System

Abstract

A system is provided.SOLUTION: A system including means for inputting medication information of a medicine, means for storing the input medication information in a database, means for receiving a query from a user, means for predicting a drug concentration in blood using a AI model based on the received query and simulating a transition of the drug concentration, means for generating an appropriate advice based on a simulation result, and means for providing the generated advice to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In drug therapy, the effectiveness and side effects of drugs are closely related to the drug concentration in the blood. It is necessary to grasp the blood concentration of drugs and take appropriate measures even in abnormal drug administration situations, such as missed doses or overdoses. However, at present, systems that perform such simulations are not widely available, making it difficult to maximize the effectiveness and safety of drug therapy. Therefore, there is a need for a system that can predict blood drug concentrations in real time based on drug administration information and provide appropriate advice. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for inputting drug administration information, a means for saving the input administration information in a database, a means for accepting inquiries from users, a means for predicting blood drug concentrations using an AI model based on the accepted inquiries and simulating the drug concentration trends, a means for generating appropriate advice based on the simulation results, and a means for providing the generated advice to the user. The system also includes a means for collecting data on drug concentration trends from drug package inserts and interview forms and registering them in a database, a means for formatting the user-entered administration information and inputting it into the AI ​​model, and a means for analyzing the simulated blood drug concentration trends and assessing the risk of incorrect administration. This system also enables prompt and appropriate response to abnormal medication situations, such as missed doses or overdoses, thereby realizing personalized medication management.

[0006] A "drug package insert" is an official document that contains important information about a drug, including detailed information on the drug's efficacy, side effects, usage, and precautions.

[0007] An "interview form" is a document created by companies involved in the development and sale of pharmaceuticals to provide detailed information about pharmaceuticals, including clinical trial data, pharmacokinetics, and drug interactions.

[0008] "Medication information" refers to information about the medicines the user takes, including the name of the medicine, dosage form, dosage, and interval between doses.

[0009] A "database" is a system for efficiently managing and searching large amounts of data, and is used to store information about pharmaceuticals and users' medication information.

[0010] An "inquiry" is a question or concern that a user inputs into the system, and includes, for example, questions about what to do if a person forgets to take a dose or takes an overdose.

[0011] An "AI model" is a mathematical model that uses artificial intelligence to analyze data and make predictions and simulations, and is used to estimate drug blood concentrations.

[0012] "Drug concentration in blood" refers to the proportion or amount of a drug that is present in the blood over time, and is an important indicator when considering the effects and side effects of a drug.

[0013] "Simulation" is a process of reproducing an actual phenomenon using a numerical model, and in the present invention, it is performed to predict the transition of drug blood concentration.

[0014] "Advice" refers to instructions or advice the system provides to the user, including, for example, what to do if you forget to take your medication or what to do in the event of an overdose.

[0015] "Medication management" is the process by which users take their medication as prescribed, and includes not only taking the medication accurately but also managing it to prevent forgetting to take it or overdosing. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] MODE FOR CARRYING OUT THE INVENTION

[0038] This invention is a system in which users input medication information, and AI predicts the progression of drug blood concentrations based on that information and provides appropriate advice. The program processing of this system is shown below.

[0039] First, the user logs in to the system and enters medication information. For example, they enter information such as "Take 100 mg of aspirin every morning." This information is sent from the terminal to the server.

[0040] The server receives the user's input information and stores it in a database. At this time, the server also organizes the user information by taking into account data on drug concentration trends collected from drug package inserts and interview forms, which are also registered in the database.

[0041] Next, the user makes a query such as "I forgot to take my morning dose" or "I accidentally took two doses." This query is sent from the device to the server, which analyzes the received query and inputs the relevant data into the AI ​​model.

[0042] The AI ​​model simulates the progression of drug blood levels. Based on the results of this simulation, the server generates appropriate advice, such as "It is best to wait until your next appointment or consult a doctor" or "There is a risk of overdose, so contact your doctor immediately."

[0043] Finally, the generated advice is displayed to the user via the device, allowing the user to know the appropriate response in real time.

[0044] Specific examples

[0045] If you forget to take this morning's dose

[0046] 1. The user enters "Take 100mg of aspirin every morning" and sends it from the terminal to the server.

[0047] 2. The server stores this information in a database for future use.

[0048] 3. The user types a question such as, "I forgot to take my morning dose. What should I do?" and sends it from the device to the server.

[0049] 4. The server analyzes the question, inputs relevant data into the AI ​​model, and performs a simulation.

[0050] 5. Based on the simulation results, the server generates advice such as "wait until the next scheduled time to take your medication" and sends it to the terminal.

[0051] 6. The device displays the advice to the user.

[0052] If you accidentally take two doses

[0053] 1. The user enters "Take 100mg of aspirin every morning" and sends it from the terminal to the server.

[0054] 2. The server stores this information in a database for future use.

[0055] 3. The user types a question such as, "I accidentally took two doses. Is that okay?" and sends it from the device to the server.

[0056] 4. The server analyzes the question, inputs relevant data into the AI ​​model, and performs a simulation.

[0057] 5. Based on the simulation results, the server generates advice such as "There is a risk of overdose, so contact a doctor immediately" and sends it to the device.

[0058] 6. The device displays the advice to the user.

[0059] This allows users to know the appropriate course of action and maximize the effectiveness and safety of drug treatment.The present invention predicts drug blood concentrations in real time and realizes individualized medication management.

[0060] The processing flow will be explained below.

[0061] Step 1:

[0062] The user logs in to the system. User authentication is performed at the time of login, and if authentication is successful, a data entry screen is displayed.

[0063] Step 2:

[0064] The user enters their medication information, such as the name of the medication, dosage, and interval between doses, into the terminal and clicks the registration button.

[0065] Step 3:

[0066] The device sends the medication information entered by the user to the server, which packages the information in a standard data format such as JSON.

[0067] Step 4:

[0068] The server stores the received medication information in a database. When saving, it checks the data for consistency and whether there is any invalid data.

[0069] Step 5:

[0070] The server analyzes data on drug concentration trends collected from drug package inserts and interview forms, and formats the data necessary for the AI ​​model. This data is also stored in the database.

[0071] Step 6:

[0072] The user enters an inquiry such as "I forgot to take this morning's dose" or "I accidentally took two doses." After entering the information, the user clicks the "Send Inquiry" button.

[0073] Step 7:

[0074] The device sends the user's query to the server in text format.

[0075] Step 8:

[0076] The server analyzes the received query and extracts relevant medication information and drug concentration data.

[0077] Step 9:

[0078] The server inputs the extracted data into an AI model, which then simulates the progression of drug concentrations in the blood.

[0079] Step 10:

[0080] The server analyzes the simulation results obtained from the AI ​​model and generates appropriate advice, such as "wait until the next scheduled dose" or "contact your doctor immediately."

[0081] Step 11:

[0082] The server sends the generated advice to the terminal in text format.

[0083] Step 12:

[0084] The device will then display the received advice to the user, allowing them to know the appropriate response.

[0085] This enables the system of the present invention to provide appropriate advice in real time based on medication information entered by the user, maximizing the effectiveness and safety of drug treatment.

[0086] Example 1

[0087] 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."

[0088] In modern medicine management, there is a lack of means to quickly learn the appropriate response when users accidentally forget to take their medicine or take an overdose, which can lead to a decrease in the effectiveness of drug treatment and an increased risk of side effects.

[0089] 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.

[0090] In this invention, the server includes means for a user to input medication information, means for saving the input medication information in a database, means for accepting inquiries from users, means for analyzing the accepted inquiries using natural language processing, predicting blood drug concentrations using a generative AI model, and simulating changes in drug concentrations, means for generating appropriate advice based on the simulation results, and means for providing the generated advice to the user. This enables the user to quickly respond to situations such as forgetting to take medication or overdosing, and maximize the effectiveness of drug treatment.

[0091] A "user" is a person who uses the system to input medication information and make inquiries.

[0092] "Medication information" refers to information regarding the type, dosage, and time of administration of medicines taken by the user.

[0093] The "database" is a storage device that accumulates and stores data relating to medication information and drug concentration trends received by the server.

[0094] An "inquiry" is a question or confirmation that a user makes to the system, including any unclear points or problems regarding medication.

[0095] "Natural language processing" is a technology for analyzing text data such as user inquiries to understand their meaning and intent.

[0096] A "generative AI model" is an artificial intelligence model that uses received data to predict and simulate drug concentrations in the blood and generate appropriate advice.

[0097] "Simulation" refers to the computational process performed by the generative AI model to predict the progression of drug concentrations in the blood.

[0098] "Advice" refers to specific guidelines or suggestions provided to users based on the simulation results of the generative AI model.

[0099] "Additional information on drugs" refers to information including detailed data on drug concentration trends obtained from drug package inserts, interview forms, etc.

[0100] "Formatting" is the process of converting the input medication information into a format that is easy for the generative AI model to analyze.

[0101] MODE FOR CARRYING OUT THE INVENTION

[0102] The present invention is a system in which a user inputs medication information, and based on that information, AI predicts the progression of drug blood concentrations and provides appropriate advice. This system performs a series of processes: inputting medication information, accepting inquiries, managing a database, conducting simulations using AI, and generating advice. Specific embodiments of this system are described below.

[0103] Hardware and software used

[0104] Hardware:

[0105] Device: The smartphone, tablet, or computer where the user enters information

[0106] Server: Cloud server or dedicated server for storing data, simulations, and generating advice

[0107] software:

[0108] Database management systems (e.g., MySQL, PostgreSQL)

[0109] Natural Language Processing (NLP) tools (e.g., spaCy, NLTK)

[0110] Generative AI models (e.g., TensorFlow, PyTorch)

[0111] Communication protocol (e.g. HTTPS)

[0112] Program processing (natural language explanation)

[0113] 1. The user enters medication information using a terminal. For example, "Take 100 mg of aspirin every morning."

[0114] 2. The terminal sends the entered medication information to the server.

[0115] 3. The server stores the received medication information in a database, including additional information about the drug (such as the drug package insert and interview form data).

[0116] 4. The user enters the inquiry information using the terminal. For example, "I forgot to take my morning dose. What should I do?" or "I accidentally took two doses. Is that okay?"

[0117] 5. The terminal sends the query information to the server.

[0118] 6. The server uses natural language processing (NLP) to analyze the received query information and extract relevant data, which then forms the information needed for the generative AI model.

[0119] 7. The server uses a generative AI model to simulate the progression of drug blood concentrations based on the query. For example, the model can be implemented using PyTorch or TensorFlow.

[0120] 8. The server generates appropriate advice based on the simulation results, such as a specific action plan, such as whether to wait until the next scheduled medication dose or consult a doctor.

[0121] 9. The device displays the advice received from the server to the user.

[0122] Specific examples and prompt sentence examples

[0123] Specific examples

[0124] 1. If you forget to take this morning's dose

[0125] The user enters medication information such as "Take 100 mg of aspirin every morning" and sends it from the terminal to the server.

[0126] The server stores this information in a database.

[0127] The user enters a query such as "I forgot to take my morning dose. What should I do?" into the terminal and sends it to the server.

[0128] The server parses the query and feeds the data into a generative AI model.

[0129] The AI ​​model performs a simulation, and the server generates advice to "wait until the next scheduled medication time" and sends it to the device.

[0130] The device displays the advice to the user.

[0131] 2. If you accidentally take two doses

[0132] The user enters medication information such as "Take 100 mg of aspirin every morning" and sends it from the terminal to the server.

[0133] The server stores this information in a database.

[0134] The user enters a question into the terminal, such as "I accidentally took two doses. Is that okay?", and sends it to the server.

[0135] The server parses the query and feeds the data into a generative AI model.

[0136] The AI ​​model runs a simulation, and the server generates advice such as "There is a risk of overdose, so contact a doctor immediately" and sends it to the device.

[0137] The device displays the advice to the user.

[0138] Prompt Sentence Examples

[0139] 1. If you forget to take this morning's dose

[0140] A user takes 100mg of aspirin every morning and forgot to take their morning dose. Can you advise them on what to do next?

[0141] 2. If you accidentally take two doses

[0142] A user takes 100mg of aspirin every morning and accidentally takes two doses. Can you advise what to do next?

[0143] The above is an embodiment of the present invention. This system allows users to quickly respond to medication-related problems and maximize the effectiveness of drug therapy.

[0144] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0145] Step 1:

[0146] The user enters medication information.

[0147] Input: The user types "Take 100 mg of aspirin daily in the morning" into an application input field.

[0148] Specific operation: The user operates the device (smartphone or PC) and enters the required information in text format into the designated fields.

[0149] Output: Medication information is temporarily stored in the device's memory.

[0150] Step 2:

[0151] The terminal transmits medication information to the server.

[0152] Input: Medication information entered by the user.

[0153] Specific operation: The terminal sends the medication information entered via the Internet to the server using the HTTPS protocol.

[0154] Output: Medication information is sent to the server.

[0155] Step 3:

[0156] The server stores the received medication information in a database.

[0157] Input: Medication information received by the server.

[0158] Specific operation: The server converts the received medication information into an appropriate format and saves it in a database (MySQL, PostgreSQL, etc.). Here, for example, an SQL statement is generated to add data.

[0159] Output: Medication information is permanently stored in a database.

[0160] Step 4:

[0161] The user enters the inquiry information.

[0162] Input: The user types "I forgot my morning dose. What should I do?" into an application input field.

[0163] Specific actions: The user operates the device and enters the inquiry information in text format into the designated field.

[0164] Output: The query information is temporarily stored in the device's memory.

[0165] Step 5:

[0166] The terminal transmits the inquiry information to the server.

[0167] Input: The inquiry information entered by the user.

[0168] Specific operation: The terminal sends the query information to the server via the Internet using the HTTPS protocol.

[0169] Output: The query information is forwarded to the server.

[0170] Step 6:

[0171] The server analyzes the query and inputs it into a generative AI model.

[0172] Input: The query information received by the server.

[0173] What it does: The server uses natural language processing (NLP) tools to analyze the query and extract relevant data, such as spaCy to tokenize the text and extract important keywords.

[0174] Output: The analyzed information is formatted to be input into an AI model.

[0175] Step 7:

[0176] The AI ​​model simulates the drug's blood concentration.

[0177] Input: Formatted inquiry information and medication information.

[0178] How it works: The AI ​​model uses PyTorch, TensorFlow, etc. to run simulations based on query information. Specifically, it references existing medication data and uses a time-series prediction model to calculate drug concentrations in the blood.

[0179] Output: Simulation results are generated.

[0180] Step 8:

[0181] The server generates advice based on the simulation results.

[0182] Input: Simulation results obtained from the AI ​​model.

[0183] Specific operation: Based on the simulation results, the server generates appropriate advice using predefined templates, such as "wait until the next scheduled dose" or "consult a doctor."

[0184] Output: Advice is generated in text format.

[0185] Step 9:

[0186] The device displays the advice to the user.

[0187] Input: Advice sent by the server.

[0188] Specific operation: The device displays the advice received from the server on the application interface, specifically by using notifications or pop-up windows to present the advice to the user in an easy-to-read format.

[0189] Output: User receives advice and decides next action.

[0190] The above is a detailed description of the processing steps of the program of this system and the specific operations of each.

[0191] (Application example 1)

[0192] 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."

[0193] With existing medication management systems, it is difficult for users to receive appropriate advice in real time when they encounter problems such as forgetting to take a dose or overdosing. Furthermore, pharmacy and drugstore staff have limited means of providing prompt and appropriate advice to patients, making it difficult to maximize user safety and therapeutic effectiveness. The present invention was developed to solve these problems, and aims to increase practicality, particularly in pharmacies and drugstores.

[0194] 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.

[0195] In this invention, the server includes a means for inputting medication information, a means for storing the input medication information in a database, a means for accepting inquiries from users, a means for predicting blood drug concentrations using an AI model based on the accepted inquiries and simulating the progression of drug concentrations, a means for generating appropriate advice based on the simulation results, a means for providing the generated advice to the user, and a means for displaying the advice to staff wearing smart devices. This makes it possible to predict drug concentrations in real time from the input medication information and generate and provide appropriate advice. Furthermore, staff can use the smart devices to quickly communicate advice to users, making medication management for users more efficient and safe.

[0196] "Medicine medication information" is information about the medicines taken by the user, including, for example, the name of the medicine, dosage, and time of administration.

[0197] A "database" is a structured collection of data that efficiently stores and manages input information.

[0198] "Means for accepting inquiries from users" refers to an interface that allows users to input questions or problems, such as forgotten medication or overdose, into the system.

[0199] An "AI model" is a collection of algorithms and methods for analyzing data and making predictions using artificial intelligence technology.

[0200] "Means for predicting drug concentrations in the blood and simulating trends in drug concentrations" refers to means for using AI models to calculate and show fluctuations in drug concentrations in the body.

[0201] "Means for generating appropriate advice" refers to means for recommending actions and points of caution that are beneficial to the user based on the results of the simulation.

[0202] The "means for providing the generated advice to the user" refers to a means for notifying or displaying the generated advice to the user.

[0203] "Smart devices" are devices with internet connectivity, such as wearable devices and mobile devices, that allow users and staff to access information in real time.

[0204] This invention is a system in which users input medication information, and AI predicts changes in blood drug concentrations based on that information and provides appropriate advice. The invention is designed to enable staff at pharmacies and drug stores to efficiently provide appropriate advice to patients.

[0205] System configuration and operation

[0206] 1. Data Entry

[0207] The user (pharmacy staff) uses a smart device (e.g., smart glasses or a smartphone) to input medication information provided by the patient, such as "Take 100 mg of aspirin every morning."

[0208] 2. Data Transmission

[0209] The entered medication information is sent via smartphone to a cloud server, which stores the information in a database such as MySQL or PostgreSQL.

[0210] 3. AI-based predictions

[0211] The cloud server runs an AI model using Python and TensorFlow based on the stored medication information and data from drug package inserts and interview forms registered in the database. The AI ​​model simulates the progression of drug concentrations in the blood and outputs the results.

[0212] 4. Generating Advice

[0213] Based on the simulation results, the server uses a web framework such as Flask to generate appropriate advice, such as "You should wait until your next scheduled dose" or "You are at risk of overdose, so contact your doctor immediately."

[0214] 5. Providing advice

[0215] The generated advice is displayed on the smart glasses' display, allowing pharmacy staff to provide appropriate advice to patients in real time. By using the smart glasses in conjunction with the smartphone application, more detailed information can be viewed.

[0216] Specific examples

[0217] If you miss a dose:

[0218] 1. The server receives the user's input, "Take 100 mg of aspirin every morning," and stores it in a database.

[0219] 2. When the user types in a question such as "I forgot to take my morning dose," the information is sent to the server.

[0220] 3. The server runs an AI model based on the received question and generates advice such as, "You should wait until your next scheduled medication dose."

[0221] 4. Advice is displayed on the smart glasses display, and staff relays it to the patient.

[0222] In case of overdose:

[0223] 1. The server receives the user's input, "Take 100 mg of aspirin every morning," and stores it in a database.

[0224] 2. When the user types a question like, "I accidentally took two doses, is that okay?", the information is sent to the server.

[0225] 3. The server runs an AI model based on the received question and generates advice such as, "There is a risk of overdose, so contact your doctor immediately."

[0226] 4. Advice is displayed on the smart glasses display, and staff relays it to the patient.

[0227] Prompt Sentence Examples

[0228] A user has entered medication information. Medication Information: Aspirin 100mg daily in the morning. Question: I forgot to take my morning dose. Please provide appropriate advice.

[0229]

[0230] A user has entered medication information. Medication information: Take 100mg of aspirin every morning. Question: I accidentally took two doses. Is this ok? Please provide appropriate advice.

[0231] This enables the system to provide appropriate medication advice in real time, maximizing patient safety and therapeutic effectiveness.

[0232] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0233] Step 1:

[0234] The user enters medication information using a smart device. Specifically, the user enters information such as "Take 100 mg of aspirin every morning" through a smartphone app or smart glasses. The entered information is temporarily stored on the device.

[0235] Step 2:

[0236] The device sends the entered medication information to the cloud server. Specifically, the smartphone app issues an HTTP request over the Internet to send the data to the API endpoint of the cloud server. At this time, the data is serialized in JSON format.

[0237] Step 3:

[0238] The medication information received by the server is saved in a database. Specifically, the server uses Python to deserialize the received data and stores the information in a database such as MySQL or PostgreSQL. The saved information is used for subsequent processing.

[0239] Step 4:

[0240] The user enters additional information or a question (e.g., "I forgot my morning dose"), and the information entered through the smartphone app or smart glasses is temporarily stored on the device.

[0241] Step 5:

[0242] The device sends the added information and question to the cloud server. As in step 2, the data entered by the user is sent to the server using an HTTP request. This data is also serialized in JSON format.

[0243] Step 6:

[0244] The server analyzes the received question and inputs the relevant data into the AI ​​model. Specifically, it uses a web framework such as Flask to parse the query, retrieves relevant medication information from a database, and formats it into a data format to be input into the AI ​​model.

[0245] Step 7:

[0246] The server runs an AI model to predict drug concentrations in the blood and simulate their progression. Specifically, it supplies input data to an AI model using TensorFlow and executes model inference. To obtain simulation results, the model calculates multidimensional array data.

[0247] Step 8:

[0248] The server generates appropriate advice based on the simulation results. Specifically, it executes logic to generate messages such as "Wait until your next scheduled dose" or "Contact your doctor immediately as there is a risk of overdose" based on the inferred drug concentration.

[0249] Step 9:

[0250] The server provides the generated advice to the user. Specifically, it generates JSON data including the generated advice message as a response from the application and sends it to the user's device.

[0251] Step 10:

[0252] The device displays the received advice to the user. Specifically, the advice message is displayed on the smart glasses display, allowing the user to check it in real time. A notification is also sent to the smartphone app, which displays detailed information.

[0253] At each step, the input information undergoes the necessary data processing or calculation and is passed to the next step in an appropriate format, so that final advice can be provided to the user.

[0254] 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.

