Program, method for processing information, and information processor

Abstract

To provide a program which can simultaneously manage nutrition and medication of a patient.SOLUTION: The program causes a computer to execute processing of: acquiring medication information on medicines that a patient is taking and biological information of the patient; receiving input of meal information regarding meals that the patient is having; outputting a first message to manage nutrition of the patient on the basis of the biological information and the meal information; and outputting a second message prompting the patient to take medicines when the patient is supposed to take medicines, on the basis of the medication information.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a program, an information processing method, and an information processing apparatus.

Background Art

[0002] There is technology for assisting patients. For example, in Patent Document 1, a control program that presents matters to be preferentially performed by a patient based on the patient's state information and behavior information is disclosed.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In one aspect, an object is to provide a program or the like that can simultaneously perform nutritional management and medication management of a patient.

Means for Solving the Problems

[0005] In one aspect, (1) the program causes a computer to execute a process of acquiring medication information regarding medications taken by a patient and biometric information of the patient, receiving an input of dietary information regarding meals ingested by the patient, outputting a first message for nutritional management of the patient based on the biometric information and the dietary information, and outputting a second message prompting the patient to take the medication at the medication timing based on the medication information.

[0006] (2) The program of (1) above outputs a predetermined dialogue screen, receives an input of the dietary information via the dialogue screen, and outputs the first message and the second message to the dialogue screen.

[0007] (3) When the program of (1) or (2) above is input with an input sentence, it generates and outputs the first message or the second message using a pre-trained language model that generates a response sentence when an input sentence is input.

[0008] (4) The program according to any one of (1) to (3) above, wherein the meal information includes an image of the meal, recognizes the type and amount of each food included in the meal from the image, calculates the intake nutrient amount based on the recognized type and amount of each food, and outputs the first message based on the calculated intake nutrients and the biological information.

[0009] (5) The program of (4) above, wherein the meal information includes the image before the meal and the image after the meal, recognizes the type and amount of each food from each of the image before the meal and the image after the meal, calculates the intake amount of each food based on the type and amount of each food recognized from the image before the meal and the type and amount of each food recognized from the image after the meal, and calculates the intake nutrient amount based on the calculated intake amount of each food.

[0010] (6) The program according to any one of (1) to (5) above calculates the amount of nutrients required for the patient from the biological information, calculates the excess or deficiency amount of the nutrients ingested by the patient based on the required nutrient amount and the meal information, and outputs the first message indicating the calculated excess or deficiency amount.

[0011] (7) The program of (6) above calculates the excess or deficiency amounts of calories and protein as the excess or deficiency amounts of the nutrients ingested by the patient.

[0012] (8) The program according to any one of (1) to (7) above receives a reply from the user to the second message and records the medication history according to the reply content.

[0013] (9) The program according to any one of (1) to (8) above outputs an alert to medical staff according to the biological information or the meal information.

[0014] On one side, the (10) information processing method acquires medication information regarding the medications taken by a patient and the biometric information of the patient, accepts input of dietary information regarding the diet consumed by the patient, outputs a first message for the nutritional management of the patient based on the biometric information and the dietary information, and outputs a second message that prompts the patient to take the medication at the medication-taking timing based on the medication information. The computer executes the processing.

[0015] On one side, the (11) information processing apparatus is an information processing apparatus provided with a control unit, and the control unit acquires medication information regarding the medications taken by a patient and the biometric information of the patient, accepts input of dietary information regarding the diet consumed by the patient, outputs a first message for the nutritional management of the patient based on the biometric information and the dietary information, and outputs a second message that prompts the patient to take the medication at the medication-taking timing based on the medication information.

Advantages of the Invention

[0016] On one side, it is possible to simultaneously perform nutritional management and medication management of a patient.

Brief Description of the Drawings

[0017]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Mode for Carrying Out the Invention

[0018] Hereinafter, the present invention will be described in detail based on the drawings showing its embodiments. (Embodiment) FIG. 1 is an explanatory diagram showing a configuration example of a management system. In the present embodiment, a management system for nutrition management and medication management of cancer patients will be described. The management system includes an information processing device 1, a user terminal 2, a generation server 3, and a medical staff terminal 4. Each device is communicatively connected via a network N such as the Internet.

