System
A system translates user symptoms and coordinates transportation to medical institutions using generative AI, addressing language and logistical barriers for emergency medical access.
Patent Information
- Application Number
- JP2024130405
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-08-06
- Publication Date
- 2026-02-19
AI Technical Summary
It is difficult for individuals, especially non-Japanese speakers and those unfamiliar with their surroundings, to quickly access appropriate medical institutions during emergencies due to language barriers and limited availability of municipal consultation centers, particularly at night or on holidays.
A system that allows users to input symptoms in their preferred language, translates them using generative AI, searches for the nearest medical institution based on location and time, and coordinates transportation through a ride-hailing service.
Enables users to quickly and accurately access appropriate medical care by overcoming language barriers and logistical challenges, reducing health risks in emergency situations.
Smart Images

Figure 2026028107000001_ABST
Abstract
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] It is difficult to predict when and where sudden illness will occur, and it can occur anywhere, including at home, on a business trip, or while traveling. Municipal consultation centers are often closed, especially at night or on holidays, making it difficult to quickly access medical institutions. Furthermore, people who are not familiar with Japanese, such as foreign tourists and business people, have limited means of quickly obtaining information about appropriate medical institutions. The present invention aims to address this information gap regarding medical care, allowing everyone to quickly obtain information about appropriate medical institutions. [Means for solving the problem]
[0005] The present invention provides a system that allows users to select an input method and communication language and input their symptoms. It then provides a translation system that translates the input using generative artificial intelligence. It also provides a system that analyzes the translated symptoms and searches for the most appropriate medical institution based on the user's current location and time of day. Finally, it provides a system that includes a system that coordinates with a ride-hailing service to arrange transportation, enabling users to access a medical institution quickly and appropriately.
[0006] "User" refers to a person who uses the system to input symptoms and seek access to an appropriate medical institution.
[0007] "Input method" refers to the means by which the user communicates symptoms to the system, and includes both text input and voice input.
[0008] "Communication language" refers to the language used by the user when providing information to the system, and includes languages other than Japanese.
[0009] "Symptom" refers to a specific physical or mental condition that refers to a malaise or illness experienced by a user.
[0010] "Generative artificial intelligence" refers to machine translation techniques used to translate user-entered information into different languages.
[0011] "Translation" refers to the act or process of converting text or words from one language into another.
[0012] "Current location" refers to the geographical location information when the user uses the system.
[0013] "Time zone" refers to the time period when a user uses the system, and depending on this, available medical institutions may differ.
[0014] "Medical institution" refers to a facility that provides medical services to users, such as a hospital or clinic.
[0015] "Search" refers to the process by which the system finds medical institution information based on the user's current location, symptoms, and time of day.
[0016] "Vehicle dispatch service" refers to a service that provides transportation to arrange transportation from a user's current location to a medical institution.
[0017] "Pick-up" refers to the act of moving the user from their current location to their destination (in this case, a medical institution).
[0018] "System" refers to the computer program and its operating environment that executes a series of processes from user input to symptom analysis, medical institution search, and vehicle dispatch arrangement. [Brief explanation of the drawings]
[0019] [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
[0020] 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.
[0021] First, the terms used in the following description will be explained.
[0022] 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).
[0023] 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.
[0024] 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.
[0025] 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.
[0026] 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."
[0027] [First embodiment]
[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.
[0029] 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.
[0030] 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).
[0031] 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.
[0032] 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.
[0033] 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.
[0034] 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.
[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.
[0036] 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.
[0037] 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.
[0038] 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.
[0039] 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."
[0040] This invention is a system that supports users in quickly accessing appropriate medical institutions in situations where emergency medical care is required. The system uses generative artificial intelligence to translate and analyze symptoms entered by the user, searches for the most appropriate medical institution based on the results, and arranges for a vehicle dispatch service if necessary.
[0041] The system starts by having the user select the input method (text input or voice input) and communication language. When the user inputs their symptoms by text or voice, the information is sent to the server via the terminal. For example, consider the case where a user inputs the symptom "I have chest pain and can't breathe."
[0042] The server then uses generative artificial intelligence to translate this input in real time. Even if the user types in a language other than Japanese, the AI translation converts it into accurate Japanese or other standard languages. The server then analyzes this translated text to identify symptoms, specifically extracting keywords such as "chest pain" and "shortness of breath."
[0043] The server then obtains the user's current location and time zone. Location information is obtained using the user's device's GPS function, and time zone information is obtained by referencing the system time. Based on this information and the user's symptoms, the server searches the medical institution database for the most suitable emergency medical institution. The search results may include hospitals and clinics that are currently open.
[0044] If necessary, the server will coordinate with a ride-hailing service to arrange transportation from the user's current location to a medical facility. For example, if the user does not have a car, the server will call a ride-hailing service such as DiDi or Uber to assist with emergency transportation for the user.
[0045] Finally, after receiving medical treatment, users can provide feedback through their devices, which the server collects and stores in a database to improve the accuracy and quality of the overall system.
[0046] As a specific example, if a user experiences sudden chest pain while on a business trip, they can voice-input "I have chest pain" into the app. This information is sent to a server and analyzed using generative artificial intelligence. The server obtains the user's current location and searches for the nearest hospital that is open even at night. If the user does not have transportation, the server arranges for a ride-hailing service, helping the user to quickly receive appropriate treatment at a hospital. In this way, the present invention allows users to access medical institutions quickly and appropriately, no matter where they are.
[0047] The processing flow will be explained below.
[0048] Step 1:
[0049] The user inputs their symptoms into the device. They can choose to input text or voice, and also select the communication language. For example, the user can input "I have chest pain and can't breathe" by text input.
[0050] Step 2:
[0051] The device sends the user's input information to the server. In the case of voice input, the device converts the voice into text before sending it to the server.
[0052] Step 3:
[0053] The server uses generative artificial intelligence to translate information entered by users in real time. For example, even if the information is entered in a language other than Japanese, it will be translated into a standard language using AI.
[0054] Step 4:
[0055] The server analyzes the translated text and extracts specific symptoms, for example, identifying keywords such as "chest pain" and "shortness of breath" from the translated text "My chest hurts and I can't breathe."
[0056] Step 5:
[0057] The server obtains the current location from the user's device, using the device's GPS function to obtain latitude and longitude information.
[0058] Step 6:
[0059] The server obtains the current time and uses this information to prepare data to identify medical institutions that are open at the time of the user's visit.
[0060] Step 7:
[0061] The server searches the medical institution database for the most suitable medical institution based on the patient's current location, time zone, and analyzed symptoms. As a result, for example, a nearby 24-hour emergency hospital may be identified.
[0062] Step 8:
[0063] The server checks whether the user has a means of transportation based on the information provided by the user. If the device reports "no means of transportation," the server proceeds to the next step.
[0064] Step 9:
[0065] The server works in cooperation with the vehicle dispatch service to arrange appropriate transportation, for example, by calling a vehicle dispatch service such as DiDi or Uber and arranging for a prompt transportation from the user's current location to the specified medical institution.
[0066] Step 10:
[0067] After the consultation, the user provides feedback through the terminal, for example, by entering a comment such as "The hospital's response was quick."
[0068] Step 11:
[0069] The server collects the feedback data and stores it in a database, which accumulates data to improve the accuracy and quality of service of the entire system.
[0070] Example 1
[0071] 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."
[0072] Conventional emergency medical support systems make it difficult for users to accurately describe their symptoms and quickly find an appropriate medical institution. Furthermore, language barriers and a lack of transportation can significantly delay the time it takes to receive appropriate care in an emergency. This increases the risk to users' health.
[0073] 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.
[0074] In this invention, the server includes means for selecting a user's input method and communication language and inputting symptoms, means for translating the user's input using generative artificial intelligence, means for analyzing the translated symptoms, means for acquiring a current location and time zone, means for searching for an optimal medical facility based on the acquired current location and time zone, and means for arranging transportation in cooperation with a vehicle allocation service. This allows the user to quickly access an appropriate medical institution and, if necessary, arrange transportation, thereby reducing health risks in an emergency.
[0075] A "user" is an individual who uses the system to input symptoms and access appropriate medical care.
[0076] "Input method" refers to the means used by the user to communicate symptoms to the system, and includes text input and voice input.
[0077] The "communication language" is the language used by the user to communicate symptoms to the system, and is the target language for the system to translate.
[0078] "Generative AI" is an AI technology that translates and analyzes symptom information entered by users in real time.
[0079] "Translation" is a process that uses generative artificial intelligence to translate user-entered symptom information into another language.
[0080] The "analysis means" is the process of analyzing the symptom information translated by the generative artificial intelligence and extracting important keywords.
[0081] "Current location" is location information obtained through the GPS function of the user's device.
[0082] The "time zone" is the current time information obtained by referring to the system time.
[0083] "Medical facilities" are medical institutions such as hospitals and clinics that users need to access in an emergency.
[0084] A "vehicle deployment service" is a service that provides a means for quickly transporting users to medical facilities.
[0085] "Transportation" means the transportation required for a User to access a Medical Facility, and is provided by a vehicle deployment service.
[0086] This invention is a system that supports users who require emergency medical care by enabling them to quickly access appropriate medical institutions. The system uses generative artificial intelligence to translate and analyze symptoms input by the user, searches for the most suitable medical facility based on the acquired current location and time of day, and arranges for vehicle deployment services if necessary. Each component and its specific operation are explained below.
[0087] A user opens an application using a device such as a smartphone or tablet. The application provides a method for the user to input symptoms using text input or voice input. The user can also select the communication language to use. For example, consider the case where a user inputs "I have chest pain" by voice.
[0088] The entered information is sent from the device to the server. At this time, the device uses the HTTPS protocol to transfer data securely. Specifically, the user enters the information "I have chest pain," and the device encrypts it and sends it to the server.
[0089] The server inputs the received symptom information into a generative artificial intelligence (AI model). The generative AI translates and analyzes the information entered by the user in real time. For example, if a user enters "I have chest pain" in English, the AI model translates this into Japanese as "Chest pain." The server then analyzes the translated text and extracts keywords such as "chest pain" and "shortness of breath."
[0090] The server also obtains the user's current location and time zone by obtaining location information through the device's GPS function and referencing the system time to obtain time information. For example, the server may use GPS data sent from the device to determine the user's current location as Shibuya Ward, Tokyo.
[0091] Next, the server searches for the most suitable emergency medical facility from the medical facility database based on the user's location, time zone, and analyzed symptom information. For example, the server searches for hospitals that are open late at night and are located near Shibuya Ward, Tokyo.
[0092] If the user does not own a car and needs transportation, the server will arrange for a vehicle dispatch service. In this case, the server will use various APIs (Application Programming Interfaces) to connect with the vehicle dispatch service and arrange for transportation from the user's current location to the medical facility. Specifically, the server will request a vehicle dispatch from the user's current location (Shibuya-ku, Tokyo) to the hospital through the vehicle dispatch service's API.
[0093] After receiving medical treatment, users can provide feedback through their devices. Specifically, the application displays a survey-style question such as "Were you satisfied with the service?", and the user submits their answer. The server collects this feedback, stores it in a database, and uses it to improve the accuracy of the entire system and the quality of the service.
[0094] The above is a specific description of an embodiment of the present invention. Examples of prompt sentences are shown below. "I have chest pain" and "I have chest pain" are examples of prompt sentences. This system allows users to quickly access appropriate medical institutions and arranges transportation if necessary, thereby reducing health risks in emergencies.
[0095] The flow of the identification process in the first embodiment will be described with reference to FIG.
[0096] Step 1:
[0097] The user uses the device to launch the application and select the communication language and input method (text input or voice input). As input, the user types "I have chest pain" in text or voice input. This is the specific operation. The output is the user's input data.
[0098] Step 2:
[0099] The terminal sends the symptom data entered by the user to the server using the HTTPS protocol. The input is the user's symptom data (e.g., "My chest hurts"), and the output is the process of encrypting this data and sending it to the server. The terminal performs specific operations to securely transfer the symptom data.
[0100] Step 3:
[0101] The server uses a generative AI model to translate and analyze the received user symptom data in real time. The input is the user's symptom data (e.g., "I have chest pain"), and the output is the translated data and symptom keywords (e.g., "chest pain"). The server performs the specific operations of translating the English text into Japanese and extracting important keywords.
[0102] Step 4:
[0103] The server obtains the current location from the user's device using the GPS function and references the system time to obtain the current time zone. The input is the user's location data and system time, and the output is the current location (e.g., Shibuya-ku, Tokyo) and time information. The server performs the specific operations to obtain the GPS data and time information.
[0104] Step 5:
[0105] The server searches for the most suitable medical facility from the medical institution database based on the acquired current location, time zone, and analyzed symptom data. The input is the current location, time information, and symptom keywords, and the output is a list of the most suitable medical facilities. The server performs a specific operation of querying the database to identify the nearest medical facility that is open.
[0106] Step 6:
[0107] If the user does not have transportation, the server uses the API of the vehicle dispatch service to arrange transportation from the user's current location to the medical facility. The input is the user's current location and the location of the medical facility, and the output is reservation confirmation information for the vehicle dispatch service. The server sends an emergency vehicle dispatch request and performs specific operations to arrange the vehicle dispatch service.
[0108] Step 7:
[0109] After receiving medical treatment at a medical facility, the user provides feedback through a terminal. The input is the user's feedback (e.g., answer to the question, "Are you satisfied with this service?"), and the output is the transmission of the feedback data to the server. The terminal performs the specific operation of collecting the feedback data and sending it to the server. The server stores the feedback data in a database and uses it to improve the entire system.
[0110] (Application example 1)
[0111] 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."
[0112] In modern food delivery services, delivery workers are often exposed to harsh working conditions. In particular, if they feel unwell, they have limited access to appropriate medical facilities, which can pose serious health risks. Furthermore, language barriers and uncertain location information further complicate emergency response. There is a need to develop a system that can solve these problems and efficiently support the health management of delivery workers.
[0113] 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.
[0114] In this invention, the server includes means for selecting a user input method and communication language and inputting symptoms, translation means using generative artificial intelligence to translate the user's input, means for analyzing the translated symptoms, means for searching for the most appropriate medical institution based on the current location and time zone, means for arranging transportation in cooperation with a vehicle dispatch service, and means for inputting symptoms when a delivery person feels unwell, searching for the most appropriate medical institution, and arranging a vehicle dispatch service. This enables a delivery person to quickly and accurately access an appropriate medical institution when they feel unwell, and even arranges transportation if necessary.
[0115] "User input method" refers to the means by which a user reports a symptom to the system, including forms of text or voice input.
[0116] A "communication language" is a language used by a user and a system to exchange information, and provides multiple languages that a user can select.
[0117] "Generative AI translation means" refers to AI technologies used to accurately translate input text or audio data into other languages in real time.
[0118] The "means for symptom analysis" is a method for extracting specific symptoms from the translated input information and identifying the type of health problem the user is experiencing.
[0119] The "means for searching for the most suitable medical institution based on the current location and time zone" is a method for searching for the nearest and most suitable medical institution for the user using the user's location information and the current time.
[0120] "Means of arranging transportation in cooperation with a ride-hailing service" refers to a method of coordinating with a ride-hailing service provider to arrange transportation to a medical institution.
[0121] "A means for delivery workers to input their symptoms when they feel unwell, search for the most appropriate medical institution, and arrange for a ride-hailing service" refers to a method for food delivery workers who feel unwell while on the job to quickly report their symptoms, find the most appropriate medical institution, and arrange for the necessary transportation.
[0122] The system embodying this invention provides a method for quickly accessing the most appropriate medical institution when a user feels unwell, while also incorporating a function to support health management, particularly for food delivery personnel.
[0123] The main components of the system include a means for users to input symptoms, a translation means using generative AI, a symptom analysis means, a medical institution search means, and a means for linking with vehicle dispatch services. The specific configuration and processing flow for realizing these means are described below.
[0124] Main Components and Processing Flow
[0125] 1. User symptom input method:
[0126] Users report their symptoms by typing or speaking using a smartphone or other mobile device. First, users enter their symptoms and complaints into the application.
[0127] 2. Generative AI translation methods:
[0128] The inputted symptoms are sent to a server where they are translated in real time by a generative artificial intelligence (NLP model), which uses common language processing tools such as Google Translate API and Azure Cognitive Services.
[0129] 3. Symptom analysis means:
[0130] The translated text is then analyzed to extract specific symptoms. This analysis process involves detecting keywords that correspond to the symptoms (e.g., chest pain, dizziness).
[0131] 4. Medical institution search methods:
[0132] The server searches for the most suitable medical institution based on the user's current location (obtained by the GPS function) and the current time. This information is obtained by the server by referring to the medical institution database.
[0133] 5. Ride-hailing service integration methods:
[0134] If necessary, the server will use a ride-hailing service (e.g., Uber or Lyft API) to arrange transportation for the user to the designated medical facility.
[0135] Hardware and software used
[0136] Smartphone: The primary device for users to enter symptoms.
[0137] GPS function: Used to obtain current location.
[0138] Generative artificial intelligence (NLP models): Used to translate and analyze input text. Examples include Google Translate API and Azure Cognitive Services.
[0139] Server: The central component that processes data and searches for medical institutions.
[0140] Ride-hailing service API: Used to arrange transportation for users.
[0141] Examples of concrete examples and prompts
[0142] As a concrete example, consider the case where a food delivery person suddenly experiences dizziness while on a delivery and voice-inputs into the app, "I'm feeling very dizzy." The app sends this information to a server and analyzes it using generative artificial intelligence. The server then searches for the nearest open clinic and arranges for a ride-hailing service if necessary.
[0143] Example prompt sentence:
[0144] "I feel extremely dizzy, please find the nearest medical facility."
[0145] This system allows delivery personnel to quickly and accurately access appropriate medical facilities and be provided with the necessary transportation if they feel unwell.
[0146] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[0147] Step 1:
[0148] The user opens the smartphone application and reports their symptoms by text or voice input. Input here includes symptoms such as "I feel very dizzy." The device sends this information to the server. The input for this step is the user's symptom description, and the output is the symptom data sent to the server.
[0149] Step 2:
[0150] The server passes the symptom data sent by the user to a generative AI. The generative AI (NLP model) translates this information in real time and extracts symptom keywords as needed. The input is the symptom data from the user, and the output is a list of translated and analyzed symptom keywords.
[0151] Step 3:
[0152] The server identifies specific symptoms from the translated and analyzed symptom keyword list. For example, if the keyword "dizziness" is detected, it searches for appropriate medical institutions based on this symptom. The input of this step is the translated and analyzed keyword list, and the output is a symptom-based medical institution search query.
[0153] Step 4:
[0154] The server obtains the user's current location and the current time using the GPS function and the system clock. The input is the user's location information and the current time, and the output is search conditions based on the location and time.
[0155] Step 5:
[0156] The server searches for the most suitable medical institution from the medical institution database using the acquired current location, time, and keywords based on the symptoms. At this time, the server generates a list of medical institutions that meet the specified conditions. The input is the search conditions, and the output is a list of medical institutions that meet the conditions.
[0157] Step 6:
[0158] The server arranges a ride-hailing service as needed. For example, if a delivery person does not have their own means of transportation, it arranges for a ride-hailing service API. The input is the user's current location and the location of the medical institution, and the output is a ride-hailing service reservation confirmation.
[0159] Step 7:
[0160] The server notifies the delivery person of the information on the most suitable medical institution and details of the vehicle dispatch service. The notification is sent via a smartphone application. The input of this step is the searched medical institution and details of the vehicle dispatch service, and the output is a notification to the user.