[0255] MODE FOR CARRYING OUT THE INVENTION

[0256] This invention combines a system in which a user inputs medication information, and AI predicts the progression of drug blood concentrations based on that information and provides appropriate advice, with an emotion engine that recognizes the user's emotions, to provide advice that is appropriate to the user's psychological state. The program processing of this system is shown below.

[0257] First, the user logs in to the system and enters medication information. For example, they enter information such as "Take 100 mg of aspirin every morning." This information is sent from the terminal to the server.

[0258] The server receives the user's input information and stores it in a database. At this time, the server also organizes user information by taking into account the drug concentration transition data collected from drug package inserts and interview forms, which are also registered in the database.

[0259] Next, the user makes a query such as "I forgot to take my morning dose" or "I accidentally took two doses." This query is sent from the device to the server, which analyzes the received query and inputs the relevant data into the AI ​​model.

[0260] The AI ​​model simulates the progression of drug blood levels. Based on the results of this simulation, the server generates appropriate advice, such as "It is best to wait until your next appointment or consult a doctor" or "There is a risk of overdose, so contact your doctor immediately."

[0261] Furthermore, the system of the present invention is equipped with an emotion engine that analyzes user input and voice data to recognize emotions. Based on the emotions recognized by the emotion engine, the server adjusts the content and format of advice. For example, if the user is feeling anxious, more reassuring and polite advice will be provided.

[0262] The server also monitors the user's emotional state over the long term and analyzes the history of emotional fluctuations, making it possible to assess the effectiveness of drug treatment and the risk of side effects based on the emotional fluctuations.

[0263] A specific example of processing will be shown below.

[0264] If you forget to take this morning's dose

[0265] 1. The user enters "Take 100mg of aspirin every morning" and sends it from the terminal to the server.

[0266] 2. The server stores this information in a database for future use.

[0267] 3. The user types a question such as, "I forgot to take my morning dose. What should I do?" and sends it from the device to the server.

[0268] 4. The server analyzes the question, inputs relevant data into the AI ​​model, and performs a simulation.

[0269] 5. Based on the simulation results, the server generates advice such as "wait until the next scheduled time to take your medication."

[0270] 6. The emotion engine analyzes user input and voice data and recognizes that the user is anxious.

[0271] 7. The server provides more polite and reassuring advice to anxious users.

[0272] 8. The device displays the advice to the user.

[0273] If you accidentally take two doses

[0274] 1. The user enters "Take 100mg of aspirin every morning" and sends it from the terminal to the server.

[0275] 2. The server stores this information in a database for future use.

[0276] 3. The user types a question such as, "I accidentally took two doses. Is that okay?" and sends it from the device to the server.

[0277] 4. The server analyzes the question, inputs relevant data into the AI ​​model, and performs a simulation.

[0278] 5. Based on the simulation results, the server generates advice such as "There is a risk of overdose, so contact a doctor immediately."

[0279] 6. The emotion engine analyzes the user's input and voice data and recognizes that the user is in a panic.

[0280] 7. The server provides calming advice to panicked users, encouraging them to stay calm.

[0281] 8. The device displays the advice to the user.

[0282] In this way, by combining the emotion engine, the system of the present invention can provide personalized advice based on the user's psychological state, maximizing the effectiveness and safety of drug treatment.

[0283] The processing flow will be explained below.

[0284] If you forget to take this morning's dose

[0285] Step 1:

[0286] The user logs in to the system. User authentication is performed at login, and if authentication is successful, a data entry screen is displayed.

[0287] Step 2:

[0288] The user enters their medication information, for example, "Take 100 mg of aspirin every morning," into the terminal and clicks the registration button.

[0289] Step 3:

[0290] The device sends the medication information entered by the user to the server, which packages the information in a standard data format such as JSON.

[0291] Step 4:

[0292] The server stores the received medication information in a database. When saving, it checks the data for consistency and whether there is any invalid data.

[0293] Step 5:

[0294] The server analyzes data on drug concentration trends collected from drug package inserts and interview forms, and formats the data necessary for the AI ​​model. This data is also stored in the database.

[0295] Step 6:

[0296] The user types in a query such as "I forgot to take my morning dose, what should I do?" and clicks the send button.

[0297] Step 7:

[0298] The device sends the user's query to the server in text format.

[0299] Step 8:

[0300] The server analyzes the received query and inputs relevant medication information and drug concentration data into the AI ​​model.

[0301] Step 9:

[0302] The server uses an AI model to simulate the progression of drug blood concentrations.

[0303] Step 10:

[0304] The server analyzes the simulation results and generates advice such as "wait until the next scheduled time to take your medication."

[0305] Step 11:

[0306] The emotion engine analyzes user input and voice data and recognizes that the user is anxious.

[0307] Step 12:

[0308] The server generates more polite and reassuring advice for anxious users and sends it to their terminals.

[0309] Step 13:

[0310] The device will display advice to the user, allowing them to know the appropriate response.

[0311] If you accidentally take two doses

[0312] Step 1:

[0313] The user logs in to the system. User authentication is performed at login, and if authentication is successful, a data entry screen is displayed.

[0314] Step 2:

[0315] The user enters their medication information, for example, "Take 100 mg of aspirin every morning," into the terminal and clicks the registration button.

[0316] Step 3:

[0317] The device sends the medication information entered by the user to the server, which packages the information in a standard data format such as JSON.

[0318] Step 4:

[0319] The server stores the received medication information in a database. When saving, it checks the data for consistency and whether there is any invalid data.

[0320] Step 5:

[0321] The server analyzes data on drug concentration trends collected from drug package inserts and interview forms, and formats the data necessary for the AI ​​model. This data is also stored in the database.

[0322] Step 6:

[0323] The user types in a query such as "I accidentally took two doses, what should I do?" and clicks the send button.

[0324] Step 7:

[0325] The device sends the user's query to the server in text format.

[0326] Step 8:

[0327] The server analyzes the received query and inputs relevant medication information and drug concentration data into the AI ​​model.

[0328] Step 9:

[0329] The server uses an AI model to simulate the progression of drug blood concentrations.

[0330] Step 10:

[0331] The server analyzes the simulation results and generates advice such as "There is a risk of overdose, so contact a doctor immediately."

[0332] Step 11:

[0333] The emotion engine analyzes user input and voice data and recognizes when the user is in a panic.

[0334] Step 12:

[0335] The server generates calm advice for panicked users, urging them to stay calm, and sends it to their devices.

[0336] Step 13:

[0337] The device will display advice to the user, allowing them to know the appropriate response.

[0338] In this way, by combining the emotion engine, the system of the present invention can provide personalized advice based on the user's psychological state, maximizing the effectiveness and safety of drug treatment.

[0339] Example 2

[0340] 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."

[0341] Conventional medication management systems can predict drug blood concentrations and provide advice based on medication information entered by the user, but it has been difficult to provide personalized advice that takes into account the user's psychological state. As a result, these systems have not been effective enough in reducing the user's psychological burden and anxiety regarding medication and health management. To address this issue, the present invention aims to provide a system that recognizes the user's emotions and provides personalized advice based on them.

[0342] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for inputting medication information of a drug; means for saving the input medication information in a database; means for accepting inquiries from a user; means for predicting drug concentrations in blood using an artificial intelligence model based on the accepted inquiries and simulating the progress of drug concentrations; means for generating appropriate advice based on the simulation results; means for providing an emotion engine for recognizing emotions by analyzing user input and voice data; means for adjusting the advice content based on the recognized emotions; and means for providing the generated advice to the user. This makes it possible to provide personalized advice that takes into account the psychological state of the user.

[0343] The "means for inputting medication information" refers to an interface that allows a user to input information such as the name, dosage, and time of administration of the medication via a terminal.

[0344] The "means for saving input medication information in a database" is a server-side function that registers the medication information input by the user in a database so that it can be referenced later.

[0345] "Means for accepting inquiries from users" refers to an interface that allows users to send questions or inquiries to the system, and the server receives this information.

[0346] "Means for predicting drug concentrations in the blood using an artificial intelligence model and simulating trends in drug concentrations" refers to a program that uses AI technology to predict fluctuations in drug concentrations in the blood based on input medication information and related data, and simulates those trends.

[0347] "Means for generating appropriate advice based on simulation results" refers to a server-side function that generates appropriate behavioral instructions and advice for users based on the simulation results obtained by the AI ​​model.

[0348] An "emotion engine that recognizes emotions by analyzing user input and voice data" is an engine that determines the user's emotions and psychological state at that time by analyzing the text and voice data entered by the user.

[0349] The "means for adjusting the advice content based on the recognized emotions" is a server-side function for appropriately changing the content and expression of the advice provided according to the user's emotional state recognized by the emotion engine.

[0350] The "means for providing generated advice to the user" is an interface for displaying the advice generated by the system to the user via a terminal.

[0351] "Means of collecting data on changes in drug concentration from drug package inserts and interview forms and registering it in a database" refers to a function that extracts data on changes in drug blood concentration from official drug documents and questionnaires, and registers that data in a database.

[0352] MODE FOR CARRYING OUT THE INVENTION

[0353] This invention combines a system in which medication information is input, and AI predicts changes in blood drug concentrations based on that information and provides appropriate advice, with an emotion engine that recognizes the user's emotions, to provide advice that is tailored to the user's psychological state. Specific embodiments of this system are described below.

[0354] First, a user logs in to the system and enters medication information. For example, the user enters that they take 100 mg of aspirin every morning. This information is sent from the user's device to the server. The device packages the entered information in JSON format and sends an HTTP POST request to the server.

[0355] The server then stores the medication information in a database, typically using a database management system (DBMS). The server receives the HTTP request, analyzes the data, and then executes an SQL query to insert the information into the user table in the database.

[0356] After receiving and saving the medication information, the server accepts inquiries from the user. The user types "I forgot to take my morning dose. What should I do?" into the chat box on the device's application screen and clicks the send button. The device then sends this inquiry to the server as an HTTP POST request.

[0357] The server analyzes the received query using a natural language processing (NLP) engine. The analyzed query content, along with related drug data, is then input into an AI model. The AI ​​model uses machine learning algorithms to simulate the progression of drug concentrations in the blood based on medication information and drug data. This simulation uses information from existing datasets and drug package inserts.

[0358] The simulation results generated by the AI ​​model are used by the server to generate appropriate advice, such as "It is best to wait until your next scheduled dose" or "There is a risk of overdose, so contact your doctor immediately."

[0359] Furthermore, the server is equipped with an emotion engine that recognizes emotions using user input and voice data. The emotion engine analyzes whether the user is feeling anxious or panicked. For example, if the user inputs, "I forgot my morning dose. What should I do?", the emotion engine will recognize that the user is anxious.

[0360] Based on this recognition, the server can adjust the content and format of the advice it generates: if a user feels anxious, it will provide advice in more reassuring language. In this way, the system can provide personalized advice that takes into account the user's psychological state.

[0361] As an example, the following scenario can be considered.

[0362] Example of what to do if you forget to take this morning's dose

[0363] 1. The user enters "Take 100mg of aspirin every morning" and sends it from the terminal to the server.

[0364] Example prompt: "Take 100 mg of aspirin every morning."

[0365] 2. The server stores this information in a database for future use.

[0366] 3. The user types a question such as, "I forgot to take my morning dose. What should I do?" and sends it from the device to the server.

[0367] Example prompt: "I forgot to take my morning dose. What should I do?"

[0368] 4. The server analyzes the question, inputs relevant data into the AI ​​model, and performs a simulation.

[0369] 5. Based on the simulation results, the server generates advice such as "wait until the next scheduled time to take your medication."

[0370] Sample prompt: "It's best to wait until your next scheduled dose."

[0371] 6. The emotion engine analyzes user input and voice data and recognizes that the user is anxious.

[0372] 7. The server provides more polite and reassuring advice to anxious users.

[0373] Sample prompt: "Don't worry. It's best to wait until your next dose. However, if you're concerned, talk to your doctor."

[0374] 8. The device displays the advice to the user.

[0375] In this way, the system of the present invention aims to improve the effectiveness and safety of drug treatment by combining an emotion engine to provide optimal advice according to the user's psychological state.

[0376] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0377] Processing Steps

[0378] Step 1:

[0379] The user logs into the system and enters medication information.

[0380] Input: A user enters "Take 100mg of aspirin daily in the morning" into a form.

[0381] Specific actions: The user enters medication information into the form on the application screen and clicks the submit button.

[0382] Output: The device converts the user's input information into JSON format and generates an HTTP POST request.

[0383] Step 2:

[0384] The terminal transmits the entered medication information to the server.

[0385] Input: The HTTP POST request generated by the device.

[0386] Specific operation: The device stores JSON format data in the body of the HTTP request and sends the request to the specified server endpoint.

[0387] Output: The server receives the HTTP request.

[0388] Step 3:

[0389] The server stores the received medication information in a database.

[0390] Input: Medication information received by the server in JSON format.

[0391] Specific operation: The server parses the JSON format data and saves it by issuing an INSERT query to the corresponding table in the database.

[0392] Output: A new record is added to the database.

[0393] Step 4:

[0394] The user inputs a question about medication and sends it from the terminal to the server.

[0395] Input: User types in chat box, "I forgot my morning dose. What should I do?"

[0396] Specific Actions: The user types a query into the chat box and clicks the send button.

[0397] Output: The terminal converts the query content into JSON format and generates an HTTP POST request.

[0398] Step 5:

[0399] The terminal sends the inquiry to the server.

[0400] Input: The HTTP POST request generated by the device.

[0401] Specific operation: The terminal stores the query content in JSON format in the body of an HTTP request and sends it to the server.

[0402] Output: The server receives the HTTP request.

[0403] Step 6:

[0404] The server analyzes the query and inputs the relevant data into the AI ​​model.

[0405] Input: The query received by the server in JSON format.

[0406] Specific operation: The server uses a natural language processing (NLP) engine to analyze the query, extract relevant data such as drug information, and input it into the AI ​​model.

[0407] Output: The AI ​​model is provided with input data.

[0408] Step 7:

[0409] The AI ​​model simulates the progression of drug blood concentrations.

[0410] Input: Medication information and related data fed into the AI ​​model.

[0411] How it works: The AI ​​model uses a trained neural network to predict and simulate time series data of drug concentrations in the blood.

[0412] Output: As a result of the simulation, data on the drug concentration over time is generated.

[0413] Step 8:

[0414] The server generates advice based on the simulation results.

[0415] Input: Simulation results provided by the AI ​​model.

[0416] Specific operation: The server obtains the simulation results and generates appropriate advice (e.g., "wait until the next scheduled medication time") using a rule-based engine.

[0417] Output: The generated advice is provided in text format.

[0418] Step 9:

[0419] The emotion engine analyzes user input and voice data to recognize emotions.

[0420] Input: User-provided input text or voice data.

[0421] What it does: The emotion engine uses text and speech recognition technology to determine the user's emotion (e.g., anxiety, panic).

[0422] Output: The emotion recognition result is the user's emotional state.

[0423] Step 10:

[0424] The advice content is adjusted based on the emotion recognized by the server.

[0425] Input: Emotion recognition results from the emotion engine and initial advice content.

[0426] Specific operation: The server takes into account the emotion recognition results and adjusts the wording of the advice (e.g., changes the wording to make it more reassuring).

[0427] Output: An emotion-adjusted advice is generated.

[0428] Step 11:

[0429] The device displays the advice to the user.

[0430] Input: The final advice provided by the server.

[0431] Specific operation: The device receives the advice content and displays it on the user interface (UI).

[0432] Output: The advice is ready for the user to review.

[0433] Through this process, the system can provide personalized advice based on the information entered by the user, using AI models and emotion engines.

[0434] (Application example 2)

[0435] 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."

[0436] In recent years, there has been an increasing need for more efficient and effective medication management. It is particularly important to provide prompt and accurate advice when users forget to take their medication or overdose. However, conventional systems only provide standardized advice without taking into account the user's emotional state. Therefore, there is a problem in that it is difficult to provide appropriate support when the user is feeling anxious or panicked.

[0437] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for inputting medication information on drugs; means for saving the input medication information in a database; means for accepting inquiries from users; means for predicting blood drug concentrations using an AI model based on the accepted inquiries and simulating the progress of drug concentrations; means for generating appropriate advice based on the simulation results; means for providing the generated advice to the user; means for having an emotion analysis engine and analyzing user input and voice data to recognize emotions; and means for providing appropriate advice content and format based on the recognized emotions. This makes it possible to provide personalized advice according to the user's emotional state, maximizing the effectiveness and safety of drug treatment.

[0438] "Pharmaceuticals" is a general term for chemicals and biological products used for the prevention, diagnosis, treatment, or alleviation of disease.

[0439] "Medication information" refers to data regarding the name, dosage, and timing of taking the medication the user is taking.

[0440] A "database" is an information collection system that systematically accumulates information and is designed to make it easy to search and manage.

[0441] "Inquiries" refer to questions, doubts, or inquiries that users have about the system they use.

[0442] An "AI model" is a computational algorithm or statistical model that mimics human intelligence and is capable of learning, reasoning, and self-improvement.

[0443] "Blood drug concentration" is data that indicates the amount of a particular drug present in a user's blood.

[0444] "Simulation" is a technical technique for virtually reproducing real-world situations and phenomena and conducting analysis and predictions.

[0445] "Appropriate advice" refers to specific and accurate instructions and recommendations provided based on simulation results and data analysis.

[0446] An "emotion analysis engine" is a technology that analyzes a user's text input and voice data and automatically recognizes their emotional state (joy, anger, sadness, happiness, etc.).

[0447] "Input and voice data" means text messages and voice utterances that a user enters into the system.

[0448] This invention is a system in which users input their medication information, and AI predicts the progression of drug blood concentrations based on that information and provides appropriate advice. By combining this with an emotion analysis engine that recognizes the user's emotions, the system provides advice tailored to the user's psychological state. This system is particularly applicable as a customer support app in brick-and-mortar stores (pharmacies and drugstores).

[0449] System configuration

[0450] The system consists of the following main components:

[0451] 1. User terminal: A device (such as a smartphone) through which the user enters medication information.

[0452] 2. Server: A computer system that holds a database and runs AI models and sentiment analysis engines.

[0453] 3. Database: A system (such as MongoDB) for storing drug concentration trend data and user medication information.

[0454] Program processing

[0455] The processing of this program consists of the following major steps:

[0456] 1. Getting user input:

[0457] Users enter information about their medication (such as name, dosage, and timing of administration) via a smartphone app, which is then sent from the device to a server.

[0458] 2. Data storage:

[0459] The server stores the received medication information in a database, which also includes data collected from drug package inserts and interview forms.

[0460] 3. User Inquiries:

[0461] Users can use the app to make inquiries such as, "I forgot to take my morning dose" or "I accidentally took two doses."

[0462] 4. Simulation using AI models:

[0463] Based on the queries received, the server uses an AI model (using PyTorch) to predict the progression of drug concentrations in the blood.

[0464] 5. Generating Advice:

[0465] Based on the simulation results, the server generates appropriate advice, using a sentiment analysis engine (using Google Cloud Natural Language API) to analyze the user's sentiment and provide advice accordingly.

[0466] 6. Providing advice:

[0467] The generated advice is sent to the terminal and displayed to the user.

[0468] Technical details

[0469] Hardware and software used:

[0470] User device: Smartphone (iOS or Android)

[0471] Server: Backend built with Node.js and Express

[0472] Database: MongoDB

[0473] AI Simulation: PyTorch

[0474] Sentiment analysis engine: Google Cloud Natural Language API

[0475] Specific examples

[0476] If you forget to take this morning's dose

[0477] 1. The user enters "Take 100mg of aspirin every morning" and sends it from the terminal to the server.

[0478] 2. The server stores this information in a database.

[0479] 3. The user types a question such as, "I forgot to take my morning dose. What should I do?" and sends it from the device to the server.

[0480] 4. The server analyzes the question, inputs relevant data into the AI ​​model, and performs a simulation.

[0481] 5. Based on the simulation results, the server generates advice such as "wait until the next scheduled time to take your medication."

[0482] 6. The sentiment analysis engine analyzes user input and voice data and recognizes that the user is anxious.

[0483] 7. The server provides more reassuring and courteous advice to anxious users.

[0484] 8. The device displays the advice to the user.

[0485] Prompt Sentence Examples

[0486] When a user sends a question such as "I forgot to take my medicine this morning. What should I do?", the prompt text is "Please provide advice about the next dose time. The user is feeling anxious, so please provide reassuring advice." Based on this prompt, the AI ​​model generates advice such as "Please wait until the next scheduled dose time. Also, if you feel anxious, it is best to consult a doctor. Rest assured that this will be resolved quickly."

[0487] As described above, the system of the present invention can maximize the effectiveness and safety of drug treatment by providing personalized advice that takes into account the user's emotional state.

[0488] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0489] Step 1:

[0490] Users open the app on their smartphone and enter information about their medication (such as name, dosage, and timing of administration). This information is sent from the device to the server. Input is done using text fields and drop-down menus, and the data is sent by pressing the send button. The input data includes the name of the medication, dosage, and timing of administration.

[0491] Step 2:

[0492] The server stores the received medication information in a database (MongoDB). After receiving the request, the server parses the information and stores it in the appropriate table (collection) in the database. The output is the medication information stored in the database.

[0493] Step 3:

[0494] Users input their questions (e.g., "I forgot to take my morning dose," "I accidentally took two doses," etc.) through a smartphone app and send them to the server from their device. A text field is used for input, and the question is sent by pressing the send button. The input data includes the question text.

[0495] Step 4:

[0496] The server provides the necessary data to the AI ​​model (using PyTorch) based on the received query, predicting the progression of drug concentrations in the blood. The server processes the received query, retrieves relevant medication information from the database, and inputs it into the AI ​​model. The output is simulated data on the progression of drug concentrations in the blood.

[0497] Step 5:

[0498] The server generates appropriate advice based on the simulation results. In doing so, it uses a sentiment analysis engine (using the Google Cloud Natural Language API) to analyze the user's emotional state. The server compares the simulation results with the query text and generates optimal advice. The sentiment analysis engine detects emotions from the user's input text and incorporates this emotional information into the advice generation process. The output is advice that takes the user's emotional state into account.