[0019] In the present embodiment, the disease is described as cancer, but the present embodiment may be applied to patients suffering from other diseases. For example, it is suitable to apply the present embodiment to cases where the patient's nutritional status is said to be poor, such as sarcopenia, frailty, heart failure, etc.

[0020] The information processing device 1 is an information processing device capable of various information processing and information transmission and reception, such as a server computer, a personal computer, etc. In the present embodiment, the information processing device 1 is assumed to be a server computer, and hereinafter it will be read as server 1 for simplicity. As will be described later, the server 1 performs nutrition management and medication management of the patient by outputting a first message for nutrition management of the patient (hereinafter referred to as "nutrition management message") and a second message for prompting the patient to take medicine (hereinafter referred to as "medication message") to the user terminal 2.

[0021] The user terminal 2 is a terminal device used by the user of this system, such as a smartphone, a tablet terminal, a personal computer, etc. For example, the user terminal 2 has a dedicated application program (hereinafter referred to as "this app") installed in advance, and by executing this app, the following screen displays and the like are performed (see FIGS. 5 to 8).

[0022] In this embodiment, a series of processes are executed on a dedicated application, but a series of processes may also be executed on a web browser.

[0023] Also, the "user" of this system is not limited to the patient himself / herself, and may be, for example, a nurse, a clinical nutritionist, a dietitian, a care worker, a family member caring for the patient, etc.

[0024] Also, in the following description, it is described that the server 1 mainly performs processes such as message generation, but this embodiment is not limited to this, and the user terminal 2, which is the client, may mainly perform the processes.

[0025] The generation server 3 is a server computer that generates a message according to a request (prompt) from the server 1. The generation server 3 generates a message using a learned LLM (Large Language Model) 50 that generates a response message when an input sentence is input. The LLM 50 is, for example, GPT (Generative Pre-trained Transformer), PaLM (Pathways Language Model), LLaMA (Large Language Model AI), etc., but its model is not particularly limited.

[0026] As will be described later, the server 1 outputs an interactive screen (see FIGS. 7 and 8A) to the user terminal 2 that can input and output messages in a chat format between the user and the system side (chatbot), and displays the messages on the interactive screen. In the present embodiment, the LLM 50 is used to generate the messages to be displayed on the interactive screen. That is, the server 1 creates a prompt for causing the LLM 50 to generate a message, outputs the prompt to the generation server 3, obtains the response sentence generated by inputting the prompt to the LLM 50 as a message to the user, and outputs it to the interactive screen.

[0027] In the present embodiment, the LLM 50 is used to generate the messages. However, the server 1 may generate rule-based fixed-form messages and output them to the user terminal 2.

[0028] The medical staff terminal 4 is a terminal device used by medical staff, such as a personal computer, a smartphone, a tablet terminal, etc. As will be described later, the server 1 may output (notify) an alert to the medical staff terminal according to the biometric information (weight) or dietary information (amount of food intake) of the patient.

[0029] FIG. 2 is a block diagram showing a configuration example of the server 1. The server 1 includes a control unit 11, a main memory unit 12, a communication unit 13, and an auxiliary storage unit 14. The control unit 11 has one or more processors such as a CPU (Central Processing Unit), an MPU (Micro-Processing Unit), and a GPU (Graphics Processing Unit), and reads and executes the program P1 stored in the auxiliary storage unit 14 to perform various information processing, control processing, and the like. The main memory unit 12 is a temporary storage area such as an SRAM (Static Random Access Memory) or a DRAM (Dynamic Random Access Memory), and temporarily stores the data necessary for the control unit 11 to execute arithmetic processing. The communication unit 13 is a communication module for performing communication-related processing, and transmits and receives information to and from the outside.

[0030] The auxiliary storage unit 14 is a non-volatile storage area such as a large-capacity memory or a hard disk, and stores a program P1 (program product) and other data necessary for the control unit 11 to execute processing. The auxiliary storage unit 14 also stores an image recognition model 40, a nutrition calculation table 141, a patient DB 142, a medication history DB 143, and a diet history DB 144.

