

[1347] User: The patient accepts the advice and indicates their intention to end the conversation (e.g., hang up the phone, enter an end command).

[1348] Step 11:

[1349] Terminal: Sends an intention to end the conversation to the server.

[1350] Step 12:

[1351] Server: Ends the conversation and closes the session, optionally logging and resetting the system.

[1352] ---

[1353] The above is the flow of specific processing steps for the "AI that is always kind" system that combines an emotion engine, and an explanation of the specific operations at each step.

[1354] Example 2

[1355] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1356] Conventional patient care systems have the problem that the information obtained from patients through voice communication is limited, making it difficult to fully grasp the patient's emotional state. Furthermore, the process of analyzing the obtained information in real time and providing advice is often inefficient. This increases the workload of medical professionals and risks reducing the quality of care provided to patients. Therefore, there was a need for the development of a system that can simultaneously extract important medical information and emotional information from voice data and provide prompt and appropriate advice.

[1357] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an interface means for voice communication with the patient, a voice recognition means for converting received voice data into text data, a natural language processing means for analyzing the text data and extracting important information, an emotion recognition means for identifying emotions from the extracted voice and text data, a record updating means for reflecting the extracted information in the medical record, and an advice generation means for generating advice for the patient based on the extracted information. This makes it possible to simultaneously extract important medical information and emotional information from the voice data and provide prompt and appropriate advice.

[1358] The "interface means" is a means for taking charge of voice communication with the patient, capturing the patient's voice, and transmitting it to the server.

[1359] The "voice recognition means" is a means for converting received voice data into text data.

[1360] "Natural language processing means" is a means for analyzing text data and extracting important information.

[1361] The "emotion recognition means" is a means for identifying emotions from extracted speech and text data.

[1362] The "record updating means" is a means for updating the extracted information in the patient's medical record.

[1363] The "advice generation means" is a means for generating advice for the patient based on the extracted information.

[1364] The present invention is a system that efficiently extracts important medical information and emotional information of patients through voice communication with them and provides appropriate advice. This system includes the following main components:

[1365] 1. Interface Method

[1366] Terminal: Responsible for voice communication with the patient, capturing the patient's voice and sending it to the server. The terminal can be a smartphone, tablet, PC, etc. Specifically, it collects voice using a microphone and sends the voice data to the server via an internet connection.

[1367] 2. Voice Recognition Method

[1368] Server: Receives voice data sent from the device and converts it into text data using a speech recognition engine. Google Cloud Speech-to-Text and Microsoft Azure Cognitive Services are used as speech recognition engines. For example, the server receives voice data and converts a patient's speech, such as "I've lost my appetite recently and I'm worried," into text.

[1369] 3. Natural Language Processing Methods

[1370] Server: Analyzes the converted text data and extracts important medical information. During this process, it automatically identifies keywords and phrases (e.g., "no appetite") and determines whether they correspond to symptoms. Apache OpenNLP and spaCy are used as natural language processing engines.

[1371] 4. Emotion recognition means

[1372] Server: Identifies the patient's emotion from the received voice and converted text data. IBM Watson Tone Analyzer and Affectiva SDK are used as emotion engines. For example, if a patient says "I'm worried," the server recognizes this as the emotion "worried."

[1373] 5. Record-updating methods

[1374] Server: The extracted important medical and emotional information is reflected in the patient's medical record. Epic Systems or Cerner is used as the medical record management system, and Oracle Database or PostgreSQL is used as the database.

[1375] 6. Advice Generation Methods

[1376] Server: Based on the extracted information, the server generates appropriate lifestyle and treatment advice for the patient. Generative AI models such as GPT (Generative Pre-trained Transformer) and BERT (Bidirectional Encoder Representations from Transformers) are used. For example, the server might generate advice such as, "Try to maintain a healthy lifestyle and gradually incorporate your favorite foods into your diet. If you continue to feel anxious, we recommend relaxation and counseling."

[1377] Examples:

[1378] If the user says, "I'm worried because I haven't had much of an appetite lately," the system operates as follows.

[1379] 1. Interface method: The user speaks through the smartphone microphone, saying, "I'm worried because I haven't had much of an appetite lately."

[1380] 2. Speech recognition: The device captures the voice and sends it to the server, which converts the voice into text using a speech recognition engine.

[1381] 3. Natural language processing: Analyze the converted text "I'm worried because I've had no appetite lately" and extract important information. Specifically, extract the symptom information of "no appetite."

[1382] 4. Emotion recognition means: The server identifies the emotional information "worry" from the text and voice.

[1383] 5. Record updating method: The extracted symptom information of "loss of appetite" and emotional information of "worry" are added to the medical record.