[0499] Step 6:

[0500] The server sends the generated advice to the terminal and provides it to the user.The server sends the generated advice to the user's terminal so that the user can view the advice on the screen.As an output, the advice displayed on the user's smartphone screen is obtained.

[0501] Step 7:

[0502] The user checks the advice displayed on the device and takes the next action if necessary. The user reads the advice and takes action (e.g., wait until the next appointment time, consult a doctor, etc.). The output is a decision on the user's action.

[0503] Through these steps, the system can provide personalized advice based on the user's emotional state, maximizing the effectiveness and safety of drug treatment.

[0504] 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.

[0505] 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.

[0506] 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.

[0507] [Second embodiment]

[0508] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0509] 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.

[0510] 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).

[0511] 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.

[0512] 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.

[0513] 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).

[0514] 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.

[0515] 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.

[0516] 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.

[0517] 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.

[0518] In the smart glasses 214, the 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.

[0519] 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."

[0520] MODE FOR CARRYING OUT THE INVENTION

[0521] This invention is a system in which users input medication information, and AI predicts the progression of drug blood concentrations based on that information and provides appropriate advice. The program processing of this system is shown below.

[0522] First, the user logs in to the system and enters medication information. For example, they enter information such as "Take 100 mg of aspirin every morning." This information is sent from the terminal to the server.

[0523] The server receives the user's input information and stores it in a database. At this time, the server also organizes the user information by taking into account data on drug concentration trends collected from drug package inserts and interview forms, which are also registered in the database.

[0524] Next, the user makes a query such as "I forgot to take my morning dose" or "I accidentally took two doses." This query is sent from the device to the server, which analyzes the received query and inputs the relevant data into the AI ​​model.

[0525] The AI ​​model simulates the progression of drug blood levels. Based on the results of this simulation, the server generates appropriate advice, such as "It is best to wait until your next appointment or consult a doctor" or "There is a risk of overdose, so contact your doctor immediately."

[0526] Finally, the generated advice is displayed to the user via the device, allowing the user to know the appropriate response in real time.

[0527] Specific examples

[0528] If you forget to take this morning's dose

[0529] 1. The user enters "Take 100mg of aspirin every morning" and sends it from the terminal to the server.

[0530] 2. The server stores this information in a database for future use.

[0531] 3. The user types a question such as, "I forgot to take my morning dose. What should I do?" and sends it from the device to the server.

[0532] 4. The server analyzes the question, inputs relevant data into the AI ​​model, and performs a simulation.

[0533] 5. Based on the simulation results, the server generates advice such as "wait until the next scheduled time to take your medication" and sends it to the terminal.

[0534] 6. The device displays the advice to the user.

[0535] If you accidentally take two doses

[0536] 1. The user enters "Take 100mg of aspirin every morning" and sends it from the terminal to the server.

[0537] 2. The server stores this information in a database for future use.

[0538] 3. The user types a question such as, "I accidentally took two doses. Is that okay?" and sends it from the device to the server.

[0539] 4. The server analyzes the question, inputs relevant data into the AI ​​model, and performs a simulation.

[0540] 5. Based on the simulation results, the server generates advice such as "There is a risk of overdose, so contact a doctor immediately" and sends it to the device.

[0541] 6. The device displays the advice to the user.

[0542] This allows users to know the appropriate course of action and maximize the effectiveness and safety of drug treatment.The present invention predicts drug blood concentrations in real time and realizes individualized medication management.

[0543] The processing flow will be explained below.

[0544] Step 1:

[0545] The user logs in to the system. User authentication is performed at the time of login, and if authentication is successful, a data entry screen is displayed.

[0546] Step 2:

[0547] The user enters their medication information, such as the name of the medication, dosage, and interval between doses, into the terminal and clicks the registration button.

[0548] Step 3:

[0549] The device sends the medication information entered by the user to the server, which packages the information in a standard data format such as JSON.

[0550] Step 4:

[0551] The server stores the received medication information in a database. When saving, it checks the data for consistency and whether there is any invalid data.

[0552] Step 5:

[0553] The server analyzes data on drug concentration trends collected from drug package inserts and interview forms, and formats the data necessary for the AI ​​model. This data is also stored in the database.

[0554] Step 6:

[0555] The user enters an inquiry such as "I forgot to take this morning's dose" or "I accidentally took two doses." After entering the information, the user clicks the "Send Inquiry" button.

[0556] Step 7:

[0557] The device sends the user's query to the server in text format.

[0558] Step 8:

[0559] The server analyzes the received query and extracts relevant medication information and drug concentration data.

[0560] Step 9:

[0561] The server inputs the extracted data into an AI model, which then simulates the progression of drug concentrations in the blood.

[0562] Step 10:

[0563] The server analyzes the simulation results obtained from the AI ​​model and generates appropriate advice, such as "wait until the next scheduled dose" or "contact your doctor immediately."

[0564] Step 11:

[0565] The server sends the generated advice to the terminal in text format.

[0566] Step 12:

[0567] The device will then display the received advice to the user, allowing them to know the appropriate response.

[0568] This enables the system of the present invention to provide appropriate advice in real time based on medication information entered by the user, maximizing the effectiveness and safety of drug treatment.

[0569] Example 1

[0570] 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."

[0571] In modern medicine management, there is a lack of means to quickly learn the appropriate response when users accidentally forget to take their medicine or take an overdose, which can lead to a decrease in the effectiveness of drug treatment and an increased risk of side effects.

[0572] 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.

[0573] In this invention, the server includes means for a user to input medication information, means for saving the input medication information in a database, means for accepting inquiries from users, means for analyzing the accepted inquiries using natural language processing, predicting blood drug concentrations using a generative AI model, and simulating changes in drug concentrations, means for generating appropriate advice based on the simulation results, and means for providing the generated advice to the user. This enables the user to quickly respond to situations such as forgetting to take medication or overdosing, and maximize the effectiveness of drug treatment.

[0574] A "user" is a person who uses the system to input medication information and make inquiries.

[0575] "Medication information" refers to information regarding the type, dosage, and time of administration of medicines taken by the user.

[0576] The "database" is a storage device that accumulates and stores data relating to medication information and drug concentration trends received by the server.

[0577] An "inquiry" is a question or confirmation that a user makes to the system, including any unclear points or problems regarding medication.

[0578] "Natural language processing" is a technology for analyzing text data such as user inquiries to understand their meaning and intent.

[0579] A "generative AI model" is an artificial intelligence model that uses received data to predict and simulate drug concentrations in the blood and generate appropriate advice.

[0580] "Simulation" refers to the computational process performed by the generative AI model to predict the progression of drug concentrations in the blood.

[0581] "Advice" refers to specific guidelines or suggestions provided to users based on the simulation results of the generative AI model.

[0582] "Additional information on drugs" refers to information including detailed data on drug concentration trends obtained from drug package inserts, interview forms, etc.

[0583] "Formatting" is the process of converting the input medication information into a format that is easy for the generative AI model to analyze.

[0584] MODE FOR CARRYING OUT THE INVENTION

[0585] The present invention is a system in which a user inputs medication information, and based on that information, AI predicts the progression of drug blood concentrations and provides appropriate advice. This system performs a series of processes: inputting medication information, accepting inquiries, managing a database, conducting simulations using AI, and generating advice. Specific embodiments of this system are described below.

[0586] Hardware and software used

[0587] Hardware:

[0588] Device: The smartphone, tablet, or computer where the user enters information

[0589] Server: Cloud server or dedicated server for storing data, simulations, and generating advice

[0590] software:

[0591] Database management systems (e.g., MySQL, PostgreSQL)

[0592] Natural Language Processing (NLP) tools (e.g., spaCy, NLTK)

[0593] Generative AI models (e.g., TensorFlow, PyTorch)

[0594] Communication protocol (e.g. HTTPS)

[0595] Program processing (natural language explanation)

[0596] 1. The user enters medication information using a terminal. For example, "Take 100 mg of aspirin every morning."

[0597] 2. The terminal sends the entered medication information to the server.

[0598] 3. The server stores the received medication information in a database, including additional information about the drug (such as the drug package insert and interview form data).

[0599] 4. The user enters the inquiry information using the terminal. For example, "I forgot to take my morning dose. What should I do?" or "I accidentally took two doses. Is that okay?"

[0600] 5. The terminal sends the query information to the server.

[0601] 6. The server uses natural language processing (NLP) to analyze the received query information and extract relevant data, which then forms the information needed for the generative AI model.

[0602] 7. The server uses a generative AI model to simulate the progression of drug blood concentrations based on the query. For example, the model can be implemented using PyTorch or TensorFlow.

[0603] 8. The server generates appropriate advice based on the simulation results, such as a specific action plan, such as whether to wait until the next scheduled medication dose or consult a doctor.

[0604] 9. The device displays the advice received from the server to the user.

[0605] Specific examples and prompt sentence examples

[0606] Specific examples

[0607] 1. If you forget to take this morning's dose

[0608] The user enters medication information such as "Take 100 mg of aspirin every morning" and sends it from the terminal to the server.

[0609] The server stores this information in a database.

[0610] The user enters a query such as "I forgot to take my morning dose. What should I do?" into the terminal and sends it to the server.

[0611] The server parses the query and feeds the data into a generative AI model.

[0612] The AI ​​model performs a simulation, and the server generates advice to "wait until the next scheduled medication time" and sends it to the device.

[0613] The device displays the advice to the user.

[0614] 2. If you accidentally take two doses

[0615] The user enters medication information such as "Take 100 mg of aspirin every morning" and sends it from the terminal to the server.

[0616] The server stores this information in a database.

[0617] The user enters a question into the terminal, such as "I accidentally took two doses. Is that okay?", and sends it to the server.

[0618] The server parses the query and feeds the data into a generative AI model.

[0619] The AI ​​model runs a simulation, and the server generates advice such as "There is a risk of overdose, so contact a doctor immediately" and sends it to the device.

[0620] The device displays the advice to the user.

[0621] Prompt Sentence Examples

[0622] 1. If you forget to take this morning's dose

[0623] A user takes 100mg of aspirin every morning and forgot to take their morning dose. Can you advise them on what to do next?

[0624] 2. If you accidentally take two doses

[0625] A user takes 100mg of aspirin every morning and accidentally takes two doses. Can you advise what to do next?

[0626] The above is an embodiment of the present invention. This system allows users to quickly respond to medication-related problems and maximize the effectiveness of drug therapy.

[0627] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0628] Step 1:

[0629] The user enters medication information.

[0630] Input: The user types "Take 100 mg of aspirin daily in the morning" into an application input field.

[0631] Specific operation: The user operates the device (smartphone or PC) and enters the required information in text format into the designated fields.

[0632] Output: Medication information is temporarily stored in the device's memory.

[0633] Step 2:

[0634] The terminal transmits medication information to the server.

[0635] Input: Medication information entered by the user.

[0636] Specific operation: The terminal sends the medication information entered via the Internet to the server using the HTTPS protocol.

[0637] Output: Medication information is sent to the server.

[0638] Step 3:

[0639] The server stores the received medication information in a database.

[0640] Input: Medication information received by the server.

[0641] Specific operation: The server converts the received medication information into an appropriate format and saves it in a database (MySQL, PostgreSQL, etc.). Here, for example, an SQL statement is generated to add data.

[0642] Output: Medication information is permanently stored in a database.

[0643] Step 4:

[0644] The user enters the inquiry information.

[0645] Input: The user types "I forgot my morning dose. What should I do?" into an application input field.

[0646] Specific actions: The user operates the device and enters the inquiry information in text format into the designated field.

[0647] Output: The query information is temporarily stored in the device's memory.

[0648] Step 5:

[0649] The terminal transmits the inquiry information to the server.

[0650] Input: The inquiry information entered by the user.

[0651] Specific operation: The terminal sends the query information to the server via the Internet using the HTTPS protocol.

[0652] Output: The query information is forwarded to the server.

[0653] Step 6:

[0654] The server analyzes the query and inputs it into a generative AI model.

[0655] Input: The query information received by the server.

[0656] What it does: The server uses natural language processing (NLP) tools to analyze the query and extract relevant data, such as spaCy to tokenize the text and extract important keywords.

[0657] Output: The analyzed information is formatted to be input into an AI model.

[0658] Step 7:

[0659] The AI ​​model simulates the drug's blood concentration.

[0660] Input: Formatted inquiry information and medication information.

[0661] How it works: The AI ​​model uses PyTorch, TensorFlow, etc. to run simulations based on query information. Specifically, it references existing medication data and uses a time-series prediction model to calculate drug concentrations in the blood.

[0662] Output: Simulation results are generated.

[0663] Step 8:

[0664] The server generates advice based on the simulation results.

[0665] Input: Simulation results obtained from the AI ​​model.

[0666] Specific operation: Based on the simulation results, the server generates appropriate advice using predefined templates, such as "wait until the next scheduled dose" or "consult a doctor."

[0667] Output: Advice is generated in text format.

[0668] Step 9:

[0669] The device displays the advice to the user.

[0670] Input: Advice sent by the server.

[0671] Specific operation: The device displays the advice received from the server on the application interface, specifically by using notifications or pop-up windows to present the advice to the user in an easy-to-read format.

[0672] Output: User receives advice and decides next action.

[0673] The above is a detailed description of the processing steps of the program of this system and the specific operations of each.

[0674] (Application example 1)

[0675] 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."

[0676] With existing medication management systems, it is difficult for users to receive appropriate advice in real time when they encounter problems such as forgetting to take a dose or overdosing. Furthermore, pharmacy and drugstore staff have limited means of providing prompt and appropriate advice to patients, making it difficult to maximize user safety and therapeutic effectiveness. The present invention was developed to solve these problems, and aims to increase practicality, particularly in pharmacies and drugstores.

[0677] 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.

[0678] In this invention, the server includes a means for inputting medication information, a means for storing the input medication information in a database, a means for accepting inquiries from users, a means for predicting blood drug concentrations using an AI model based on the accepted inquiries and simulating the progression of drug concentrations, a means for generating appropriate advice based on the simulation results, a means for providing the generated advice to the user, and a means for displaying the advice to staff wearing smart devices. This makes it possible to predict drug concentrations in real time from the input medication information and generate and provide appropriate advice. Furthermore, staff can use the smart devices to quickly communicate advice to users, making medication management for users more efficient and safe.

[0679] "Medicine medication information" is information about the medicines taken by the user, including, for example, the name of the medicine, dosage, and time of administration.

[0680] A "database" is a structured collection of data that efficiently stores and manages input information.

[0681] "Means for accepting inquiries from users" refers to an interface that allows users to input questions or problems, such as forgotten medication or overdose, into the system.

[0682] An "AI model" is a collection of algorithms and methods for analyzing data and making predictions using artificial intelligence technology.

[0683] "Means for predicting drug concentrations in the blood and simulating trends in drug concentrations" refers to means for using AI models to calculate and show fluctuations in drug concentrations in the body.

[0684] "Means for generating appropriate advice" refers to means for recommending actions and points of caution that are beneficial to the user based on the results of the simulation.

[0685] The "means for providing the generated advice to the user" refers to a means for notifying or displaying the generated advice to the user.

[0686] "Smart devices" are devices with internet connectivity, such as wearable devices and mobile devices, that allow users and staff to access information in real time.

[0687] This invention is a system in which users input medication information, and AI predicts changes in blood drug concentrations based on that information and provides appropriate advice. The invention is designed to enable staff at pharmacies and drug stores to efficiently provide appropriate advice to patients.

[0688] System configuration and operation

[0689] 1. Data Entry

[0690] The user (pharmacy staff) uses a smart device (e.g., smart glasses or a smartphone) to input medication information provided by the patient, such as "Take 100 mg of aspirin every morning."

[0691] 2. Data Transmission

[0692] The entered medication information is sent via smartphone to a cloud server, which stores the information in a database such as MySQL or PostgreSQL.

[0693] 3. AI-based predictions

[0694] The cloud server runs an AI model using Python and TensorFlow based on the stored medication information and data from drug package inserts and interview forms registered in the database. The AI ​​model simulates the progression of drug concentrations in the blood and outputs the results.

[0695] 4. Generating Advice

[0696] Based on the simulation results, the server uses a web framework such as Flask to generate appropriate advice, such as "You should wait until your next scheduled dose" or "You are at risk of overdose, so contact your doctor immediately."

[0697] 5. Providing advice

[0698] The generated advice is displayed on the smart glasses' display, allowing pharmacy staff to provide appropriate advice to patients in real time. By using the smart glasses in conjunction with the smartphone application, more detailed information can be viewed.

[0699] Specific examples

[0700] If you miss a dose:

[0701] 1. The server receives the user's input, "Take 100 mg of aspirin every morning," and stores it in a database.

[0702] 2. When the user types in a question such as "I forgot to take my morning dose," the information is sent to the server.

[0703] 3. The server runs an AI model based on the received question and generates advice such as, "You should wait until your next scheduled medication dose."

[0704] 4. Advice is displayed on the smart glasses display, and staff relays it to the patient.

[0705] In case of overdose:

[0706] 1. The server receives the user's input, "Take 100 mg of aspirin every morning," and stores it in a database.

[0707] 2. When the user types a question like, "I accidentally took two doses, is that okay?", the information is sent to the server.

[0708] 3. The server runs an AI model based on the received question and generates advice such as, "There is a risk of overdose, so contact your doctor immediately."

[0709] 4. Advice is displayed on the smart glasses display, and staff relays it to the patient.

[0710] Prompt Sentence Examples

[0711] A user has entered medication information. Medication Information: Aspirin 100mg daily in the morning. Question: I forgot to take my morning dose. Please provide appropriate advice.

[0712]

[0713] A user has entered medication information. Medication information: Take 100mg of aspirin every morning. Question: I accidentally took two doses. Is this ok? Please provide appropriate advice.

[0714] This enables the system to provide appropriate medication advice in real time, maximizing patient safety and therapeutic effectiveness.

[0715] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0716] Step 1:

[0717] The user enters medication information using a smart device. Specifically, the user enters information such as "Take 100 mg of aspirin every morning" through a smartphone app or smart glasses. The entered information is temporarily stored on the device.

[0718] Step 2:

[0719] The device sends the entered medication information to the cloud server. Specifically, the smartphone app issues an HTTP request over the Internet to send the data to the API endpoint of the cloud server. At this time, the data is serialized in JSON format.

[0720] Step 3:

[0721] The medication information received by the server is saved in a database. Specifically, the server uses Python to deserialize the received data and stores the information in a database such as MySQL or PostgreSQL. The saved information is used for subsequent processing.

[0722] Step 4:

[0723] The user enters additional information or a question (e.g., "I forgot my morning dose"), and the information entered through the smartphone app or smart glasses is temporarily stored on the device.

[0724] Step 5:

[0725] The device sends the added information and question to the cloud server. As in step 2, the data entered by the user is sent to the server using an HTTP request. This data is also serialized in JSON format.

[0726] Step 6:

[0727] The server analyzes the received question and inputs the relevant data into the AI ​​model. Specifically, it uses a web framework such as Flask to parse the query, retrieves relevant medication information from a database, and formats it into a data format to be input into the AI ​​model.

[0728] Step 7:

[0729] The server runs an AI model to predict drug concentrations in the blood and simulate their progression. Specifically, it supplies input data to an AI model using TensorFlow and executes model inference. To obtain simulation results, the model calculates multidimensional array data.

[0730] Step 8:

[0731] The server generates appropriate advice based on the simulation results. Specifically, it executes logic to generate messages such as "Wait until your next scheduled dose" or "Contact your doctor immediately as there is a risk of overdose" based on the inferred drug concentration.

[0732] Step 9:

[0733] The server provides the generated advice to the user. Specifically, it generates JSON data including the generated advice message as a response from the application and sends it to the user's device.

[0734] Step 10:

[0735] The device displays the received advice to the user. Specifically, the advice message is displayed on the smart glasses display, allowing the user to check it in real time. A notification is also sent to the smartphone app, which displays detailed information.

[0736] At each step, the input information undergoes the necessary data processing or calculation and is passed to the next step in an appropriate format, so that final advice can be provided to the user.

[0737] 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.

[0738] MODE FOR CARRYING OUT THE INVENTION

[0739] This invention combines a system in which a user inputs medication information, and AI predicts the progression of drug blood concentrations based on that information and provides appropriate advice, with an emotion engine that recognizes the user's emotions, to provide advice that is appropriate to the user's psychological state. The program processing of this system is shown below.

[0740] First, the user logs in to the system and enters medication information. For example, they enter information such as "Take 100 mg of aspirin every morning." This information is sent from the terminal to the server.

[0741] The server receives the user's input information and stores it in a database. At this time, the server also organizes user information by taking into account the drug concentration transition data collected from drug package inserts and interview forms, which are also registered in the database.

[0742] Next, the user makes a query such as "I forgot to take my morning dose" or "I accidentally took two doses." This query is sent from the device to the server, which analyzes the received query and inputs the relevant data into the AI ​​model.

[0743] The AI ​​model simulates the progression of drug blood levels. Based on the results of this simulation, the server generates appropriate advice, such as "It is best to wait until your next appointment or consult a doctor" or "There is a risk of overdose, so contact your doctor immediately."

[0744] Furthermore, the system of the present invention is equipped with an emotion engine that analyzes user input and voice data to recognize emotions. Based on the emotions recognized by the emotion engine, the server adjusts the content and format of advice. For example, if the user is feeling anxious, more reassuring and polite advice will be provided.

[0745] The server also monitors the user's emotional state over the long term and analyzes the history of emotional fluctuations, making it possible to assess the effectiveness of drug treatment and the risk of side effects based on the emotional fluctuations.

[0746] A specific example of processing will be shown below.

[0747] If you forget to take this morning's dose

[0748] 1. The user enters "Take 100mg of aspirin every morning" and sends it from the terminal to the server.

[0749] 2. The server stores this information in a database for future use.

[0750] 3. The user types a question such as, "I forgot to take my morning dose. What should I do?" and sends it from the device to the server.

[0751] 4. The server analyzes the question, inputs relevant data into the AI ​​model, and performs a simulation.

[0752] 5. Based on the simulation results, the server generates advice such as "wait until the next scheduled time to take your medication."

[0753] 6. The emotion engine analyzes user input and voice data and recognizes that the user is anxious.