[0161] In this way, the data entered at each processing step is appropriately processed and calculated, and the final output supports the user in quickly accessing an appropriate medical institution.
[0162] 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.
[0163] This invention is a system that supports users in quickly accessing appropriate medical institutions in situations requiring emergency medical care. The system uses generative artificial intelligence to translate and analyze symptoms entered by the user, searches for the most appropriate medical institution based on the results, and arranges for a vehicle dispatch service if necessary. Furthermore, an emotion engine that recognizes the user's emotions has been added, providing appropriate responses based on the user's emotions.
[0164] The system starts by having the user select the input method (text input or voice input) and communication language. When the user inputs their symptoms by text or voice, the information is sent to the server via the terminal. For example, consider the case where a user inputs the symptom "I have chest pain and can't breathe."
[0165] The server then uses generative artificial intelligence to translate this input in real time. Even if the user types in a language other than Japanese, the AI translation converts it into accurate Japanese or other standard languages. The server then analyzes this translated text to identify symptoms, specifically extracting keywords such as "chest pain" and "shortness of breath."
[0166] The server then uses an emotion engine to recognize emotions from the user's input. For example, it can determine whether the user is feeling anxious or confused from their voice tone or input text. Once the emotion engine identifies the user's emotion, that information is reflected in the system's overall response. The emotion engine analyzes the user's stress level and urgency, and adjusts the priority of medical facility searches and the speed of vehicle dispatch accordingly.
[0167] Next, the server obtains the user's current location and time zone. Location information is obtained using the user's device's GPS function, and time zone information is obtained by referencing the system time. Based on this information and the user's symptoms, the server searches the medical institution database for the most suitable emergency medical institution. The search results may include hospitals and clinics that are currently open.
[0168] If necessary, the server coordinates with a vehicle dispatch service to arrange transportation from the user's current location to a medical facility. For example, if the user does not have a car, the server calls a vehicle dispatch service to assist the user in emergency transportation.
[0169] Finally, after receiving medical treatment, the user provides feedback through the terminal. The server collects this feedback, stores it in a database, and uses it to improve the accuracy and quality of the service of the entire system.
[0170] As a specific example, a user experiences sudden chest pain while on a business trip and voice-types "My chest hurts" into the app. This information is sent to the server, where it is translated and analyzed in real time using generative artificial intelligence. Furthermore, the emotion engine recognizes the user's anxious tone and determines the level of urgency. The server obtains the user's current location and searches for the nearest hospital that is open even at night. If the user does not have transportation, the server arranges for a ride-hailing service, helping the user quickly receive appropriate treatment at a hospital. In this way, the present invention enables users to access medical institutions quickly and appropriately, regardless of their location. Furthermore, the introduction of the emotion engine enables more personalized care, increasing user satisfaction and peace of mind.
[0171] The processing flow will be explained below.
[0172] Step 1:
[0173] The user inputs symptoms into the terminal. Input methods can be selected from text input and voice input. The communication language can also be selected. For example, consider the case where the user inputs "I have chest pain and can't breathe" by voice input.
[0174] Step 2:
[0175] The device sends the user's input information to the server. In the case of voice input, the device converts the voice into text before sending it to the server.
[0176] Step 3:
[0177] The server uses generative artificial intelligence to translate information entered by users in real time. For example, even if the information is entered in a language other than Japanese, it will be translated into a standard language using AI.
[0178] Step 4:
[0179] The server analyzes the translated text and extracts specific symptoms, such as keywords like "chest pain" or "shortness of breath."
[0180] Step 5:
[0181] The server uses an emotion engine to recognize emotions from the user's input, determining whether the user is feeling anxious or confused based on the tone of voice and the text entered.
[0182] Step 6:
[0183] The server then suggests appropriate responses to the user based on the emotions recognized by the emotion engine. For example, if anxiety is judged to be high, a more immediate response will be prioritized.
[0184] Step 7:
[0185] The server obtains the current location from the user's device, using the device's GPS function to obtain latitude and longitude information.
[0186] Step 8:
[0187] The server obtains the current time and uses this information to prepare data to identify medical institutions that are open at the time of the user's visit.
[0188] Step 9:
[0189] The server searches the medical institution database for the most suitable medical institution based on the patient's current location, time zone, and analyzed symptoms. As a result, for example, a nearby 24-hour emergency hospital may be identified.
[0190] Step 10:
[0191] The server checks whether the user has a means of transportation. If it determines that the user does not have a means of transportation based on the report from the user terminal, it proceeds to the next step.
[0192] Step 11:
[0193] The server cooperates with the vehicle dispatch service to arrange appropriate transportation, for example, calling the vehicle dispatch service and arranging for a prompt transportation of the user from the current location to the identified medical institution.
[0194] Step 12:
[0195] After receiving medical treatment at a medical institution, the user provides feedback through the terminal. For example, the user can input a comment such as "The hospital's response was quick."
[0196] Step 13:
[0197] The server collects the feedback and stores it in a database, which provides data to improve the accuracy and quality of service of the entire system.
[0198] Example 2
[0199] 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."
[0200] In modern society, when emergency medical assistance is needed, it is important to access appropriate medical institutions quickly and accurately. However, users often have difficulty accurately describing their symptoms and are unable to easily find appropriate medical institutions. In addition, there is a lack of personalized care that takes into account the user's feelings and the level of urgency, which leads to issues of insufficient satisfaction and peace of mind.
[0201] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.
[0202] In this invention, the server includes a translation means using generative artificial intelligence to translate user input, a means for analyzing the translated symptoms, an emotion recognition means using an emotion engine to recognize emotions from the user input, a means for searching for the most suitable medical institution based on the current location and time zone, a means for arranging transportation in cooperation with a ride-hailing service, and a means for collecting feedback after the medical treatment and storing it in a database. This allows the user to access a medical institution quickly and accurately no matter where they are, and further enables individualized treatment based on the user's emotions and urgency, thereby increasing satisfaction and peace of mind.
[0203] "User" refers to a person who uses this system to input symptoms and search for an appropriate medical institution.
[0204] "Input method" refers to the means by which a user communicates symptoms to the system by text input or voice input.
[0205] "Communication language" refers to the language used by the user to interact with the system.
[0206] "Generative AI" refers to artificial intelligence technology used to translate user input in real time and convert it into the appropriate language.
[0207] "Translation means" refers to a means for translating information entered by a user into another language using generative artificial intelligence.
[0208] "Means for analyzing symptoms" refers to means for analyzing the translated symptom information and identifying specific medical symptoms.
[0209] "Emotion recognition means" refers to a means for recognizing emotions from user input information or voice using an emotion engine.
[0210] "Emotion engine" refers to technology that analyzes emotions from user input and vocal tone to identify emotional states.
[0211] "Current location" refers to the user's location information identified using the GPS function of the user's device, etc.
[0212] "Time zone information" refers to information about the current time obtained by referring to the system time.
[0213] The "means for searching for a medical institution" refers to a means for searching a database for the most suitable medical institution based on the user's location information and symptoms.
[0214] "Vehicle dispatch service" refers to a transportation arrangement service used by users to quickly arrive at medical institutions.
[0215] "Means for arranging transportation" refers to a means of arranging transportation to and from a medical institution in cooperation with a vehicle dispatch service.
[0216] "Feedback" refers to the opinions and evaluations that users provide to the system after receiving medical treatment.
[0217] "Means for storing in a database" refers to the means for storing the collected feedback in a database and utilizing it to improve the accuracy of the system and the quality of the service.
[0218] This invention is a system that supports users in quickly accessing appropriate medical institutions in situations requiring emergency medical care. The system uses generative artificial intelligence to translate and analyze symptoms entered by the user, searches for the most appropriate medical institution based on the results, and arranges for a vehicle dispatch service if necessary. Furthermore, an emotion engine that recognizes the user's emotions has been added, providing appropriate responses based on the user's emotions.
[0219] The system starts by having the user select the input method (text input or voice input) and communication language. When the user inputs their symptoms by text or voice, the information is sent to the server via the terminal. For example, consider the case where a user inputs the symptom "I have chest pain and can't breathe."
[0220] The server then uses generative artificial intelligence (e.g., Google Cloud Translation API) to translate this input in real time. Even if the user types in a language other than Japanese, the AI translation converts it into accurate Japanese or other standard languages. The server then analyzes this translated text to identify symptoms, specifically extracting keywords such as "chest pain" and "shortness of breath."
[0221] The server then uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize emotions from the user's input. For example, it can determine whether the user is feeling anxious or confused from the tone of their voice or the text they enter. Once the emotion engine identifies the user's emotion, that information is reflected in the system's overall response. The emotion engine analyzes the user's stress level and urgency, and adjusts the priority of medical facility searches and the speed of vehicle dispatch based on that information.
[0222] Next, the server obtains the user's current location and time zone. Location information is obtained using the user's device's GPS function, and time zone information is obtained by referencing the system time. Based on this information and the user's symptoms, the server searches for the most suitable emergency medical institution from a medical institution database (e.g., a MySQL database). The search results may include hospitals and clinics that are currently open.
[0223] If necessary, the server will coordinate with a ride-hailing service (e.g., Uber API) to arrange transportation from the user's current location to a medical facility. For example, if the user does not have a car, the server will call a ride-hailing service to assist the user in emergency transportation.
[0224] Finally, after receiving medical treatment, the user provides feedback through the terminal. The server collects this feedback, stores it in a database, and uses it to improve the accuracy and quality of the service of the entire system.
[0225] Examples:
[0226] A user experiences sudden chest pain while on a business trip and voice-types "I have chest pain" into the app. This information is sent from the device to the server, where it is translated and analyzed in real time using generative artificial intelligence (e.g., Google Cloud Translation API). Furthermore, an emotion engine (e.g., IBM Watson Tone Analyzer) recognizes the user's anxious tone and determines the level of urgency. The server obtains the user's current location and searches for the nearest hospital that is open even at night.
[0227] If the user does not have transportation, the server will arrange for a ride-hailing service (e.g., Uber API) to help the user quickly receive appropriate treatment at a hospital. In this way, users can access medical institutions quickly and appropriately, no matter where they are. In addition, the introduction of an emotion engine enables more personalized responses, increasing user satisfaction and a sense of security.
[0228] Example prompt sentence:
[0229] "A user utters 'I have chest pain' into the app. Send this information to the server, translate it in real time, and analyze the symptoms. Also, recognize the user's emotion (anxious tone) and explain the steps to find a medical facility and arrange transportation."
[0230] The flow of the identification process in the second embodiment will be described with reference to FIG.
[0231] Step 1:
[0232] The user enters the symptoms into the terminal.
[0233] Specifically, the user starts the application, selects text input or voice input, enters the symptoms, and presses the send button.
[0234] Input: Symptom information entered by the user into the device (e.g., "I have chest pain").
[0235] Output: Symptom information sent from the device to the server.
[0236] Step 2:
[0237] The terminal sends the input information to the server.
[0238] Specifically, the device transmits the symptom information entered by the user to the server in real time, as well as the input method and communication language selected by the user.
[0239] Input: Symptom information entered into the terminal.
[0240] Output: Symptom information, input method, and language information sent to the server.
[0241] Step 3:
[0242] The server uses the generated AI model to translate and analyze.
[0243] Specifically, the server translates user input in real time using a generative AI model (e.g., Google Cloud Translation API), then analyzes the translated text to extract keywords related to the symptoms.
[0244] Input: Symptom information, input method, and language information sent to the server.
[0245] Output: Translated symptom information and extracted keywords (e.g., "chest pain," "shortness of breath").
[0246] Step 4:
[0247] The server uses an emotion engine to recognize the user's emotion.
[0248] Specifically, the server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize emotions from the user's input, determining the user's anxiety or confusion from the voice tone and text, and assessing the level of urgency.
[0249] Input: Translated symptom information and extracted keywords.
[0250] Output: User's emotional state (e.g., anxiety, urgency rating).
[0251] Step 5:
[0252] The server obtains the user's current location and time zone information.
[0253] Specifically, the server uses the device's GPS function to obtain the user's current location and also references the system time to obtain the current time zone information.
[0254] Input: Location information obtained from the user's device and system time.
[0255] Output: User's current location and time zone information.
[0256] Step 6:
[0257] The server searches for the most suitable medical institution from the medical institution database.
[0258] Specifically, the server uses a MySQL database to search for the most suitable medical facility based on the user's location and symptoms, for example, listing hospitals that are open at night.
[0259] Input: User's current location, time zone information, and keywords related to the symptom.
[0260] Output: A list of the best medical institutions.
[0261] Step 7:
[0262] The server will arrange a ride-hailing service if necessary.
[0263] Specifically, if the user does not have a car, the server calls a ride-hailing service (e.g., Uber API) and arranges transportation from the user's current location to the medical facility.
[0264] Input: User's current location and information about the destination medical institution.
[0265] Output: Arrange a ride.
[0266] Step 8:
[0267] The user provides feedback via the terminal after the treatment.
[0268] Specifically, after receiving medical treatment, the user restarts the application on the terminal, inputs and sends their evaluation and opinions of the treatment.
[0269] Input: User's ratings and opinions after treatment.
[0270] Output: Feedback sent from the device to the server.
[0271] Step 9:
[0272] The server collects the feedback and stores it in a database.
[0273] Specifically, the server collects the feedback provided by users and stores it in a MySQL database, which is used to improve the accuracy and quality of the service of the entire system.
[0274] Input: Feedback sent from the device.
[0275] Output: Feedback information stored in a database.
[0276] (Application example 2)
[0277] 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."
[0278] Conventional emergency response systems have had problems in providing a fast and appropriate response when users face an emergency. In particular, it is difficult to communicate in multiple languages and analyze users' emotions, making it difficult to select the appropriate emergency agency and quickly arrange for vehicle dispatch. In addition, there is a lack of a mechanism for collecting user feedback and reflecting it in the service.
[0279] 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.
[0280] In this invention, the server includes: a means for selecting a user's input method and communication language and inputting symptoms and conditions; a translation means using generative artificial intelligence to translate the user's input; a means for analyzing the translated symptoms and conditions; a means for searching for the most appropriate response agency based on the user's current location and time of day; a means for arranging transportation in cooperation with a ride-hailing service; a means for analyzing the user's emotions using an emotion engine to determine the urgency of the emergency response and an appropriate response; a means for collecting feedback and using it to improve the service; and a means for providing a response based on the emotion engine. This allows information provided by users in multiple languages to be analyzed quickly and accurately, and an appropriate response to be provided based on the user's emotions. Furthermore, collecting and incorporating feedback allows for continuous improvement of the system.
[0281] A "user input method" is the means a user uses to provide information to a system, such as speech input or text input.
[0282] "Communication language" refers to the language used by the user to interact with the system, and includes, for example, Japanese, English, Chinese, etc.
[0283] "Symptoms and circumstances" are detailed information about the emergency that the user provides to the system, such as chest pain, shortness of breath, or the presence of a suspicious person.
[0284] "Generative AI" is an AI that has the ability to analyze input information and translate it into accurate language.
[0285] "Translation means" refers to a means for converting input information into another language using generative artificial intelligence.
[0286] "Analysis means" refers to the extraction of keywords and context from translated information, and the use of this information to determine the level of urgency and appropriate countermeasures.
[0287] "Current location" refers to the geographical information of the point where the user is accessing the system, and is obtained using technology such as GPS.
[0288] "Time zone" is information about the time when a user accesses the system, and refers to the system time.
[0289] A "response organization" is an organization or facility that responds appropriately to a user's emergency, and includes, for example, a hospital, a police station, a fire station, and the like.
[0290] A "vehicle dispatch service" is a service that arranges transportation from the user's current location to an emergency response organization.
[0291] An "emotion engine" is a program that recognizes emotions from the user's voice or text and adjusts the system's response based on the results.
[0292] "Feedback" refers to opinions and evaluation information provided by users after using the system, and is data that is useful for improving the system.
[0293] The present invention is a system for speeding up and optimizing emergency responses, supporting users in quickly accessing appropriate response organizations when faced with an emergency. This system includes a means for users to select an input method and communication language and input symptoms and circumstances, a translation means using generative artificial intelligence, a means for analyzing the translated symptoms and circumstances, a means for searching for the most appropriate response organization based on the current location and time of day, a means for arranging transportation in cooperation with a ride-hailing service, a means for analyzing user emotions using an emotion engine to determine the urgency, and a means for collecting feedback to help improve the service.
[0294] System configuration
[0295] 1. User Input Method
[0296] The user can provide the system with an emergency situation by voice or text input using a smartphone or smart glasses. For example, the user can input "someone is trying to enter my house."
[0297] 2. Translation Methods
[0298] The server uses generative artificial intelligence to translate user input in real time. For example, if a user types "help" in Japanese, it will translate this into English as "Help!"
[0299] 3. Analysis method
[0300] The translated text is then analyzed in conjunction with an emotion engine to assess the user's level of urgency and the necessary response. For example, an input such as "someone is trying to get into my house" could indicate a situation of high anxiety and urgency.
[0301] 4. Search Methods
[0302] The server searches for emergency response agencies (police, fire department, hospitals, etc.) based on the current location and time information, and uses location information services such as Google Maps API to present the most appropriate response agency.
[0303] 5. Vehicle dispatch method
[0304] If the user does not have transportation, the server will use an API such as Uber to arrange a ride, for example, a police car will be dispatched from the nearest police station to the user's location.
[0305] 6. Emotion analysis method
[0306] It uses an emotion engine to analyze the user's emotions and determine the level of urgency, determining whether the user is feeling anxious or scared based on their input and tone of voice.
[0307] 7. Feedback Collection Methods
[0308] After users use the system, feedback is collected and used to improve the system, which will be used to improve the accuracy of the next emergency response.
[0309] Specific examples
[0310] Imagine a case where a user hears a suspicious sound at home at night and voice-records, "There's someone in the house." This information is sent from the smartphone to a server, where it is translated and analyzed in real time using generative artificial intelligence. The emotion engine recognizes the user's anxiety and determines that the situation is urgent. The server obtains the user's current location, searches for the nearest police station, and dispatches a patrol car. At the same time, it provides the user with guidelines such as, "Stay in a safe place and don't go outside." The system then collects user feedback and uses it to improve future responses.
[0311] Prompt Sentence Examples
[0312] User: "Someone is trying to get into my house. Help!"
[0313] Generative AI: Translated into English: "Someone is trying to break into my house. Help!"
[0314] Emotion Engine Assessment: User exhibits extreme anxiety.
[0315] Optimal solution: Send location information to the police. Arrange for a patrol car.
[0316] Guidelines provided: "Please lock your room and secure it. Do not move until the police arrive."
[0317] As described above, this system allows users to receive prompt and reliable support even in emergency situations.
[0318] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[0319] Step 1:
[0320] The user selects the input method (voice or text) and communication language using a smartphone or smart glasses. The input symptom or situation (e.g., "There is someone in the house") is sent to the device's input interface.
[0321] Input: The user's chosen input method and language, spoken or written symptoms or conditions.
[0322] Output: Sends input information (audio data or text data) to the server.
[0323] Step 2:
[0324] The server uses generative artificial intelligence to translate input information sent from the device in real time. For example, if the voice input is in Japanese, it will translate it into English.
[0325] Input: Audio or text data from the user.
[0326] Output: The translated text data.
[0327] Step 3:
[0328] The server analyzes the translated text data to extract important keywords and context (e.g., "There is an intruder in my house") and uses an emotion engine to analyze the user's emotions (e.g., anxiety, fear).
[0329] Input: Translated text data.
[0330] Output: Extracted keywords, parsed sentiment data.