[0031] The image recognition model 40 is a machine learning model that has learned predetermined training data, and is a model that outputs a recognition result of recognizing (detecting) each food included in the meal when an image of the meal is input. The nutrition calculation table 141 is a table referred to when calculating the amount of nutrients ingested by the patient, and is a table that defines the amount of nutrients (calories and protein) per unit weight of food in association with the food.

[0032] The patient DB 142 is a database that stores information on each patient. The medication history DB 143 is a database that stores the medication history of the patient. The diet history DB 144 is a database that stores the diet history of the patient.

[0033] Note that the auxiliary storage unit 14 may be an external storage device connected to the server 1. Further, the server 1 may be a multi-computer composed of a plurality of computers, or may be a virtual machine virtually constructed by software.

[0034] In addition, in the present embodiment, the server 1 is not limited to the above configuration, and may include, for example, an input unit that receives operation inputs, a display unit that displays images, and the like. Further, the server 1 may be provided with a reading unit that reads a portable storage medium 1a such as a CD (Compact Disk)-ROM or a DVD (Digital Versatile Disc)-ROM, and reads and executes the program P1 from the portable storage medium 1a.

[0035] FIG. 3 is an explanatory diagram showing an example of the record layouts of the nutrition calculation table 141, the patient DB 142, the medication history DB 143, and the dietary history DB 144.

[0036] The nutrition calculation table 141 includes a food ID column, a food name column, and a nutrition amount column. The food ID column stores the food ID, which is the identifier of each food. The food name column and the nutrition amount column store the food name and the nutrition amount per unit weight, respectively, in association with the food ID. For example, the nutrition amount column stores the calorie and protein amounts per unit weight.

[0037] The patient DB 142 includes a patient ID column, a patient name column, a biological information column, and a medication information column. The patient ID column stores the patient ID, which is the identifier of each patient. The patient name column, the biological information column, and the medication information column store the patient name, the patient's biological information, and the medication information regarding the drugs taken by the patient, respectively, in association with the patient ID. The biological information column stores, for example, the patient's weight, height, fat-free weight, etc. The medication information column stores, for example, the drug name, dosage, administration timing, etc. taken by the patient.

[0038] The medication history DB 143 includes a patient ID column, a date and time column, a medication column, and a medication presence / absence column. The patient ID column stores the patient ID. The date and time column, the medication column, and the medication presence / absence column store the date and time, the drug name, and whether the drug has been taken, respectively, in association with the patient ID.

[0039] The dietary history DB 144 includes a patient ID column, a date column, a meal type column, an image information column, and an ingested nutrition amount column. The patient ID column stores the patient ID. The date column, the meal type column, the image information column, and the ingested nutrition amount column store the date, the meal type, the meal image, and the nutrition amount estimated to be ingested in the meal, respectively, in association with the patient ID. The image information column stores, for example, the input time of the image and the meal image, divided into before and after the meal. The ingested nutrition amount column stores, for example, the ingestion amounts of calories and proteins, respectively.

[0040] FIG. 4 is a block diagram showing a configuration example of the user terminal 2. The user terminal 2 includes a control unit 21, a main memory unit 22, a communication unit 23, a display unit 24, an input unit 25, an imaging unit 26, and an auxiliary storage unit 27. The control unit 21 has a processor such as one or more CPUs, and performs various information processes by reading and executing the program P2 stored in the auxiliary storage unit 27. The main memory unit 22 is a temporary storage area such as a RAM, and temporarily stores data necessary for the control unit 21 to execute arithmetic processing. The communication unit 23 is a communication module for performing communication-related processing, and transmits and receives information to and from the outside. The display unit 24 is a display screen such as a liquid crystal display, and displays an image. The input unit 25 is an operation interface such as a touch panel, and receives an operation input from the user. The imaging unit 26 is a camera including an imaging element such as a CMOS (Complementary MOS) sensor, and captures an image. The auxiliary storage unit 27 is a non-volatile storage area such as a hard disk, and stores the program P2 (program product) and other data necessary for the control unit 21 to execute processing.