[0754] 7. The server provides more polite and reassuring advice to anxious users.

[0755] 8. The device displays the advice to the user.

[0756] If you accidentally take two doses

[0757] 1. The user enters "Take 100mg of aspirin every morning" and sends it from the terminal to the server.

[0758] 2. The server stores this information in a database for future use.

[0759] 3. The user types a question such as, "I accidentally took two doses. Is that okay?" and sends it from the device to the server.

[0760] 4. The server analyzes the question, inputs relevant data into the AI ​​model, and performs a simulation.

[0761] 5. Based on the simulation results, the server generates advice such as "There is a risk of overdose, so contact a doctor immediately."

[0762] 6. The emotion engine analyzes the user's input and voice data and recognizes that the user is in a panic.

[0763] 7. The server provides calming advice to panicked users, encouraging them to stay calm.

[0764] 8. The device displays the advice to the user.

[0765] In this way, by combining the emotion engine, the system of the present invention can provide personalized advice based on the user's psychological state, maximizing the effectiveness and safety of drug treatment.

[0766] The processing flow will be explained below.

[0767] If you forget to take this morning's dose

[0768] Step 1:

[0769] The user logs in to the system. User authentication is performed at login, and if authentication is successful, a data entry screen is displayed.

[0770] Step 2:

[0771] The user enters their medication information, for example, "Take 100 mg of aspirin every morning," into the terminal and clicks the registration button.

[0772] Step 3:

[0773] The device sends the medication information entered by the user to the server, which packages the information in a standard data format such as JSON.

[0774] Step 4:

[0775] The server stores the received medication information in a database. When saving, it checks the data for consistency and whether there is any invalid data.

[0776] Step 5:

[0777] The server analyzes data on drug concentration trends collected from drug package inserts and interview forms, and formats the data necessary for the AI ​​model. This data is also stored in the database.

[0778] Step 6:

[0779] The user types in a query such as "I forgot to take my morning dose, what should I do?" and clicks the send button.

[0780] Step 7:

[0781] The device sends the user's query to the server in text format.

[0782] Step 8:

[0783] The server analyzes the received query and inputs relevant medication information and drug concentration data into the AI ​​model.

[0784] Step 9:

[0785] The server uses an AI model to simulate the progression of drug blood concentrations.

[0786] Step 10:

[0787] The server analyzes the simulation results and generates advice such as "wait until the next scheduled time to take your medication."

[0788] Step 11:

[0789] The emotion engine analyzes user input and voice data and recognizes that the user is anxious.

[0790] Step 12:

[0791] The server generates more polite and reassuring advice for anxious users and sends it to their terminals.

[0792] Step 13:

[0793] The device will display advice to the user, allowing them to know the appropriate response.

[0794] If you accidentally take two doses

[0795] Step 1:

[0796] The user logs in to the system. User authentication is performed at login, and if authentication is successful, a data entry screen is displayed.

[0797] Step 2:

[0798] The user enters their medication information, for example, "Take 100 mg of aspirin every morning," into the terminal and clicks the registration button.

[0799] Step 3:

[0800] The device sends the medication information entered by the user to the server, which packages the information in a standard data format such as JSON.

[0801] Step 4:

[0802] The server stores the received medication information in a database. When saving, it checks the data for consistency and whether there is any invalid data.

[0803] Step 5:

[0804] The server analyzes data on drug concentration trends collected from drug package inserts and interview forms, and formats the data necessary for the AI ​​model. This data is also stored in the database.

[0805] Step 6:

[0806] The user types in a query such as "I accidentally took two doses, what should I do?" and clicks the send button.

[0807] Step 7:

[0808] The device sends the user's query to the server in text format.

[0809] Step 8:

[0810] The server analyzes the received query and inputs relevant medication information and drug concentration data into the AI ​​model.

[0811] Step 9:

[0812] The server uses an AI model to simulate the progression of drug blood concentrations.

[0813] Step 10:

[0814] The server analyzes the simulation results and generates advice such as "There is a risk of overdose, so contact a doctor immediately."

[0815] Step 11:

[0816] The emotion engine analyzes user input and voice data and recognizes when the user is in a panic.

[0817] Step 12:

[0818] The server generates calm advice for panicked users, urging them to stay calm, and sends it to their devices.

[0819] Step 13:

[0820] The device will display advice to the user, allowing them to know the appropriate response.

[0821] In this way, by combining the emotion engine, the system of the present invention can provide personalized advice based on the user's psychological state, maximizing the effectiveness and safety of drug treatment.

[0822] Example 2

[0823] 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."

[0824] Conventional medication management systems can predict drug blood concentrations and provide advice based on medication information entered by the user, but it has been difficult to provide personalized advice that takes into account the user's psychological state. As a result, these systems have not been effective enough in reducing the user's psychological burden and anxiety regarding medication and health management. To address this issue, the present invention aims to provide a system that recognizes the user's emotions and provides personalized advice based on them.

[0825] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for inputting medication information of a drug; means for saving the input medication information in a database; means for accepting inquiries from a user; means for predicting drug concentrations in blood using an artificial intelligence model based on the accepted inquiries and simulating the progress of drug concentrations; means for generating appropriate advice based on the simulation results; means for providing an emotion engine for recognizing emotions by analyzing user input and voice data; means for adjusting the advice content based on the recognized emotions; and means for providing the generated advice to the user. This makes it possible to provide personalized advice that takes into account the psychological state of the user.

[0826] The "means for inputting medication information" refers to an interface that allows a user to input information such as the name, dosage, and time of administration of the medication via a terminal.

[0827] The "means for saving input medication information in a database" is a server-side function that registers the medication information input by the user in a database so that it can be referenced later.

[0828] "Means for accepting inquiries from users" refers to an interface that allows users to send questions or inquiries to the system, and the server receives this information.

[0829] "Means for predicting drug concentrations in the blood using an artificial intelligence model and simulating trends in drug concentrations" refers to a program that uses AI technology to predict fluctuations in drug concentrations in the blood based on input medication information and related data, and simulates those trends.

[0830] "Means for generating appropriate advice based on simulation results" refers to a server-side function that generates appropriate behavioral instructions and advice for users based on the simulation results obtained by the AI ​​model.

[0831] An "emotion engine that recognizes emotions by analyzing user input and voice data" is an engine that determines the user's emotions and psychological state at that time by analyzing the text and voice data entered by the user.

[0832] The "means for adjusting the advice content based on the recognized emotions" is a server-side function for appropriately changing the content and expression of the advice provided according to the user's emotional state recognized by the emotion engine.

[0833] The "means for providing generated advice to the user" is an interface for displaying the advice generated by the system to the user via a terminal.

[0834] "Means of collecting data on changes in drug concentration from drug package inserts and interview forms and registering it in a database" refers to a function that extracts data on changes in drug blood concentration from official drug documents and questionnaires, and registers that data in a database.

[0835] MODE FOR CARRYING OUT THE INVENTION

[0836] This invention combines a system in which medication information is input, and AI predicts changes in blood drug concentrations based on that information and provides appropriate advice, with an emotion engine that recognizes the user's emotions, to provide advice that is tailored to the user's psychological state. Specific embodiments of this system are described below.

[0837] First, a user logs in to the system and enters medication information. For example, the user enters that they take 100 mg of aspirin every morning. This information is sent from the user's device to the server. The device packages the entered information in JSON format and sends an HTTP POST request to the server.

[0838] The server then stores the medication information in a database, typically using a database management system (DBMS). The server receives the HTTP request, analyzes the data, and then executes an SQL query to insert the information into the user table in the database.

[0839] After receiving and saving the medication information, the server accepts inquiries from the user. The user types "I forgot to take my morning dose. What should I do?" into the chat box on the device's application screen and clicks the send button. The device then sends this inquiry to the server as an HTTP POST request.

[0840] The server analyzes the received query using a natural language processing (NLP) engine. The analyzed query content, along with related drug data, is then input into an AI model. The AI ​​model uses machine learning algorithms to simulate the progression of drug concentrations in the blood based on medication information and drug data. This simulation uses information from existing datasets and drug package inserts.

[0841] The simulation results generated by the AI ​​model are used by the server to generate appropriate advice, such as "It is best to wait until your next scheduled dose" or "There is a risk of overdose, so contact your doctor immediately."

[0842] Furthermore, the server is equipped with an emotion engine that recognizes emotions using user input and voice data. The emotion engine analyzes whether the user is feeling anxious or panicked. For example, if the user inputs, "I forgot my morning dose. What should I do?", the emotion engine will recognize that the user is anxious.

[0843] Based on this recognition, the server can adjust the content and format of the advice it generates: if a user feels anxious, it will provide advice in more reassuring language. In this way, the system can provide personalized advice that takes into account the user's psychological state.

[0844] As an example, the following scenario can be considered.

[0845] Example of what to do if you forget to take this morning's dose

[0846] 1. The user enters "Take 100mg of aspirin every morning" and sends it from the terminal to the server.

[0847] Example prompt: "Take 100 mg of aspirin every morning."

[0848] 2. The server stores this information in a database for future use.

[0849] 3. The user types a question such as, "I forgot to take my morning dose. What should I do?" and sends it from the device to the server.

[0850] Example prompt: "I forgot to take my morning dose. What should I do?"

[0851] 4. The server analyzes the question, inputs relevant data into the AI ​​model, and performs a simulation.

[0852] 5. Based on the simulation results, the server generates advice such as "wait until the next scheduled time to take your medication."

[0853] Sample prompt: "It's best to wait until your next scheduled dose."

[0854] 6. The emotion engine analyzes user input and voice data and recognizes that the user is anxious.

[0855] 7. The server provides more polite and reassuring advice to anxious users.

[0856] Sample prompt: "Don't worry. It's best to wait until your next dose. However, if you're concerned, talk to your doctor."

[0857] 8. The device displays the advice to the user.

[0858] In this way, the system of the present invention aims to improve the effectiveness and safety of drug treatment by combining an emotion engine to provide optimal advice according to the user's psychological state.

[0859] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0860] Processing Steps

[0861] Step 1:

[0862] The user logs into the system and enters medication information.

[0863] Input: A user enters "Take 100mg of aspirin daily in the morning" into a form.

[0864] Specific actions: The user enters medication information into the form on the application screen and clicks the submit button.

[0865] Output: The device converts the user's input information into JSON format and generates an HTTP POST request.

[0866] Step 2:

[0867] The terminal transmits the entered medication information to the server.

[0868] Input: The HTTP POST request generated by the device.

[0869] Specific operation: The device stores JSON format data in the body of the HTTP request and sends the request to the specified server endpoint.

[0870] Output: The server receives the HTTP request.

[0871] Step 3:

[0872] The server stores the received medication information in a database.

[0873] Input: Medication information received by the server in JSON format.

[0874] Specific operation: The server parses the JSON format data and saves it by issuing an INSERT query to the corresponding table in the database.

[0875] Output: A new record is added to the database.

[0876] Step 4:

[0877] The user inputs a question about medication and sends it from the terminal to the server.

[0878] Input: User types in chat box, "I forgot my morning dose. What should I do?"

[0879] Specific Actions: The user types a query into the chat box and clicks the send button.

[0880] Output: The terminal converts the query content into JSON format and generates an HTTP POST request.

[0881] Step 5:

[0882] The terminal sends the inquiry to the server.

[0883] Input: The HTTP POST request generated by the device.

[0884] Specific operation: The terminal stores the query content in JSON format in the body of an HTTP request and sends it to the server.

[0885] Output: The server receives the HTTP request.

[0886] Step 6:

[0887] The server analyzes the query and inputs the relevant data into the AI ​​model.

[0888] Input: The query received by the server in JSON format.

[0889] Specific operation: The server uses a natural language processing (NLP) engine to analyze the query, extract relevant data such as drug information, and input it into the AI ​​model.

[0890] Output: The AI ​​model is provided with input data.

[0891] Step 7:

[0892] The AI ​​model simulates the progression of drug blood concentrations.

[0893] Input: Medication information and related data fed into the AI ​​model.

[0894] How it works: The AI ​​model uses a trained neural network to predict and simulate time series data of drug concentrations in the blood.

[0895] Output: As a result of the simulation, data on the drug concentration over time is generated.

[0896] Step 8:

[0897] The server generates advice based on the simulation results.

[0898] Input: Simulation results provided by the AI ​​model.

[0899] Specific operation: The server obtains the simulation results and generates appropriate advice (e.g., "wait until the next scheduled medication time") using a rule-based engine.

[0900] Output: The generated advice is provided in text format.

[0901] Step 9:

[0902] The emotion engine analyzes user input and voice data to recognize emotions.

[0903] Input: User-provided input text or voice data.

[0904] What it does: The emotion engine uses text and speech recognition technology to determine the user's emotion (e.g., anxiety, panic).

[0905] Output: The emotion recognition result is the user's emotional state.

[0906] Step 10:

[0907] The advice content is adjusted based on the emotion recognized by the server.

[0908] Input: Emotion recognition results from the emotion engine and initial advice content.

[0909] Specific operation: The server takes into account the emotion recognition results and adjusts the wording of the advice (e.g., changes the wording to make it more reassuring).

[0910] Output: An emotion-adjusted advice is generated.

[0911] Step 11:

[0912] The device displays the advice to the user.

[0913] Input: The final advice provided by the server.

[0914] Specific operation: The device receives the advice content and displays it on the user interface (UI).

[0915] Output: The advice is ready for the user to review.

[0916] Through this process, the system can provide personalized advice based on the information entered by the user, using AI models and emotion engines.

[0917] (Application example 2)

[0918] 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."

[0919] In recent years, there has been an increasing need for more efficient and effective medication management. It is particularly important to provide prompt and accurate advice when users forget to take their medication or overdose. However, conventional systems only provide standardized advice without taking into account the user's emotional state. Therefore, there is a problem in that it is difficult to provide appropriate support when the user is feeling anxious or panicked.

[0920] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for inputting medication information on drugs; means for saving the input medication information in a database; means for accepting inquiries from users; means for predicting blood drug concentrations using an AI model based on the accepted inquiries and simulating the progress of drug concentrations; means for generating appropriate advice based on the simulation results; means for providing the generated advice to the user; means for having an emotion analysis engine and analyzing user input and voice data to recognize emotions; and means for providing appropriate advice content and format based on the recognized emotions. This makes it possible to provide personalized advice according to the user's emotional state, maximizing the effectiveness and safety of drug treatment.

[0921] "Pharmaceuticals" is a general term for chemicals and biological products used for the prevention, diagnosis, treatment, or alleviation of disease.

[0922] "Medication information" refers to data regarding the name, dosage, and timing of taking the medication the user is taking.

[0923] A "database" is an information collection system that systematically accumulates information and is designed to make it easy to search and manage.

[0924] "Inquiries" refer to questions, doubts, or inquiries that users have about the system they use.

[0925] An "AI model" is a computational algorithm or statistical model that mimics human intelligence and is capable of learning, reasoning, and self-improvement.

[0926] "Blood drug concentration" is data that indicates the amount of a particular drug present in a user's blood.

[0927] "Simulation" is a technical technique for virtually reproducing real-world situations and phenomena and conducting analysis and predictions.

[0928] "Appropriate advice" refers to specific and accurate instructions and recommendations provided based on simulation results and data analysis.

[0929] An "emotion analysis engine" is a technology that analyzes a user's text input and voice data and automatically recognizes their emotional state (joy, anger, sadness, happiness, etc.).

[0930] "Input and voice data" means text messages and voice utterances that a user enters into the system.

[0931] This invention is a system in which users input their medication information, and AI predicts the progression of drug blood concentrations based on that information and provides appropriate advice. By combining this with an emotion analysis engine that recognizes the user's emotions, the system provides advice tailored to the user's psychological state. This system is particularly applicable as a customer support app in brick-and-mortar stores (pharmacies and drugstores).

[0932] System configuration

[0933] The system consists of the following main components:

[0934] 1. User terminal: A device (such as a smartphone) through which the user enters medication information.

[0935] 2. Server: A computer system that holds a database and runs AI models and sentiment analysis engines.

[0936] 3. Database: A system (such as MongoDB) for storing drug concentration trend data and user medication information.

[0937] Program processing

[0938] The processing of this program consists of the following major steps:

[0939] 1. Getting user input:

[0940] Users enter information about their medication (such as name, dosage, and timing of administration) via a smartphone app, which is then sent from the device to a server.

[0941] 2. Data storage:

[0942] The server stores the received medication information in a database, which also includes data collected from drug package inserts and interview forms.

[0943] 3. User Inquiries:

[0944] Users can use the app to make inquiries such as, "I forgot to take my morning dose" or "I accidentally took two doses."

[0945] 4. Simulation using AI models:

[0946] Based on the queries received, the server uses an AI model (using PyTorch) to predict the progression of drug concentrations in the blood.

[0947] 5. Generating Advice:

[0948] Based on the simulation results, the server generates appropriate advice, using a sentiment analysis engine (using Google Cloud Natural Language API) to analyze the user's sentiment and provide advice accordingly.

[0949] 6. Providing advice:

[0950] The generated advice is sent to the terminal and displayed to the user.

[0951] Technical details

[0952] Hardware and software used:

[0953] User device: Smartphone (iOS or Android)

[0954] Server: Backend built with Node.js and Express

[0955] Database: MongoDB

[0956] AI Simulation: PyTorch

[0957] Sentiment analysis engine: Google Cloud Natural Language API

[0958] Specific examples

[0959] If you forget to take this morning's dose

[0960] 1. The user enters "Take 100mg of aspirin every morning" and sends it from the terminal to the server.

[0961] 2. The server stores this information in a database.

[0962] 3. The user types a question such as, "I forgot to take my morning dose. What should I do?" and sends it from the device to the server.

[0963] 4. The server analyzes the question, inputs relevant data into the AI ​​model, and performs a simulation.

[0964] 5. Based on the simulation results, the server generates advice such as "wait until the next scheduled time to take your medication."

[0965] 6. The sentiment analysis engine analyzes user input and voice data and recognizes that the user is anxious.

[0966] 7. The server provides more reassuring and courteous advice to anxious users.

[0967] 8. The device displays the advice to the user.

[0968] Prompt Sentence Examples

[0969] When a user sends a question such as "I forgot to take my medicine this morning. What should I do?", the prompt text is "Please provide advice about the next dose time. The user is feeling anxious, so please provide reassuring advice." Based on this prompt, the AI ​​model generates advice such as "Please wait until the next scheduled dose time. Also, if you feel anxious, it is best to consult a doctor. Rest assured that this will be resolved quickly."

[0970] As described above, the system of the present invention can maximize the effectiveness and safety of drug treatment by providing personalized advice that takes into account the user's emotional state.

[0971] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0972] Step 1:

[0973] Users open the app on their smartphone and enter information about their medication (such as name, dosage, and timing of administration). This information is sent from the device to the server. Input is done using text fields and drop-down menus, and the data is sent by pressing the send button. The input data includes the name of the medication, dosage, and timing of administration.

[0974] Step 2:

[0975] The server stores the received medication information in a database (MongoDB). After receiving the request, the server parses the information and stores it in the appropriate table (collection) in the database. The output is the medication information stored in the database.

[0976] Step 3:

[0977] Users input their questions (e.g., "I forgot to take my morning dose," "I accidentally took two doses," etc.) through a smartphone app and send them to the server from their device. A text field is used for input, and the question is sent by pressing the send button. The input data includes the question text.

[0978] Step 4:

[0979] The server provides the necessary data to the AI ​​model (using PyTorch) based on the received query, predicting the progression of drug concentrations in the blood. The server processes the received query, retrieves relevant medication information from the database, and inputs it into the AI ​​model. The output is simulated data on the progression of drug concentrations in the blood.

[0980] Step 5:

[0981] The server generates appropriate advice based on the simulation results. In doing so, it uses a sentiment analysis engine (using the Google Cloud Natural Language API) to analyze the user's emotional state. The server compares the simulation results with the query text and generates optimal advice. The sentiment analysis engine detects emotions from the user's input text and incorporates this emotional information into the advice generation process. The output is advice that takes the user's emotional state into account.

[0982] Step 6:

[0983] The server sends the generated advice to the terminal and provides it to the user.The server sends the generated advice to the user's terminal so that the user can view the advice on the screen.As an output, the advice displayed on the user's smartphone screen is obtained.

[0984] Step 7:

[0985] The user checks the advice displayed on the device and takes the next action if necessary. The user reads the advice and takes action (e.g., wait until the next appointment time, consult a doctor, etc.). The output is a decision on the user's action.

[0986] Through these steps, the system can provide personalized advice based on the user's emotional state, maximizing the effectiveness and safety of drug treatment.

[0987] 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.

[0988] 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.

[0989] 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.

[0990] [Third embodiment]

[0991] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0992] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0993] 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).

[0994] 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.

[0995] 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.

[0996] 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).

[0997] 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.

[0998] 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.

[0999] 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.

[1000] 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.

[1001] 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.

[1002] 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."

[1003] MODE FOR CARRYING OUT THE INVENTION

[1004] This invention is a system in which users input medication information, and AI predicts the progression of drug blood concentrations based on that information and provides appropriate advice. The program processing of this system is shown below.

[1005] First, the user logs in to the system and enters medication information. For example, they enter information such as "Take 100 mg of aspirin every morning." This information is sent from the terminal to the server.

[1006] The server receives the user's input information and stores it in a database. At this time, the server also organizes the user information by taking into account data on drug concentration trends collected from drug package inserts and interview forms, which are also registered in the database.

[1007] Next, the user makes a query such as "I forgot to take my morning dose" or "I accidentally took two doses." This query is sent from the device to the server, which analyzes the received query and inputs the relevant data into the AI ​​model.

[1008] The AI ​​model simulates the progression of drug blood levels. Based on the results of this simulation, the server generates appropriate advice, such as "It is best to wait until your next appointment or consult a doctor" or "There is a risk of overdose, so contact your doctor immediately."

[1009] Finally, the generated advice is displayed to the user via the device, allowing the user to know the appropriate response in real time.

[1010] Specific examples

[1011] If you forget to take this morning's dose

[1012] 1. The user enters "Take 100mg of aspirin every morning" and sends it from the terminal to the server.