[0331] Step 4:
[0332] The server obtains the user's current location using the GPS function and also references the system time information. Based on this, it uses the Google Maps API to search for the most appropriate emergency response organization (e.g., the nearest police station).
[0333] Input: User's GPS location data, system time.
[0334] Output: A list of the best emergency response agencies.
[0335] Step 5:
[0336] Once the optimal facility has been determined, the server will connect with a ride-hailing service (e.g., Uber API) and arrange transportation from the user's current location to the facility if necessary.
[0337] Input: A list of the best emergency response agencies, the user's current location.
[0338] Output: Ride dispatch information.
[0339] Step 6:
[0340] The server responds to the user based on the emotional information analyzed by the emotion engine. For example, if a user feels anxious, the server provides specific guidelines such as "stay in a safe place and do not go outside."
[0341] Input: Emotion data, analysis results.
[0342] Output: A response message to the user.
[0343] Step 7:
[0344] After using the system, users provide feedback, which is sent to the server via their device and used to improve the accuracy of future emergency responses.
[0345] Input: Feedback data from users.
[0346] Output: Save feedback information and data to improve accuracy next time.
[0347] 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.
[0348] 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.
[0349] 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.
[0350] [Second embodiment]
[0351] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.
[0352] 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.
[0353] 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).
[0354] 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.
[0355] 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.
[0356] 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).
[0357] 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.
[0358] 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.
[0359] 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.
[0360] 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.
[0361] 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.
[0362] 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."
[0363] This invention is a system that supports users in quickly accessing appropriate medical institutions in situations where emergency medical care is required. The system uses generative artificial intelligence to translate and analyze symptoms entered by the user, searches for the most appropriate medical institution based on the results, and arranges for a vehicle dispatch service if necessary.
[0364] The system starts by having the user select the input method (text input or voice input) and communication language. When the user inputs their symptoms by text or voice, the information is sent to the server via the terminal. For example, consider the case where a user inputs the symptom "I have chest pain and can't breathe."
[0365] The server then uses generative artificial intelligence to translate this input in real time. Even if the user types in a language other than Japanese, the AI translation converts it into accurate Japanese or other standard languages. The server then analyzes this translated text to identify symptoms, specifically extracting keywords such as "chest pain" and "shortness of breath."
[0366] The server then obtains the user's current location and time zone. Location information is obtained using the user's device's GPS function, and time zone information is obtained by referencing the system time. Based on this information and the user's symptoms, the server searches the medical institution database for the most suitable emergency medical institution. The search results may include hospitals and clinics that are currently open.
[0367] If necessary, the server will coordinate with a ride-hailing service to arrange transportation from the user's current location to a medical facility. For example, if the user does not have a car, the server will call a ride-hailing service such as DiDi or Uber to assist with emergency transportation for the user.
[0368] Finally, after receiving medical treatment, users can provide feedback through their devices, which the server collects and stores in a database to improve the accuracy and quality of the overall system.
[0369] As a specific example, if a user experiences sudden chest pain while on a business trip, they can voice-input "I have chest pain" into the app. This information is sent to a server and analyzed using generative artificial intelligence. The server obtains the user's current location and searches for the nearest hospital that is open even at night. If the user does not have transportation, the server arranges for a ride-hailing service, helping the user to quickly receive appropriate treatment at a hospital. In this way, the present invention allows users to access medical institutions quickly and appropriately, no matter where they are.
[0370] The processing flow will be explained below.
[0371] Step 1:
[0372] The user inputs their symptoms into the device. They can choose to input text or voice, and also select the communication language. For example, the user can input "I have chest pain and can't breathe" by text input.
[0373] Step 2:
[0374] The device sends the user's input information to the server. In the case of voice input, the device converts the voice into text before sending it to the server.
[0375] Step 3:
[0376] The server uses generative artificial intelligence to translate information entered by users in real time. For example, even if the information is entered in a language other than Japanese, it will be translated into a standard language using AI.
[0377] Step 4:
[0378] The server analyzes the translated text and extracts specific symptoms, for example, identifying keywords such as "chest pain" and "shortness of breath" from the translated text "My chest hurts and I can't breathe."
[0379] Step 5:
[0380] The server obtains the current location from the user's device, using the device's GPS function to obtain latitude and longitude information.
[0381] Step 6:
[0382] The server obtains the current time and uses this information to prepare data to identify medical institutions that are open at the time of the user's visit.
[0383] Step 7:
[0384] The server searches the medical institution database for the most suitable medical institution based on the patient's current location, time zone, and analyzed symptoms. As a result, for example, a nearby 24-hour emergency hospital may be identified.
[0385] Step 8:
[0386] The server checks whether the user has a means of transportation based on the information provided by the user. If the device reports "no means of transportation," the server proceeds to the next step.
[0387] Step 9:
[0388] The server works in cooperation with the vehicle dispatch service to arrange appropriate transportation, for example, by calling a vehicle dispatch service such as DiDi or Uber and arranging for a prompt transportation from the user's current location to the specified medical institution.
[0389] Step 10:
[0390] After the consultation, the user provides feedback through the terminal, for example, by entering a comment such as "The hospital's response was quick."
[0391] Step 11:
[0392] The server collects the feedback data and stores it in a database, which accumulates data to improve the accuracy and quality of service of the entire system.
[0393] Example 1
[0394] 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."
[0395] Conventional emergency medical support systems make it difficult for users to accurately describe their symptoms and quickly find an appropriate medical institution. Furthermore, language barriers and a lack of transportation can significantly delay the time it takes to receive appropriate care in an emergency. This increases the risk to users' health.
[0396] 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.
[0397] In this invention, the server includes means for selecting a user's input method and communication language and inputting symptoms, means for translating the user's input using generative artificial intelligence, means for analyzing the translated symptoms, means for acquiring a current location and time zone, means for searching for an optimal medical facility based on the acquired current location and time zone, and means for arranging transportation in cooperation with a vehicle allocation service. This allows the user to quickly access an appropriate medical institution and, if necessary, arrange transportation, thereby reducing health risks in an emergency.
[0398] A "user" is an individual who uses the system to input symptoms and access appropriate medical care.
[0399] "Input method" refers to the means used by the user to communicate symptoms to the system, and includes text input and voice input.
[0400] The "communication language" is the language used by the user to communicate symptoms to the system, and is the target language for the system to translate.
[0401] "Generative AI" is an AI technology that translates and analyzes symptom information entered by users in real time.
[0402] "Translation" is a process that uses generative artificial intelligence to translate user-entered symptom information into another language.
[0403] The "analysis means" is the process of analyzing the symptom information translated by the generative artificial intelligence and extracting important keywords.
[0404] "Current location" is location information obtained through the GPS function of the user's device.
[0405] The "time zone" is the current time information obtained by referring to the system time.
[0406] "Medical facilities" are medical institutions such as hospitals and clinics that users need to access in an emergency.
[0407] A "vehicle deployment service" is a service that provides a means for quickly transporting users to medical facilities.
[0408] "Transportation" means the transportation required for a User to access a Medical Facility, and is provided by a vehicle deployment service.
[0409] This invention is a system that supports users who require emergency medical care by enabling them to quickly access appropriate medical institutions. The system uses generative artificial intelligence to translate and analyze symptoms input by the user, searches for the most suitable medical facility based on the acquired current location and time of day, and arranges for vehicle deployment services if necessary. Each component and its specific operation are explained below.
[0410] A user opens an application using a device such as a smartphone or tablet. The application provides a method for the user to input symptoms using text input or voice input. The user can also select the communication language to use. For example, consider the case where a user inputs "I have chest pain" by voice.
[0411] The entered information is sent from the device to the server. At this time, the device uses the HTTPS protocol to transfer data securely. Specifically, the user enters the information "I have chest pain," and the device encrypts it and sends it to the server.
[0412] The server inputs the received symptom information into a generative artificial intelligence (AI model). The generative AI translates and analyzes the information entered by the user in real time. For example, if a user enters "I have chest pain" in English, the AI model translates this into Japanese as "Chest pain." The server then analyzes the translated text and extracts keywords such as "chest pain" and "shortness of breath."
[0413] The server also obtains the user's current location and time zone by obtaining location information through the device's GPS function and referencing the system time to obtain time information. For example, the server may use GPS data sent from the device to determine the user's current location as Shibuya Ward, Tokyo.
[0414] Next, the server searches for the most suitable emergency medical facility from the medical facility database based on the user's location, time zone, and analyzed symptom information. For example, the server searches for hospitals that are open late at night and are located near Shibuya Ward, Tokyo.
[0415] If the user does not own a car and needs transportation, the server will arrange for a vehicle dispatch service. In this case, the server will use various APIs (Application Programming Interfaces) to connect with the vehicle dispatch service and arrange for transportation from the user's current location to the medical facility. Specifically, the server will request a vehicle dispatch from the user's current location (Shibuya-ku, Tokyo) to the hospital through the vehicle dispatch service's API.
[0416] After receiving medical treatment, users can provide feedback through their devices. Specifically, the application displays a survey-style question such as "Were you satisfied with the service?", and the user submits their answer. The server collects this feedback, stores it in a database, and uses it to improve the accuracy of the entire system and the quality of the service.
[0417] The above is a specific description of an embodiment of the present invention. Examples of prompt sentences are shown below. "I have chest pain" and "I have chest pain" are examples of prompt sentences. This system allows users to quickly access appropriate medical institutions and arranges transportation if necessary, thereby reducing health risks in emergencies.
[0418] The flow of the identification process in the first embodiment will be described with reference to FIG.
[0419] Step 1:
[0420] The user uses the device to launch the application and select the communication language and input method (text input or voice input). As input, the user types "I have chest pain" in text or voice input. This is the specific operation. The output is the user's input data.
[0421] Step 2:
[0422] The terminal sends the symptom data entered by the user to the server using the HTTPS protocol. The input is the user's symptom data (e.g., "My chest hurts"), and the output is the process of encrypting this data and sending it to the server. The terminal performs specific operations to securely transfer the symptom data.
[0423] Step 3:
[0424] The server uses a generative AI model to translate and analyze the received user symptom data in real time. The input is the user's symptom data (e.g., "I have chest pain"), and the output is the translated data and symptom keywords (e.g., "chest pain"). The server performs the specific operations of translating the English text into Japanese and extracting important keywords.
[0425] Step 4:
[0426] The server obtains the current location from the user's device using the GPS function and references the system time to obtain the current time zone. The input is the user's location data and system time, and the output is the current location (e.g., Shibuya-ku, Tokyo) and time information. The server performs the specific operations to obtain the GPS data and time information.
[0427] Step 5:
[0428] The server searches for the most suitable medical facility from the medical institution database based on the acquired current location, time zone, and analyzed symptom data. The input is the current location, time information, and symptom keywords, and the output is a list of the most suitable medical facilities. The server performs a specific operation of querying the database to identify the nearest medical facility that is open.
[0429] Step 6:
[0430] If the user does not have transportation, the server uses the API of the vehicle dispatch service to arrange transportation from the user's current location to the medical facility. The input is the user's current location and the location of the medical facility, and the output is reservation confirmation information for the vehicle dispatch service. The server sends an emergency vehicle dispatch request and performs specific operations to arrange the vehicle dispatch service.
[0431] Step 7:
[0432] After receiving medical treatment at a medical facility, the user provides feedback through a terminal. The input is the user's feedback (e.g., answer to the question, "Are you satisfied with this service?"), and the output is the transmission of the feedback data to the server. The terminal performs the specific operation of collecting the feedback data and sending it to the server. The server stores the feedback data in a database and uses it to improve the entire system.
[0433] (Application example 1)
[0434] 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."
[0435] In modern food delivery services, delivery workers are often exposed to harsh working conditions. In particular, if they feel unwell, they have limited access to appropriate medical facilities, which can pose serious health risks. Furthermore, language barriers and uncertain location information further complicate emergency response. There is a need to develop a system that can solve these problems and efficiently support the health management of delivery workers.
[0436] 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.
[0437] In this invention, the server includes means for selecting a user input method and communication language and inputting symptoms, translation means using generative artificial intelligence to translate the user's input, means for analyzing the translated symptoms, means for searching for the most appropriate medical institution based on the current location and time zone, means for arranging transportation in cooperation with a vehicle dispatch service, and means for inputting symptoms when a delivery person feels unwell, searching for the most appropriate medical institution, and arranging a vehicle dispatch service. This enables a delivery person to quickly and accurately access an appropriate medical institution when they feel unwell, and even arranges transportation if necessary.
[0438] "User input method" refers to the means by which a user reports a symptom to the system, including forms of text or voice input.
[0439] A "communication language" is a language used by a user and a system to exchange information, and provides multiple languages that a user can select.
[0440] "Generative AI translation means" refers to AI technologies used to accurately translate input text or audio data into other languages in real time.
[0441] The "means for symptom analysis" is a method for extracting specific symptoms from the translated input information and identifying the type of health problem the user is experiencing.
[0442] The "means for searching for the most suitable medical institution based on the current location and time zone" is a method for searching for the nearest and most suitable medical institution for the user using the user's location information and the current time.
[0443] "Means of arranging transportation in cooperation with a ride-hailing service" refers to a method of coordinating with a ride-hailing service provider to arrange transportation to a medical institution.
[0444] "A means for delivery workers to input their symptoms when they feel unwell, search for the most appropriate medical institution, and arrange for a ride-hailing service" refers to a method for food delivery workers who feel unwell while on the job to quickly report their symptoms, find the most appropriate medical institution, and arrange for the necessary transportation.
[0445] The system embodying this invention provides a method for quickly accessing the most appropriate medical institution when a user feels unwell, while also incorporating a function to support health management, particularly for food delivery personnel.
[0446] The main components of the system include a means for users to input symptoms, a translation means using generative AI, a symptom analysis means, a medical institution search means, and a means for linking with vehicle dispatch services. The specific configuration and processing flow for realizing these means are described below.
[0447] Main Components and Processing Flow
[0448] 1. User symptom input method:
[0449] Users report their symptoms by typing or speaking using a smartphone or other mobile device. First, users enter their symptoms and complaints into the application.
[0450] 2. Generative AI translation methods:
[0451] The inputted symptoms are sent to a server where they are translated in real time by a generative artificial intelligence (NLP model), which uses common language processing tools such as Google Translate API and Azure Cognitive Services.
[0452] 3. Symptom analysis means:
[0453] The translated text is then analyzed to extract specific symptoms. This analysis process involves detecting keywords that correspond to the symptoms (e.g., chest pain, dizziness).
[0454] 4. Medical institution search methods:
[0455] The server searches for the most suitable medical institution based on the user's current location (obtained by the GPS function) and the current time. This information is obtained by the server by referring to the medical institution database.
[0456] 5. Ride-hailing service integration methods:
[0457] If necessary, the server will use a ride-hailing service (e.g., Uber or Lyft API) to arrange transportation for the user to the designated medical facility.
[0458] Hardware and software used
[0459] Smartphone: The primary device for users to enter symptoms.
[0460] GPS function: Used to obtain current location.
[0461] Generative artificial intelligence (NLP models): Used to translate and analyze input text. Examples include Google Translate API and Azure Cognitive Services.
[0462] Server: The central component that processes data and searches for medical institutions.
[0463] Ride-hailing service API: Used to arrange transportation for users.
[0464] Examples of concrete examples and prompts
[0465] As a concrete example, consider the case where a food delivery person suddenly experiences dizziness while on a delivery and voice-inputs into the app, "I'm feeling very dizzy." The app sends this information to a server and analyzes it using generative artificial intelligence. The server then searches for the nearest open clinic and arranges for a ride-hailing service if necessary.
[0466] Example prompt sentence:
[0467] "I feel extremely dizzy, please find the nearest medical facility."
[0468] This system allows delivery personnel to quickly and accurately access appropriate medical facilities and be provided with the necessary transportation if they feel unwell.
[0469] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[0470] Step 1:
[0471] The user opens the smartphone application and reports their symptoms by text or voice input. Input here includes symptoms such as "I feel very dizzy." The device sends this information to the server. The input for this step is the user's symptom description, and the output is the symptom data sent to the server.
[0472] Step 2:
[0473] The server passes the symptom data sent by the user to a generative AI. The generative AI (NLP model) translates this information in real time and extracts symptom keywords as needed. The input is the symptom data from the user, and the output is a list of translated and analyzed symptom keywords.
[0474] Step 3:
[0475] The server identifies specific symptoms from the translated and analyzed symptom keyword list. For example, if the keyword "dizziness" is detected, it searches for appropriate medical institutions based on this symptom. The input of this step is the translated and analyzed keyword list, and the output is a symptom-based medical institution search query.
[0476] Step 4:
[0477] The server obtains the user's current location and the current time using the GPS function and the system clock. The input is the user's location information and the current time, and the output is search conditions based on the location and time.
[0478] Step 5:
[0479] The server searches for the most suitable medical institution from the medical institution database using the acquired current location, time, and keywords based on the symptoms. At this time, the server generates a list of medical institutions that meet the specified conditions. The input is the search conditions, and the output is a list of medical institutions that meet the conditions.
[0480] Step 6:
[0481] The server arranges a ride-hailing service as needed. For example, if a delivery person does not have their own means of transportation, it arranges for a ride-hailing service API. The input is the user's current location and the location of the medical institution, and the output is a ride-hailing service reservation confirmation.
[0482] Step 7:
[0483] The server notifies the delivery person of the information on the most suitable medical institution and details of the vehicle dispatch service. The notification is sent via a smartphone application. The input of this step is the searched medical institution and details of the vehicle dispatch service, and the output is a notification to the user.
[0484] In this way, the data entered at each processing step is appropriately processed and calculated, and the final output supports the user in quickly accessing an appropriate medical institution.
[0485] 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.
[0486] This invention is a system that supports users in quickly accessing appropriate medical institutions in situations requiring emergency medical care. The system uses generative artificial intelligence to translate and analyze symptoms entered by the user, searches for the most appropriate medical institution based on the results, and arranges for a vehicle dispatch service if necessary. Furthermore, an emotion engine that recognizes the user's emotions has been added, providing appropriate responses based on the user's emotions.
[0487] The system starts by having the user select the input method (text input or voice input) and communication language. When the user inputs their symptoms by text or voice, the information is sent to the server via the terminal. For example, consider the case where a user inputs the symptom "I have chest pain and can't breathe."
[0488] The server then uses generative artificial intelligence to translate this input in real time. Even if the user types in a language other than Japanese, the AI translation converts it into accurate Japanese or other standard languages. The server then analyzes this translated text to identify symptoms, specifically extracting keywords such as "chest pain" and "shortness of breath."
[0489] The server then uses an emotion engine to recognize emotions from the user's input. For example, it can determine whether the user is feeling anxious or confused from their voice tone or input text. Once the emotion engine identifies the user's emotion, that information is reflected in the system's overall response. The emotion engine analyzes the user's stress level and urgency, and adjusts the priority of medical facility searches and the speed of vehicle dispatch accordingly.
[0490] Next, the server obtains the user's current location and time zone. Location information is obtained using the user's device's GPS function, and time zone information is obtained by referencing the system time. Based on this information and the user's symptoms, the server searches the medical institution database for the most suitable emergency medical institution. The search results may include hospitals and clinics that are currently open.
[0491] If necessary, the server coordinates with a vehicle dispatch service to arrange transportation from the user's current location to a medical facility. For example, if the user does not have a car, the server calls a vehicle dispatch service to assist the user in emergency transportation.
[0492] Finally, after receiving medical treatment, the user provides feedback through the terminal. The server collects this feedback, stores it in a database, and uses it to improve the accuracy and quality of the service of the entire system.