[0041] Note that the user terminal 2 may include a reading unit for reading a portable storage medium 2a such as a CD-ROM, and may read and execute the program P2 from the portable storage medium 2a.

[0042] FIGS. 5 to 8 are diagrams showing display screen examples of the user terminal 2. Based on FIGS. 5 to 8, the outline of the present embodiment will be described.

[0043] FIG. 5 is a diagram showing an example of an initial registration screen. When the present application is initially used, the user terminal 2 displays the screen shown in FIG. 5. The screen is a screen for registering medication information regarding the medicine that the patient takes and the biological information of the patient.

[0044] For example, the user terminal 2 receives an input of the name of the medicine that the patient takes and the way of taking the medicine (the amount of each dose and the timing of taking) as the medication information. Note that a plurality of medicines can be registered on the screen.

[0045] In addition, the user terminal 2 accepts input of the patient's weight, height, and fat-free weight as biometric information. In addition to weight and the like, the user terminal 2 may also accept input of items that can be measured by a general household scale. For example, the user terminal 2 may accept input of muscle mass, skeletal muscle mass, body fat percentage, subcutaneous fat, visceral fat level, protein, etc.

[0046] The server 1 associates the medication information and biometric information input on the registration screen with the patient ID and stores them in the patient DB 142.

[0047] Note that the user terminal 2 may display the registration screen according to an operation input from the user or periodically, and accept changes in the setting of the medication information and biometric information from the user.

[0048] FIG. 6 is a diagram showing an example of the display of a medication message. When it is time to take the medicine with reference to the medication information registered above, the server 1 outputs (notifies) a medication message prompting the user to take the medicine to the user terminal 2 and causes it to be displayed.

[0049] For example, when the user terminal 2 (such as a smartphone) is in the sleep mode, as shown on the left side of FIG. 6, the user terminal 2 displays a medication message indicating that it is time to take the medicine on the lock screen. Also, when the user is using this application, as shown on the right side of FIG. 6, the user terminal 2 displays a medication message indicating the name of the medicine to be taken and the dosage as an alert.

[0050] Various methods can be considered for determining the timing (time) of outputting the medication message. For example, the server 1 may determine the time at which to output (notify) the medication message for each medicine in advance, and output the medication message when that time arrives. For example, for a medicine with a dosing time of "before breakfast", it can be set to "7:00 am", and for a medicine with a dosing time of "after breakfast", it can be set to "8:00 am", and the timing at which the medication message should be output can be tabulated.

[0051] Alternatively, Server 1 may estimate the time when a medication message should be output from the history of the input times of the dietary information (diet images) described later, and output the medication message when that time arrives. For example, if the medication timing is "before breakfast" and the average input time of the dietary information for breakfast is "7:00 am", a medication message is output at "7:00 am".

[0052] FIG. 7 is a diagram showing an example display of a dialogue screen. FIG. 7 illustrates an example screen for replying to a medication message. When the user terminal 2 receives an operation input to the medication message exemplified in FIG. 6, the user terminal 2 displays the screen shown in FIG. 7.

[0053] The dialogue screen is a screen on which messages can be input and output in a chat format between the user and the system side (chatbot). The user terminal 2 receives inputs such as text and images from the user on the dialogue screen and displays the response text output from the server 1. In the present embodiment, as described above, the server 1 generates a message using the LLM 50 that generates a response text when an input text is input, and displays it on the dialogue screen.

[0054] The user terminal 2 displays a medication message asking whether the medicine has been taken on the dialogue screen and receives a reply as to whether the medicine has been taken. For example, the server 1 outputs a prompt including the name of the medicine to be taken by the patient to the generation server 3, and obtains the response text generated by inputting the prompt to the LLM 50 as a medication message to the user. The user terminal 2 displays the medication message and also displays options of "Yes" and "No". The user terminal 2 receives an input for selecting one of the options. In this way, the user terminal 2 receives a reply to the medication message.

[0055] The server 1 records the medication history by associating the reply content with the patient ID, date and time, medicine name, etc. and storing it in the medication history DB 143. The medication history can be confirmed (displayed) on this application. Also, the server 1 may output the medication history of the patient by the patient to the medical staff terminal 4.