[1013] 2. The server stores this information in a database for future use.

[1014] 3. The user types a question such as, "I forgot to take my morning dose. What should I do?" and sends it from the device to the server.

[1015] 4. The server analyzes the question, inputs relevant data into the AI ​​model, and performs a simulation.

[1016] 5. Based on the simulation results, the server generates advice such as "wait until the next scheduled time to take your medication" and sends it to the terminal.

[1017] 6. The device displays the advice to the user.

[1018] If you accidentally take two doses

[1019] 1. The user enters "Take 100mg of aspirin every morning" and sends it from the terminal to the server.

[1020] 2. The server stores this information in a database for future use.

[1021] 3. The user types a question such as, "I accidentally took two doses. Is that okay?" and sends it from the device to the server.

[1022] 4. The server analyzes the question, inputs relevant data into the AI ​​model, and performs a simulation.

[1023] 5. Based on the simulation results, the server generates advice such as "There is a risk of overdose, so contact a doctor immediately" and sends it to the device.

[1024] 6. The device displays the advice to the user.

[1025] This allows users to know the appropriate course of action and maximize the effectiveness and safety of drug treatment.The present invention predicts drug blood concentrations in real time and realizes individualized medication management.

[1026] The processing flow will be explained below.

[1027] Step 1:

[1028] The user logs in to the system. User authentication is performed at the time of login, and if authentication is successful, a data entry screen is displayed.

[1029] Step 2:

[1030] The user enters their medication information, such as the name of the medication, dosage, and interval between doses, into the terminal and clicks the registration button.

[1031] Step 3:

[1032] The device sends the medication information entered by the user to the server, which packages the information in a standard data format such as JSON.

[1033] Step 4:

[1034] The server stores the received medication information in a database. When saving, it checks the data for consistency and whether there is any invalid data.

[1035] Step 5:

[1036] The server analyzes data on drug concentration trends collected from drug package inserts and interview forms, and formats the data necessary for the AI ​​model. This data is also stored in the database.

[1037] Step 6:

[1038] The user enters an inquiry such as "I forgot to take this morning's dose" or "I accidentally took two doses." After entering the information, the user clicks the "Send Inquiry" button.

[1039] Step 7:

[1040] The device sends the user's query to the server in text format.

[1041] Step 8:

[1042] The server analyzes the received query and extracts relevant medication information and drug concentration data.

[1043] Step 9:

[1044] The server inputs the extracted data into an AI model, which then simulates the progression of drug concentrations in the blood.

[1045] Step 10:

[1046] The server analyzes the simulation results obtained from the AI ​​model and generates appropriate advice, such as "wait until the next scheduled dose" or "contact your doctor immediately."

[1047] Step 11:

[1048] The server sends the generated advice to the terminal in text format.

[1049] Step 12:

[1050] The device will then display the received advice to the user, allowing them to know the appropriate response.

[1051] This enables the system of the present invention to provide appropriate advice in real time based on medication information entered by the user, maximizing the effectiveness and safety of drug treatment.

[1052] Example 1

[1053] 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."

[1054] In modern medicine management, there is a lack of means to quickly learn the appropriate response when users accidentally forget to take their medicine or take an overdose, which can lead to a decrease in the effectiveness of drug treatment and an increased risk of side effects.

[1055] 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.

[1056] In this invention, the server includes means for a user to input medication information, means for saving the input medication information in a database, means for accepting inquiries from users, means for analyzing the accepted inquiries using natural language processing, predicting blood drug concentrations using a generative AI model, and simulating changes in drug concentrations, means for generating appropriate advice based on the simulation results, and means for providing the generated advice to the user. This enables the user to quickly respond to situations such as forgetting to take medication or overdosing, and maximize the effectiveness of drug treatment.

[1057] A "user" is a person who uses the system to input medication information and make inquiries.

[1058] "Medication information" refers to information regarding the type, dosage, and time of administration of medicines taken by the user.

[1059] The "database" is a storage device that accumulates and stores data relating to medication information and drug concentration trends received by the server.

[1060] An "inquiry" is a question or confirmation that a user makes to the system, including any unclear points or problems regarding medication.

[1061] "Natural language processing" is a technology for analyzing text data such as user inquiries to understand their meaning and intent.

[1062] A "generative AI model" is an artificial intelligence model that uses received data to predict and simulate drug concentrations in the blood and generate appropriate advice.

[1063] "Simulation" refers to the computational process performed by the generative AI model to predict the progression of drug concentrations in the blood.

[1064] "Advice" refers to specific guidelines or suggestions provided to users based on the simulation results of the generative AI model.

[1065] "Additional information on drugs" refers to information including detailed data on drug concentration trends obtained from drug package inserts, interview forms, etc.

[1066] "Formatting" is the process of converting the input medication information into a format that is easy for the generative AI model to analyze.

[1067] MODE FOR CARRYING OUT THE INVENTION

[1068] The present invention is a system in which a user inputs medication information, and based on that information, AI predicts the progression of drug blood concentrations and provides appropriate advice. This system performs a series of processes: inputting medication information, accepting inquiries, managing a database, conducting simulations using AI, and generating advice. Specific embodiments of this system are described below.

[1069] Hardware and software used

[1070] Hardware:

[1071] Device: The smartphone, tablet, or computer where the user enters information

[1072] Server: Cloud server or dedicated server for storing data, simulations, and generating advice

[1073] software:

[1074] Database management systems (e.g., MySQL, PostgreSQL)

[1075] Natural Language Processing (NLP) tools (e.g., spaCy, NLTK)

[1076] Generative AI models (e.g., TensorFlow, PyTorch)

[1077] Communication protocol (e.g. HTTPS)

[1078] Program processing (natural language explanation)

[1079] 1. The user enters medication information using a terminal. For example, "Take 100 mg of aspirin every morning."

[1080] 2. The terminal sends the entered medication information to the server.

[1081] 3. The server stores the received medication information in a database, including additional information about the drug (such as the drug package insert and interview form data).

[1082] 4. The user enters the inquiry information using the terminal. For example, "I forgot to take my morning dose. What should I do?" or "I accidentally took two doses. Is that okay?"

[1083] 5. The terminal sends the query information to the server.

[1084] 6. The server uses natural language processing (NLP) to analyze the received query information and extract relevant data, which then forms the information needed for the generative AI model.

[1085] 7. The server uses a generative AI model to simulate the progression of drug blood concentrations based on the query. For example, the model can be implemented using PyTorch or TensorFlow.

[1086] 8. The server generates appropriate advice based on the simulation results, such as a specific action plan, such as whether to wait until the next scheduled medication dose or consult a doctor.

[1087] 9. The device displays the advice received from the server to the user.

[1088] Specific examples and prompt sentence examples

[1089] Specific examples

[1090] 1. If you forget to take this morning's dose

[1091] The user enters medication information such as "Take 100 mg of aspirin every morning" and sends it from the terminal to the server.

[1092] The server stores this information in a database.

[1093] The user enters a query such as "I forgot to take my morning dose. What should I do?" into the terminal and sends it to the server.

[1094] The server parses the query and feeds the data into a generative AI model.

[1095] The AI ​​model performs a simulation, and the server generates advice to "wait until the next scheduled medication time" and sends it to the device.

[1096] The device displays the advice to the user.

[1097] 2. If you accidentally take two doses

[1098] The user enters medication information such as "Take 100 mg of aspirin every morning" and sends it from the terminal to the server.

[1099] The server stores this information in a database.

[1100] The user enters a question into the terminal, such as "I accidentally took two doses. Is that okay?", and sends it to the server.

[1101] The server parses the query and feeds the data into a generative AI model.

[1102] The AI ​​model runs a simulation, and the server generates advice such as "There is a risk of overdose, so contact a doctor immediately" and sends it to the device.

[1103] The device displays the advice to the user.

[1104] Prompt Sentence Examples

[1105] 1. If you forget to take this morning's dose

[1106] A user takes 100mg of aspirin every morning and forgot to take their morning dose. Can you advise them on what to do next?

[1107] 2. If you accidentally take two doses

[1108] A user takes 100mg of aspirin every morning and accidentally takes two doses. Can you advise what to do next?

[1109] The above is an embodiment of the present invention. This system allows users to quickly respond to medication-related problems and maximize the effectiveness of drug therapy.

[1110] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1111] Step 1:

[1112] The user enters medication information.

[1113] Input: The user types "Take 100 mg of aspirin daily in the morning" into an application input field.

[1114] Specific operation: The user operates the device (smartphone or PC) and enters the required information in text format into the designated fields.

[1115] Output: Medication information is temporarily stored in the device's memory.

[1116] Step 2:

[1117] The terminal transmits medication information to the server.

[1118] Input: Medication information entered by the user.

[1119] Specific operation: The terminal sends the medication information entered via the Internet to the server using the HTTPS protocol.

[1120] Output: Medication information is sent to the server.

[1121] Step 3:

[1122] The server stores the received medication information in a database.

[1123] Input: Medication information received by the server.

[1124] Specific operation: The server converts the received medication information into an appropriate format and saves it in a database (MySQL, PostgreSQL, etc.). Here, for example, an SQL statement is generated to add data.

[1125] Output: Medication information is permanently stored in a database.

[1126] Step 4:

[1127] The user enters the inquiry information.

[1128] Input: The user types "I forgot my morning dose. What should I do?" into an application input field.

[1129] Specific actions: The user operates the device and enters the inquiry information in text format into the designated field.

[1130] Output: The query information is temporarily stored in the device's memory.

[1131] Step 5:

[1132] The terminal transmits the inquiry information to the server.

[1133] Input: The inquiry information entered by the user.

[1134] Specific operation: The terminal sends the query information to the server via the Internet using the HTTPS protocol.

[1135] Output: The query information is forwarded to the server.

[1136] Step 6:

[1137] The server analyzes the query and inputs it into a generative AI model.

[1138] Input: The query information received by the server.

[1139] What it does: The server uses natural language processing (NLP) tools to analyze the query and extract relevant data, such as spaCy to tokenize the text and extract important keywords.

[1140] Output: The analyzed information is formatted to be input into an AI model.

[1141] Step 7:

[1142] The AI ​​model simulates the drug's blood concentration.

[1143] Input: Formatted inquiry information and medication information.

[1144] How it works: The AI ​​model uses PyTorch, TensorFlow, etc. to run simulations based on query information. Specifically, it references existing medication data and uses a time-series prediction model to calculate drug concentrations in the blood.

[1145] Output: Simulation results are generated.

[1146] Step 8:

[1147] The server generates advice based on the simulation results.

[1148] Input: Simulation results obtained from the AI ​​model.

[1149] Specific operation: Based on the simulation results, the server generates appropriate advice using predefined templates, such as "wait until the next scheduled dose" or "consult a doctor."

[1150] Output: Advice is generated in text format.

[1151] Step 9:

[1152] The device displays the advice to the user.

[1153] Input: Advice sent by the server.

[1154] Specific operation: The device displays the advice received from the server on the application interface, specifically by using notifications or pop-up windows to present the advice to the user in an easy-to-read format.

[1155] Output: User receives advice and decides next action.

[1156] The above is a detailed description of the processing steps of the program of this system and the specific operations of each.

[1157] (Application example 1)

[1158] 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."

[1159] With existing medication management systems, it is difficult for users to receive appropriate advice in real time when they encounter problems such as forgetting to take a dose or overdosing. Furthermore, pharmacy and drugstore staff have limited means of providing prompt and appropriate advice to patients, making it difficult to maximize user safety and therapeutic effectiveness. The present invention was developed to solve these problems, and aims to increase practicality, particularly in pharmacies and drugstores.

[1160] 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.

[1161] In this invention, the server includes a means for inputting medication information, a means for storing the input medication information in a database, a means for accepting inquiries from users, a means for predicting blood drug concentrations using an AI model based on the accepted inquiries and simulating the progression of drug concentrations, a means for generating appropriate advice based on the simulation results, a means for providing the generated advice to the user, and a means for displaying the advice to staff wearing smart devices. This makes it possible to predict drug concentrations in real time from the input medication information and generate and provide appropriate advice. Furthermore, staff can use the smart devices to quickly communicate advice to users, making medication management for users more efficient and safe.

[1162] "Medicine medication information" is information about the medicines taken by the user, including, for example, the name of the medicine, dosage, and time of administration.

[1163] A "database" is a structured collection of data that efficiently stores and manages input information.

[1164] "Means for accepting inquiries from users" refers to an interface that allows users to input questions or problems, such as forgotten medication or overdose, into the system.

[1165] An "AI model" is a collection of algorithms and methods for analyzing data and making predictions using artificial intelligence technology.

[1166] "Means for predicting drug concentrations in the blood and simulating trends in drug concentrations" refers to means for using AI models to calculate and show fluctuations in drug concentrations in the body.

[1167] "Means for generating appropriate advice" refers to means for recommending actions and points of caution that are beneficial to the user based on the results of the simulation.

[1168] The "means for providing the generated advice to the user" refers to a means for notifying or displaying the generated advice to the user.

[1169] "Smart devices" are devices with internet connectivity, such as wearable devices and mobile devices, that allow users and staff to access information in real time.

[1170] This invention is a system in which users input medication information, and AI predicts changes in blood drug concentrations based on that information and provides appropriate advice. The invention is designed to enable staff at pharmacies and drug stores to efficiently provide appropriate advice to patients.

[1171] System configuration and operation

[1172] 1. Data Entry

[1173] The user (pharmacy staff) uses a smart device (e.g., smart glasses or a smartphone) to input medication information provided by the patient, such as "Take 100 mg of aspirin every morning."

[1174] 2. Data Transmission

[1175] The entered medication information is sent via smartphone to a cloud server, which stores the information in a database such as MySQL or PostgreSQL.

[1176] 3. AI-based predictions

[1177] The cloud server runs an AI model using Python and TensorFlow based on the stored medication information and data from drug package inserts and interview forms registered in the database. The AI ​​model simulates the progression of drug concentrations in the blood and outputs the results.

[1178] 4. Generating Advice

[1179] Based on the simulation results, the server uses a web framework such as Flask to generate appropriate advice, such as "You should wait until your next scheduled dose" or "You are at risk of overdose, so contact your doctor immediately."

[1180] 5. Providing advice

[1181] The generated advice is displayed on the smart glasses' display, allowing pharmacy staff to provide appropriate advice to patients in real time. By using the smart glasses in conjunction with the smartphone application, more detailed information can be viewed.

[1182] Specific examples

[1183] If you miss a dose:

[1184] 1. The server receives the user's input, "Take 100 mg of aspirin every morning," and stores it in a database.

[1185] 2. When the user types in a question such as "I forgot to take my morning dose," the information is sent to the server.

[1186] 3. The server runs an AI model based on the received question and generates advice such as, "You should wait until your next scheduled medication dose."

[1187] 4. Advice is displayed on the smart glasses display, and staff relays it to the patient.

[1188] In case of overdose:

[1189] 1. The server receives the user's input, "Take 100 mg of aspirin every morning," and stores it in a database.

[1190] 2. When the user types a question like, "I accidentally took two doses, is that okay?", the information is sent to the server.

[1191] 3. The server runs an AI model based on the received question and generates advice such as, "There is a risk of overdose, so contact your doctor immediately."

[1192] 4. Advice is displayed on the smart glasses display, and staff relays it to the patient.

[1193] Prompt Sentence Examples

[1194] A user has entered medication information. Medication Information: Aspirin 100mg daily in the morning. Question: I forgot to take my morning dose. Please provide appropriate advice.

[1195]

[1196] A user has entered medication information. Medication information: Take 100mg of aspirin every morning. Question: I accidentally took two doses. Is this ok? Please provide appropriate advice.

[1197] This enables the system to provide appropriate medication advice in real time, maximizing patient safety and therapeutic effectiveness.

[1198] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1199] Step 1:

[1200] The user enters medication information using a smart device. Specifically, the user enters information such as "Take 100 mg of aspirin every morning" through a smartphone app or smart glasses. The entered information is temporarily stored on the device.

[1201] Step 2:

[1202] The device sends the entered medication information to the cloud server. Specifically, the smartphone app issues an HTTP request over the Internet to send the data to the API endpoint of the cloud server. At this time, the data is serialized in JSON format.

[1203] Step 3:

[1204] The medication information received by the server is saved in a database. Specifically, the server uses Python to deserialize the received data and stores the information in a database such as MySQL or PostgreSQL. The saved information is used for subsequent processing.

[1205] Step 4:

[1206] The user enters additional information or a question (e.g., "I forgot my morning dose"), and the information entered through the smartphone app or smart glasses is temporarily stored on the device.

[1207] Step 5:

[1208] The device sends the added information and question to the cloud server. As in step 2, the data entered by the user is sent to the server using an HTTP request. This data is also serialized in JSON format.

[1209] Step 6:

[1210] The server analyzes the received question and inputs the relevant data into the AI ​​model. Specifically, it uses a web framework such as Flask to parse the query, retrieves relevant medication information from a database, and formats it into a data format to be input into the AI ​​model.

[1211] Step 7:

[1212] The server runs an AI model to predict drug concentrations in the blood and simulate their progression. Specifically, it supplies input data to an AI model using TensorFlow and executes model inference. To obtain simulation results, the model calculates multidimensional array data.

[1213] Step 8:

[1214] The server generates appropriate advice based on the simulation results. Specifically, it executes logic to generate messages such as "Wait until your next scheduled dose" or "Contact your doctor immediately as there is a risk of overdose" based on the inferred drug concentration.

[1215] Step 9:

[1216] The server provides the generated advice to the user. Specifically, it generates JSON data including the generated advice message as a response from the application and sends it to the user's device.

[1217] Step 10:

[1218] The device displays the received advice to the user. Specifically, the advice message is displayed on the smart glasses display, allowing the user to check it in real time. A notification is also sent to the smartphone app, which displays detailed information.

[1219] At each step, the input information undergoes the necessary data processing or calculation and is passed to the next step in an appropriate format, so that final advice can be provided to the user.

[1220] 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.

[1221] MODE FOR CARRYING OUT THE INVENTION

[1222] This invention combines a system in which a user inputs medication information, and AI predicts the progression of drug blood concentrations based on that information and provides appropriate advice, with an emotion engine that recognizes the user's emotions, to provide advice that is appropriate to the user's psychological state. The program processing of this system is shown below.

[1223] First, the user logs in to the system and enters medication information. For example, they enter information such as "Take 100 mg of aspirin every morning." This information is sent from the terminal to the server.

[1224] The server receives the user's input information and stores it in a database. At this time, the server also organizes user information by taking into account the drug concentration transition data collected from drug package inserts and interview forms, which are also registered in the database.

[1225] Next, the user makes a query such as "I forgot to take my morning dose" or "I accidentally took two doses." This query is sent from the device to the server, which analyzes the received query and inputs the relevant data into the AI ​​model.

[1226] The AI ​​model simulates the progression of drug blood levels. Based on the results of this simulation, the server generates appropriate advice, such as "It is best to wait until your next appointment or consult a doctor" or "There is a risk of overdose, so contact your doctor immediately."

[1227] Furthermore, the system of the present invention is equipped with an emotion engine that analyzes user input and voice data to recognize emotions. Based on the emotions recognized by the emotion engine, the server adjusts the content and format of advice. For example, if the user is feeling anxious, more reassuring and polite advice will be provided.

[1228] The server also monitors the user's emotional state over the long term and analyzes the history of emotional fluctuations, making it possible to assess the effectiveness of drug treatment and the risk of side effects based on the emotional fluctuations.

[1229] A specific example of processing will be shown below.

[1230] If you forget to take this morning's dose

[1231] 1. The user enters "Take 100mg of aspirin every morning" and sends it from the terminal to the server.

[1232] 2. The server stores this information in a database for future use.

[1233] 3. The user types a question such as, "I forgot to take my morning dose. What should I do?" and sends it from the device to the server.

[1234] 4. The server analyzes the question, inputs relevant data into the AI ​​model, and performs a simulation.

[1235] 5. Based on the simulation results, the server generates advice such as "wait until the next scheduled time to take your medication."

[1236] 6. The emotion engine analyzes user input and voice data and recognizes that the user is anxious.

[1237] 7. The server provides more polite and reassuring advice to anxious users.

[1238] 8. The device displays the advice to the user.

[1239] If you accidentally take two doses

[1240] 1. The user enters "Take 100mg of aspirin every morning" and sends it from the terminal to the server.

[1241] 2. The server stores this information in a database for future use.

[1242] 3. The user types a question such as, "I accidentally took two doses. Is that okay?" and sends it from the device to the server.

[1243] 4. The server analyzes the question, inputs relevant data into the AI ​​model, and performs a simulation.

[1244] 5. Based on the simulation results, the server generates advice such as "There is a risk of overdose, so contact a doctor immediately."

[1245] 6. The emotion engine analyzes the user's input and voice data and recognizes that the user is in a panic.

[1246] 7. The server provides calming advice to panicked users, encouraging them to stay calm.

[1247] 8. The device displays the advice to the user.

[1248] In this way, by combining the emotion engine, the system of the present invention can provide personalized advice based on the user's psychological state, maximizing the effectiveness and safety of drug treatment.

[1249] The processing flow will be explained below.

[1250] If you forget to take this morning's dose

[1251] Step 1:

[1252] The user logs in to the system. User authentication is performed at login, and if authentication is successful, a data entry screen is displayed.

[1253] Step 2:

[1254] The user enters their medication information, for example, "Take 100 mg of aspirin every morning," into the terminal and clicks the registration button.

[1255] Step 3:

[1256] The device sends the medication information entered by the user to the server, which packages the information in a standard data format such as JSON.

[1257] Step 4:

[1258] The server stores the received medication information in a database. When saving, it checks the data for consistency and whether there is any invalid data.

[1259] Step 5:

[1260] The server analyzes data on drug concentration trends collected from drug package inserts and interview forms, and formats the data necessary for the AI ​​model. This data is also stored in the database.

[1261] Step 6:

[1262] The user types in a query such as "I forgot to take my morning dose, what should I do?" and clicks the send button.

[1263] Step 7:

[1264] The device sends the user's query to the server in text format.