[1384] 6. Advice generation method: Using the generative AI model, advice such as "Try to maintain a regular lifestyle and gradually incorporate your favorite foods into your diet. Also, if you continue to feel anxious, we recommend that you seek relaxation and counseling" is generated and provided to the patient via their device.

[1385] Example prompt sentence:

[1386] Patient symptoms: Loss of appetite

[1387] Patient Emotions: Anxiety

[1388] Good advice:

[1389] Try to maintain a regular lifestyle and gradually incorporate your favorite foods into your diet. If you continue to feel anxious, we recommend seeking relaxation and counseling.

[1390] The above is a detailed description of an embodiment of the present invention. This system quickly and accurately extracts important medical and emotional information from speech data, enabling personalized advice to be provided to patients.

[1391] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1392] Step 1:

[1393] User: The patient uses the device to start a conversation with the AI, for example, saying, "I'm worried because I've lost my appetite recently."

[1394] Input: Patient's voice

[1395] Output: Captured audio data

[1396] Specific operation: A user speaks into the microphone of a smartphone or tablet. An application on the device captures the voice data and converts it into a voice data format.

[1397] Step 2:

[1398] Terminal: Sends captured audio data to the server.

[1399] Input: Captured audio data

[1400] Output: Audio data sent to the server

[1401] What it does: The device uses an internet connection to send audio data to the server, using HTTPS as the communication protocol to ensure secure data transfer.

[1402] Step 3:

[1403] Server: Receives the voice data sent from the terminal.

[1404] Input: Transmitted audio data

[1405] Output: Received audio data

[1406] Specific operation: The server receives the voice data and stores it in temporary storage.

[1407] Step 4:

[1408] Server: The received voice data is converted into text data using a voice recognition engine.

[1409] Input: Received audio data

[1410] Output: Text data

[1411] Specific operation: The server calls a speech recognition engine (for example, Google Cloud Speech-to-Text), analyzes the voice signal, and converts it into text data such as "I'm worried because I've lost my appetite lately."

[1412] Step 5:

[1413] Server: The converted text data is analyzed using a natural language processing engine.

[1414] Input: Converted text data

[1415] Output: Extracted symptom information and emotion information

[1416] Specific operation: The server uses a natural language processing engine (e.g., spaCy) to extract symptom information such as "no appetite" from the text data, and simultaneously uses an emotion engine (e.g., IBM Watson Tone Analyzer) to extract emotion information such as "worry."

[1417] Step 6:

[1418] Server: Reflects the extracted information in the patient's medical record.

[1419] Input: Extracted symptom information and emotion information

[1420] Output: Updated medical record

[1421] Specific operation: The server accesses a medical record management system (e.g., Epic Systems) and updates the patient's medical record database (e.g., Oracle Database). New information is added: the symptom "loss of appetite" and the emotion "anxiety."

[1422] Step 7:

[1423] Server: Generates advice for the patient based on the extracted information.

[1424] Input: Updated medical record

[1425] Output: Generated advice

[1426] Specific operation: The server uses an advice generation engine (e.g., GPT-3) to generate advice such as, "Try to maintain a regular lifestyle and incorporate your favorite foods little by little. Also, if you continue to feel anxious, we recommend relaxation and counseling."

[1427] Step 8:

[1428] Server: Sends the generated advice to the device.

[1429] Input: Generated advice

[1430] Output: Advice sent

[1431] Specific operation: The server generates advice and sends it to the device. HTTPS is used as the communication protocol to transfer data securely.

[1432] Step 9:

[1433] Terminal: Receives advice and provides it to the user by display or voice.

[1434] Input: Submitted advice

[1435] Output: Advice given to the user

[1436] Specific behavior: The device displays the advice received from the server, alerts the user with a notification sound or a pop-up message, and, if necessary, reads the advice aloud via the voice assistant.

[1437] (Application example 2)

[1438] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1439] Conventional medical information systems equipped with voice recognition and emotion recognition technologies have difficulty responding in real time to patients' emotional states. Furthermore, there is a lack of systems that can take appropriate measures immediately in emergency situations. Therefore, there is a need to ensure patient safety and respond quickly and efficiently.

[1440] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1441] In this invention, the server includes an interface means for voice communication with the patient, a voice recognition means for converting received voice data into text data, a natural language processing means for analyzing the text data and extracting important information, a record updating means for updating the extracted information in the medical record, an advice generation means for generating advice for the patient based on the extracted information and emotional information, an emotion recognition means for identifying emotional information from the voice data, and an emergency response means for detecting an emergency based on the extracted information and emotional information and sending an alert as necessary. This enables the provision of personalized care according to the patient's emotional state and a rapid response in the event of an emergency.