[0056] FIG. 8 is a diagram showing an example of display of a nutrition management message. FIG. 8A illustrates an example of display when inputting meal information on an interactive screen, and FIG. 8B illustrates an example of display when inputting meal information on an input screen for meal information.

[0057] The meal information is information regarding the meals consumed by the patient, and is, for example, an image of the meals consumed by the patient. In the present embodiment, as the meal information, inputs of an image captured before the meal and an image captured after the meal are accepted.

[0058] Note that, in the present embodiment, although the description will be given assuming that inputs of images are accepted as the meal information, the present embodiment is not limited thereto. For example, the user terminal 2 may be configured to accept inputs of the types of foods consumed by the patient and the intake amounts of each food. Alternatively, when the meal (food) consumed by the patient is a processed food or the like, the user terminal 2 may accept, as the meal information, an input of an image of the package label thereof, and acquire intake amounts such as calories and protein from the image by character recognition. Or, instead of just meals, enteral nutritional agents that are administered to the patient via a tube for nutritional supplementation may also be used.

[0059] For example, as shown in FIG. 8A, the user terminal 2 displays, on the interactive screen, a message prompting the input of an image before the meal, and accepts the input of the image before the meal. Subsequently, the user terminal 2 displays, on the interactive screen, a message prompting the input of an image after the meal, and accepts the input of the image after the meal.

[0060] The server 1 calculates the amount of nutrition consumed by the patient from the input images of the meals. Then, the server 1 calculates the excess or deficiency amount of nutrition (particularly the deficiency amount in the present embodiment), and outputs a nutrition management message for performing nutrition management of the patient according to the excess or deficiency amount, and causes the user terminal 2 to display it.

[0061] FIG. 9 is a diagram related to the generation process of nutrition management messages. In FIG. 9, it illustrates the state of calculating the excess or deficiency amount of nutrition from biological information and dietary information and generating nutrition management messages using the LLM 50.

[0062] First, the server 1 uses the image recognition model 40 to recognize the type and quantity of each food included in the meal from each of the pre-meal image and the post-meal image. The image recognition model 40 is a machine learning model that has learned training data to recognize (detect) each food (and reference object) included in the meal when an image of the meal is input, and is, for example, a CNN (Convolutional Neural Network; convolutional neural network).

[0063] Note that the image recognition model 40 may be a neural network other than the CNN. Also, the image recognition model 40 may be a machine learning model other than a neural network, such as an SVM (Support Vector Machine) or a decision tree.

[0064] Also, in the present embodiment, a machine learning model is used for image recognition, but image recognition may be performed by rule-based pattern matching based on image features.

[0065] The server 1 inputs each of the pre-meal image and the post-meal image into the image recognition model 40, and recognizes various types of foods from each of the pre-meal image and the post-meal image. For example, when the server 1 performs the recognition of the food, it also recognizes the reference object included in the image. The reference object is an object used as a reference when recognizing the quantity (size) of each food, and is, for example, tableware such as chopsticks, forks, cups, and dishes.

[0066] The server 1 estimates the quantity (weight) of each food according to the size (area) of each food with respect to the size (area) of the reference object. The server 1 performs the estimation for each of the pre-meal image and the post-meal image, recognizes the type and quantity of each food from the pre-meal image, and recognizes the type and quantity of each food from the post-meal image.

[0067] Server 1 calculates the amount (weight) of each food ingested by the patient for each food by taking the difference between the type and amount of each food recognized from the pre-meal image and the type and amount of each food recognized from the post-meal image. Server 1 refers to the nutrition calculation table 141 that defines the amount of nutrition per unit weight of each food, and calculates the ingested nutrition amount from the ingested amount of each food of the patient. Specifically, in this embodiment, Server 1 calculates the ingested amount of calories and protein, respectively, in particular to cope with the weight loss of cancer patients.