[1265] Step 8:

[1266] The server analyzes the received query and inputs relevant medication information and drug concentration data into the AI ​​model.

[1267] Step 9:

[1268] The server uses an AI model to simulate the progression of drug blood concentrations.

[1269] Step 10:

[1270] The server analyzes the simulation results and generates advice such as "wait until the next scheduled time to take your medication."

[1271] Step 11:

[1272] The emotion engine analyzes user input and voice data and recognizes that the user is anxious.

[1273] Step 12:

[1274] The server generates more polite and reassuring advice for anxious users and sends it to their terminals.

[1275] Step 13:

[1276] The device will display advice to the user, allowing them to know the appropriate response.

[1277] If you accidentally take two doses

[1278] Step 1:

[1279] The user logs in to the system. User authentication is performed at login, and if authentication is successful, a data entry screen is displayed.

[1280] Step 2:

[1281] The user enters their medication information, for example, "Take 100 mg of aspirin every morning," into the terminal and clicks the registration button.

[1282] Step 3:

[1283] The device sends the medication information entered by the user to the server, which packages the information in a standard data format such as JSON.

[1284] Step 4:

[1285] The server stores the received medication information in a database. When saving, it checks the data for consistency and whether there is any invalid data.

[1286] Step 5:

[1287] The server analyzes data on drug concentration trends collected from drug package inserts and interview forms, and formats the data necessary for the AI ​​model. This data is also stored in the database.

[1288] Step 6:

[1289] The user types in a query such as "I accidentally took two doses, what should I do?" and clicks the send button.

[1290] Step 7:

[1291] The device sends the user's query to the server in text format.

[1292] Step 8:

[1293] The server analyzes the received query and inputs relevant medication information and drug concentration data into the AI ​​model.

[1294] Step 9:

[1295] The server uses an AI model to simulate the progression of drug blood concentrations.

[1296] Step 10:

[1297] The server analyzes the simulation results and generates advice such as "There is a risk of overdose, so contact a doctor immediately."

[1298] Step 11:

[1299] The emotion engine analyzes user input and voice data and recognizes when the user is in a panic.

[1300] Step 12:

[1301] The server generates calm advice for panicked users, urging them to stay calm, and sends it to their devices.

[1302] Step 13:

[1303] The device will display advice to the user, allowing them to know the appropriate response.

[1304] In this way, by combining the emotion engine, the system of the present invention can provide personalized advice based on the user's psychological state, maximizing the effectiveness and safety of drug treatment.

[1305] Example 2

[1306] 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."

[1307] Conventional medication management systems can predict drug blood concentrations and provide advice based on medication information entered by the user, but it has been difficult to provide personalized advice that takes into account the user's psychological state. As a result, these systems have not been effective enough in reducing the user's psychological burden and anxiety regarding medication and health management. To address this issue, the present invention aims to provide a system that recognizes the user's emotions and provides personalized advice based on them.

[1308] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for inputting medication information of a drug; means for saving the input medication information in a database; means for accepting inquiries from a user; means for predicting drug concentrations in blood using an artificial intelligence model based on the accepted inquiries and simulating the progress of drug concentrations; means for generating appropriate advice based on the simulation results; means for providing an emotion engine for recognizing emotions by analyzing user input and voice data; means for adjusting the advice content based on the recognized emotions; and means for providing the generated advice to the user. This makes it possible to provide personalized advice that takes into account the psychological state of the user.

[1309] The "means for inputting medication information" refers to an interface that allows a user to input information such as the name, dosage, and time of administration of the medication via a terminal.

[1310] The "means for saving input medication information in a database" is a server-side function that registers the medication information input by the user in a database so that it can be referenced later.

[1311] "Means for accepting inquiries from users" refers to an interface that allows users to send questions or inquiries to the system, and the server receives this information.

[1312] "Means for predicting drug concentrations in the blood using an artificial intelligence model and simulating trends in drug concentrations" refers to a program that uses AI technology to predict fluctuations in drug concentrations in the blood based on input medication information and related data, and simulates those trends.

[1313] "Means for generating appropriate advice based on simulation results" refers to a server-side function that generates appropriate behavioral instructions and advice for users based on the simulation results obtained by the AI ​​model.

[1314] An "emotion engine that recognizes emotions by analyzing user input and voice data" is an engine that determines the user's emotions and psychological state at that time by analyzing the text and voice data entered by the user.

[1315] The "means for adjusting the advice content based on the recognized emotions" is a server-side function for appropriately changing the content and expression of the advice provided according to the user's emotional state recognized by the emotion engine.

[1316] The "means for providing generated advice to the user" is an interface for displaying the advice generated by the system to the user via a terminal.

[1317] "Means of collecting data on changes in drug concentration from drug package inserts and interview forms and registering it in a database" refers to a function that extracts data on changes in drug blood concentration from official drug documents and questionnaires, and registers that data in a database.

[1318] MODE FOR CARRYING OUT THE INVENTION

[1319] This invention combines a system in which medication information is input, and AI predicts changes in blood drug concentrations based on that information and provides appropriate advice, with an emotion engine that recognizes the user's emotions, to provide advice that is tailored to the user's psychological state. Specific embodiments of this system are described below.

[1320] First, a user logs in to the system and enters medication information. For example, the user enters that they take 100 mg of aspirin every morning. This information is sent from the user's device to the server. The device packages the entered information in JSON format and sends an HTTP POST request to the server.

[1321] The server then stores the medication information in a database, typically using a database management system (DBMS). The server receives the HTTP request, analyzes the data, and then executes an SQL query to insert the information into the user table in the database.

[1322] After receiving and saving the medication information, the server accepts inquiries from the user. The user types "I forgot to take my morning dose. What should I do?" into the chat box on the device's application screen and clicks the send button. The device then sends this inquiry to the server as an HTTP POST request.

[1323] The server analyzes the received query using a natural language processing (NLP) engine. The analyzed query content, along with related drug data, is then input into an AI model. The AI ​​model uses machine learning algorithms to simulate the progression of drug concentrations in the blood based on medication information and drug data. This simulation uses information from existing datasets and drug package inserts.

[1324] The simulation results generated by the AI ​​model are used by the server to generate appropriate advice, such as "It is best to wait until your next scheduled dose" or "There is a risk of overdose, so contact your doctor immediately."

[1325] Furthermore, the server is equipped with an emotion engine that recognizes emotions using user input and voice data. The emotion engine analyzes whether the user is feeling anxious or panicked. For example, if the user inputs, "I forgot my morning dose. What should I do?", the emotion engine will recognize that the user is anxious.

[1326] Based on this recognition, the server can adjust the content and format of the advice it generates: if a user feels anxious, it will provide advice in more reassuring language. In this way, the system can provide personalized advice that takes into account the user's psychological state.

[1327] As an example, the following scenario can be considered.

[1328] Example of what to do if you forget to take this morning's dose

[1329] 1. The user enters "Take 100mg of aspirin every morning" and sends it from the terminal to the server.

[1330] Example prompt: "Take 100 mg of aspirin every morning."

[1331] 2. The server stores this information in a database for future use.

[1332] 3. The user types a question such as, "I forgot to take my morning dose. What should I do?" and sends it from the device to the server.

[1333] Example prompt: "I forgot to take my morning dose. What should I do?"

[1334] 4. The server analyzes the question, inputs relevant data into the AI ​​model, and performs a simulation.

[1335] 5. Based on the simulation results, the server generates advice such as "wait until the next scheduled time to take your medication."

[1336] Sample prompt: "It's best to wait until your next scheduled dose."

[1337] 6. The emotion engine analyzes user input and voice data and recognizes that the user is anxious.

[1338] 7. The server provides more polite and reassuring advice to anxious users.

[1339] Sample prompt: "Don't worry. It's best to wait until your next dose. However, if you're concerned, talk to your doctor."

[1340] 8. The device displays the advice to the user.

[1341] In this way, the system of the present invention aims to improve the effectiveness and safety of drug treatment by combining an emotion engine to provide optimal advice according to the user's psychological state.

[1342] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1343] Processing Steps

[1344] Step 1:

[1345] The user logs into the system and enters medication information.

[1346] Input: A user enters "Take 100mg of aspirin daily in the morning" into a form.

[1347] Specific actions: The user enters medication information into the form on the application screen and clicks the submit button.

[1348] Output: The device converts the user's input information into JSON format and generates an HTTP POST request.

[1349] Step 2:

[1350] The terminal transmits the entered medication information to the server.

[1351] Input: The HTTP POST request generated by the device.

[1352] Specific operation: The device stores JSON format data in the body of the HTTP request and sends the request to the specified server endpoint.

[1353] Output: The server receives the HTTP request.

[1354] Step 3:

[1355] The server stores the received medication information in a database.

[1356] Input: Medication information received by the server in JSON format.

[1357] Specific operation: The server parses the JSON format data and saves it by issuing an INSERT query to the corresponding table in the database.

[1358] Output: A new record is added to the database.

[1359] Step 4:

[1360] The user inputs a question about medication and sends it from the terminal to the server.

[1361] Input: User types in chat box, "I forgot my morning dose. What should I do?"

[1362] Specific Actions: The user types a query into the chat box and clicks the send button.

[1363] Output: The terminal converts the query content into JSON format and generates an HTTP POST request.

[1364] Step 5:

[1365] The terminal sends the inquiry to the server.

[1366] Input: The HTTP POST request generated by the device.

[1367] Specific operation: The terminal stores the query content in JSON format in the body of an HTTP request and sends it to the server.

[1368] Output: The server receives the HTTP request.

[1369] Step 6:

[1370] The server analyzes the query and inputs the relevant data into the AI ​​model.

[1371] Input: The query received by the server in JSON format.

[1372] Specific operation: The server uses a natural language processing (NLP) engine to analyze the query, extract relevant data such as drug information, and input it into the AI ​​model.

[1373] Output: The AI ​​model is provided with input data.

[1374] Step 7:

[1375] The AI ​​model simulates the progression of drug blood concentrations.

[1376] Input: Medication information and related data fed into the AI ​​model.

[1377] How it works: The AI ​​model uses a trained neural network to predict and simulate time series data of drug concentrations in the blood.

[1378] Output: As a result of the simulation, data on the drug concentration over time is generated.

[1379] Step 8:

[1380] The server generates advice based on the simulation results.

[1381] Input: Simulation results provided by the AI ​​model.

[1382] Specific operation: The server obtains the simulation results and generates appropriate advice (e.g., "wait until the next scheduled medication time") using a rule-based engine.

[1383] Output: The generated advice is provided in text format.

[1384] Step 9:

[1385] The emotion engine analyzes user input and voice data to recognize emotions.

[1386] Input: User-provided input text or voice data.

[1387] What it does: The emotion engine uses text and speech recognition technology to determine the user's emotion (e.g., anxiety, panic).

[1388] Output: The emotion recognition result is the user's emotional state.

[1389] Step 10:

[1390] The advice content is adjusted based on the emotion recognized by the server.

[1391] Input: Emotion recognition results from the emotion engine and initial advice content.

[1392] Specific operation: The server takes into account the emotion recognition results and adjusts the wording of the advice (e.g., changes the wording to make it more reassuring).

[1393] Output: An emotion-adjusted advice is generated.

[1394] Step 11:

[1395] The device displays the advice to the user.

[1396] Input: The final advice provided by the server.

[1397] Specific operation: The device receives the advice content and displays it on the user interface (UI).

[1398] Output: The advice is ready for the user to review.

[1399] Through this process, the system can provide personalized advice based on the information entered by the user, using AI models and emotion engines.

[1400] (Application example 2)

[1401] 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."

[1402] In recent years, there has been an increasing need for more efficient and effective medication management. It is particularly important to provide prompt and accurate advice when users forget to take their medication or overdose. However, conventional systems only provide standardized advice without taking into account the user's emotional state. Therefore, there is a problem in that it is difficult to provide appropriate support when the user is feeling anxious or panicked.

[1403] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for inputting medication information on drugs; means for saving the input medication information in a database; means for accepting inquiries from users; means for predicting blood drug concentrations using an AI model based on the accepted inquiries and simulating the progress of drug concentrations; means for generating appropriate advice based on the simulation results; means for providing the generated advice to the user; means for having an emotion analysis engine and analyzing user input and voice data to recognize emotions; and means for providing appropriate advice content and format based on the recognized emotions. This makes it possible to provide personalized advice according to the user's emotional state, maximizing the effectiveness and safety of drug treatment.

[1404] "Pharmaceuticals" is a general term for chemicals and biological products used for the prevention, diagnosis, treatment, or alleviation of disease.

[1405] "Medication information" refers to data regarding the name, dosage, and timing of taking the medication the user is taking.

[1406] A "database" is an information collection system that systematically accumulates information and is designed to make it easy to search and manage.

[1407] "Inquiries" refer to questions, doubts, or inquiries that users have about the system they use.

[1408] An "AI model" is a computational algorithm or statistical model that mimics human intelligence and is capable of learning, reasoning, and self-improvement.

[1409] "Blood drug concentration" is data that indicates the amount of a particular drug present in a user's blood.

[1410] "Simulation" is a technical technique for virtually reproducing real-world situations and phenomena and conducting analysis and predictions.

[1411] "Appropriate advice" refers to specific and accurate instructions and recommendations provided based on simulation results and data analysis.

[1412] An "emotion analysis engine" is a technology that analyzes a user's text input and voice data and automatically recognizes their emotional state (joy, anger, sadness, happiness, etc.).

[1413] "Input and voice data" means text messages and voice utterances that a user enters into the system.

[1414] This invention is a system in which users input their medication information, and AI predicts the progression of drug blood concentrations based on that information and provides appropriate advice. By combining this with an emotion analysis engine that recognizes the user's emotions, the system provides advice tailored to the user's psychological state. This system is particularly applicable as a customer support app in brick-and-mortar stores (pharmacies and drugstores).

[1415] System configuration

[1416] The system consists of the following main components:

[1417] 1. User terminal: A device (such as a smartphone) through which the user enters medication information.

[1418] 2. Server: A computer system that holds a database and runs AI models and sentiment analysis engines.

[1419] 3. Database: A system (such as MongoDB) for storing drug concentration trend data and user medication information.

[1420] Program processing

[1421] The processing of this program consists of the following major steps:

[1422] 1. Getting user input:

[1423] Users enter information about their medication (such as name, dosage, and timing of administration) via a smartphone app, which is then sent from the device to a server.

[1424] 2. Data storage:

[1425] The server stores the received medication information in a database, which also includes data collected from drug package inserts and interview forms.

[1426] 3. User Inquiries:

[1427] Users can use the app to make inquiries such as, "I forgot to take my morning dose" or "I accidentally took two doses."

[1428] 4. Simulation using AI models:

[1429] Based on the queries received, the server uses an AI model (using PyTorch) to predict the progression of drug concentrations in the blood.

[1430] 5. Generating Advice:

[1431] Based on the simulation results, the server generates appropriate advice, using a sentiment analysis engine (using Google Cloud Natural Language API) to analyze the user's sentiment and provide advice accordingly.

[1432] 6. Providing advice:

[1433] The generated advice is sent to the terminal and displayed to the user.

[1434] Technical details

[1435] Hardware and software used:

[1436] User device: Smartphone (iOS or Android)

[1437] Server: Backend built with Node.js and Express

[1438] Database: MongoDB

[1439] AI Simulation: PyTorch

[1440] Sentiment analysis engine: Google Cloud Natural Language API

[1441] Specific examples

[1442] If you forget to take this morning's dose

[1443] 1. The user enters "Take 100mg of aspirin every morning" and sends it from the terminal to the server.

[1444] 2. The server stores this information in a database.

[1445] 3. The user types a question such as, "I forgot to take my morning dose. What should I do?" and sends it from the device to the server.

[1446] 4. The server analyzes the question, inputs relevant data into the AI ​​model, and performs a simulation.

[1447] 5. Based on the simulation results, the server generates advice such as "wait until the next scheduled time to take your medication."

[1448] 6. The sentiment analysis engine analyzes user input and voice data and recognizes that the user is anxious.

[1449] 7. The server provides more reassuring and courteous advice to anxious users.

[1450] 8. The device displays the advice to the user.

[1451] Prompt Sentence Examples

[1452] When a user sends a question such as "I forgot to take my medicine this morning. What should I do?", the prompt text is "Please provide advice about the next dose time. The user is feeling anxious, so please provide reassuring advice." Based on this prompt, the AI ​​model generates advice such as "Please wait until the next scheduled dose time. Also, if you feel anxious, it is best to consult a doctor. Rest assured that this will be resolved quickly."

[1453] As described above, the system of the present invention can maximize the effectiveness and safety of drug treatment by providing personalized advice that takes into account the user's emotional state.

[1454] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1455] Step 1:

[1456] Users open the app on their smartphone and enter information about their medication (such as name, dosage, and timing of administration). This information is sent from the device to the server. Input is done using text fields and drop-down menus, and the data is sent by pressing the send button. The input data includes the name of the medication, dosage, and timing of administration.

[1457] Step 2:

[1458] The server stores the received medication information in a database (MongoDB). After receiving the request, the server parses the information and stores it in the appropriate table (collection) in the database. The output is the medication information stored in the database.

[1459] Step 3:

[1460] Users input their questions (e.g., "I forgot to take my morning dose," "I accidentally took two doses," etc.) through a smartphone app and send them to the server from their device. A text field is used for input, and the question is sent by pressing the send button. The input data includes the question text.

[1461] Step 4:

[1462] The server provides the necessary data to the AI ​​model (using PyTorch) based on the received query, predicting the progression of drug concentrations in the blood. The server processes the received query, retrieves relevant medication information from the database, and inputs it into the AI ​​model. The output is simulated data on the progression of drug concentrations in the blood.

[1463] Step 5:

[1464] The server generates appropriate advice based on the simulation results. In doing so, it uses a sentiment analysis engine (using the Google Cloud Natural Language API) to analyze the user's emotional state. The server compares the simulation results with the query text and generates optimal advice. The sentiment analysis engine detects emotions from the user's input text and incorporates this emotional information into the advice generation process. The output is advice that takes the user's emotional state into account.

[1465] Step 6:

[1466] The server sends the generated advice to the terminal and provides it to the user.The server sends the generated advice to the user's terminal so that the user can view the advice on the screen.As an output, the advice displayed on the user's smartphone screen is obtained.

[1467] Step 7:

[1468] The user checks the advice displayed on the device and takes the next action if necessary. The user reads the advice and takes action (e.g., wait until the next appointment time, consult a doctor, etc.). The output is a decision on the user's action.

[1469] Through these steps, the system can provide personalized advice based on the user's emotional state, maximizing the effectiveness and safety of drug treatment.

[1470] 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.

[1471] 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.

[1472] 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.

[1473] [Fourth embodiment]

[1474] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1475] 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.

[1476] 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).

[1477] 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.

[1478] 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.

[1479] 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).

[1480] 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.

[1481] 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.

[1482] 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.

[1483] 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.

[1484] 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.

[1485] 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.

[1486] 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."

[1487] MODE FOR CARRYING OUT THE INVENTION

[1488] This invention is a system in which users input medication information, and AI predicts the progression of drug blood concentrations based on that information and provides appropriate advice. The program processing of this system is shown below.

[1489] First, the user logs in to the system and enters medication information. For example, they enter information such as "Take 100 mg of aspirin every morning." This information is sent from the terminal to the server.

[1490] The server receives the user's input information and stores it in a database. At this time, the server also organizes the user information by taking into account data on drug concentration trends collected from drug package inserts and interview forms, which are also registered in the database.

[1491] Next, the user makes a query such as "I forgot to take my morning dose" or "I accidentally took two doses." This query is sent from the device to the server, which analyzes the received query and inputs the relevant data into the AI ​​model.

[1492] The AI ​​model simulates the progression of drug blood levels. Based on the results of this simulation, the server generates appropriate advice, such as "It is best to wait until your next appointment or consult a doctor" or "There is a risk of overdose, so contact your doctor immediately."

[1493] Finally, the generated advice is displayed to the user via the device, allowing the user to know the appropriate response in real time.

[1494] Specific examples

[1495] If you forget to take this morning's dose

[1496] 1. The user enters "Take 100mg of aspirin every morning" and sends it from the terminal to the server.

[1497] 2. The server stores this information in a database for future use.

[1498] 3. The user types a question such as, "I forgot to take my morning dose. What should I do?" and sends it from the device to the server.

[1499] 4. The server analyzes the question, inputs relevant data into the AI ​​model, and performs a simulation.

[1500] 5. Based on the simulation results, the server generates advice such as "wait until the next scheduled time to take your medication" and sends it to the terminal.

[1501] 6. The device displays the advice to the user.

[1502] If you accidentally take two doses

[1503] 1. The user enters "Take 100mg of aspirin every morning" and sends it from the terminal to the server.

[1504] 2. The server stores this information in a database for future use.

[1505] 3. The user types a question such as, "I accidentally took two doses. Is that okay?" and sends it from the device to the server.

[1506] 4. The server analyzes the question, inputs relevant data into the AI ​​model, and performs a simulation.

[1507] 5. Based on the simulation results, the server generates advice such as "There is a risk of overdose, so contact a doctor immediately" and sends it to the device.

[1508] 6. The device displays the advice to the user.

[1509] This allows users to know the appropriate course of action and maximize the effectiveness and safety of drug treatment.The present invention predicts drug blood concentrations in real time and realizes individualized medication management.

[1510] The processing flow will be explained below.

[1511] Step 1:

[1512] The user logs in to the system. User authentication is performed at the time of login, and if authentication is successful, a data entry screen is displayed.

[1513] Step 2:

[1514] The user enters their medication information, such as the name of the medication, dosage, and interval between doses, into the terminal and clicks the registration button.

[1515] Step 3:

[1516] The device sends the medication information entered by the user to the server, which packages the information in a standard data format such as JSON.

[1517] Step 4:

[1518] The server stores the received medication information in a database. When saving, it checks the data for consistency and whether there is any invalid data.

[1519] Step 5:

[1520] The server analyzes data on drug concentration trends collected from drug package inserts and interview forms, and formats the data necessary for the AI ​​model. This data is also stored in the database.