[1442] The "interface means" is a device that is responsible for voice communication with the patient, captures the patient's voice, and transmits it to the server.

[1443] The "voice recognition means" is an engine that converts received voice data into text data.

[1444] A "natural language processing tool" is an engine that analyzes text data and extracts important medical and other information from it.

[1445] The "record updating means" is a system for updating extracted information into the patient's medical record and security log.

[1446] The "advice generation means" is an engine that generates appropriate advice for the patient based on the extracted information and emotional information.

[1447] The "emotion recognition means" is an engine that identifies the patient's emotional information from the voice data.

[1448] The "emergency response tool" is a system for detecting emergency situations based on extracted information and emotion information and sending alerts as needed.

[1449] The system for implementing the present invention comprises an interface means, a speech recognition means, a natural language processing means, a record updating means, an advice generation means, an emotion recognition means, and an emergency response means. The following is a detailed description of each means and how they work together.

[1450] Interface Means

[1451] The server manages the interface means for voice communication with the patient, which has the function of capturing the patient's voice using a smartphone with a microphone or a dedicated application and transmitting it to the server.

[1452] Voice recognition means

[1453] The server converts the voice data sent from the device into text data using Google's speech recognition API, etc. For example, if a patient says, "Help me, someone has broken into my house," the server converts the voice data into text data.

[1454] Natural language processing tools

[1455] The server then analyzes the converted text data using HuggingFace's natural language processing engine to extract important information, identifying the keyword "home intrusion" from the text and recognizing that this is an emergency.

[1456] Record updating method

[1457] The server then updates the patient's security log with the extracted information, for example adding an emergency event such as "home intrusion" to the security log.

[1458] Advice Generation Method

[1459] The server generates appropriate advice for the patient based on the extracted information and emotion information. For example, in the event of an intrusion, the server generates specific advice such as "Evacuate to a safe place and immediately contact your emergency contact."

[1460] emotion recognition means

[1461] The server identifies the patient's emotions from the voice data by analyzing factors such as tone, speed, and pitch of the voice to assess whether the patient is feeling anxious or scared.

[1462] Emergency response measures

[1463] Based on the extracted information and emotion information, the server detects emergencies and sends alerts to emergency contacts as needed. For example, if an intruder occurs, an email is sent immediately to emergency contacts (family members or a security company).

[1464] Specific examples

[1465] Example speech input: "Help, someone is breaking into my house."

[1466] Emergency Alert: "Emergency. Please help, someone has broken into my house."

[1467] Email recipients: Emergency contacts (e.g., family, security company)

[1468] Prompt Sentence Examples

[1469] If a user says, "Help me, someone's broken into my house," the system captures that speech, converts it to text, and then runs a sentiment analysis on that text. If the emotion of fear is recognized, an email alert is sent to emergency contacts.

[1470] The system allows for personalized care according to the patient's emotional state and rapid response in emergency situations.

[1471] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1472] Step 1:

[1473] The user inputs voice using the terminal. The terminal captures the voice and sends this voice data to the server. The input is the user's voice data, and the output is the voice data sent to the server.

[1474] Step 2:

[1475] The server converts the received voice data into text data using Google's speech recognition API. The input is voice data, and the output is text data. For example, this conversion converts a voice message like "Help me, someone has broken into my house" into text data.

[1476] Step 3:

[1477] The server then analyzes the converted text data using HuggingFace's natural language processing engine to extract important information. The input is text data, and the output is the extracted important information. During this analysis, the keyword "house intrusion" is identified, and it is recognized that this is an emergency.

[1478] Step 4:

[1479] The server analyzes emotional information from the voice data. It analyzes the tone, speed, and pitch of the voice to identify emotional states such as anxiety or fear. The input is voice data, and the output is emotional information.

[1480] Step 5:

[1481] The server reflects the extracted important information and emotional information in the patient's security log. The input is the extracted important information and emotional information, and the output is the updated security log. Here, the information "house intrusion" and the user's feeling of fear are recorded in the log.

[1482] Step 6:

[1483] The server generates appropriate advice for the patient based on the extracted information. For example, advice such as "Evacuate to a safe place and immediately contact your emergency contacts" is generated. The input is the extracted information and emotion information, and the output is the generated advice.

[1484] Step 7:

[1485] If the server determines that an emergency has occurred, it will send an alert to the emergency contact as needed. The input is the emergency information and emotion information, and the output is an alert email to the emergency contact. For example, a message such as "An emergency has occurred. Please help, someone has broken into my house" is sent.

[1486] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1487] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1488] 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 the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1489] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1490] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1491] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1492] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1493] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1494] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1495] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1496] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1497] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1498] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1499] 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.

[1500] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1501] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1502] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[1503] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1504] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1505] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1506] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1507] The following is further disclosed regarding the above embodiment.