[0493] As a specific example, a user experiences sudden chest pain while on a business trip and voice-types "My chest hurts" into the app. This information is sent to the server, where it is translated and analyzed in real time using generative artificial intelligence. Furthermore, the emotion engine recognizes the user's anxious tone and determines the level of urgency. The server obtains the user's current location and searches for the nearest hospital that is open even at night. If the user does not have transportation, the server arranges for a ride-hailing service, helping the user quickly receive appropriate treatment at a hospital. In this way, the present invention enables users to access medical institutions quickly and appropriately, regardless of their location. Furthermore, the introduction of the emotion engine enables more personalized care, increasing user satisfaction and peace of mind.
[0494] The processing flow will be explained below.
[0495] Step 1:
[0496] The user inputs symptoms into the terminal. Input methods can be selected from text input and voice input. The communication language can also be selected. For example, consider the case where the user inputs "I have chest pain and can't breathe" by voice input.
[0497] Step 2:
[0498] The device sends the user's input information to the server. In the case of voice input, the device converts the voice into text before sending it to the server.
[0499] Step 3:
[0500] The server uses generative artificial intelligence to translate information entered by users in real time. For example, even if the information is entered in a language other than Japanese, it will be translated into a standard language using AI.
[0501] Step 4:
[0502] The server analyzes the translated text and extracts specific symptoms, such as keywords like "chest pain" or "shortness of breath."
[0503] Step 5:
[0504] The server uses an emotion engine to recognize emotions from the user's input, determining whether the user is feeling anxious or confused based on the tone of voice and the text entered.
[0505] Step 6:
[0506] The server then suggests appropriate responses to the user based on the emotions recognized by the emotion engine. For example, if anxiety is judged to be high, a more immediate response will be prioritized.
[0507] Step 7:
[0508] The server obtains the current location from the user's device, using the device's GPS function to obtain latitude and longitude information.
[0509] Step 8:
[0510] The server obtains the current time and uses this information to prepare data to identify medical institutions that are open at the time of the user's visit.
[0511] Step 9:
[0512] The server searches the medical institution database for the most suitable medical institution based on the patient's current location, time zone, and analyzed symptoms. As a result, for example, a nearby 24-hour emergency hospital may be identified.
[0513] Step 10:
[0514] The server checks whether the user has a means of transportation. If it determines that the user does not have a means of transportation based on the report from the user terminal, it proceeds to the next step.
[0515] Step 11:
[0516] The server cooperates with the vehicle dispatch service to arrange appropriate transportation, for example, calling the vehicle dispatch service and arranging for a prompt transportation of the user from the current location to the identified medical institution.
[0517] Step 12:
[0518] After receiving medical treatment at a medical institution, the user provides feedback through the terminal. For example, the user can input a comment such as "The hospital's response was quick."
[0519] Step 13:
[0520] The server collects the feedback and stores it in a database, which provides data to improve the accuracy and quality of service of the entire system.
[0521] Example 2
[0522] 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."
[0523] In modern society, when emergency medical assistance is needed, it is important to access appropriate medical institutions quickly and accurately. However, users often have difficulty accurately describing their symptoms and are unable to easily find appropriate medical institutions. In addition, there is a lack of personalized care that takes into account the user's feelings and the level of urgency, which leads to issues of insufficient satisfaction and peace of mind.
[0524] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.
[0525] In this invention, the server includes a translation means using generative artificial intelligence to translate user input, a means for analyzing the translated symptoms, an emotion recognition means using an emotion engine to recognize emotions from the user input, a means for searching for the most suitable medical institution based on the current location and time zone, a means for arranging transportation in cooperation with a ride-hailing service, and a means for collecting feedback after the medical treatment and storing it in a database. This allows the user to access a medical institution quickly and accurately no matter where they are, and further enables individualized treatment based on the user's emotions and urgency, thereby increasing satisfaction and peace of mind.
[0526] "User" refers to a person who uses this system to input symptoms and search for an appropriate medical institution.
[0527] "Input method" refers to the means by which a user communicates symptoms to the system by text input or voice input.
[0528] "Communication language" refers to the language used by the user to interact with the system.
[0529] "Generative AI" refers to artificial intelligence technology used to translate user input in real time and convert it into the appropriate language.
[0530] "Translation means" refers to a means for translating information entered by a user into another language using generative artificial intelligence.
[0531] "Means for analyzing symptoms" refers to means for analyzing the translated symptom information and identifying specific medical symptoms.
[0532] "Emotion recognition means" refers to a means for recognizing emotions from user input information or voice using an emotion engine.
[0533] "Emotion engine" refers to technology that analyzes emotions from user input and vocal tone to identify emotional states.
[0534] "Current location" refers to the user's location information identified using the GPS function of the user's device, etc.
[0535] "Time zone information" refers to information about the current time obtained by referring to the system time.
[0536] The "means for searching for a medical institution" refers to a means for searching a database for the most suitable medical institution based on the user's location information and symptoms.
[0537] "Vehicle dispatch service" refers to a transportation arrangement service used by users to quickly arrive at medical institutions.
[0538] "Means for arranging transportation" refers to a means of arranging transportation to and from a medical institution in cooperation with a vehicle dispatch service.
[0539] "Feedback" refers to the opinions and evaluations that users provide to the system after receiving medical treatment.
[0540] "Means for storing in a database" refers to the means for storing the collected feedback in a database and utilizing it to improve the accuracy of the system and the quality of the service.
[0541] This invention is a system that supports users in quickly accessing appropriate medical institutions in situations requiring emergency medical care. The system uses generative artificial intelligence to translate and analyze symptoms entered by the user, searches for the most appropriate medical institution based on the results, and arranges for a vehicle dispatch service if necessary. Furthermore, an emotion engine that recognizes the user's emotions has been added, providing appropriate responses based on the user's emotions.
[0542] The system starts by having the user select the input method (text input or voice input) and communication language. When the user inputs their symptoms by text or voice, the information is sent to the server via the terminal. For example, consider the case where a user inputs the symptom "I have chest pain and can't breathe."
[0543] The server then uses generative artificial intelligence (e.g., Google Cloud Translation API) to translate this input in real time. Even if the user types in a language other than Japanese, the AI translation converts it into accurate Japanese or other standard languages. The server then analyzes this translated text to identify symptoms, specifically extracting keywords such as "chest pain" and "shortness of breath."
[0544] The server then uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize emotions from the user's input. For example, it can determine whether the user is feeling anxious or confused from the tone of their voice or the text they enter. Once the emotion engine identifies the user's emotion, that information is reflected in the system's overall response. The emotion engine analyzes the user's stress level and urgency, and adjusts the priority of medical facility searches and the speed of vehicle dispatch based on that information.
[0545] Next, the server obtains the user's current location and time zone. Location information is obtained using the user's device's GPS function, and time zone information is obtained by referencing the system time. Based on this information and the user's symptoms, the server searches for the most suitable emergency medical institution from a medical institution database (e.g., a MySQL database). The search results may include hospitals and clinics that are currently open.
[0546] If necessary, the server will coordinate with a ride-hailing service (e.g., Uber API) to arrange transportation from the user's current location to a medical facility. For example, if the user does not have a car, the server will call a ride-hailing service to assist the user in emergency transportation.
[0547] Finally, after receiving medical treatment, the user provides feedback through the terminal. The server collects this feedback, stores it in a database, and uses it to improve the accuracy and quality of the service of the entire system.
[0548] Examples:
[0549] A user experiences sudden chest pain while on a business trip and voice-types "I have chest pain" into the app. This information is sent from the device to the server, where it is translated and analyzed in real time using generative artificial intelligence (e.g., Google Cloud Translation API). Furthermore, an emotion engine (e.g., IBM Watson Tone Analyzer) recognizes the user's anxious tone and determines the level of urgency. The server obtains the user's current location and searches for the nearest hospital that is open even at night.
[0550] If the user does not have transportation, the server will arrange for a ride-hailing service (e.g., Uber API) to help the user quickly receive appropriate treatment at a hospital. In this way, users can access medical institutions quickly and appropriately, no matter where they are. In addition, the introduction of an emotion engine enables more personalized responses, increasing user satisfaction and a sense of security.
[0551] Example prompt sentence:
[0552] "A user utters 'I have chest pain' into the app. Send this information to the server, translate it in real time, and analyze the symptoms. Also, recognize the user's emotion (anxious tone) and explain the steps to find a medical facility and arrange transportation."
[0553] The flow of the identification process in the second embodiment will be described with reference to FIG.
[0554] Step 1:
[0555] The user enters the symptoms into the terminal.
[0556] Specifically, the user starts the application, selects text input or voice input, enters the symptoms, and presses the send button.
[0557] Input: Symptom information entered by the user into the device (e.g., "I have chest pain").
[0558] Output: Symptom information sent from the device to the server.
[0559] Step 2:
[0560] The terminal sends the input information to the server.
[0561] Specifically, the device transmits the symptom information entered by the user to the server in real time, as well as the input method and communication language selected by the user.
[0562] Input: Symptom information entered into the terminal.
[0563] Output: Symptom information, input method, and language information sent to the server.
[0564] Step 3:
[0565] The server uses the generated AI model to translate and analyze.
[0566] Specifically, the server translates user input in real time using a generative AI model (e.g., Google Cloud Translation API), then analyzes the translated text to extract keywords related to the symptoms.
[0567] Input: Symptom information, input method, and language information sent to the server.
[0568] Output: Translated symptom information and extracted keywords (e.g., "chest pain," "shortness of breath").
[0569] Step 4:
[0570] The server uses an emotion engine to recognize the user's emotion.
[0571] Specifically, the server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize emotions from the user's input, determining the user's anxiety or confusion from the voice tone and text, and assessing the level of urgency.
[0572] Input: Translated symptom information and extracted keywords.
[0573] Output: User's emotional state (e.g., anxiety, urgency rating).
[0574] Step 5:
[0575] The server obtains the user's current location and time zone information.
[0576] Specifically, the server uses the device's GPS function to obtain the user's current location and also references the system time to obtain the current time zone information.
[0577] Input: Location information obtained from the user's device and system time.
[0578] Output: User's current location and time zone information.
[0579] Step 6:
[0580] The server searches for the most suitable medical institution from the medical institution database.
[0581] Specifically, the server uses a MySQL database to search for the most suitable medical facility based on the user's location and symptoms, for example, listing hospitals that are open at night.
[0582] Input: User's current location, time zone information, and keywords related to the symptom.
[0583] Output: A list of the best medical institutions.
[0584] Step 7:
[0585] The server will arrange a ride-hailing service if necessary.
[0586] Specifically, if the user does not have a car, the server calls a ride-hailing service (e.g., Uber API) and arranges transportation from the user's current location to the medical facility.
[0587] Input: User's current location and information about the destination medical institution.
[0588] Output: Arrange a ride.
[0589] Step 8:
[0590] The user provides feedback via the terminal after the treatment.
[0591] Specifically, after receiving medical treatment, the user restarts the application on the terminal, inputs and sends their evaluation and opinions of the treatment.
[0592] Input: User's ratings and opinions after treatment.
[0593] Output: Feedback sent from the device to the server.
[0594] Step 9:
[0595] The server collects the feedback and stores it in a database.
[0596] Specifically, the server collects the feedback provided by users and stores it in a MySQL database, which is used to improve the accuracy and quality of the service of the entire system.
[0597] Input: Feedback sent from the device.
[0598] Output: Feedback information stored in a database.
[0599] (Application example 2)
[0600] 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."
[0601] Conventional emergency response systems have had problems in providing a fast and appropriate response when users face an emergency. In particular, it is difficult to communicate in multiple languages and analyze users' emotions, making it difficult to select the appropriate emergency agency and quickly arrange for vehicle dispatch. In addition, there is a lack of a mechanism for collecting user feedback and reflecting it in the service.
[0602] 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.
[0603] In this invention, the server includes: a means for selecting a user's input method and communication language and inputting symptoms and conditions; a translation means using generative artificial intelligence to translate the user's input; a means for analyzing the translated symptoms and conditions; a means for searching for the most appropriate response agency based on the user's current location and time of day; a means for arranging transportation in cooperation with a ride-hailing service; a means for analyzing the user's emotions using an emotion engine to determine the urgency of the emergency response and an appropriate response; a means for collecting feedback and using it to improve the service; and a means for providing a response based on the emotion engine. This allows information provided by users in multiple languages to be analyzed quickly and accurately, and an appropriate response to be provided based on the user's emotions. Furthermore, collecting and incorporating feedback allows for continuous improvement of the system.
[0604] A "user input method" is the means a user uses to provide information to a system, such as speech input or text input.
[0605] "Communication language" refers to the language used by the user to interact with the system, and includes, for example, Japanese, English, Chinese, etc.
[0606] "Symptoms and circumstances" are detailed information about the emergency that the user provides to the system, such as chest pain, shortness of breath, or the presence of a suspicious person.
[0607] "Generative AI" is an AI that has the ability to analyze input information and translate it into accurate language.
[0608] "Translation means" refers to a means for converting input information into another language using generative artificial intelligence.
[0609] "Analysis means" refers to the extraction of keywords and context from translated information, and the use of this information to determine the level of urgency and appropriate countermeasures.
[0610] "Current location" refers to the geographical information of the point where the user is accessing the system, and is obtained using technology such as GPS.
[0611] "Time zone" is information about the time when a user accesses the system, and refers to the system time.
[0612] A "response organization" is an organization or facility that responds appropriately to a user's emergency, and includes, for example, a hospital, a police station, a fire station, and the like.
[0613] A "vehicle dispatch service" is a service that arranges transportation from the user's current location to an emergency response organization.
[0614] An "emotion engine" is a program that recognizes emotions from the user's voice or text and adjusts the system's response based on the results.
[0615] "Feedback" refers to opinions and evaluation information provided by users after using the system, and is data that is useful for improving the system.
[0616] The present invention is a system for speeding up and optimizing emergency responses, supporting users in quickly accessing appropriate response organizations when faced with an emergency. This system includes a means for users to select an input method and communication language and input symptoms and circumstances, a translation means using generative artificial intelligence, a means for analyzing the translated symptoms and circumstances, a means for searching for the most appropriate response organization based on the current location and time of day, a means for arranging transportation in cooperation with a ride-hailing service, a means for analyzing user emotions using an emotion engine to determine the urgency, and a means for collecting feedback to help improve the service.
[0617] System configuration
[0618] 1. User Input Method
[0619] The user can provide the system with an emergency situation by voice or text input using a smartphone or smart glasses. For example, the user can input "someone is trying to enter my house."
[0620] 2. Translation Methods
[0621] The server uses generative artificial intelligence to translate user input in real time. For example, if a user types "help" in Japanese, it will translate this into English as "Help!"
[0622] 3. Analysis method
[0623] The translated text is then analyzed in conjunction with an emotion engine to assess the user's level of urgency and the necessary response. For example, an input such as "someone is trying to get into my house" could indicate a situation of high anxiety and urgency.
[0624] 4. Search Methods
[0625] The server searches for emergency response agencies (police, fire department, hospitals, etc.) based on the current location and time information, and uses location information services such as Google Maps API to present the most appropriate response agency.
[0626] 5. Vehicle dispatch method
[0627] If the user does not have transportation, the server will use an API such as Uber to arrange a ride, for example, a police car will be dispatched from the nearest police station to the user's location.
[0628] 6. Emotion analysis method
[0629] It uses an emotion engine to analyze the user's emotions and determine the level of urgency, determining whether the user is feeling anxious or scared based on their input and tone of voice.
[0630] 7. Feedback Collection Methods
[0631] After users use the system, feedback is collected and used to improve the system, which will be used to improve the accuracy of the next emergency response.
[0632] Specific examples
[0633] Imagine a case where a user hears a suspicious sound at home at night and voice-records, "There's someone in the house." This information is sent from the smartphone to a server, where it is translated and analyzed in real time using generative artificial intelligence. The emotion engine recognizes the user's anxiety and determines that the situation is urgent. The server obtains the user's current location, searches for the nearest police station, and dispatches a patrol car. At the same time, it provides the user with guidelines such as, "Stay in a safe place and don't go outside." The system then collects user feedback and uses it to improve future responses.
[0634] Prompt Sentence Examples
[0635] User: "Someone is trying to get into my house. Help!"
[0636] Generative AI: Translated into English: "Someone is trying to break into my house. Help!"
[0637] Emotion Engine Assessment: User exhibits extreme anxiety.
[0638] Optimal solution: Send location information to the police. Arrange for a patrol car.
[0639] Guidelines provided: "Please lock your room and secure it. Do not move until the police arrive."
[0640] As described above, this system allows users to receive prompt and reliable support even in emergency situations.
[0641] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[0642] Step 1:
[0643] The user selects the input method (voice or text) and communication language using a smartphone or smart glasses. The input symptom or situation (e.g., "There is someone in the house") is sent to the device's input interface.
[0644] Input: The user's chosen input method and language, spoken or written symptoms or conditions.
[0645] Output: Sends input information (audio data or text data) to the server.
[0646] Step 2:
[0647] The server uses generative artificial intelligence to translate input information sent from the device in real time. For example, if the voice input is in Japanese, it will translate it into English.
[0648] Input: Audio or text data from the user.
[0649] Output: The translated text data.
[0650] Step 3:
[0651] The server analyzes the translated text data to extract important keywords and context (e.g., "There is an intruder in my house") and uses an emotion engine to analyze the user's emotions (e.g., anxiety, fear).
[0652] Input: Translated text data.
[0653] Output: Extracted keywords, parsed sentiment data.
[0654] Step 4:
[0655] The server obtains the user's current location using the GPS function and also references the system time information. Based on this, it uses the Google Maps API to search for the most appropriate emergency response organization (e.g., the nearest police station).
[0656] Input: User's GPS location data, system time.
[0657] Output: A list of the best emergency response agencies.
[0658] Step 5:
[0659] Once the optimal facility has been determined, the server will connect with a ride-hailing service (e.g., Uber API) and arrange transportation from the user's current location to the facility if necessary.
[0660] Input: A list of the best emergency response agencies, the user's current location.
[0661] Output: Ride dispatch information.
[0662] Step 6:
[0663] The server responds to the user based on the emotional information analyzed by the emotion engine. For example, if a user feels anxious, the server provides specific guidelines such as "stay in a safe place and do not go outside."
[0664] Input: Emotion data, analysis results.
[0665] Output: A response message to the user.
[0666] Step 7:
[0667] After using the system, users provide feedback, which is sent to the server via their device and used to improve the accuracy of future emergency responses.
[0668] Input: Feedback data from users.
[0669] Output: Save feedback information and data to improve accuracy next time.
[0670] 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.
[0671] 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.
[0672] 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.
[0673] [Third embodiment]
[0674] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.
[0675] 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.
[0676] 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).
[0677] 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.
[0678] 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.
[0679] 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).
[0680] 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.
[0681] 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.
[0682] 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.
[0683] 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.
[0684] 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.
[0685] 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."
[0686] This invention is a system that supports users in quickly accessing appropriate medical institutions in situations where emergency medical care is required. The system uses generative artificial intelligence to translate and analyze symptoms entered by the user, searches for the most appropriate medical institution based on the results, and arranges for a vehicle dispatch service if necessary.
[0687] The system starts by having the user select the input method (text input or voice input) and communication language. When the user inputs their symptoms by text or voice, the information is sent to the server via the terminal. For example, consider the case where a user inputs the symptom "I have chest pain and can't breathe."
[0688] The server then uses generative artificial intelligence to translate this input in real time. Even if the user types in a language other than Japanese, the AI translation converts it into accurate Japanese or other standard languages. The server then analyzes this translated text to identify symptoms, specifically extracting keywords such as "chest pain" and "shortness of breath."