[1521] Step 6:

[1522] The user enters an inquiry such as "I forgot to take this morning's dose" or "I accidentally took two doses." After entering the information, the user clicks the "Send Inquiry" button.

[1523] Step 7:

[1524] The device sends the user's query to the server in text format.

[1525] Step 8:

[1526] The server analyzes the received query and extracts relevant medication information and drug concentration data.

[1527] Step 9:

[1528] The server inputs the extracted data into an AI model, which then simulates the progression of drug concentrations in the blood.

[1529] Step 10:

[1530] The server analyzes the simulation results obtained from the AI ​​model and generates appropriate advice, such as "wait until the next scheduled dose" or "contact your doctor immediately."

[1531] Step 11:

[1532] The server sends the generated advice to the terminal in text format.

[1533] Step 12:

[1534] The device will then display the received advice to the user, allowing them to know the appropriate response.

[1535] This enables the system of the present invention to provide appropriate advice in real time based on medication information entered by the user, maximizing the effectiveness and safety of drug treatment.

[1536] Example 1

[1537] 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."

[1538] In modern medicine management, there is a lack of means to quickly learn the appropriate response when users accidentally forget to take their medicine or take an overdose, which can lead to a decrease in the effectiveness of drug treatment and an increased risk of side effects.

[1539] 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.

[1540] In this invention, the server includes means for a user to input medication information, means for saving the input medication information in a database, means for accepting inquiries from users, means for analyzing the accepted inquiries using natural language processing, predicting blood drug concentrations using a generative AI model, and simulating changes in drug concentrations, means for generating appropriate advice based on the simulation results, and means for providing the generated advice to the user. This enables the user to quickly respond to situations such as forgetting to take medication or overdosing, and maximize the effectiveness of drug treatment.

[1541] A "user" is a person who uses the system to input medication information and make inquiries.

[1542] "Medication information" refers to information regarding the type, dosage, and time of administration of medicines taken by the user.

[1543] The "database" is a storage device that accumulates and stores data relating to medication information and drug concentration trends received by the server.

[1544] An "inquiry" is a question or confirmation that a user makes to the system, including any unclear points or problems regarding medication.

[1545] "Natural language processing" is a technology for analyzing text data such as user inquiries to understand their meaning and intent.

[1546] A "generative AI model" is an artificial intelligence model that uses received data to predict and simulate drug concentrations in the blood and generate appropriate advice.

[1547] "Simulation" refers to the computational process performed by the generative AI model to predict the progression of drug concentrations in the blood.

[1548] "Advice" refers to specific guidelines or suggestions provided to users based on the simulation results of the generative AI model.

[1549] "Additional information on drugs" refers to information including detailed data on drug concentration trends obtained from drug package inserts, interview forms, etc.

[1550] "Formatting" is the process of converting the input medication information into a format that is easy for the generative AI model to analyze.

[1551] MODE FOR CARRYING OUT THE INVENTION

[1552] The present invention is a system in which a user inputs medication information, and based on that information, AI predicts the progression of drug blood concentrations and provides appropriate advice. This system performs a series of processes: inputting medication information, accepting inquiries, managing a database, conducting simulations using AI, and generating advice. Specific embodiments of this system are described below.

[1553] Hardware and software used

[1554] Hardware:

[1555] Device: The smartphone, tablet, or computer where the user enters information

[1556] Server: Cloud server or dedicated server for storing data, simulations, and generating advice

[1557] software:

[1558] Database management systems (e.g., MySQL, PostgreSQL)

[1559] Natural Language Processing (NLP) tools (e.g., spaCy, NLTK)

[1560] Generative AI models (e.g., TensorFlow, PyTorch)

[1561] Communication protocol (e.g. HTTPS)

[1562] Program processing (natural language explanation)

[1563] 1. The user enters medication information using a terminal. For example, "Take 100 mg of aspirin every morning."

[1564] 2. The terminal sends the entered medication information to the server.

[1565] 3. The server stores the received medication information in a database, including additional information about the drug (such as the drug package insert and interview form data).

[1566] 4. The user enters the inquiry information using the terminal. For example, "I forgot to take my morning dose. What should I do?" or "I accidentally took two doses. Is that okay?"

[1567] 5. The terminal sends the query information to the server.

[1568] 6. The server uses natural language processing (NLP) to analyze the received query information and extract relevant data, which then forms the information needed for the generative AI model.

[1569] 7. The server uses a generative AI model to simulate the progression of drug blood concentrations based on the query. For example, the model can be implemented using PyTorch or TensorFlow.

[1570] 8. The server generates appropriate advice based on the simulation results, such as a specific action plan, such as whether to wait until the next scheduled medication dose or consult a doctor.

[1571] 9. The device displays the advice received from the server to the user.

[1572] Specific examples and prompt sentence examples

[1573] Specific examples

[1574] 1. If you forget to take this morning's dose

[1575] The user enters medication information such as "Take 100 mg of aspirin every morning" and sends it from the terminal to the server.

[1576] The server stores this information in a database.

[1577] The user enters a query such as "I forgot to take my morning dose. What should I do?" into the terminal and sends it to the server.

[1578] The server parses the query and feeds the data into a generative AI model.

[1579] The AI ​​model performs a simulation, and the server generates advice to "wait until the next scheduled medication time" and sends it to the device.

[1580] The device displays the advice to the user.

[1581] 2. If you accidentally take two doses

[1582] The user enters medication information such as "Take 100 mg of aspirin every morning" and sends it from the terminal to the server.

[1583] The server stores this information in a database.

[1584] The user enters a question into the terminal, such as "I accidentally took two doses. Is that okay?", and sends it to the server.

[1585] The server parses the query and feeds the data into a generative AI model.

[1586] The AI ​​model runs a simulation, and the server generates advice such as "There is a risk of overdose, so contact a doctor immediately" and sends it to the device.

[1587] The device displays the advice to the user.

[1588] Prompt Sentence Examples

[1589] 1. If you forget to take this morning's dose

[1590] A user takes 100mg of aspirin every morning and forgot to take their morning dose. Can you advise them on what to do next?

[1591] 2. If you accidentally take two doses

[1592] A user takes 100mg of aspirin every morning and accidentally takes two doses. Can you advise what to do next?

[1593] The above is an embodiment of the present invention. This system allows users to quickly respond to medication-related problems and maximize the effectiveness of drug therapy.

[1594] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1595] Step 1:

[1596] The user enters medication information.

[1597] Input: The user types "Take 100 mg of aspirin daily in the morning" into an application input field.

[1598] Specific operation: The user operates the device (smartphone or PC) and enters the required information in text format into the designated fields.

[1599] Output: Medication information is temporarily stored in the device's memory.

[1600] Step 2:

[1601] The terminal transmits medication information to the server.

[1602] Input: Medication information entered by the user.

[1603] Specific operation: The terminal sends the medication information entered via the Internet to the server using the HTTPS protocol.

[1604] Output: Medication information is sent to the server.

[1605] Step 3:

[1606] The server stores the received medication information in a database.

[1607] Input: Medication information received by the server.

[1608] Specific operation: The server converts the received medication information into an appropriate format and saves it in a database (MySQL, PostgreSQL, etc.). Here, for example, an SQL statement is generated to add data.

[1609] Output: Medication information is permanently stored in a database.

[1610] Step 4:

[1611] The user enters the inquiry information.

[1612] Input: The user types "I forgot my morning dose. What should I do?" into an application input field.

[1613] Specific actions: The user operates the device and enters the inquiry information in text format into the designated field.

[1614] Output: The query information is temporarily stored in the device's memory.

[1615] Step 5:

[1616] The terminal transmits the inquiry information to the server.

[1617] Input: The inquiry information entered by the user.

[1618] Specific operation: The terminal sends the query information to the server via the Internet using the HTTPS protocol.

[1619] Output: The query information is forwarded to the server.

[1620] Step 6:

[1621] The server analyzes the query and inputs it into a generative AI model.

[1622] Input: The query information received by the server.

[1623] What it does: The server uses natural language processing (NLP) tools to analyze the query and extract relevant data, such as spaCy to tokenize the text and extract important keywords.

[1624] Output: The analyzed information is formatted to be input into an AI model.

[1625] Step 7:

[1626] The AI ​​model simulates the drug's blood concentration.

[1627] Input: Formatted inquiry information and medication information.

[1628] How it works: The AI ​​model uses PyTorch, TensorFlow, etc. to run simulations based on query information. Specifically, it references existing medication data and uses a time-series prediction model to calculate drug concentrations in the blood.

[1629] Output: Simulation results are generated.

[1630] Step 8:

[1631] The server generates advice based on the simulation results.

[1632] Input: Simulation results obtained from the AI ​​model.

[1633] Specific operation: Based on the simulation results, the server generates appropriate advice using predefined templates, such as "wait until the next scheduled dose" or "consult a doctor."

[1634] Output: Advice is generated in text format.

[1635] Step 9:

[1636] The device displays the advice to the user.

[1637] Input: Advice sent by the server.

[1638] Specific operation: The device displays the advice received from the server on the application interface, specifically by using notifications or pop-up windows to present the advice to the user in an easy-to-read format.

[1639] Output: User receives advice and decides next action.

[1640] The above is a detailed description of the processing steps of the program of this system and the specific operations of each.

[1641] (Application example 1)

[1642] 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."

[1643] With existing medication management systems, it is difficult for users to receive appropriate advice in real time when they encounter problems such as forgetting to take a dose or overdosing. Furthermore, pharmacy and drugstore staff have limited means of providing prompt and appropriate advice to patients, making it difficult to maximize user safety and therapeutic effectiveness. The present invention was developed to solve these problems, and aims to increase practicality, particularly in pharmacies and drugstores.

[1644] 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.

[1645] In this invention, the server includes a means for inputting medication information, a means for storing the input medication information in a database, a means for accepting inquiries from users, a means for predicting blood drug concentrations using an AI model based on the accepted inquiries and simulating the progression of drug concentrations, a means for generating appropriate advice based on the simulation results, a means for providing the generated advice to the user, and a means for displaying the advice to staff wearing smart devices. This makes it possible to predict drug concentrations in real time from the input medication information and generate and provide appropriate advice. Furthermore, staff can use the smart devices to quickly communicate advice to users, making medication management for users more efficient and safe.

[1646] "Medicine medication information" is information about the medicines taken by the user, including, for example, the name of the medicine, dosage, and time of administration.

[1647] A "database" is a structured collection of data that efficiently stores and manages input information.

[1648] "Means for accepting inquiries from users" refers to an interface that allows users to input questions or problems, such as forgotten medication or overdose, into the system.

[1649] An "AI model" is a collection of algorithms and methods for analyzing data and making predictions using artificial intelligence technology.

[1650] "Means for predicting drug concentrations in the blood and simulating trends in drug concentrations" refers to means for using AI models to calculate and show fluctuations in drug concentrations in the body.

[1651] "Means for generating appropriate advice" refers to means for recommending actions and points of caution that are beneficial to the user based on the results of the simulation.

[1652] The "means for providing the generated advice to the user" refers to a means for notifying or displaying the generated advice to the user.

[1653] "Smart devices" are devices with internet connectivity, such as wearable devices and mobile devices, that allow users and staff to access information in real time.

[1654] This invention is a system in which users input medication information, and AI predicts changes in blood drug concentrations based on that information and provides appropriate advice. The invention is designed to enable staff at pharmacies and drug stores to efficiently provide appropriate advice to patients.

[1655] System configuration and operation

[1656] 1. Data Entry

[1657] The user (pharmacy staff) uses a smart device (e.g., smart glasses or a smartphone) to input medication information provided by the patient, such as "Take 100 mg of aspirin every morning."

[1658] 2. Data Transmission

[1659] The entered medication information is sent via smartphone to a cloud server, which stores the information in a database such as MySQL or PostgreSQL.

[1660] 3. AI-based predictions

[1661] The cloud server runs an AI model using Python and TensorFlow based on the stored medication information and data from drug package inserts and interview forms registered in the database. The AI ​​model simulates the progression of drug concentrations in the blood and outputs the results.

[1662] 4. Generating Advice

[1663] Based on the simulation results, the server uses a web framework such as Flask to generate appropriate advice, such as "You should wait until your next scheduled dose" or "You are at risk of overdose, so contact your doctor immediately."

[1664] 5. Providing advice

[1665] The generated advice is displayed on the smart glasses' display, allowing pharmacy staff to provide appropriate advice to patients in real time. By using the smart glasses in conjunction with the smartphone application, more detailed information can be viewed.

[1666] Specific examples

[1667] If you miss a dose:

[1668] 1. The server receives the user's input, "Take 100 mg of aspirin every morning," and stores it in a database.

[1669] 2. When the user types in a question such as "I forgot to take my morning dose," the information is sent to the server.

[1670] 3. The server runs an AI model based on the received question and generates advice such as, "You should wait until your next scheduled medication dose."

[1671] 4. Advice is displayed on the smart glasses display, and staff relays it to the patient.

[1672] In case of overdose:

[1673] 1. The server receives the user's input, "Take 100 mg of aspirin every morning," and stores it in a database.

[1674] 2. When the user types a question like, "I accidentally took two doses, is that okay?", the information is sent to the server.

[1675] 3. The server runs an AI model based on the received question and generates advice such as, "There is a risk of overdose, so contact your doctor immediately."

[1676] 4. Advice is displayed on the smart glasses display, and staff relays it to the patient.

[1677] Prompt Sentence Examples

[1678] A user has entered medication information. Medication Information: Aspirin 100mg daily in the morning. Question: I forgot to take my morning dose. Please provide appropriate advice.

[1679]

[1680] A user has entered medication information. Medication information: Take 100mg of aspirin every morning. Question: I accidentally took two doses. Is this ok? Please provide appropriate advice.

[1681] This enables the system to provide appropriate medication advice in real time, maximizing patient safety and therapeutic effectiveness.

[1682] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1683] Step 1:

[1684] The user enters medication information using a smart device. Specifically, the user enters information such as "Take 100 mg of aspirin every morning" through a smartphone app or smart glasses. The entered information is temporarily stored on the device.

[1685] Step 2:

[1686] The device sends the entered medication information to the cloud server. Specifically, the smartphone app issues an HTTP request over the Internet to send the data to the API endpoint of the cloud server. At this time, the data is serialized in JSON format.

[1687] Step 3:

[1688] The medication information received by the server is saved in a database. Specifically, the server uses Python to deserialize the received data and stores the information in a database such as MySQL or PostgreSQL. The saved information is used for subsequent processing.

[1689] Step 4:

[1690] The user enters additional information or a question (e.g., "I forgot my morning dose"), and the information entered through the smartphone app or smart glasses is temporarily stored on the device.

[1691] Step 5:

[1692] The device sends the added information and question to the cloud server. As in step 2, the data entered by the user is sent to the server using an HTTP request. This data is also serialized in JSON format.

[1693] Step 6:

[1694] The server analyzes the received question and inputs the relevant data into the AI ​​model. Specifically, it uses a web framework such as Flask to parse the query, retrieves relevant medication information from a database, and formats it into a data format to be input into the AI ​​model.

[1695] Step 7:

[1696] The server runs an AI model to predict drug concentrations in the blood and simulate their progression. Specifically, it supplies input data to an AI model using TensorFlow and executes model inference. To obtain simulation results, the model calculates multidimensional array data.

[1697] Step 8:

[1698] The server generates appropriate advice based on the simulation results. Specifically, it executes logic to generate messages such as "Wait until your next scheduled dose" or "Contact your doctor immediately as there is a risk of overdose" based on the inferred drug concentration.

[1699] Step 9:

[1700] The server provides the generated advice to the user. Specifically, it generates JSON data including the generated advice message as a response from the application and sends it to the user's device.

[1701] Step 10:

[1702] The device displays the received advice to the user. Specifically, the advice message is displayed on the smart glasses display, allowing the user to check it in real time. A notification is also sent to the smartphone app, which displays detailed information.

[1703] At each step, the input information undergoes the necessary data processing or calculation and is passed to the next step in an appropriate format, so that final advice can be provided to the user.

[1704] 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.

[1705] MODE FOR CARRYING OUT THE INVENTION

[1706] This invention combines a system in which a user inputs medication information, and AI predicts the progression of drug blood concentrations based on that information and provides appropriate advice, with an emotion engine that recognizes the user's emotions, to provide advice that is appropriate to the user's psychological state. The program processing of this system is shown below.

[1707] First, the user logs in to the system and enters medication information. For example, they enter information such as "Take 100 mg of aspirin every morning." This information is sent from the terminal to the server.

[1708] The server receives the user's input information and stores it in a database. At this time, the server also organizes user information by taking into account the drug concentration transition data collected from drug package inserts and interview forms, which are also registered in the database.

[1709] Next, the user makes a query such as "I forgot to take my morning dose" or "I accidentally took two doses." This query is sent from the device to the server, which analyzes the received query and inputs the relevant data into the AI ​​model.

[1710] The AI ​​model simulates the progression of drug blood levels. Based on the results of this simulation, the server generates appropriate advice, such as "It is best to wait until your next appointment or consult a doctor" or "There is a risk of overdose, so contact your doctor immediately."

[1711] Furthermore, the system of the present invention is equipped with an emotion engine that analyzes user input and voice data to recognize emotions. Based on the emotions recognized by the emotion engine, the server adjusts the content and format of advice. For example, if the user is feeling anxious, more reassuring and polite advice will be provided.

[1712] The server also monitors the user's emotional state over the long term and analyzes the history of emotional fluctuations, making it possible to assess the effectiveness of drug treatment and the risk of side effects based on the emotional fluctuations.

[1713] A specific example of processing will be shown below.

[1714] If you forget to take this morning's dose

[1715] 1. The user enters "Take 100mg of aspirin every morning" and sends it from the terminal to the server.

[1716] 2. The server stores this information in a database for future use.

[1717] 3. The user types a question such as, "I forgot to take my morning dose. What should I do?" and sends it from the device to the server.

[1718] 4. The server analyzes the question, inputs relevant data into the AI ​​model, and performs a simulation.

[1719] 5. Based on the simulation results, the server generates advice such as "wait until the next scheduled time to take your medication."

[1720] 6. The emotion engine analyzes user input and voice data and recognizes that the user is anxious.

[1721] 7. The server provides more polite and reassuring advice to anxious users.

[1722] 8. The device displays the advice to the user.

[1723] If you accidentally take two doses

[1724] 1. The user enters "Take 100mg of aspirin every morning" and sends it from the terminal to the server.

[1725] 2. The server stores this information in a database for future use.

[1726] 3. The user types a question such as, "I accidentally took two doses. Is that okay?" and sends it from the device to the server.

[1727] 4. The server analyzes the question, inputs relevant data into the AI ​​model, and performs a simulation.

[1728] 5. Based on the simulation results, the server generates advice such as "There is a risk of overdose, so contact a doctor immediately."

[1729] 6. The emotion engine analyzes the user's input and voice data and recognizes that the user is in a panic.

[1730] 7. The server provides calming advice to panicked users, encouraging them to stay calm.

[1731] 8. The device displays the advice to the user.

[1732] In this way, by combining the emotion engine, the system of the present invention can provide personalized advice based on the user's psychological state, maximizing the effectiveness and safety of drug treatment.

[1733] The processing flow will be explained below.

[1734] If you forget to take this morning's dose

[1735] Step 1:

[1736] The user logs in to the system. User authentication is performed at login, and if authentication is successful, a data entry screen is displayed.

[1737] Step 2:

[1738] The user enters their medication information, for example, "Take 100 mg of aspirin every morning," into the terminal and clicks the registration button.

[1739] Step 3:

[1740] The device sends the medication information entered by the user to the server, which packages the information in a standard data format such as JSON.

[1741] Step 4:

[1742] The server stores the received medication information in a database. When saving, it checks the data for consistency and whether there is any invalid data.

[1743] Step 5:

[1744] The server analyzes data on drug concentration trends collected from drug package inserts and interview forms, and formats the data necessary for the AI ​​model. This data is also stored in the database.

[1745] Step 6:

[1746] The user types in a query such as "I forgot to take my morning dose, what should I do?" and clicks the send button.

[1747] Step 7:

[1748] The device sends the user's query to the server in text format.

[1749] Step 8:

[1750] The server analyzes the received query and inputs relevant medication information and drug concentration data into the AI ​​model.

[1751] Step 9:

[1752] The server uses an AI model to simulate the progression of drug blood concentrations.

[1753] Step 10:

[1754] The server analyzes the simulation results and generates advice such as "wait until the next scheduled time to take your medication."

[1755] Step 11:

[1756] The emotion engine analyzes user input and voice data and recognizes that the user is anxious.

[1757] Step 12:

[1758] The server generates more polite and reassuring advice for anxious users and sends it to their terminals.

[1759] Step 13:

[1760] The device will display advice to the user, allowing them to know the appropriate response.

[1761] If you accidentally take two doses

[1762] Step 1:

[1763] The user logs in to the system. User authentication is performed at login, and if authentication is successful, a data entry screen is displayed.

[1764] Step 2:

[1765] The user enters their medication information, for example, "Take 100 mg of aspirin every morning," into the terminal and clicks the registration button.

[1766] Step 3:

[1767] The device sends the medication information entered by the user to the server, which packages the information in a standard data format such as JSON.

[1768] Step 4:

[1769] The server stores the received medication information in a database. When saving, it checks the data for consistency and whether there is any invalid data.

[1770] Step 5:

[1771] The server analyzes data on drug concentration trends collected from drug package inserts and interview forms, and formats the data necessary for the AI ​​model. This data is also stored in the database.

[1772] Step 6:

[1773] The user types in a query such as "I accidentally took two doses, what should I do?" and clicks the send button.

[1774] Step 7:

[1775] The device sends the user's query to the server in text format.

[1776] Step 8:

[1777] The server analyzes the received query and inputs relevant medication information and drug concentration data into the AI ​​model.

[1778] Step 9:

[1779] The server uses an AI model to simulate the progression of drug blood concentrations.

[1780] Step 10:

[1781] The server analyzes the simulation results and generates advice such as "There is a risk of overdose, so contact a doctor immediately."

[1782] Step 11:

[1783] The emotion engine analyzes user input and voice data and recognizes when the user is in a panic.