[0068] In this embodiment, although the calculation of the ingested amounts of calories and protein is described, other nutrients (lipids, saturated fatty acids, n-6 fatty acids, n-3 fatty acids, cholesterol, carbohydrates, dietary fiber, sugars, vitamin A, vitamin D, vitamin E, vitamin K, vitamin B1, vitamin B2, niacin, vitamin B6, vitamin B12, folic acid, pantothenic acid, biotin, vitamin C, sodium, potassium, calcium, magnesium, phosphorus, chlorine, iron, zinc, copper, manganese, iodine, selenium, chromium, molybdenum, sulfur, carnitine, choline, etc.) may also be calculated.

[0069] Server 1 calculates the amount of nutrition required for the patient in one meal (hereinafter referred to as "required nutrition amount") based on the patient's biological information. Specifically, Server 1 calculates the amounts of calories and protein required in one meal according to the patient's weight, height, etc.

[0070] Server 1 calculates the excess or deficiency amount of nutrition (specifically, the deficiency amount in this embodiment) based on the ingested nutrition amount calculated above and the required nutrition amount. That is, Server 1 calculates the difference value between the ingested amount and the required amount for each of calories and protein.

[0071] Server 1 creates a prompt including the calculated excess or deficiency amount of nutrition and outputs it to the generation server 3. Then Server 1 obtains the response text generated by inputting the prompt to the LLM 50 as a nutrition management message.

[0072] For example, as shown in FIG. 9, the server 1 creates a prompt that includes the text "You are an expert in nutritional management" that specifies the role to be played by the LLM 50, the text "Please provide... according to the following output format" that requests the generation of a nutritional management message, the output format (description rules) of the nutritional management message, and the excess or deficiency amount of nutrients to be referred to when generating the nutritional management message. The generation server 3 generates a nutritional management message by inputting the prompt to the LLM 50.

[0073] When creating the prompt, if the server 1 determines that the amount of nutrients is insufficient (when the difference value obtained by subtracting the required nutrient amount from the ingested nutrient amount is negative), it is preferable to create a prompt that specifies identifying foods that can supplement the deficiency from the nutritional calculation table 141 and including the foods in the nutritional management message. Thereby, as described below, it is possible to prompt the user as to what foods should be ingested to supplement the deficiency amount.

[0074] Returning to FIG. 8 to continue the explanation. The user terminal 2 displays the above-generated nutritional management message on the dialogue screen. For example, as shown at the end of the dialogue screen in FIG. 8A, the user terminal 2 displays a nutritional management message indicating the deficiency amounts of protein and calories (energy) respectively, and foods for supplementing the deficiency amounts. In this way, when the user terminal 2 receives an input of dietary information (an image of a meal) from the user, it displays a nutritional management message for the nutritional management of the patient.

[0075] The input of dietary information and the display of the nutritional management message can also be performed on a screen other than the dialogue screen. FIG. 8B illustrates an example of a screen for inputting dietary information. The user terminal 2 receives the input of pre-meal and post-meal images on the screen shown on the left side of FIG. 8B. If an excess or deficiency occurs as a result of calculating the ingested nutrient amount from the images, the user terminal 2 transitions to the screen shown on the right side of FIG. 8B and displays a nutritional management message.

[0076] As described above, according to the present embodiment, based on the patient's medication information, biological information, and dietary information, a nutrition management message and a medication message are presented. Thereby, the patient's nutrition management and medication management can be performed simultaneously.

[0077] In addition, when the server 1 detects a decrease in the patient's weight and food intake according to the patient's biological information and dietary information, it is preferable to output (notify) an alert to the medical staff terminal 4. Thereby, the medical staff can be notified of the deterioration of the patient's symptoms.

[0078] FIGS. 10 and 11 are flowcharts showing an example of the processing procedure executed by the server 1. In the following description, it is assumed that the user has already completed the initial registration, and the biological information and medication information are registered (stored) in the patient DB 142.

[0079] FIG. 10 is a flowchart showing the procedure of the output process of the medication message. Based on FIG. 10, the processing content when outputting the medication message will be described. The control unit 11 of the server 1 determines whether it is the medication timing at which the patient should take the medicine (step S11). For example, the control unit 11 may define the time at which the patient should take each medicine, or may estimate the time at which the medication message should be output from the history of the input time of the dietary information (image of the meal). If it is determined that it is not the medication timing (S11: NO), the control unit 11 waits for the process.