[0689] The server then obtains the user's current location and time zone. Location information is obtained using the user's device's GPS function, and time zone information is obtained by referencing the system time. Based on this information and the user's symptoms, the server searches the medical institution database for the most suitable emergency medical institution. The search results may include hospitals and clinics that are currently open.
[0690] If necessary, the server will coordinate with a ride-hailing service to arrange transportation from the user's current location to a medical facility. For example, if the user does not have a car, the server will call a ride-hailing service such as DiDi or Uber to assist with emergency transportation for the user.
[0691] Finally, after receiving medical treatment, users can provide feedback through their devices, which the server collects and stores in a database to improve the accuracy and quality of the overall system.
[0692] As a specific example, if a user experiences sudden chest pain while on a business trip, they can voice-input "I have chest pain" into the app. This information is sent to a server and analyzed using generative artificial intelligence. The server obtains the user's current location and searches for the nearest hospital that is open even at night. If the user does not have transportation, the server arranges for a ride-hailing service, helping the user to quickly receive appropriate treatment at a hospital. In this way, the present invention allows users to access medical institutions quickly and appropriately, no matter where they are.
[0693] The processing flow will be explained below.
[0694] Step 1:
[0695] The user inputs their symptoms into the device. They can choose to input text or voice, and also select the communication language. For example, the user can input "I have chest pain and can't breathe" by text input.
[0696] Step 2:
[0697] The device sends the user's input information to the server. In the case of voice input, the device converts the voice into text before sending it to the server.
[0698] Step 3:
[0699] The server uses generative artificial intelligence to translate information entered by users in real time. For example, even if the information is entered in a language other than Japanese, it will be translated into a standard language using AI.
[0700] Step 4:
[0701] The server analyzes the translated text and extracts specific symptoms, for example, identifying keywords such as "chest pain" and "shortness of breath" from the translated text "My chest hurts and I can't breathe."
[0702] Step 5:
[0703] The server obtains the current location from the user's device, using the device's GPS function to obtain latitude and longitude information.
[0704] Step 6:
[0705] The server obtains the current time and uses this information to prepare data to identify medical institutions that are open at the time of the user's visit.
[0706] Step 7:
[0707] The server searches the medical institution database for the most suitable medical institution based on the patient's current location, time zone, and analyzed symptoms. As a result, for example, a nearby 24-hour emergency hospital may be identified.
[0708] Step 8:
[0709] The server checks whether the user has a means of transportation based on the information provided by the user. If the device reports "no means of transportation," the server proceeds to the next step.
[0710] Step 9:
[0711] The server works in cooperation with the vehicle dispatch service to arrange appropriate transportation, for example, by calling a vehicle dispatch service such as DiDi or Uber and arranging for a prompt transportation from the user's current location to the specified medical institution.
[0712] Step 10:
[0713] After the consultation, the user provides feedback through the terminal, for example, by entering a comment such as "The hospital's response was quick."
[0714] Step 11:
[0715] The server collects the feedback data and stores it in a database, which accumulates data to improve the accuracy and quality of service of the entire system.
[0716] Example 1
[0717] 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."
[0718] Conventional emergency medical support systems make it difficult for users to accurately describe their symptoms and quickly find an appropriate medical institution. Furthermore, language barriers and a lack of transportation can significantly delay the time it takes to receive appropriate care in an emergency. This increases the risk to users' health.
[0719] 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.
[0720] In this invention, the server includes means for selecting a user's input method and communication language and inputting symptoms, means for translating the user's input using generative artificial intelligence, means for analyzing the translated symptoms, means for acquiring a current location and time zone, means for searching for an optimal medical facility based on the acquired current location and time zone, and means for arranging transportation in cooperation with a vehicle allocation service. This allows the user to quickly access an appropriate medical institution and, if necessary, arrange transportation, thereby reducing health risks in an emergency.
[0721] A "user" is an individual who uses the system to input symptoms and access appropriate medical care.
[0722] "Input method" refers to the means used by the user to communicate symptoms to the system, and includes text input and voice input.
[0723] The "communication language" is the language used by the user to communicate symptoms to the system, and is the target language for the system to translate.
[0724] "Generative AI" is an AI technology that translates and analyzes symptom information entered by users in real time.
[0725] "Translation" is a process that uses generative artificial intelligence to translate user-entered symptom information into another language.
[0726] The "analysis means" is the process of analyzing the symptom information translated by the generative artificial intelligence and extracting important keywords.
[0727] "Current location" is location information obtained through the GPS function of the user's device.
[0728] The "time zone" is the current time information obtained by referring to the system time.
[0729] "Medical facilities" are medical institutions such as hospitals and clinics that users need to access in an emergency.
[0730] A "vehicle deployment service" is a service that provides a means for quickly transporting users to medical facilities.
[0731] "Transportation" means the transportation required for a User to access a Medical Facility, and is provided by a vehicle deployment service.
[0732] This invention is a system that supports users who require emergency medical care by enabling them to quickly access appropriate medical institutions. The system uses generative artificial intelligence to translate and analyze symptoms input by the user, searches for the most suitable medical facility based on the acquired current location and time of day, and arranges for vehicle deployment services if necessary. Each component and its specific operation are explained below.
[0733] A user opens an application using a device such as a smartphone or tablet. The application provides a method for the user to input symptoms using text input or voice input. The user can also select the communication language to use. For example, consider the case where a user inputs "I have chest pain" by voice.
[0734] The entered information is sent from the device to the server. At this time, the device uses the HTTPS protocol to transfer data securely. Specifically, the user enters the information "I have chest pain," and the device encrypts it and sends it to the server.
[0735] The server inputs the received symptom information into a generative artificial intelligence (AI model). The generative AI translates and analyzes the information entered by the user in real time. For example, if a user enters "I have chest pain" in English, the AI model translates this into Japanese as "Chest pain." The server then analyzes the translated text and extracts keywords such as "chest pain" and "shortness of breath."
[0736] The server also obtains the user's current location and time zone by obtaining location information through the device's GPS function and referencing the system time to obtain time information. For example, the server may use GPS data sent from the device to determine the user's current location as Shibuya Ward, Tokyo.
[0737] Next, the server searches for the most suitable emergency medical facility from the medical facility database based on the user's location, time zone, and analyzed symptom information. For example, the server searches for hospitals that are open late at night and are located near Shibuya Ward, Tokyo.
[0738] If the user does not own a car and needs transportation, the server will arrange for a vehicle dispatch service. In this case, the server will use various APIs (Application Programming Interfaces) to connect with the vehicle dispatch service and arrange for transportation from the user's current location to the medical facility. Specifically, the server will request a vehicle dispatch from the user's current location (Shibuya-ku, Tokyo) to the hospital through the vehicle dispatch service's API.
[0739] After receiving medical treatment, users can provide feedback through their devices. Specifically, the application displays a survey-style question such as "Were you satisfied with the service?", and the user submits their answer. The server collects this feedback, stores it in a database, and uses it to improve the accuracy of the entire system and the quality of the service.
[0740] The above is a specific description of an embodiment of the present invention. Examples of prompt sentences are shown below. "I have chest pain" and "I have chest pain" are examples of prompt sentences. This system allows users to quickly access appropriate medical institutions and arranges transportation if necessary, thereby reducing health risks in emergencies.
[0741] The flow of the identification process in the first embodiment will be described with reference to FIG.
[0742] Step 1:
[0743] The user uses the device to launch the application and select the communication language and input method (text input or voice input). As input, the user types "I have chest pain" in text or voice input. This is the specific operation. The output is the user's input data.
[0744] Step 2:
[0745] The terminal sends the symptom data entered by the user to the server using the HTTPS protocol. The input is the user's symptom data (e.g., "My chest hurts"), and the output is the process of encrypting this data and sending it to the server. The terminal performs specific operations to securely transfer the symptom data.
[0746] Step 3:
[0747] The server uses a generative AI model to translate and analyze the received user symptom data in real time. The input is the user's symptom data (e.g., "I have chest pain"), and the output is the translated data and symptom keywords (e.g., "chest pain"). The server performs the specific operations of translating the English text into Japanese and extracting important keywords.
[0748] Step 4:
[0749] The server obtains the current location from the user's device using the GPS function and references the system time to obtain the current time zone. The input is the user's location data and system time, and the output is the current location (e.g., Shibuya-ku, Tokyo) and time information. The server performs the specific operations to obtain the GPS data and time information.
[0750] Step 5:
[0751] The server searches for the most suitable medical facility from the medical institution database based on the acquired current location, time zone, and analyzed symptom data. The input is the current location, time information, and symptom keywords, and the output is a list of the most suitable medical facilities. The server performs a specific operation of querying the database to identify the nearest medical facility that is open.
[0752] Step 6:
[0753] If the user does not have transportation, the server uses the API of the vehicle dispatch service to arrange transportation from the user's current location to the medical facility. The input is the user's current location and the location of the medical facility, and the output is reservation confirmation information for the vehicle dispatch service. The server sends an emergency vehicle dispatch request and performs specific operations to arrange the vehicle dispatch service.
[0754] Step 7:
[0755] After receiving medical treatment at a medical facility, the user provides feedback through a terminal. The input is the user's feedback (e.g., answer to the question, "Are you satisfied with this service?"), and the output is the transmission of the feedback data to the server. The terminal performs the specific operation of collecting the feedback data and sending it to the server. The server stores the feedback data in a database and uses it to improve the entire system.
[0756] (Application example 1)
[0757] 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."
[0758] In modern food delivery services, delivery workers are often exposed to harsh working conditions. In particular, if they feel unwell, they have limited access to appropriate medical facilities, which can pose serious health risks. Furthermore, language barriers and uncertain location information further complicate emergency response. There is a need to develop a system that can solve these problems and efficiently support the health management of delivery workers.
[0759] 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.
[0760] In this invention, the server includes means for selecting a user input method and communication language and inputting symptoms, translation means using generative artificial intelligence to translate the user's input, means for analyzing the translated symptoms, means for searching for the most appropriate medical institution based on the current location and time zone, means for arranging transportation in cooperation with a vehicle dispatch service, and means for inputting symptoms when a delivery person feels unwell, searching for the most appropriate medical institution, and arranging a vehicle dispatch service. This enables a delivery person to quickly and accurately access an appropriate medical institution when they feel unwell, and even arranges transportation if necessary.
[0761] "User input method" refers to the means by which a user reports a symptom to the system, including forms of text or voice input.
[0762] A "communication language" is a language used by a user and a system to exchange information, and provides multiple languages that a user can select.
[0763] "Generative AI translation means" refers to AI technologies used to accurately translate input text or audio data into other languages in real time.
[0764] The "means for symptom analysis" is a method for extracting specific symptoms from the translated input information and identifying the type of health problem the user is experiencing.
[0765] The "means for searching for the most suitable medical institution based on the current location and time zone" is a method for searching for the nearest and most suitable medical institution for the user using the user's location information and the current time.
[0766] "Means of arranging transportation in cooperation with a ride-hailing service" refers to a method of coordinating with a ride-hailing service provider to arrange transportation to a medical institution.
[0767] "A means for delivery workers to input their symptoms when they feel unwell, search for the most appropriate medical institution, and arrange for a ride-hailing service" refers to a method for food delivery workers who feel unwell while on the job to quickly report their symptoms, find the most appropriate medical institution, and arrange for the necessary transportation.
[0768] The system embodying this invention provides a method for quickly accessing the most appropriate medical institution when a user feels unwell, while also incorporating a function to support health management, particularly for food delivery personnel.
[0769] The main components of the system include a means for users to input symptoms, a translation means using generative AI, a symptom analysis means, a medical institution search means, and a means for linking with vehicle dispatch services. The specific configuration and processing flow for realizing these means are described below.
[0770] Main Components and Processing Flow
[0771] 1. User symptom input method:
[0772] Users report their symptoms by typing or speaking using a smartphone or other mobile device. First, users enter their symptoms and complaints into the application.
[0773] 2. Generative AI translation methods:
[0774] The inputted symptoms are sent to a server where they are translated in real time by a generative artificial intelligence (NLP model), which uses common language processing tools such as Google Translate API and Azure Cognitive Services.
[0775] 3. Symptom analysis means:
[0776] The translated text is then analyzed to extract specific symptoms. This analysis process involves detecting keywords that correspond to the symptoms (e.g., chest pain, dizziness).
[0777] 4. Medical institution search methods:
[0778] The server searches for the most suitable medical institution based on the user's current location (obtained by the GPS function) and the current time. This information is obtained by the server by referring to the medical institution database.
[0779] 5. Ride-hailing service integration methods:
[0780] If necessary, the server will use a ride-hailing service (e.g., Uber or Lyft API) to arrange transportation for the user to the designated medical facility.
[0781] Hardware and software used
[0782] Smartphone: The primary device for users to enter symptoms.
[0783] GPS function: Used to obtain current location.
[0784] Generative artificial intelligence (NLP models): Used to translate and analyze input text. Examples include Google Translate API and Azure Cognitive Services.
[0785] Server: The central component that processes data and searches for medical institutions.
[0786] Ride-hailing service API: Used to arrange transportation for users.
[0787] Examples of concrete examples and prompts
[0788] As a concrete example, consider the case where a food delivery person suddenly experiences dizziness while on a delivery and voice-inputs into the app, "I'm feeling very dizzy." The app sends this information to a server and analyzes it using generative artificial intelligence. The server then searches for the nearest open clinic and arranges for a ride-hailing service if necessary.
[0789] Example prompt sentence:
[0790] "I feel extremely dizzy, please find the nearest medical facility."
[0791] This system allows delivery personnel to quickly and accurately access appropriate medical facilities and be provided with the necessary transportation if they feel unwell.
[0792] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[0793] Step 1:
[0794] The user opens the smartphone application and reports their symptoms by text or voice input. Input here includes symptoms such as "I feel very dizzy." The device sends this information to the server. The input for this step is the user's symptom description, and the output is the symptom data sent to the server.
[0795] Step 2:
[0796] The server passes the symptom data sent by the user to a generative AI. The generative AI (NLP model) translates this information in real time and extracts symptom keywords as needed. The input is the symptom data from the user, and the output is a list of translated and analyzed symptom keywords.
[0797] Step 3:
[0798] The server identifies specific symptoms from the translated and analyzed symptom keyword list. For example, if the keyword "dizziness" is detected, it searches for appropriate medical institutions based on this symptom. The input of this step is the translated and analyzed keyword list, and the output is a symptom-based medical institution search query.
[0799] Step 4:
[0800] The server obtains the user's current location and the current time using the GPS function and the system clock. The input is the user's location information and the current time, and the output is search conditions based on the location and time.
[0801] Step 5:
[0802] The server searches for the most suitable medical institution from the medical institution database using the acquired current location, time, and keywords based on the symptoms. At this time, the server generates a list of medical institutions that meet the specified conditions. The input is the search conditions, and the output is a list of medical institutions that meet the conditions.
[0803] Step 6:
[0804] The server arranges a ride-hailing service as needed. For example, if a delivery person does not have their own means of transportation, it arranges for a ride-hailing service API. The input is the user's current location and the location of the medical institution, and the output is a ride-hailing service reservation confirmation.
[0805] Step 7:
[0806] The server notifies the delivery person of the information on the most suitable medical institution and details of the vehicle dispatch service. The notification is sent via a smartphone application. The input of this step is the searched medical institution and details of the vehicle dispatch service, and the output is a notification to the user.
[0807] In this way, the data entered at each processing step is appropriately processed and calculated, and the final output supports the user in quickly accessing an appropriate medical institution.
[0808] 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.
[0809] This invention is a system that supports users in quickly accessing appropriate medical institutions in situations requiring emergency medical care. The system uses generative artificial intelligence to translate and analyze symptoms entered by the user, searches for the most appropriate medical institution based on the results, and arranges for a vehicle dispatch service if necessary. Furthermore, an emotion engine that recognizes the user's emotions has been added, providing appropriate responses based on the user's emotions.
[0810] The system starts by having the user select the input method (text input or voice input) and communication language. When the user inputs their symptoms by text or voice, the information is sent to the server via the terminal. For example, consider the case where a user inputs the symptom "I have chest pain and can't breathe."
[0811] The server then uses generative artificial intelligence to translate this input in real time. Even if the user types in a language other than Japanese, the AI translation converts it into accurate Japanese or other standard languages. The server then analyzes this translated text to identify symptoms, specifically extracting keywords such as "chest pain" and "shortness of breath."
[0812] The server then uses an emotion engine to recognize emotions from the user's input. For example, it can determine whether the user is feeling anxious or confused from their voice tone or input text. Once the emotion engine identifies the user's emotion, that information is reflected in the system's overall response. The emotion engine analyzes the user's stress level and urgency, and adjusts the priority of medical facility searches and the speed of vehicle dispatch accordingly.
[0813] Next, the server obtains the user's current location and time zone. Location information is obtained using the user's device's GPS function, and time zone information is obtained by referencing the system time. Based on this information and the user's symptoms, the server searches the medical institution database for the most suitable emergency medical institution. The search results may include hospitals and clinics that are currently open.
[0814] If necessary, the server coordinates with a vehicle dispatch service to arrange transportation from the user's current location to a medical facility. For example, if the user does not have a car, the server calls a vehicle dispatch service to assist the user in emergency transportation.
[0815] Finally, after receiving medical treatment, the user provides feedback through the terminal. The server collects this feedback, stores it in a database, and uses it to improve the accuracy and quality of the service of the entire system.
[0816] As a specific example, a user experiences sudden chest pain while on a business trip and voice-types "My chest hurts" into the app. This information is sent to the server, where it is translated and analyzed in real time using generative artificial intelligence. Furthermore, the emotion engine recognizes the user's anxious tone and determines the level of urgency. The server obtains the user's current location and searches for the nearest hospital that is open even at night. If the user does not have transportation, the server arranges for a ride-hailing service, helping the user quickly receive appropriate treatment at a hospital. In this way, the present invention enables users to access medical institutions quickly and appropriately, regardless of their location. Furthermore, the introduction of the emotion engine enables more personalized care, increasing user satisfaction and peace of mind.
[0817] The processing flow will be explained below.
[0818] Step 1:
[0819] The user inputs symptoms into the terminal. Input methods can be selected from text input and voice input. The communication language can also be selected. For example, consider the case where the user inputs "I have chest pain and can't breathe" by voice input.
[0820] Step 2:
[0821] The device sends the user's input information to the server. In the case of voice input, the device converts the voice into text before sending it to the server.
[0822] Step 3:
[0823] The server uses generative artificial intelligence to translate information entered by users in real time. For example, even if the information is entered in a language other than Japanese, it will be translated into a standard language using AI.
[0824] Step 4:
[0825] The server analyzes the translated text and extracts specific symptoms, such as keywords like "chest pain" or "shortness of breath."
[0826] Step 5:
[0827] The server uses an emotion engine to recognize emotions from the user's input, determining whether the user is feeling anxious or confused based on the tone of voice and the text entered.
[0828] Step 6:
[0829] The server suggests appropriate responses to the user based on the emotions recognized by the emotion engine. For example, if anxiety is judged to be high, a faster response will be prioritized.
[0830] Step 7:
[0831] The server obtains the current location from the user's device, using the device's GPS function to obtain latitude and longitude information.
[0832] Step 8:
[0833] The server obtains the current time and uses this information to prepare data to identify medical institutions that are open at the time of the user's visit.
[0834] Step 9:
[0835] The server searches the medical institution database for the most suitable medical institution based on the patient's current location, time zone, and analyzed symptoms. As a result, for example, a nearby 24-hour emergency hospital may be identified.