[1508] (Claim 1)

[1509] an interface means for voice communication with the patient;

[1510] a speech recognition means for converting received speech data into text data;

[1511] natural language processing means for analyzing text data and extracting important information;

[1512] a record updating means for updating the medical record with the extracted information;

[1513] an advice generating means for generating advice for the patient based on the extracted information;

[1514] A system including:

[1515] (Claim 2)

[1516] 2. The system according to claim 1, further comprising a natural language processing means for extracting information on the patient's lifestyle and symptoms in analyzing the text data.

[1517] (Claim 3)

[1518] 2. The system according to claim 1, further comprising means for analyzing the text data converted by said speech recognition means in real time.

[1519] "Example 1"

[1520] (Claim 1)

[1521] an interface means for audio communication with the patient;

[1522] A speech recognition means for converting received speech data into text data using a natural language processing engine;

[1523] natural language processing means for analyzing the converted text data and extracting medical information;

[1524] a record updating means for updating the extracted medical information in the patient's medical record;

[1525] an advice generating means for generating and providing advice on lifestyle habits and treatment based on the extracted medical information;

[1526] A system including:

[1527] (Claim 2)

[1528] 2. The system according to claim 1, further comprising natural language processing means for extracting symptom information of a patient in analyzing the text data.

[1529] (Claim 3)

[1530] 2. The system according to claim 1, further comprising means for analyzing the text data converted by said speech recognition means in real time.

[1531] "Application Example 1"

[1532] New Claims

[1533] (Claim 1)

[1534] an interface means for voice communication with the patient;

[1535] a speech recognition means for converting received speech data into text data;

[1536] natural language processing means for analyzing text data and extracting important information;

[1537] a record updating means for updating the medical record with the extracted information;

[1538] an advice generating means for generating advice for the patient based on the extracted information;

[1539] A means of converting order details into text data through voice communication with users;

[1540] natural language processing means for analyzing text data and extracting order details;

[1541] a means for storing the extracted order details in a database;

[1542] a means for generating additional product recommendations and advice based on the extracted order details;

[1543] A system including:

[1544] (Claim 2)

[1545] 2. The system according to claim 1, further comprising a natural language processing means for extracting the contents of the user's order in analyzing the text data.

[1546] (Claim 3)

[1547] 2. The system according to claim 1, further comprising means for analyzing the text data converted by said speech recognition means in real time.

[1548] "Example 2: Combining Emotion Engines"

[1549] (Claim 1)

[1550] an interface means for voice communication with the patient;

[1551] a speech recognition means for converting received speech data into text data;

[1552] natural language processing means for analyzing text data and extracting important information;

[1553] emotion recognition means for identifying emotions from the extracted speech and text data;

[1554] a record updating means for updating the medical record with the extracted information;

[1555] an advice generating means for generating advice for the patient based on the extracted information;

[1556] A system including:

[1557] (Claim 2)

[1558] 2. The system according to claim 1, further comprising a natural language processing means and an emotion recognition means for extracting information about the patient's lifestyle and symptoms in the analysis of the text data and the emotion recognition.

[1559] (Claim 3)

[1560] 2. The system according to claim 1, further comprising means for analyzing and recognizing emotions in real time from the text data converted by said speech recognition means.

[1561] "Application example 2 when combining emotion engines"

[1562] (Claim 1)

[1563] an interface means for voice communication with the patient;

[1564] a speech recognition means for converting received speech data into text data;

[1565] natural language processing means for analyzing text data and extracting important information;

[1566] a record updating means for updating the medical record with the extracted information;

[1567] an advice generating means for generating advice for the patient based on the extracted information and the emotion information;

[1568] emotion recognition means for identifying emotion information from voice data;

[1569] an emergency response means for detecting an emergency situation based on the extracted information and emotion information and sending an alert as necessary;

[1570] A system including:

[1571] (Claim 2)

[1572] 10. The system of claim 1, further comprising a natural language processing means for extracting patient lifestyle and symptom information.

[1573] (Claim 3)

[1574] 2. The system according to claim 1, further comprising means for analyzing the text data converted by said speech recognition means in real time. [Explanation of symbols]

[1575] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. an interface means for voice communication with the patient; a speech recognition means for converting received speech data into text data; natural language processing means for analyzing text data and extracting important information; a record updating means for updating the medical record with the extracted information; an advice generating means for generating advice for the patient based on the extracted information; A system including:

2. 2. The system according to claim 1, further comprising natural language processing means for extracting information on the patient's lifestyle and symptoms in analyzing the text data.

3. 2. The system according to claim 1, further comprising means for analyzing the text data converted by said speech recognition means in real time.

Images