[1784] Step 12:

[1785] The server generates calm advice for panicked users, urging them to stay calm, and sends it to their devices.

[1786] Step 13:

[1787] The device will display advice to the user, allowing them to know the appropriate response.

[1788] In this way, by combining the emotion engine, the system of the present invention can provide personalized advice based on the user's psychological state, maximizing the effectiveness and safety of drug treatment.

[1789] Example 2

[1790] 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."

[1791] Conventional medication management systems can predict drug blood concentrations and provide advice based on medication information entered by the user, but it has been difficult to provide personalized advice that takes into account the user's psychological state. As a result, these systems have not been effective enough in reducing the user's psychological burden and anxiety regarding medication and health management. To address this issue, the present invention aims to provide a system that recognizes the user's emotions and provides personalized advice based on them.

[1792] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for inputting medication information of a drug; means for saving the input medication information in a database; means for accepting inquiries from a user; means for predicting drug concentrations in blood using an artificial intelligence model based on the accepted inquiries and simulating the progress of drug concentrations; means for generating appropriate advice based on the simulation results; means for providing an emotion engine for recognizing emotions by analyzing user input and voice data; means for adjusting the advice content based on the recognized emotions; and means for providing the generated advice to the user. This makes it possible to provide personalized advice that takes into account the psychological state of the user.

[1793] The "means for inputting medication information" refers to an interface that allows a user to input information such as the name, dosage, and time of administration of the medication via a terminal.

[1794] The "means for saving input medication information in a database" is a server-side function that registers the medication information input by the user in a database so that it can be referenced later.

[1795] "Means for accepting inquiries from users" refers to an interface that allows users to send questions or inquiries to the system, and the server receives this information.

[1796] "Means for predicting drug concentrations in the blood using an artificial intelligence model and simulating trends in drug concentrations" refers to a program that uses AI technology to predict fluctuations in drug concentrations in the blood based on input medication information and related data, and simulates those trends.

[1797] "Means for generating appropriate advice based on simulation results" refers to a server-side function that generates appropriate behavioral instructions and advice for users based on the simulation results obtained by the AI ​​model.

[1798] An "emotion engine that recognizes emotions by analyzing user input and voice data" is an engine that determines the user's emotions and psychological state at that time by analyzing the text and voice data entered by the user.

[1799] The "means for adjusting the advice content based on the recognized emotions" is a server-side function for appropriately changing the content and expression of the advice provided according to the user's emotional state recognized by the emotion engine.

[1800] The "means for providing generated advice to the user" is an interface for displaying the advice generated by the system to the user via a terminal.

[1801] "Means of collecting data on changes in drug concentration from drug package inserts and interview forms and registering it in a database" refers to a function that extracts data on changes in drug blood concentration from official drug documents and questionnaires, and registers that data in a database.

[1802] MODE FOR CARRYING OUT THE INVENTION

[1803] This invention combines a system in which medication information is input, and AI predicts changes in blood drug concentrations based on that information and provides appropriate advice, with an emotion engine that recognizes the user's emotions, to provide advice that is tailored to the user's psychological state. Specific embodiments of this system are described below.

[1804] First, a user logs in to the system and enters medication information. For example, the user enters that they take 100 mg of aspirin every morning. This information is sent from the user's device to the server. The device packages the entered information in JSON format and sends an HTTP POST request to the server.

[1805] The server then stores the medication information in a database, typically using a database management system (DBMS). The server receives the HTTP request, analyzes the data, and then executes an SQL query to insert the information into the user table in the database.

[1806] After receiving and saving the medication information, the server accepts inquiries from the user. The user types "I forgot to take my morning dose. What should I do?" into the chat box on the device's application screen and clicks the send button. The device then sends this inquiry to the server as an HTTP POST request.

[1807] The server analyzes the received query using a natural language processing (NLP) engine. The analyzed query content, along with related drug data, is then input into an AI model. The AI ​​model uses machine learning algorithms to simulate the progression of drug concentrations in the blood based on medication information and drug data. This simulation uses information from existing datasets and drug package inserts.

[1808] The simulation results generated by the AI ​​model are used by the server to generate appropriate advice, such as "It is best to wait until your next scheduled dose" or "There is a risk of overdose, so contact your doctor immediately."

[1809] Furthermore, the server is equipped with an emotion engine that recognizes emotions using user input and voice data. The emotion engine analyzes whether the user is feeling anxious or panicked. For example, if the user inputs, "I forgot my morning dose. What should I do?", the emotion engine will recognize that the user is anxious.

[1810] Based on this recognition, the server can adjust the content and format of the advice it generates: if a user feels anxious, it will provide advice in more reassuring language. In this way, the system can provide personalized advice that takes into account the user's psychological state.

[1811] As an example, the following scenario can be considered.

[1812] Example of what to do if you forget to take this morning's dose

[1813] 1. The user enters "Take 100mg of aspirin every morning" and sends it from the terminal to the server.

[1814] Example prompt: "Take 100 mg of aspirin every morning."

[1815] 2. The server stores this information in a database for future use.

[1816] 3. The user types a question such as, "I forgot to take my morning dose. What should I do?" and sends it from the device to the server.

[1817] Example prompt: "I forgot to take my morning dose. What should I do?"

[1818] 4. The server analyzes the question, inputs relevant data into the AI ​​model, and performs a simulation.

[1819] 5. Based on the simulation results, the server generates advice such as "wait until the next scheduled time to take your medication."

[1820] Sample prompt: "It's best to wait until your next scheduled dose."

[1821] 6. The emotion engine analyzes user input and voice data and recognizes that the user is anxious.

[1822] 7. The server provides more polite and reassuring advice to anxious users.

[1823] Sample prompt: "Don't worry. It's best to wait until your next dose. However, if you're concerned, talk to your doctor."

[1824] 8. The device displays the advice to the user.

[1825] In this way, the system of the present invention aims to improve the effectiveness and safety of drug treatment by combining an emotion engine to provide optimal advice according to the user's psychological state.

[1826] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1827] Processing Steps

[1828] Step 1:

[1829] The user logs into the system and enters medication information.

[1830] Input: A user enters "Take 100mg of aspirin daily in the morning" into a form.

[1831] Specific actions: The user enters medication information into the form on the application screen and clicks the submit button.

[1832] Output: The device converts the user's input information into JSON format and generates an HTTP POST request.

[1833] Step 2:

[1834] The terminal transmits the entered medication information to the server.

[1835] Input: The HTTP POST request generated by the device.

[1836] Specific operation: The device stores JSON format data in the body of the HTTP request and sends the request to the specified server endpoint.

[1837] Output: The server receives the HTTP request.

[1838] Step 3:

[1839] The server stores the received medication information in a database.

[1840] Input: Medication information received by the server in JSON format.

[1841] Specific operation: The server parses the JSON format data and saves it by issuing an INSERT query to the corresponding table in the database.

[1842] Output: A new record is added to the database.

[1843] Step 4:

[1844] The user inputs a question about medication and sends it from the terminal to the server.

[1845] Input: User types in chat box, "I forgot my morning dose. What should I do?"

[1846] Specific Actions: The user types a query into the chat box and clicks the send button.

[1847] Output: The terminal converts the query content into JSON format and generates an HTTP POST request.

[1848] Step 5:

[1849] The terminal sends the inquiry to the server.

[1850] Input: The HTTP POST request generated by the device.

[1851] Specific operation: The terminal stores the query content in JSON format in the body of an HTTP request and sends it to the server.

[1852] Output: The server receives the HTTP request.

[1853] Step 6:

[1854] The server analyzes the query and inputs the relevant data into the AI ​​model.

[1855] Input: The query received by the server in JSON format.

[1856] Specific operation: The server uses a natural language processing (NLP) engine to analyze the query, extract relevant data such as drug information, and input it into the AI ​​model.

[1857] Output: The AI ​​model is provided with input data.

[1858] Step 7:

[1859] The AI ​​model simulates the progression of drug blood concentrations.

[1860] Input: Medication information and related data fed into the AI ​​model.

[1861] How it works: The AI ​​model uses a trained neural network to predict and simulate time series data of drug concentrations in the blood.

[1862] Output: As a result of the simulation, data on the drug concentration over time is generated.

[1863] Step 8:

[1864] The server generates advice based on the simulation results.

[1865] Input: Simulation results provided by the AI ​​model.

[1866] Specific operation: The server obtains the simulation results and generates appropriate advice (e.g., "wait until the next scheduled medication time") using a rule-based engine.

[1867] Output: The generated advice is provided in text format.

[1868] Step 9:

[1869] The emotion engine analyzes user input and voice data to recognize emotions.

[1870] Input: User-provided input text or voice data.

[1871] What it does: The emotion engine uses text and speech recognition technology to determine the user's emotion (e.g., anxiety, panic).

[1872] Output: The emotion recognition result is the user's emotional state.

[1873] Step 10:

[1874] The advice content is adjusted based on the emotion recognized by the server.

[1875] Input: Emotion recognition results from the emotion engine and initial advice content.

[1876] Specific operation: The server takes into account the emotion recognition results and adjusts the wording of the advice (e.g., changes the wording to make it more reassuring).

[1877] Output: An emotion-adjusted advice is generated.

[1878] Step 11:

[1879] The device displays the advice to the user.

[1880] Input: The final advice provided by the server.

[1881] Specific operation: The device receives the advice content and displays it on the user interface (UI).

[1882] Output: The advice is ready for the user to review.

[1883] Through this process, the system can provide personalized advice based on the information entered by the user, using AI models and emotion engines.

[1884] (Application example 2)

[1885] 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."

[1886] In recent years, there has been an increasing need for more efficient and effective medication management. It is particularly important to provide prompt and accurate advice when users forget to take their medication or overdose. However, conventional systems only provide standardized advice without taking into account the user's emotional state. Therefore, there is a problem in that it is difficult to provide appropriate support when the user is feeling anxious or panicked.

[1887] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for inputting medication information on drugs; means for saving the input medication information in a database; means for accepting inquiries from users; means for predicting blood drug concentrations using an AI model based on the accepted inquiries and simulating the progress of drug concentrations; means for generating appropriate advice based on the simulation results; means for providing the generated advice to the user; means for having an emotion analysis engine and analyzing user input and voice data to recognize emotions; and means for providing appropriate advice content and format based on the recognized emotions. This makes it possible to provide personalized advice according to the user's emotional state, maximizing the effectiveness and safety of drug treatment.

[1888] "Pharmaceuticals" is a general term for chemicals and biological products used for the prevention, diagnosis, treatment, or alleviation of disease.

[1889] "Medication information" refers to data regarding the name, dosage, and timing of taking the medication the user is taking.

[1890] A "database" is an information collection system that systematically accumulates information and is designed to make it easy to search and manage.

[1891] "Inquiries" refer to questions, doubts, or inquiries that users have about the system they use.

[1892] An "AI model" is a computational algorithm or statistical model that mimics human intelligence and is capable of learning, reasoning, and self-improvement.

[1893] "Blood drug concentration" is data that indicates the amount of a particular drug present in a user's blood.

[1894] "Simulation" is a technical technique for virtually reproducing real-world situations and phenomena and conducting analysis and predictions.

[1895] "Appropriate advice" refers to specific and accurate instructions and recommendations provided based on simulation results and data analysis.

[1896] An "emotion analysis engine" is a technology that analyzes a user's text input and voice data and automatically recognizes their emotional state (joy, anger, sadness, happiness, etc.).

[1897] "Input and voice data" means text messages and voice utterances that a user enters into the system.

[1898] This invention is a system in which users input their medication information, and AI predicts the progression of drug blood concentrations based on that information and provides appropriate advice. By combining this with an emotion analysis engine that recognizes the user's emotions, the system provides advice tailored to the user's psychological state. This system is particularly applicable as a customer support app in brick-and-mortar stores (pharmacies and drugstores).

[1899] System configuration

[1900] The system consists of the following main components:

[1901] 1. User terminal: A device (such as a smartphone) through which the user enters medication information.

[1902] 2. Server: A computer system that holds a database and runs AI models and sentiment analysis engines.

[1903] 3. Database: A system (such as MongoDB) for storing drug concentration trend data and user medication information.

[1904] Program processing

[1905] The processing of this program consists of the following major steps:

[1906] 1. Getting user input:

[1907] Users enter information about their medication (such as name, dosage, and timing of administration) via a smartphone app, which is then sent from the device to a server.

[1908] 2. Data storage:

[1909] The server stores the received medication information in a database, which also includes data collected from drug package inserts and interview forms.

[1910] 3. User Inquiries:

[1911] Users can use the app to make inquiries such as, "I forgot to take my morning dose" or "I accidentally took two doses."

[1912] 4. Simulation using AI models:

[1913] Based on the queries received, the server uses an AI model (using PyTorch) to predict the progression of drug concentrations in the blood.

[1914] 5. Generating Advice:

[1915] Based on the simulation results, the server generates appropriate advice, using a sentiment analysis engine (using Google Cloud Natural Language API) to analyze the user's sentiment and provide advice accordingly.

[1916] 6. Providing advice:

[1917] The generated advice is sent to the terminal and displayed to the user.

[1918] Technical details

[1919] Hardware and software used:

[1920] User device: Smartphone (iOS or Android)

[1921] Server: Backend built with Node.js and Express

[1922] Database: MongoDB

[1923] AI Simulation: PyTorch

[1924] Sentiment analysis engine: Google Cloud Natural Language API

[1925] Specific examples

[1926] If you forget to take this morning's dose

[1927] 1. The user enters "Take 100mg of aspirin every morning" and sends it from the terminal to the server.

[1928] 2. The server stores this information in a database.

[1929] 3. The user types a question such as, "I forgot to take my morning dose. What should I do?" and sends it from the device to the server.

[1930] 4. The server analyzes the question, inputs relevant data into the AI ​​model, and performs a simulation.

[1931] 5. Based on the simulation results, the server generates advice such as "wait until the next scheduled time to take your medication."

[1932] 6. The sentiment analysis engine analyzes user input and voice data and recognizes that the user is anxious.

[1933] 7. The server provides more reassuring and courteous advice to anxious users.

[1934] 8. The device displays the advice to the user.

[1935] Prompt Sentence Examples

[1936] When a user sends a question such as "I forgot to take my medicine this morning. What should I do?", the prompt text is "Please provide advice about the next dose time. The user is feeling anxious, so please provide reassuring advice." Based on this prompt, the AI ​​model generates advice such as "Please wait until the next scheduled dose time. Also, if you feel anxious, it is best to consult a doctor. Rest assured that this will be resolved quickly."

[1937] As described above, the system of the present invention can maximize the effectiveness and safety of drug treatment by providing personalized advice that takes into account the user's emotional state.

[1938] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1939] Step 1:

[1940] Users open the app on their smartphone and enter information about their medication (such as name, dosage, and timing of administration). This information is sent from the device to the server. Input is done using text fields and drop-down menus, and the data is sent by pressing the send button. The input data includes the name of the medication, dosage, and timing of administration.

[1941] Step 2:

[1942] The server stores the received medication information in a database (MongoDB). After receiving the request, the server parses the information and stores it in the appropriate table (collection) in the database. The output is the medication information stored in the database.

[1943] Step 3:

[1944] Users input their questions (e.g., "I forgot to take my morning dose," "I accidentally took two doses," etc.) through a smartphone app and send them to the server from their device. A text field is used for input, and the question is sent by pressing the send button. The input data includes the question text.

[1945] Step 4:

[1946] The server provides the necessary data to the AI ​​model (using PyTorch) based on the received query, predicting the progression of drug concentrations in the blood. The server processes the received query, retrieves relevant medication information from the database, and inputs it into the AI ​​model. The output is simulated data on the progression of drug concentrations in the blood.

[1947] Step 5:

[1948] The server generates appropriate advice based on the simulation results. In doing so, it uses a sentiment analysis engine (using the Google Cloud Natural Language API) to analyze the user's emotional state. The server compares the simulation results with the query text and generates optimal advice. The sentiment analysis engine detects emotions from the user's input text and incorporates this emotional information into the advice generation process. The output is advice that takes the user's emotional state into account.

[1949] Step 6:

[1950] The server sends the generated advice to the terminal and provides it to the user.The server sends the generated advice to the user's terminal so that the user can view the advice on the screen.As an output, the advice displayed on the user's smartphone screen is obtained.

[1951] Step 7:

[1952] The user checks the advice displayed on the device and takes the next action if necessary. The user reads the advice and takes action (e.g., wait until the next appointment time, consult a doctor, etc.). The output is a decision on the user's action.

[1953] Through these steps, the system can provide personalized advice based on the user's emotional state, maximizing the effectiveness and safety of drug treatment.

[1954] 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.

[1955] 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.

[1956] 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.

[1957] 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.

[1958] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1959] 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.

[1960] 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).

[1961] 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, motorcycles, and other devices, 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.

[1962] 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."

[1963] 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.

[1964] 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).

[1965] 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.

[1966] 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.

[1967] 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.

[1968] 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.

[1969] 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.

[1970] 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.

[1971] 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.

[1972] 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.

[1973] 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.

[1974] 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.

[1975] The following is further disclosed regarding the above embodiment.

[1976] (Claim 1)

[1977] A means for inputting medication information;

[1978] A means for storing the input medication information in a database;

[1979] A means of receiving inquiries from users;

[1980] A means for predicting drug concentrations in the blood using an AI model based on received inquiries and simulating the progression of drug concentrations;

[1981] A means for generating appropriate advice based on the simulation results;

[1982] a means for providing the generated advice to a user;

[1983] A system including:

[1984] (Claim 2)

[1985] It has a means of collecting data on drug concentration trends from drug package inserts and interview forms and registering it in a database.

[1986] 10. The system of claim 1.

[1987] (Claim 3)

[1988] It has a means to format the medication information entered by the user and input it into the AI ​​model.

[1989] 10. The system of claim 1.

[1990] (Claim 4)

[1991] The system has a means to analyze the changes in blood drug concentrations simulated by the AI ​​model and assess the risk of incorrect medication.

[1992] 10. The system of claim 1.

[1993] "Example 1"

[1994] (Claim 1)

[1995] A means for users to input medication information;

[1996] A means for storing the input medication information in a database;

[1997] A means of receiving inquiries from users;

[1998] A means of analyzing received inquiries using natural language processing, predicting drug concentrations in the blood using a generative AI model, and simulating the progression of drug concentrations;

[1999] A means for generating appropriate advice based on the simulation results;

[2000] a means for providing the generated advice to a user;

[2001] A system including:

[2002] (Claim 2)

[2003] It has a means of collecting data on drug concentration trends from additional information on pharmaceuticals and registering it in a database.

[2004] 10. The system of claim 1.

[2005] (Claim 3)

[2006] It has a means for analyzing and formatting the medication information entered by the user and inputting it into the generative AI model.

[2007] 10. The system of claim 1.

[2008] "Application Example 1"

[2009] (Claim 1)

[2010] A means for inputting medication information;

[2011] A means for storing the input medication information in a database;

[2012] A means of receiving inquiries from users;

[2013] A means for predicting drug concentrations in the blood using an AI model based on received inquiries and simulating the progression of drug concentrations;

[2014] A means for generating appropriate advice based on the simulation results;

[2015] a means for providing the generated advice to a user;

[2016] A means of displaying advice to staff wearing smart devices;

[2017] A system including:

[2018] (Claim 2)

[2019] It has a means of collecting data on drug concentration trends from drug package inserts and interview forms and registering it in a database.

[2020] 10. The system of claim 1.

[2021] (Claim 3)

[2022] It has a means to format the medication information entered by the user and input it into the AI ​​model.

[2023] 10. The system of claim 1.

[2024] "Example 2: Combining Emotion Engines"

[2025] (Claim 1)

[2026] A means for inputting medication information;

[2027] A means for storing the input medication information in a database;

[2028] A means of receiving inquiries from users;

[2029] a means for predicting the drug concentration in the blood using an artificial intelligence model based on the received inquiry and simulating the change in the drug concentration;

[2030] A means for generating appropriate advice based on the simulation results;

[2031] a means for providing an emotion engine that analyzes user input and voice data to recognize emotions;

[2032] a means for tailoring advice based on the perceived emotions;

[2033] a means for providing the generated advice to a user;

[2034] A system including:

[2035] (Claim 2)

[2036] It has a means of collecting data on drug concentration trends from drug package inserts and interview forms and registering it in a database.

[2037] 10. The system of claim 1.

[2038] (Claim 3)

[2039] A means for formatting medication information input by a user and inputting the information into an artificial intelligence model.

[2040] 10. The system of claim 1.

[2041] "Application example 2 when combining emotion engines"

[2042] (Claim 1)

[2043] A means for inputting medication information;

[2044] A means for storing the input medication information in a database;

[2045] A means of receiving inquiries from users;

[2046] A means for predicting drug concentrations in the blood using an AI model based on received inquiries and simulating the progression of drug concentrations;

[2047] A means for generating appropriate advice based on the simulation results;

[2048] a means for providing the generated advice to a user;

[2049] a means for analyzing user input and voice data to recognize emotions, the means having an emotion analysis engine;

[2050] A means of providing appropriate advice content and format based on the perceived emotions;

[2051] A system including:

[2052] (Claim 2)

[2053] It has a means of collecting data on drug concentration trends from drug package inserts and interview forms and registering it in a database.

[2054] 10. The system of claim 1.

[2055] (Claim 3)

[2056] It has a means to format the medication information entered by the user and input it into the AI ​​model.

[2057] 10. The system of claim 1. [Explanation of symbols]

[2058] 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 inputting medication information; A means for storing the input medication information in a database; A means of receiving inquiries from users; A means for predicting drug concentrations in the blood using an AI model based on received inquiries and simulating the progression of drug concentrations; A means for generating appropriate advice based on the simulation results; a means for providing the generated advice to a user; A system including:

2. It has a means of collecting data on drug concentration trends from drug package inserts and interview forms and registering it in a database. The system of claim 1 .

3. It has a means to format the medication information entered by the user and input it into the AI ​​model. The system of claim 1 .

4. The system has a means to analyze the changes in blood drug concentrations simulated by the AI ​​model and assess the risk of incorrect medication. The system of claim 1 .

Images