[0836] Step 10:
[0837] The server checks whether the user has a means of transportation. If it determines that the user does not have a means of transportation based on the report from the user terminal, it proceeds to the next step.
[0838] Step 11:
[0839] The server cooperates with the vehicle dispatch service to arrange appropriate transportation, for example, calling the vehicle dispatch service and arranging for a prompt transportation of the user from the current location to the identified medical institution.
[0840] Step 12:
[0841] After receiving medical treatment at a medical institution, the user provides feedback through the terminal. For example, the user can input a comment such as "The hospital's response was quick."
[0842] Step 13:
[0843] The server collects the feedback and stores it in a database, which provides data to improve the accuracy and quality of service of the entire system.
[0844] Example 2
[0845] 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."
[0846] In modern society, when emergency medical assistance is needed, it is important to access appropriate medical institutions quickly and accurately. However, users often have difficulty accurately describing their symptoms and are unable to easily find appropriate medical institutions. In addition, there is a lack of personalized care that takes into account the user's feelings and the level of urgency, which leads to issues of insufficient satisfaction and peace of mind.
[0847] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.
[0848] In this invention, the server includes a translation means using generative artificial intelligence to translate user input, a means for analyzing the translated symptoms, an emotion recognition means using an emotion engine to recognize emotions from the user input, a means for searching for the most suitable medical institution based on the current location and time zone, a means for arranging transportation in cooperation with a ride-hailing service, and a means for collecting feedback after the medical treatment and storing it in a database. This allows the user to access a medical institution quickly and accurately no matter where they are, and further enables individualized treatment based on the user's emotions and urgency, thereby increasing satisfaction and peace of mind.
[0849] "User" refers to a person who uses this system to input symptoms and search for an appropriate medical institution.
[0850] "Input method" refers to the means by which a user communicates symptoms to the system by text input or voice input.
[0851] "Communication language" refers to the language used by the user to interact with the system.
[0852] "Generative AI" refers to artificial intelligence technology used to translate user input in real time and convert it into the appropriate language.
[0853] "Translation means" refers to a means for translating information entered by a user into another language using generative artificial intelligence.
[0854] "Means for analyzing symptoms" refers to means for analyzing the translated symptom information and identifying specific medical symptoms.
[0855] "Emotion recognition means" refers to a means for recognizing emotions from user input information or voice using an emotion engine.
[0856] "Emotion engine" refers to technology that analyzes emotions from user input and vocal tone to identify emotional states.
[0857] "Current location" refers to the user's location information identified using the GPS function of the user's device, etc.
[0858] "Time zone information" refers to information about the current time obtained by referring to the system time.
[0859] The "means for searching for a medical institution" refers to a means for searching a database for the most suitable medical institution based on the user's location information and symptoms.
[0860] "Vehicle dispatch service" refers to a transportation arrangement service used by users to quickly arrive at medical institutions.
[0861] "Means for arranging transportation" refers to a means of arranging transportation to and from a medical institution in cooperation with a vehicle dispatch service.
[0862] "Feedback" refers to the opinions and evaluations that users provide to the system after receiving medical treatment.
[0863] "Means for storing in a database" refers to the means for storing the collected feedback in a database and utilizing it to improve the accuracy of the system and the quality of the service.
[0864] This invention is a system that supports users in quickly accessing appropriate medical institutions in situations requiring emergency medical care. The system uses generative artificial intelligence to translate and analyze symptoms entered by the user, searches for the most appropriate medical institution based on the results, and arranges for a vehicle dispatch service if necessary. Furthermore, an emotion engine that recognizes the user's emotions has been added, providing appropriate responses based on the user's emotions.
[0865] The system starts by having the user select the input method (text input or voice input) and communication language. When the user inputs their symptoms by text or voice, the information is sent to the server via the terminal. For example, consider the case where a user inputs the symptom "I have chest pain and can't breathe."
[0866] The server then uses generative artificial intelligence (e.g., Google Cloud Translation API) to translate this input in real time. Even if the user types in a language other than Japanese, the AI translation converts it into accurate Japanese or other standard languages. The server then analyzes this translated text to identify symptoms, specifically extracting keywords such as "chest pain" and "shortness of breath."
[0867] The server then uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize emotions from the user's input. For example, it can determine whether the user is feeling anxious or confused from the tone of their voice or the text they enter. Once the emotion engine identifies the user's emotion, that information is reflected in the system's overall response. The emotion engine analyzes the user's stress level and urgency, and adjusts the priority of medical facility searches and the speed of vehicle dispatch based on that information.
[0868] Next, the server obtains the user's current location and time zone. Location information is obtained using the user's device's GPS function, and time zone information is obtained by referencing the system time. Based on this information and the user's symptoms, the server searches for the most suitable emergency medical institution from a medical institution database (e.g., a MySQL database). The search results may include hospitals and clinics that are currently open.
[0869] If necessary, the server will coordinate with a ride-hailing service (e.g., Uber API) to arrange transportation from the user's current location to a medical facility. For example, if the user does not have a car, the server will call a ride-hailing service to assist the user in emergency transportation.
[0870] Finally, after receiving medical treatment, the user provides feedback through the terminal. The server collects this feedback, stores it in a database, and uses it to improve the accuracy and quality of the service of the entire system.
[0871] Examples:
[0872] A user experiences sudden chest pain while on a business trip and voice-types "I have chest pain" into the app. This information is sent from the device to the server, where it is translated and analyzed in real time using generative artificial intelligence (e.g., Google Cloud Translation API). Furthermore, an emotion engine (e.g., IBM Watson Tone Analyzer) recognizes the user's anxious tone and determines the level of urgency. The server obtains the user's current location and searches for the nearest hospital that is open even at night.
[0873] If the user does not have transportation, the server will arrange for a ride-hailing service (e.g., Uber API) to help the user quickly receive appropriate treatment at a hospital. In this way, users can access medical institutions quickly and appropriately, no matter where they are. In addition, the introduction of an emotion engine enables more personalized responses, increasing user satisfaction and a sense of security.
[0874] Example prompt sentence:
[0875] "A user utters 'I have chest pain' into the app. Send this information to the server, translate it in real time, and analyze the symptoms. Also, recognize the user's emotion (anxious tone) and explain the steps to find a medical facility and arrange transportation."
[0876] The flow of the identification process in the second embodiment will be described with reference to FIG.
[0877] Step 1:
[0878] The user enters the symptoms into the terminal.
[0879] Specifically, the user starts the application, selects text input or voice input, enters the symptoms, and presses the send button.
[0880] Input: Symptom information entered by the user into the device (e.g., "I have chest pain").
[0881] Output: Symptom information sent from the device to the server.
[0882] Step 2:
[0883] The terminal sends the input information to the server.
[0884] Specifically, the device transmits the symptom information entered by the user to the server in real time, as well as the input method and communication language selected by the user.
[0885] Input: Symptom information entered into the terminal.
[0886] Output: Symptom information, input method, and language information sent to the server.
[0887] Step 3:
[0888] The server uses the generated AI model to translate and analyze.
[0889] Specifically, the server translates the user's input in real time using a generative AI model (e.g., Google Cloud Translation API), then analyzes the translated text to extract keywords related to the symptoms.
[0890] Input: Symptom information, input method, and language information sent to the server.
[0891] Output: Translated symptom information and extracted keywords (e.g., "chest pain," "shortness of breath").
[0892] Step 4:
[0893] The server uses an emotion engine to recognize the user's emotion.
[0894] Specifically, the server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize emotions from the user's input, determining the user's anxiety or confusion from the voice tone and text, and assessing the level of urgency.
[0895] Input: Translated symptom information and extracted keywords.
[0896] Output: User's emotional state (e.g., anxiety, urgency rating).
[0897] Step 5:
[0898] The server obtains the user's current location and time zone information.
[0899] Specifically, the server uses the device's GPS function to obtain the user's current location and also references the system time to obtain the current time zone information.
[0900] Input: Location information obtained from the user's device and system time.
[0901] Output: User's current location and time zone information.
[0902] Step 6:
[0903] The server searches for the most suitable medical institution from the medical institution database.
[0904] Specifically, the server uses a MySQL database to search for the most suitable medical facility based on the user's location and symptoms, for example, listing hospitals that are open at night.
[0905] Input: User's current location, time zone information, and keywords related to the symptom.
[0906] Output: A list of the best medical institutions.
[0907] Step 7:
[0908] The server will arrange a ride-hailing service if necessary.
[0909] Specifically, if the user does not have a car, the server calls a ride-hailing service (e.g., Uber API) and arranges transportation from the user's current location to the medical facility.
[0910] Input: User's current location and information about the destination medical institution.
[0911] Output: Arrange a ride.
[0912] Step 8:
[0913] The user provides feedback via the terminal after the treatment.
[0914] Specifically, after receiving medical treatment, the user restarts the application on the terminal, inputs and sends their evaluation and opinions of the treatment.
[0915] Input: User's ratings and opinions after treatment.
[0916] Output: Feedback sent from the device to the server.
[0917] Step 9:
[0918] The server collects the feedback and stores it in a database.
[0919] Specifically, the server collects the feedback provided by users and stores it in a MySQL database, which is used to improve the accuracy and quality of the service of the entire system.
[0920] Input: Feedback sent from the device.
[0921] Output: Feedback information stored in a database.
[0922] (Application example 2)
[0923] 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."
[0924] Conventional emergency response systems have had problems in providing a fast and appropriate response when users face an emergency. In particular, it is difficult to communicate in multiple languages and analyze users' emotions, making it difficult to select the appropriate emergency agency and quickly arrange for vehicle dispatch. In addition, there is a lack of a mechanism for collecting user feedback and reflecting it in the service.
[0925] 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.
[0926] In this invention, the server includes: a means for selecting a user's input method and communication language and inputting symptoms and conditions; a translation means using generative artificial intelligence to translate the user's input; a means for analyzing the translated symptoms and conditions; a means for searching for the most appropriate response agency based on the user's current location and time of day; a means for arranging transportation in cooperation with a ride-hailing service; a means for analyzing the user's emotions using an emotion engine to determine the urgency of the emergency response and an appropriate response; a means for collecting feedback and using it to improve the service; and a means for providing a response based on the emotion engine. This allows information provided by users in multiple languages to be analyzed quickly and accurately, and an appropriate response to be provided based on the user's emotions. Furthermore, collecting and incorporating feedback allows for continuous improvement of the system.
[0927] A "user input method" is the means a user uses to provide information to a system, such as speech input or text input.
[0928] "Communication language" refers to the language used by the user to interact with the system, and includes, for example, Japanese, English, Chinese, etc.
[0929] "Symptoms and circumstances" are detailed information about the emergency that the user provides to the system, such as chest pain, shortness of breath, or the presence of a suspicious person.
[0930] "Generative AI" is an AI that has the ability to analyze input information and translate it into accurate language.
[0931] "Translation means" refers to a means for converting input information into another language using generative artificial intelligence.
[0932] "Analysis means" refers to the extraction of keywords and context from translated information, and the use of this information to determine the level of urgency and appropriate countermeasures.
[0933] "Current location" refers to the geographical information of the point where the user is accessing the system, and is obtained using technology such as GPS.
[0934] "Time zone" is information about the time when a user accesses the system, and refers to the system time.
[0935] A "response organization" is an organization or facility that responds appropriately to a user's emergency, and includes, for example, a hospital, a police station, a fire station, and the like.
[0936] A "vehicle dispatch service" is a service that arranges transportation from the user's current location to an emergency response organization.
[0937] An "emotion engine" is a program that recognizes emotions from the user's voice or text and adjusts the system's response based on the results.
[0938] "Feedback" refers to opinions and evaluation information provided by users after using the system, and is data that is useful for improving the system.
[0939] The present invention is a system for speeding up and optimizing emergency responses, supporting users in quickly accessing appropriate response organizations when faced with an emergency. This system includes a means for users to select an input method and communication language and input symptoms and circumstances, a translation means using generative artificial intelligence, a means for analyzing the translated symptoms and circumstances, a means for searching for the most appropriate response organization based on the current location and time of day, a means for arranging transportation in cooperation with a ride-hailing service, a means for analyzing user emotions using an emotion engine to determine the urgency, and a means for collecting feedback to help improve the service.
[0940] System configuration
[0941] 1. User Input Method
[0942] The user can provide the system with an emergency situation by voice or text input using a smartphone or smart glasses. For example, the user can input "someone is trying to enter my house."
[0943] 2. Translation Methods
[0944] The server uses generative artificial intelligence to translate user input in real time. For example, if a user types "help" in Japanese, it will translate this into English as "Help!"
[0945] 3. Analysis method
[0946] The translated text is then analyzed in conjunction with an emotion engine to assess the user's level of urgency and the necessary response. For example, an input such as "someone is trying to get into my house" could indicate a situation of high anxiety and urgency.
[0947] 4. Search Methods
[0948] The server searches for emergency response agencies (police, fire department, hospitals, etc.) based on the current location and time information, and uses location information services such as Google Maps API to present the most appropriate response agency.
[0949] 5. Vehicle dispatch method
[0950] If the user does not have transportation, the server will use an API such as Uber to arrange a ride, for example, a police car will be dispatched from the nearest police station to the user's location.
[0951] 6. Emotion analysis method
[0952] It uses an emotion engine to analyze the user's emotions and determine the level of urgency, determining whether the user is feeling anxious or scared based on their input and tone of voice.
[0953] 7. Feedback Collection Methods
[0954] After users use the system, feedback is collected and used to improve the system, which will be used to improve the accuracy of the next emergency response.
[0955] Specific examples
[0956] Imagine a case where a user hears a suspicious sound at home at night and voice-records, "There's someone in the house." This information is sent from the smartphone to a server, where it is translated and analyzed in real time using generative artificial intelligence. The emotion engine recognizes the user's anxiety and determines that the situation is urgent. The server obtains the user's current location, searches for the nearest police station, and dispatches a patrol car. At the same time, it provides the user with guidelines such as, "Stay in a safe place and don't go outside." The system then collects user feedback and uses it to improve future responses.
[0957] Prompt Sentence Examples
[0958] User: "Someone is trying to get into my house. Help!"
[0959] Generative AI: Translated into English: "Someone is trying to break into my house. Help!"
[0960] Emotion Engine Assessment: User exhibits extreme anxiety.
[0961] Optimal solution: Send location information to the police. Arrange for a patrol car.
[0962] Guidelines provided: "Please lock your room and secure it. Do not move until the police arrive."
[0963] As described above, this system allows users to receive prompt and reliable support even in emergency situations.
[0964] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[0965] Step 1:
[0966] The user selects the input method (voice or text) and communication language using a smartphone or smart glasses. The input symptom or situation (e.g., "There is someone in the house") is sent to the device's input interface.
[0967] Input: The user's chosen input method and language, spoken or written symptoms or conditions.
[0968] Output: Sends input information (audio data or text data) to the server.
[0969] Step 2:
[0970] The server uses generative artificial intelligence to translate input information sent from the device in real time. For example, if the voice input is in Japanese, it will translate it into English.
[0971] Input: Audio or text data from the user.
[0972] Output: The translated text data.
[0973] Step 3:
[0974] The server analyzes the translated text data to extract important keywords and context (e.g., "There is an intruder in my house") and uses an emotion engine to analyze the user's emotions (e.g., anxiety, fear).
[0975] Input: Translated text data.
[0976] Output: Extracted keywords, parsed sentiment data.
[0977] Step 4:
[0978] The server obtains the user's current location using the GPS function and also references the system time information. Based on this, it uses the Google Maps API to search for the most appropriate emergency response organization (e.g., the nearest police station).
[0979] Input: User's GPS location data, system time.
[0980] Output: A list of the best emergency response agencies.
[0981] Step 5:
[0982] Once the optimal facility has been determined, the server will connect with a ride-hailing service (e.g., Uber API) and arrange transportation from the user's current location to the facility if necessary.
[0983] Input: A list of the best emergency response agencies, the user's current location.
[0984] Output: Ride dispatch information.
[0985] Step 6:
[0986] The server responds to the user based on the emotional information analyzed by the emotion engine. For example, if a user feels anxious, the server provides specific guidelines such as "stay in a safe place and do not go outside."
[0987] Input: Emotion data, analysis results.
[0988] Output: A response message to the user.
[0989] Step 7:
[0990] After using the system, users provide feedback, which is sent to the server via their device and used to improve the accuracy of future emergency responses.
[0991] Input: Feedback data from users.
[0992] Output: Save feedback information and data to improve accuracy next time.
[0993] 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.
[0994] 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.
[0995] 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.
[0996] [Fourth embodiment]
[0997] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.
[0998] 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.
[0999] 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).
[1000] 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.
[1001] 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.
[1002] 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).
[1003] 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.
[1004] 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.
[1005] 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.
[1006] 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.
[1007] 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.
[1008] 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.
[1009] 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."
[1010] This invention is a system that supports users in quickly accessing appropriate medical institutions in situations where emergency medical care is required. The system uses generative artificial intelligence to translate and analyze symptoms entered by the user, searches for the most appropriate medical institution based on the results, and arranges for a vehicle dispatch service if necessary.
[1011] The system starts by having the user select the input method (text input or voice input) and communication language. When the user inputs their symptoms by text or voice, the information is sent to the server via the terminal. For example, consider the case where a user inputs the symptom "I have chest pain and can't breathe."
[1012] The server then uses generative artificial intelligence to translate this input in real time. Even if the user types in a language other than Japanese, the AI translation converts it into accurate Japanese or other standard languages. The server then analyzes this translated text to identify symptoms, specifically extracting keywords such as "chest pain" and "shortness of breath."
[1013] The server then obtains the user's current location and time zone. Location information is obtained using the user's device's GPS function, and time zone information is obtained by referencing the system time. Based on this information and the user's symptoms, the server searches the medical institution database for the most suitable emergency medical institution. The search results may include hospitals and clinics that are currently open.
[1014] If necessary, the server will coordinate with a ride-hailing service to arrange transportation from the user's current location to a medical facility. For example, if the user does not have a car, the server will call a ride-hailing service such as DiDi or Uber to assist with emergency transportation for the user.
[1015] Finally, after receiving medical treatment, users can provide feedback through their devices, which the server collects and stores in a database to improve the accuracy and quality of the overall system.
[1016] As a specific example, if a user experiences sudden chest pain while on a business trip, they can voice-input "I have chest pain" into the app. This information is sent to a server and analyzed using generative artificial intelligence. The server obtains the user's current location and searches for the nearest hospital that is open even at night. If the user does not have transportation, the server arranges for a ride-hailing service, helping the user to quickly receive appropriate treatment at a hospital. In this way, the present invention allows users to access medical institutions quickly and appropriately, no matter where they are.
[1017] The processing flow will be explained below.
[1018] Step 1:
[1019] The user inputs their symptoms into the device. They can choose to input text or voice, and also select the communication language. For example, the user can input "I have chest pain and can't breathe" by text input.
[1020] Step 2:
[1021] The device sends the user's input information to the server. In the case of voice input, the device converts the voice into text before sending it to the server.
[1022] Step 3:
[1023] The server uses generative artificial intelligence to translate information entered by users in real time. For example, even if the information is entered in a language other than Japanese, it will be translated into a standard language using AI.
[1024] Step 4:
[1025] The server analyzes the translated text and extracts specific symptoms, for example, identifying keywords such as "chest pain" and "shortness of breath" from the translated text "My chest hurts and I can't breathe."
[1026] Step 5:
[1027] The server obtains the current location from the user's device, using the device's GPS function to obtain latitude and longitude information.