[0080] If it is determined that it is the medication timing (S11: YES), the control unit 11 outputs a medication message (second message) prompting the patient to take the medicine to the user terminal 2 (step S12). For example, the control unit 11 outputs a prompt including the name of the medicine to be taken by the patient to the generation server 3, and acquires the response sentence generated by inputting the prompt to the LLM 50 as the medication message. The control unit 11 outputs the acquired medication message to the user terminal 2 and displays it on the lock screen, the dialogue screen, etc. as shown in FIG. 6.

[0081] The control unit 11 receives a reply indicating whether the medicine has been taken or not in response to the medicine-taking message (step S13). Based on the content of the reply, the control unit 11 records a medicine-taking history indicating whether the patient has taken the medicine in the medicine-taking history DB 143 (step S14). The control unit 11 ends a series of processes.

[0082] Figure 11 is a flowchart showing the procedure of the output process of the nutrition management message. Based on Figure 11, the processing content when outputting the nutrition management message will be described. The control unit 11 of the server 1 receives an input of dietary information regarding the meals consumed by the patient from the user terminal 2 (step S31). The dietary information is, for example, an image of the meal. Specifically, the control unit 11 receives an input of each of the pre-meal image and the post-meal image.

[0083] The control unit 11 recognizes the type and quantity of each food included in the meal from the acquired meal image (step S32). For example, the control unit 11 inputs the pre-meal image and the post-meal image into the image recognition model 40 respectively, to recognize (detect) each food and the reference object from each of the pre-meal image and the post-meal image. The control unit 11 estimates the quantity of each food based on the size (area occupied in the image) of the food with respect to the size (area) of the reference object. The control unit 11 calculates the intake amount of each food based on the type and quantity of each food recognized from the pre-meal image and the type and quantity of each food recognized from the post-meal image (step S33). The control unit 11 refers to the nutrition calculation table 141 and calculates the ingested nutrient amount from the intake amount of each food calculated in step S33 (step S34). Specifically, the control unit 11 calculates the intake amounts of calories and protein.

[0084] The control unit 11 calculates the required nutrient amount necessary for the patient in one meal based on the patient's biological information (step S35). The control unit 11 calculates the excess or deficiency amount of nutrients based on the ingested nutrient amount calculated in step S34 and the required nutrient amount calculated in step S35 (step S36).

[0085] Based on the calculated excess or deficiency of nutrients, the control unit 11 outputs a nutrition management message (first message) for the patient's nutrition management to the user terminal 2 (step S37). Specifically, as described above, the control unit 11 generates a prompt including the excess or deficiency of nutrients calculated in step S36 and outputs it to the generation server 3, and obtains the response sentence generated by inputting the prompt into the LLM 50 as the nutrition management message. In particular, as a result of calculating the excess or deficiency of nutrients in step S36, if the nutrients are insufficient, the control unit 11 creates, in addition to the amount of nutrient deficiency, a prompt indicating foods for supplementing the deficiency amount, and inputs it into the LLM 50 to obtain a nutrition management message indicating the amount of nutrient deficiency and the foods for supplementing the deficiency amount. The control unit 11 outputs the obtained nutrition management message to the user terminal 2 and displays it on the dialogue screen, the screen for inputting dietary information, etc., as shown in FIGS. 8A and 8B. The control unit 11 ends a series of processes.

[0086] As described above, according to the present embodiment, the patient's nutrition management and medication management can be performed simultaneously.

[0087] (Modification example) In the above-described embodiment, the form of recording the medication history by receiving a reply to the medication message from the user has been described. On the other hand, it may be configured to automatically detect that the patient has taken the medicine and record the medication history.

[0088] As a technique for automatically detecting that the medicine has been taken, the technique described in U.S. Patent No. 9,756,874 can be used. Specifically, a transmitter is embedded in the medicine capsule. When the capsule is dissolved by gastric juice, the electrodes of the transmitter are exposed and current flows through the gastric juice. As a result, a radio signal is transmitted from the transmitter.