[1028] Step 6:
[1029] The server obtains the current time and uses this information to prepare data to identify medical institutions that are open at the time of the user's visit.
[1030] Step 7:
[1031] The server searches the medical institution database for the most suitable medical institution based on the patient's current location, time zone, and analyzed symptoms. As a result, for example, a nearby 24-hour emergency hospital may be identified.
[1032] Step 8:
[1033] The server checks whether the user has a means of transportation based on the information provided by the user. If the device reports "no means of transportation," the server proceeds to the next step.
[1034] Step 9:
[1035] The server works in cooperation with the vehicle dispatch service to arrange appropriate transportation, for example, by calling a vehicle dispatch service such as DiDi or Uber and arranging for a prompt transportation from the user's current location to the specified medical institution.
[1036] Step 10:
[1037] After the consultation, the user provides feedback through the terminal, for example, by entering a comment such as "The hospital's response was quick."
[1038] Step 11:
[1039] The server collects the feedback data and stores it in a database, which accumulates data to improve the accuracy and quality of service of the entire system.
[1040] Example 1
[1041] 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."
[1042] Conventional emergency medical support systems make it difficult for users to accurately describe their symptoms and quickly find an appropriate medical institution. Furthermore, language barriers and a lack of transportation can significantly delay the time it takes to receive appropriate care in an emergency. This increases the risk to users' health.
[1043] 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.
[1044] In this invention, the server includes means for selecting a user's input method and communication language and inputting symptoms, means for translating the user's input using generative artificial intelligence, means for analyzing the translated symptoms, means for acquiring a current location and time zone, means for searching for an optimal medical facility based on the acquired current location and time zone, and means for arranging transportation in cooperation with a vehicle allocation service. This allows the user to quickly access an appropriate medical institution and, if necessary, arrange transportation, thereby reducing health risks in an emergency.
[1045] A "user" is an individual who uses the system to input symptoms and access appropriate medical care.
[1046] "Input method" refers to the means used by the user to communicate symptoms to the system, and includes text input and voice input.
[1047] The "communication language" is the language used by the user to communicate symptoms to the system, and is the target language for the system to translate.
[1048] "Generative AI" is an AI technology that translates and analyzes symptom information entered by users in real time.
[1049] "Translation" is a process that uses generative artificial intelligence to translate user-entered symptom information into another language.
[1050] The "analysis means" is the process of analyzing the symptom information translated by the generative artificial intelligence and extracting important keywords.
[1051] "Current location" is location information obtained through the GPS function of the user's device.
[1052] The "time zone" is the current time information obtained by referring to the system time.
[1053] "Medical facilities" are medical institutions such as hospitals and clinics that users need to access in an emergency.
[1054] A "vehicle deployment service" is a service that provides a means for quickly transporting users to medical facilities.
[1055] "Transportation" means the transportation required for a User to access a Medical Facility, and is provided by a vehicle deployment service.
[1056] This invention is a system that supports users who require emergency medical care by enabling them to quickly access appropriate medical institutions. The system uses generative artificial intelligence to translate and analyze symptoms input by the user, searches for the most suitable medical facility based on the acquired current location and time of day, and arranges for vehicle deployment services if necessary. Each component and its specific operation are explained below.
[1057] A user opens an application using a device such as a smartphone or tablet. The application provides a method for the user to input symptoms using text input or voice input. The user can also select the communication language to use. For example, consider the case where a user inputs "I have chest pain" by voice.
[1058] The entered information is sent from the device to the server. At this time, the device uses the HTTPS protocol to transfer data securely. Specifically, the user enters the information "I have chest pain," and the device encrypts it and sends it to the server.
[1059] The server inputs the received symptom information into a generative artificial intelligence (AI model). The generative AI translates and analyzes the information entered by the user in real time. For example, if a user enters "I have chest pain" in English, the AI model translates this into Japanese as "Chest pain." The server then analyzes the translated text and extracts keywords such as "chest pain" and "shortness of breath."
[1060] The server also obtains the user's current location and time zone by obtaining location information through the device's GPS function and referencing the system time to obtain time information. For example, the server may use GPS data sent from the device to determine the user's current location as Shibuya Ward, Tokyo.
[1061] Next, the server searches for the most suitable emergency medical facility from the medical facility database based on the user's location, time zone, and analyzed symptom information. For example, the server searches for hospitals that are open late at night and are located near Shibuya Ward, Tokyo.
[1062] If the user does not own a car and needs transportation, the server will arrange for a vehicle dispatch service. In this case, the server will use various APIs (Application Programming Interfaces) to connect with the vehicle dispatch service and arrange for transportation from the user's current location to the medical facility. Specifically, the server will request a vehicle dispatch from the user's current location (Shibuya-ku, Tokyo) to the hospital through the vehicle dispatch service's API.
[1063] After receiving medical treatment, users can provide feedback through their devices. Specifically, the application displays a survey-style question such as "Were you satisfied with the service?", and the user submits their answer. The server collects this feedback, stores it in a database, and uses it to improve the accuracy of the entire system and the quality of the service.
[1064] The above is a specific description of an embodiment of the present invention. Examples of prompt sentences are shown below. "I have chest pain" and "I have chest pain" are examples of prompt sentences. This system allows users to quickly access appropriate medical institutions and arranges transportation if necessary, thereby reducing health risks in emergencies.
[1065] The flow of the identification process in the first embodiment will be described with reference to FIG.
[1066] Step 1:
[1067] The user uses the device to launch the application and select the communication language and input method (text input or voice input). As input, the user types "I have chest pain" in text or voice input. This is the specific operation. The output is the user's input data.
[1068] Step 2:
[1069] The terminal sends the symptom data entered by the user to the server using the HTTPS protocol. The input is the user's symptom data (e.g., "My chest hurts"), and the output is the process of encrypting this data and sending it to the server. The terminal performs specific operations to securely transfer the symptom data.
[1070] Step 3:
[1071] The server uses a generative AI model to translate and analyze the received user symptom data in real time. The input is the user's symptom data (e.g., "I have chest pain"), and the output is the translated data and symptom keywords (e.g., "chest pain"). The server performs the specific operations of translating the English text into Japanese and extracting important keywords.
[1072] Step 4:
[1073] The server obtains the current location from the user's device using the GPS function and references the system time to obtain the current time zone. The input is the user's location data and system time, and the output is the current location (e.g., Shibuya-ku, Tokyo) and time information. The server performs the specific operations to obtain the GPS data and time information.
[1074] Step 5:
[1075] The server searches for the most suitable medical facility from the medical institution database based on the acquired current location, time zone, and analyzed symptom data. The input is the current location, time information, and symptom keywords, and the output is a list of the most suitable medical facilities. The server performs a specific operation of querying the database to identify the nearest medical facility that is open.
[1076] Step 6:
[1077] If the user does not have transportation, the server uses the API of the vehicle dispatch service to arrange transportation from the user's current location to the medical facility. The input is the user's current location and the location of the medical facility, and the output is reservation confirmation information for the vehicle dispatch service. The server sends an emergency vehicle dispatch request and performs specific operations to arrange the vehicle dispatch service.
[1078] Step 7:
[1079] After receiving medical treatment at a medical facility, the user provides feedback through a terminal. The input is the user's feedback (e.g., answer to the question, "Are you satisfied with this service?"), and the output is the transmission of the feedback data to the server. The terminal performs the specific operation of collecting the feedback data and sending it to the server. The server stores the feedback data in a database and uses it to improve the entire system.
[1080] (Application example 1)
[1081] 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."
[1082] In modern food delivery services, delivery workers are often exposed to harsh working conditions. In particular, if they feel unwell, they have limited access to appropriate medical facilities, which can pose serious health risks. Furthermore, language barriers and uncertain location information further complicate emergency response. There is a need to develop a system that can solve these problems and efficiently support the health management of delivery workers.
[1083] 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.
[1084] In this invention, the server includes means for selecting a user input method and communication language and inputting symptoms, translation means using generative artificial intelligence to translate the user's input, means for analyzing the translated symptoms, means for searching for the most appropriate medical institution based on the current location and time zone, means for arranging transportation in cooperation with a vehicle dispatch service, and means for inputting symptoms when a delivery person feels unwell, searching for the most appropriate medical institution, and arranging a vehicle dispatch service. This enables a delivery person to quickly and accurately access an appropriate medical institution when they feel unwell, and even arranges transportation if necessary.
[1085] "User input method" refers to the means by which a user reports a symptom to the system, including forms of text or voice input.
[1086] A "communication language" is a language used by a user and a system to exchange information, and provides multiple languages that a user can select.
[1087] "Generative AI translation means" refers to AI technologies used to accurately translate input text or audio data into other languages in real time.
[1088] The "means for symptom analysis" is a method for extracting specific symptoms from the translated input information and identifying the type of health problem the user is experiencing.
[1089] The "means for searching for the most suitable medical institution based on the current location and time zone" is a method for searching for the nearest and most suitable medical institution for the user using the user's location information and the current time.
[1090] "Means of arranging transportation in cooperation with a ride-hailing service" refers to a method of coordinating with a ride-hailing service provider to arrange transportation to a medical institution.
[1091] "A means for delivery workers to input their symptoms when they feel unwell, search for the most appropriate medical institution, and arrange for a ride-hailing service" refers to a method for food delivery workers who feel unwell while on the job to quickly report their symptoms, find the most appropriate medical institution, and arrange for the necessary transportation.
[1092] The system embodying this invention provides a method for quickly accessing the most appropriate medical institution when a user feels unwell, while also incorporating a function to support health management, particularly for food delivery personnel.
[1093] The main components of the system include a means for users to input symptoms, a translation means using generative AI, a symptom analysis means, a medical institution search means, and a means for linking with vehicle dispatch services. The specific configuration and processing flow for realizing these means are described below.
[1094] Main Components and Processing Flow
[1095] 1. User symptom input method:
[1096] Users report their symptoms by typing or speaking using a smartphone or other mobile device. First, users enter their symptoms and complaints into the application.
[1097] 2. Generative AI translation methods:
[1098] The inputted symptoms are sent to a server where they are translated in real time by a generative artificial intelligence (NLP model), which uses common language processing tools such as Google Translate API and Azure Cognitive Services.
[1099] 3. Symptom analysis means:
[1100] The translated text is then analyzed to extract specific symptoms. This analysis process involves detecting keywords that correspond to the symptoms (e.g., chest pain, dizziness).
[1101] 4. Medical institution search methods:
[1102] The server searches for the most suitable medical institution based on the user's current location (obtained by the GPS function) and the current time. This information is obtained by the server by referring to the medical institution database.
[1103] 5. Ride-hailing service integration methods:
[1104] If necessary, the server will use a ride-hailing service (e.g., Uber or Lyft API) to arrange transportation for the user to the designated medical facility.
[1105] Hardware and software used
[1106] Smartphone: The primary device for users to enter symptoms.
[1107] GPS function: Used to obtain current location.
[1108] Generative artificial intelligence (NLP models): Used to translate and analyze input text. Examples include Google Translate API and Azure Cognitive Services.
[1109] Server: The central component that processes data and searches for medical institutions.
[1110] Ride-hailing service API: Used to arrange transportation for users.
[1111] Examples of concrete examples and prompts
[1112] As a concrete example, consider the case where a food delivery person suddenly experiences dizziness while on a delivery and voice-inputs into the app, "I'm feeling very dizzy." The app sends this information to a server and analyzes it using generative artificial intelligence. The server then searches for the nearest open clinic and arranges for a ride-hailing service if necessary.
[1113] Example prompt sentence:
[1114] "I feel extremely dizzy, please find the nearest medical facility."
[1115] This system allows delivery personnel to quickly and accurately access appropriate medical facilities and be provided with the necessary transportation if they feel unwell.
[1116] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[1117] Step 1:
[1118] The user opens the smartphone application and reports their symptoms by text or voice input. Input here includes symptoms such as "I feel very dizzy." The device sends this information to the server. The input for this step is the user's symptom description, and the output is the symptom data sent to the server.
[1119] Step 2:
[1120] The server passes the symptom data sent by the user to a generative AI. The generative AI (NLP model) translates this information in real time and extracts symptom keywords as needed. The input is the symptom data from the user, and the output is a list of translated and analyzed symptom keywords.
[1121] Step 3:
[1122] The server identifies specific symptoms from the translated and analyzed symptom keyword list. For example, if the keyword "dizziness" is detected, it searches for appropriate medical institutions based on this symptom. The input of this step is the translated and analyzed keyword list, and the output is a symptom-based medical institution search query.
[1123] Step 4:
[1124] The server obtains the user's current location and the current time using the GPS function and the system clock. The input is the user's location information and the current time, and the output is search conditions based on the location and time.
[1125] Step 5:
[1126] The server searches for the most suitable medical institution from the medical institution database using the acquired current location, time, and keywords based on the symptoms. At this time, the server generates a list of medical institutions that meet the specified conditions. The input is the search conditions, and the output is a list of medical institutions that meet the conditions.
[1127] Step 6:
[1128] The server arranges a ride-hailing service as needed. For example, if a delivery person does not have their own means of transportation, it arranges for a ride-hailing service API. The input is the user's current location and the location of the medical institution, and the output is a ride-hailing service reservation confirmation.
[1129] Step 7:
[1130] The server notifies the delivery person of the information on the most suitable medical institution and details of the vehicle dispatch service. The notification is sent via a smartphone application. The input of this step is the searched medical institution and details of the vehicle dispatch service, and the output is a notification to the user.
[1131] In this way, the data entered at each processing step is appropriately processed and calculated, and the final output supports the user in quickly accessing an appropriate medical institution.
[1132] 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.
[1133] This invention is a system that supports users in quickly accessing appropriate medical institutions in situations requiring emergency medical care. The system uses generative artificial intelligence to translate and analyze symptoms entered by the user, searches for the most appropriate medical institution based on the results, and arranges for a vehicle dispatch service if necessary. Furthermore, an emotion engine that recognizes the user's emotions has been added, providing appropriate responses based on the user's emotions.
[1134] The system starts by having the user select the input method (text input or voice input) and communication language. When the user inputs their symptoms by text or voice, the information is sent to the server via the terminal. For example, consider the case where a user inputs the symptom "I have chest pain and can't breathe."
[1135] The server then uses generative artificial intelligence to translate this input in real time. Even if the user types in a language other than Japanese, the AI translation converts it into accurate Japanese or other standard languages. The server then analyzes this translated text to identify symptoms, specifically extracting keywords such as "chest pain" and "shortness of breath."
[1136] The server then uses an emotion engine to recognize emotions from the user's input. For example, it can determine whether the user is feeling anxious or confused from their voice tone or input text. Once the emotion engine identifies the user's emotion, that information is reflected in the system's overall response. The emotion engine analyzes the user's stress level and urgency, and adjusts the priority of medical facility searches and the speed of vehicle dispatch accordingly.
[1137] Next, the server obtains the user's current location and time zone. Location information is obtained using the user's device's GPS function, and time zone information is obtained by referencing the system time. Based on this information and the user's symptoms, the server searches the medical institution database for the most suitable emergency medical institution. The search results may include hospitals and clinics that are currently open.
[1138] If necessary, the server coordinates with a vehicle dispatch service to arrange transportation from the user's current location to a medical facility. For example, if the user does not have a car, the server calls a vehicle dispatch service to assist the user in emergency transportation.
[1139] Finally, after receiving medical treatment, the user provides feedback through the terminal. The server collects this feedback, stores it in a database, and uses it to improve the accuracy and quality of the service of the entire system.
[1140] As a specific example, a user experiences sudden chest pain while on a business trip and voice-types "My chest hurts" into the app. This information is sent to the server, where it is translated and analyzed in real time using generative artificial intelligence. Furthermore, the emotion engine recognizes the user's anxious tone and determines the level of urgency. The server obtains the user's current location and searches for the nearest hospital that is open even at night. If the user does not have transportation, the server arranges for a ride-hailing service, helping the user quickly receive appropriate treatment at a hospital. In this way, the present invention enables users to access medical institutions quickly and appropriately, regardless of their location. Furthermore, the introduction of the emotion engine enables more personalized care, increasing user satisfaction and peace of mind.
[1141] The processing flow will be explained below.
[1142] Step 1:
[1143] The user inputs symptoms into the terminal. Input methods can be selected from text input and voice input. The communication language can also be selected. For example, consider the case where the user inputs "I have chest pain and can't breathe" by voice input.
[1144] Step 2:
[1145] The device sends the user's input information to the server. In the case of voice input, the device converts the voice into text before sending it to the server.
[1146] Step 3:
[1147] The server uses generative artificial intelligence to translate information entered by users in real time. For example, even if the information is entered in a language other than Japanese, it will be translated into a standard language using AI.
[1148] Step 4:
[1149] The server analyzes the translated text and extracts specific symptoms, such as keywords like "chest pain" or "shortness of breath."
[1150] Step 5:
[1151] The server uses an emotion engine to recognize emotions from the user's input, determining whether the user is feeling anxious or confused based on the tone of voice and the text entered.
[1152] Step 6:
[1153] The server suggests appropriate responses to the user based on the emotions recognized by the emotion engine. For example, if anxiety is judged to be high, a faster response will be prioritized.
[1154] Step 7:
[1155] The server obtains the current location from the user's device, using the device's GPS function to obtain latitude and longitude information.
[1156] Step 8:
[1157] The server obtains the current time and uses this information to prepare data to identify medical institutions that are open at the time of the user's visit.
[1158] Step 9:
[1159] The server searches the medical institution database for the most suitable medical institution based on the patient's current location, time zone, and analyzed symptoms. As a result, for example, a nearby 24-hour emergency hospital may be identified.
[1160] Step 10:
[1161] The server checks whether the user has a means of transportation. If it determines that the user does not have a means of transportation based on the report from the user terminal, it proceeds to the next step.
[1162] Step 11:
[1163] The server cooperates with the vehicle dispatch service to arrange appropriate transportation, for example, calling the vehicle dispatch service and arranging for a prompt transportation of the user from the current location to the identified medical institution.
[1164] Step 12:
[1165] After receiving medical treatment at a medical institution, the user provides feedback through the terminal. For example, the user can input a comment such as "The hospital's response was quick."
[1166] Step 13:
[1167] The server collects the feedback and stores it in a database, which provides data to improve the accuracy and quality of service of the entire system.
[1168] Example 2
[1169] 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."
[1170] In modern society, when emergency medical assistance is needed, it is important to access appropriate medical institutions quickly and accurately. However, users often have difficulty accurately describing their symptoms and are unable to easily find appropriate medical institutions. In addition, there is a lack of personalized care that takes into account the user's feelings and the level of urgency, which leads to issues of insufficient satisfaction and peace of mind.
[1171] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.
[1172] In this invention, the server includes a translation means using generative artificial intelligence to translate user input, a means for analyzing the translated symptoms, an emotion recognition means using an emotion engine to recognize emotions from the user input, a means for searching for the most suitable medical institution based on the current location and time zone, a means for arranging transportation in cooperation with a ride-hailing service, and a means for collecting feedback after the medical treatment and storing it in a database. This allows the user to access a medical institution quickly and accurately no matter where they are, and further enables individualized treatment based on the user's emotions and urgency, thereby increasing satisfaction and peace of mind.
[1173] "User" refers to a person who uses this system to input symptoms and search for an appropriate medical institution.
[1174] "Input method" refers to the means by which a user communicates symptoms to the system by text input or voice input.
[1175] "Communication language" refers to the language used by the user to interact with the system.
[1176] "Generative AI" refers to artificial intelligence technology used to translate user input in real time and convert it into the appropriate language.
[1177] "Translation means" refers to a means for translating information entered by a user into another language using generative artificial intelligence.
[1178] "Means for analyzing symptoms" refers to means for analyzing the translated symptom information and identifying specific medical symptoms.
[1179] "Emotion recognition means" refers to a means for recognizing emotions from user input information or voice using an emotion engine.
[1180] "Emotion engine" refers to technology that analyzes emotions from user input and vocal tone to identify emotional states.
[1181] "Current location" refers to the user's location information identified using the GPS function of the user's device, etc.
[1182] "Time zone information" refers to information about the current time obtained by referring to the system time.
[1183] The "means for searching for a medical institution" refers to a means for searching a database for the most suitable medical institution based on the user's location information and symptoms.
[1184] "Vehicle dispatch service" refers to a transportation arrangement service used by users to quickly arrive at medical institutions.
[1185] "Means for arranging transportation" refers to a means of arranging transportation to and from a medical institution in cooperation with a vehicle dispatch service.
[1186] "Feedback" refers to the opinions and evaluations that users provide to the system after receiving medical treatment.
[1187] "Means for storing in a database" refers to the means for storing the collected feedback in a database and utilizing it to improve the accuracy of the system and the quality of the service.
[1188] This invention is a system that supports users in quickly accessing appropriate medical institutions in situations requiring emergency medical care. The system uses generative artificial intelligence to translate and analyze symptoms entered by the user, searches for the most appropriate medical institution based on the results, and arranges for a vehicle dispatch service if necessary. Furthermore, an emotion engine that recognizes the user's emotions has been added, providing appropriate responses based on the user's emotions.
[1189] The system starts by having the user select the input method (text input or voice input) and communication language. When the user inputs their symptoms by text or voice, the information is sent to the server via the terminal. For example, consider the case where a user inputs the symptom "I have chest pain and can't breathe."
[1190] The server then uses generative artificial intelligence (e.g., Google Cloud Translation API) to translate this input in real time. Even if the user types in a language other than Japanese, the AI translation converts it into accurate Japanese or other standard languages. The server then analyzes this translated text to identify symptoms, specifically extracting keywords such as "chest pain" and "shortness of breath."
[1191] The server then uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize emotions from the user's input. For example, it can determine whether the user is feeling anxious or confused from the tone of their voice or the text they enter. Once the emotion engine identifies the user's emotion, that information is reflected in the system's overall response. The emotion engine analyzes the user's stress level and urgency, and adjusts the priority of medical facility searches and the speed of vehicle dispatch based on that information.
[1192] Next, the server obtains the user's current location and time zone. Location information is obtained using the user's device's GPS function, and time zone information is obtained by referencing the system time. Based on this information and the user's symptoms, the server searches for the most suitable emergency medical institution from a medical institution database (e.g., a MySQL database). The search results may include hospitals and clinics that are currently open.
[1193] If necessary, the server will coordinate with a ride-hailing service (e.g., Uber API) to arrange transportation from the user's current location to a medical facility. For example, if the user does not have a car, the server will call a ride-hailing service to assist the user in emergency transportation.
[1194] Finally, after receiving medical treatment, the user provides feedback through the terminal. The server collects this feedback, stores it in a database, and uses it to improve the accuracy and quality of the service of the entire system.
[1195] Examples:
[1196] A user experiences sudden chest pain while on a business trip and voice-types "I have chest pain" into the app. This information is sent from the device to the server, where it is translated and analyzed in real time using generative artificial intelligence (e.g., Google Cloud Translation API). Furthermore, an emotion engine (e.g., IBM Watson Tone Analyzer) recognizes the user's anxious tone and determines the level of urgency. The server obtains the user's current location and searches for the nearest hospital that is open even at night.
[1197] If the user does not have transportation, the server will arrange for a ride-hailing service (e.g., Uber API) to help the user quickly receive appropriate treatment at a hospital. In this way, users can access medical institutions quickly and appropriately, no matter where they are. In addition, the introduction of an emotion engine enables more personalized responses, increasing user satisfaction and a sense of security.
[1198] Example prompt sentence:
[1199] "A user utters 'I have chest pain' into the app. Send this information to the server, translate it in real time, and analyze the symptoms. Also, recognize the user's emotion (anxious tone) and explain the steps to find a medical facility and arrange transportation."
[1200] The flow of the identification process in the second embodiment will be described with reference to FIG.
[1201] Step 1:
[1202] The user enters the symptoms into the terminal.
[1203] Specifically, the user starts the application, selects text input or voice input, enters the symptoms, and presses the send button.
[1204] Input: Symptom information entered by the user into the device (e.g., "I have chest pain").
[1205] Output: Symptom information sent from the device to the server.
[1206] Step 2:
[1207] The terminal sends the input information to the server.
[1208] Specifically, the device transmits the symptom information entered by the user to the server in real time, as well as the input method and communication language selected by the user.
[1209] Input: Symptom information entered into the terminal.
[1210] Output: Symptom information, input method, and language information sent to the server.
[1211] Step 3:
[1212] The server uses the generated AI model to translate and analyze.
[1213] Specifically, the server translates the user's input in real time using a generative AI model (e.g., Google Cloud Translation API), then analyzes the translated text to extract keywords related to the symptoms.
[1214] Input: Symptom information, input method, and language information sent to the server.
[1215] Output: Translated symptom information and extracted keywords (e.g., "chest pain," "shortness of breath").
[1216] Step 4:
[1217] The server uses an emotion engine to recognize the user's emotion.
[1218] Specifically, the server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize emotions from the user's input, determining the user's anxiety or confusion from the voice tone and text, and assessing the level of urgency.
[1219] Input: Translated symptom information and extracted keywords.
[1220] Output: User's emotional state (e.g., anxiety, urgency rating).
[1221] Step 5:
[1222] The server obtains the user's current location and time zone information.
[1223] Specifically, the server uses the device's GPS function to obtain the user's current location and also references the system time to obtain the current time zone information.
[1224] Input: Location information obtained from the user's device and system time.
[1225] Output: User's current location and time zone information.
[1226] Step 6:
[1227] The server searches for the most suitable medical institution from the medical institution database.
[1228] Specifically, the server uses a MySQL database to search for the most suitable medical facility based on the user's location and symptoms, for example, listing hospitals that are open at night.
[1229] Input: User's current location, time zone information, and keywords related to the symptom.
[1230] Output: A list of the best medical institutions.
[1231] Step 7:
[1232] The server will arrange a ride-hailing service if necessary.
[1233] Specifically, if the user does not have a car, the server calls a ride-hailing service (e.g., Uber API) and arranges transportation from the user's current location to the medical facility.
[1234] Input: User's current location and information about the destination medical institution.
[1235] Output: Arrange a ride.
[1236] Step 8:
[1237] The user provides feedback via the terminal after the treatment.
[1238] Specifically, after receiving medical treatment, the user restarts the application on the terminal, inputs and sends their evaluation and opinions of the treatment.
[1239] Input: User's ratings and opinions after treatment.
[1240] Output: Feedback sent from the device to the server.
[1241] Step 9:
[1242] The server collects the feedback and stores it in a database.
[1243] Specifically, the server collects the feedback provided by users and stores it in a MySQL database, which is used to improve the accuracy and quality of the service of the entire system.
[1244] Input: Feedback sent from the device.
[1245] Output: Feedback information stored in a database.
[1246] (Application example 2)
[1247] 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."
[1248] Conventional emergency response systems have had problems in providing a fast and appropriate response when users face an emergency. In particular, it is difficult to communicate in multiple languages and analyze users' emotions, making it difficult to select the appropriate emergency agency and quickly arrange for vehicle dispatch. In addition, there is a lack of a mechanism for collecting user feedback and reflecting it in the service.
[1249] 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.
[1250] In this invention, the server includes: a means for selecting a user's input method and communication language and inputting symptoms and conditions; a translation means using generative artificial intelligence to translate the user's input; a means for analyzing the translated symptoms and conditions; a means for searching for the most appropriate response agency based on the user's current location and time of day; a means for arranging transportation in cooperation with a ride-hailing service; a means for analyzing the user's emotions using an emotion engine to determine the urgency of the emergency response and an appropriate response; a means for collecting feedback and using it to improve the service; and a means for providing a response based on the emotion engine. This allows information provided by users in multiple languages to be analyzed quickly and accurately, and an appropriate response to be provided based on the user's emotions. Furthermore, collecting and incorporating feedback allows for continuous improvement of the system.
[1251] A "user input method" is the means a user uses to provide information to a system, such as speech input or text input.
[1252] "Communication language" refers to the language used by the user to interact with the system, and includes, for example, Japanese, English, Chinese, etc.
[1253] "Symptoms and circumstances" are detailed information about the emergency that the user provides to the system, such as chest pain, shortness of breath, or the presence of a suspicious person.
[1254] "Generative AI" is an AI that has the ability to analyze input information and translate it into accurate language.
[1255] "Translation means" refers to a means for converting input information into another language using generative artificial intelligence.
[1256] "Analysis means" refers to the extraction of keywords and context from translated information, and the use of this information to determine the level of urgency and appropriate countermeasures.
[1257] "Current location" refers to the geographical information of the point where the user is accessing the system, and is obtained using technology such as GPS.
[1258] "Time zone" is information about the time when a user accesses the system, and refers to the system time.
[1259] A "response organization" is an organization or facility that responds appropriately to a user's emergency, and includes, for example, a hospital, a police station, a fire station, and the like.
[1260] A "vehicle dispatch service" is a service that arranges transportation from the user's current location to an emergency response organization.
[1261] An "emotion engine" is a program that recognizes emotions from the user's voice or text and adjusts the system's response based on the results.
[1262] "Feedback" refers to opinions and evaluation information provided by users after using the system, and is data that is useful for improving the system.
[1263] The present invention is a system for speeding up and optimizing emergency responses, supporting users in quickly accessing appropriate response organizations when they face an emergency. This system includes a means for users to select an input method and communication language and input symptoms and circumstances, a translation means using generative artificial intelligence, a means for analyzing the translated symptoms and circumstances, a means for searching for the most appropriate response organization based on the current location and time of day, a means for arranging transportation in cooperation with a ride-hailing service, a means for analyzing the user's emotions using an emotion engine to determine the urgency, and a means for collecting feedback to help improve the service.
[1264] System configuration
[1265] 1. User Input Method
[1266] The user can provide the system with an emergency situation by voice or text input using a smartphone or smart glasses. For example, the user can input "someone is trying to enter my house."
[1267] 2. Translation Methods
[1268] The server uses generative artificial intelligence to translate user input in real time. For example, if a user types "help" in Japanese, it will translate this into English as "Help!"
[1269] 3. Analysis method
[1270] The translated text is then analyzed in conjunction with an emotion engine to assess the user's level of urgency and the necessary response. For example, an input such as "someone is trying to get into my house" could indicate a situation of high anxiety and urgency.
[1271] 4. Search Methods
[1272] The server searches for emergency response agencies (police, fire department, hospitals, etc.) based on the current location and time information, and uses location information services such as Google Maps API to present the most appropriate response agency.
[1273] 5. Vehicle dispatch method
[1274] If the user does not have transportation, the server will use an API such as Uber to arrange a ride, for example, a police car will be dispatched from the nearest police station to the user's location.
[1275] 6. Emotion analysis method
[1276] It uses an emotion engine to analyze the user's emotions and determine the level of urgency, determining whether the user is feeling anxious or scared based on their input and tone of voice.
[1277] 7. Feedback Collection Methods
[1278] After users use the system, feedback is collected and used to improve the system, which will be used to improve the accuracy of the next emergency response.
[1279] Specific examples
[1280] Imagine a case where a user hears a suspicious sound at home at night and voice-records, "There's someone in the house." This information is sent from the smartphone to a server, where it is translated and analyzed in real time using generative artificial intelligence. The emotion engine recognizes the user's anxiety and determines that the situation is urgent. The server obtains the user's current location, searches for the nearest police station, and dispatches a patrol car. At the same time, it provides the user with guidelines such as, "Stay in a safe place and don't go outside." The system then collects user feedback and uses it to improve future responses.
[1281] Prompt Sentence Examples
[1282] User: "Someone is trying to get into my house. Help!"
[1283] Generative AI: Translated into English: "Someone is trying to break into my house. Help!"
[1284] Emotion Engine Assessment: User exhibits extreme anxiety.
[1285] Optimal solution: Send location information to the police. Arrange for a patrol car.
[1286] Guidelines provided: "Please lock your room and secure it. Do not move until the police arrive."
[1287] As described above, this system allows users to receive prompt and reliable support even in emergency situations.
[1288] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[1289] Step 1:
[1290] The user selects the input method (voice or text) and communication language using a smartphone or smart glasses. The input symptom or situation (e.g., "There is someone in the house") is sent to the device's input interface.
[1291] Input: The user's chosen input method and language, spoken or written symptoms or conditions.
[1292] Output: Sends input information (audio data or text data) to the server.
[1293] Step 2:
[1294] The server uses generative artificial intelligence to translate input information sent from the device in real time. For example, if the voice input is in Japanese, it will translate it into English.
[1295] Input: Audio or text data from the user.
[1296] Output: The translated text data.
[1297] Step 3:
[1298] The server analyzes the translated text data and extracts important keywords and context (e.g., "There is an intruder in my house"), and also analyzes the user's emotions (e.g., anxiety, fear) using an emotion engine.
[1299] Input: Translated text data.
[1300] Output: Extracted keywords, parsed sentiment data.
[1301] Step 4:
[1302] The server obtains the user's current location using the GPS function and also references the system time information. Based on this, it uses the Google Maps API to search for the most appropriate emergency response organization (e.g., the nearest police station).
[1303] Input: User's GPS location data, system time.
[1304] Output: A list of the best emergency response agencies.
[1305] Step 5:
[1306] Once the optimal facility has been determined, the server will connect with a ride-hailing service (e.g., Uber API) and arrange transportation from the user's current location to the facility if necessary.
[1307] Input: A list of the best emergency response agencies, the user's current location.
[1308] Output: Ride dispatch information.
[1309] Step 6:
[1310] The server responds to the user based on the emotional information analyzed by the emotion engine. For example, if a user feels anxious, the server provides specific guidelines such as "stay in a safe place and do not go outside."
[1311] Input: Emotion data, analysis results.
[1312] Output: A response message to the user.
[1313] Step 7:
[1314] After using the system, users provide feedback, which is sent to the server via their device and used to improve the accuracy of future emergency responses.
[1315] Input: Feedback data from users.
[1316] Output: Save feedback information and data to improve accuracy next time.
[1317] 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.
[1318] 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.
[1319] 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.
[1320] 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.
[1321] FIG. 9 illustrates 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 behaviors 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.
[1322] 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.
[1323] 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).
[1324] 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.
[1325] 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."
[1326] 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.
[1327] 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).
[1328] 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.
[1329] 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.
[1330] 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.
[1331] 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.
[1332] 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.
[1333] 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.
[1334] 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.
[1335] 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.
[1336] 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.
[1337] 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.
[1338] The following is further disclosed regarding the above embodiment.
[1339] (Claim 1)
[1340] a means for selecting a user input method and communication language and inputting symptoms;
[1341] a translation means using generative artificial intelligence to translate the user's input;
[1342] means for analyzing the translated symptoms;
[1343] A means for searching for the best medical institution based on the current location and time zone;
[1344] A system that includes a means to coordinate with a ride-hailing service to arrange transportation.
[1345] (Claim 2)
[1346] The system of claim 1, further comprising means for suggesting an optimal emergency medical facility based on symptoms by analyzing the user's input.
[1347] (Claim 3)
[1348] 2. The system of claim 1, further comprising means for performing real-time translation using said generative artificial intelligence.
[1349] "Example 1"
[1350] (Claim 1)
[1351] a means for selecting a user input method and communication language and inputting symptoms;
[1352] a translation means using generative artificial intelligence to translate the user's input;
[1353] means for analyzing the translated symptoms;
[1354] means for acquiring a current location and a time zone;
[1355] A means for searching for an optimal medical facility based on the acquired current location and time period;
[1356] A system including a means for coordinating transportation with a vehicle dispatching service.
[1357] (Claim 2)
[1358] The system of claim 1 , further comprising: means for suggesting an optimal emergency medical facility based on symptoms by analyzing the user's input.
[1359] (Claim 3)
[1360] 2. The system of claim 1, further comprising means for performing real-time translation using said generative artificial intelligence.
[1361] "Application Example 1"
[1362] (Claim 1)
[1363] a means for selecting a user input method and communication language and inputting symptoms;
[1364] a translation means using generative artificial intelligence to translate the user's input;
[1365] means for analyzing the translated symptoms;
[1366] A means for searching for the best medical institution based on the current location and time zone;
[1367] A means to coordinate with a ride-hailing service to arrange transportation;
[1368] The system includes a means for delivery personnel to input symptoms when they feel unwell, search for the most appropriate medical institution, and arrange for a vehicle dispatch service.
[1369] (Claim 2)
[1370] The system according to claim 1, further comprising means for suggesting an optimal emergency medical facility based on the symptoms by analyzing the user's input and arranging transportation to the medical facility from the delivery person's current location.
[1371] (Claim 3)
[1372] The system of claim 1, further comprising means for using the generative artificial intelligence to perform real-time translation and provide medical and ride-hailing services based on the delivery person's current location and time of day.
[1373] "Example 2: Combining Emotion Engines"
[1374] (Claim 1)
[1375] a means for selecting a user input method and communication language and inputting symptoms;
[1376] a translation means using generative artificial intelligence to translate the user's input;
[1377] means for analyzing the translated symptoms;
[1378] emotion recognition means using an emotion engine that recognizes emotions from the user's input;
[1379] A means for searching for the best medical institution based on the current location and time zone;
[1380] A means to coordinate with a ride-hailing service to arrange transportation;
[1381] The system further includes means for collecting and storing said post-treatment feedback in a database.
[1382] (Claim 2)
[1383] The system of claim 1, further comprising means for suggesting an optimal emergency medical facility based on symptoms by analyzing the user's input.
[1384] (Claim 3)
[1385] 2. The system of claim 1, further comprising means for performing real-time translation using said generative artificial intelligence.
[1386] "Application example 2 when combining emotion engines"
[1387] (Claim 1)
[1388] A means for selecting a user's input method and communication language and inputting symptoms and conditions;
[1389] a translation means using generative artificial intelligence to translate the user's input;
[1390] means for analyzing the translated symptoms or conditions;
[1391] A means for searching for the best response agency based on current location and time of day;
[1392] A means to coordinate with a ride-hailing service to arrange transportation;
[1393] A means for analyzing the user's emotions using an emotion engine to determine the urgency of the emergency response and the appropriate response;
[1394] How we collect feedback and use it to improve our services;
[1395] A system comprising: means for providing a response based on said emotion engine.
[1396] (Claim 2)
[1397] The system of claim 1, further comprising means for suggesting an optimal emergency response organization based on symptoms and circumstances by analyzing the user's input.
[1398] (Claim 3)
[1399] 2. The system of claim 1, further comprising means for performing real-time translation using said generative artificial intelligence. [Explanation of symbols]
[1400] 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. a means for selecting a user input method and communication language and inputting symptoms; a translation means using generative artificial intelligence to translate the user's input; means for analyzing the translated symptoms; A means for searching for the best medical institution based on the current location and time zone; A system that includes a means to coordinate with a ride-hailing service to arrange transportation.
2. The system of claim 1 , further comprising means for suggesting an optimal emergency medical facility based on symptoms by analyzing the user's input.
3. The system of claim 1 , further comprising means for performing translation in real time using said generative artificial intelligence.
Citation Information
Patent Citations
Persona chatbot control method and system
JP2022180282A