[0089] For example, the user terminal 2 receives the signal via a predetermined receiver (not shown). Thereby, it is detected that the patient has taken the medicine. The server 1 obtains the reception result of the radio signal from the user terminal 2 and records it as the medication history.

[0090] As described above, according to this modification example, the medication history can be automatically recorded without the user having to record (reply) that they have taken the medicine.

[0091] The embodiments disclosed this time should be considered as illustrative in all respects and not restrictive. The scope of the present invention is shown not by the above meaning but by the claims, and it is intended that all modifications within the meaning and scope equivalent to the claims are included.

[0092] The matters described in each embodiment can be combined with each other. Also, the independent claims and dependent claims described in the claims can be combined with each other in all possible combinations regardless of the citation form. Furthermore, although the claims use a form (multi-claim form) of describing claims that cite two or more other claims, it is not limited to this. It may be described using a form of describing a multi-claim (multi-multi-claim) that cites at least one multi-claim.

Explanation of Reference Numerals

[0093] 1 Server (information processing device) 11 Control unit 12 Main memory unit 13 Communication unit 14 Auxiliary storage unit P1 Program 40 Image recognition model 141 Nutrition calculation table 142 Patient DB 143 Medication history DB 144 Diet history DB 2 User terminal 21 Control unit 22 Main memory unit 23 Communication unit 24 Display unit 25 Input unit 26 Imaging unit 27 Auxiliary storage unit P2 Program 3 Generation server 50 LLM 4 Healthcare Worker Terminals

Claims

1. Obtain medication information regarding the medication taken by the patient and the biometric information of the patient, Accept the input of dietary information regarding the diet consumed by the patient, Based on the biometric information and dietary information, output a first message for the nutritional management of the patient, Based on the medication information, output a second message prompting the patient to take the medication at the medication timing A program for causing a computer to execute the process.

2. Output a predetermined dialogue screen, Accept the input of the dietary information via the dialogue screen, Output the first message and the second message on the dialogue screen The program according to claim 1.

3. Generate and output the first message or the second message using a learned language model that generates a response sentence when an input sentence is input The program according to claim 1.

4. The dietary information includes an image of the meal taken, Recognize the type and quantity of each food included in the meal from the image, Calculate the intake nutrient amount based on the recognized type and quantity of each food, Output the first message based on the calculated intake nutrients and the biometric information The program according to claim 1.

5. The dietary information includes the image before the meal and the image after the meal, Recognize the type and quantity of each food from each of the image before the meal and the image after the meal, Based on the type and quantity of each food recognized from the image before the meal and the type and quantity of each food recognized from the image after the meal, calculate the intake amount of each food, Calculate the intake nutrient amount based on the calculated intake amount of each food The program according to claim 4.

6. Calculate the required nutrient amount for the patient from the biometric information, Based on the required nutrient amount and the dietary information, calculate the excess or deficiency amount of the nutrients consumed by the patient, Output the first message indicating the calculated excess or deficiency amount The program according to claim 1.

7. Calculate the excess or deficiency amount of calories and protein as the excess or deficiency amount of the nutrients consumed by the patient The program according to claim 6.

8. Accept a reply from the user to the second message, Record the medication history according to the reply content The program according to claim 1.

9. Output an alert to medical staff according to the biometric information or dietary information The program according to claim 1.

10. Obtain medication information regarding the medication taken by the patient and the biometric information of the patient, receiving an input of dietary information regarding the diet consumed by the patient, outputting a first message for nutritional management of the patient based on the biological information and the dietary information, outputting a second message prompting the patient to take the medicine at the medicine-taking timing based on the medicine-taking information An information processing method executed by a computer.

11. An information processing apparatus including a control unit, wherein the control unit acquires medicine-taking information regarding the medicine taken by the patient and the biological information of the patient, receives an input of dietary information regarding the diet consumed by the patient, outputs a first message for nutritional management of the patient based on the biological information and the dietary information, outputs a second message prompting the patient to take the medicine at the medicine-taking timing based on the medicine-taking information An information processing apparatus.

Images