Diagnostic aids, health aids, diagnostic aids, and health aids

Abstract

This invention provides diagnostic assistance methods, health assistance methods, diagnostic assistance devices, and health assistance devices, enabling high-granularity judgment of sensor data. The diagnostic assistance methods include: an acquisition step, which acquires sensor data detected by the sensor and lifestyle information related to the user's lifestyle habits, and records them in a time series; an extraction step, which extracts selected lifestyle habit association information associated with the sensor data from the lifestyle habit information; and an output step, which combines the selected lifestyle habit association information with the sensor data.

Description

Technical Field

[0001] This disclosure relates to diagnostic aids, health aids, diagnostic aids, and health aids. Background Technology

[0002] In recent years, driven by increased health awareness, reduced medical costs, and the need to improve patients' quality of life, there has been a rise in health management. People are no longer simply seeking medical attention after noticing illness; instead, they are increasingly using daily behavioral records and vital data to re-examine their lifestyles and manage their health from the time they are healthy. Furthermore, the widespread availability of portable devices has made such management easier in terms of technology and infrastructure.

[0003] For example, Patent Document 1 discloses a technique for predicting a user's future physical condition based on historical sensor information obtained from sensors around the user that contains information related to the user.

[0004] Existing technical documents

[0005] Patent documents

[0006] Patent Document 1: International Publication No. 2019 / 116679 Summary of the Invention

[0007] The problem that the invention aims to solve

[0008] However, daily records using the various sensors described above are not only important for maintaining the user's health, but also serve as important background data in the event of a noticeable symptom.

[0009] However, relying solely on sensor data such as steps, heart rate, and weight only reveals daily changes in a user. Even when changes occur, it's difficult to infer any underlying health issues. For example, if a user diligently walks 10,000 steps daily and suddenly reduces their steps, it's difficult to deduce whether it's due to poor health or other reasons. In other words, if changes in step count occur, such as a user who used to walk while working from home changing jobs to commuting by car, accurate judgment is impossible without considering these factors. Without proper assessment, the user may develop more serious health problems, but conventional technologies like those in Patent Document 1 cannot provide accurate information.

[0010] This disclosure was made in view of the above circumstances, and its purpose is to provide a diagnostic assistance method, a diagnostic assistance method, a health assistance method, a diagnostic assistance device, and a health assistance device capable of making high-granular judgments on sensor data.

[0011] Methods for solving problems

[0012] To address the aforementioned problems and achieve the objective, the diagnostic assistance method disclosed herein is executed by a diagnostic assistance device equipped with a processor, wherein the processor includes the following steps: an acquisition step, which acquires sensor data detected by the sensor and lifestyle information related to the user's lifestyle, and records them in a time sequence; an extraction step, which extracts selected lifestyle association information associated with the sensor data from the lifestyle information; and an output step, which outputs the selected lifestyle association information and the sensor data.

[0013] Furthermore, it is envisioned for users who manage their own health, but it can also be used to assist medical professionals who examine that person in making diagnoses.

[0014] In addition, in the above disclosure, the diagnostic assistance method of this invention includes multiple items for the sensor data and the lifestyle information. In the acquisition step, multiple sensor data detected by multiple sensors are acquired. In the extraction step, based on the items included in the sensor data representing characteristic tendencies in the multiple sensor data, specific behavioral history information is selected from the user's multiple behavioral history information, and the specific behavioral history information is extracted as the selected lifestyle association information.

[0015] Furthermore, in the above-disclosed diagnostic assistance method, the diagnostic assistance device can access a knowledge database consisting of at least symptoms caused by lifestyle habits, treatment methods for the symptoms, and sensor data caused by the symptoms. The processor also performs the following steps: a symptom acceptance step, accepting the user's symptom input; and a retrieval step, retrieving sensor data features and lifestyle habits associated with the accepted symptom from the knowledge database. In the extraction step, based on the retrieval results of the retrieval step, the selected lifestyle habit-related information is extracted.

[0016] In addition, in the above disclosure, the diagnostic assistance method of this disclosure, in the output step, generates report information based on the association information and the sensor data, and outputs the selected lifestyle association information and the report information.

[0017] In addition, in the above disclosure of the diagnostic assistance method, the sensor data includes at least the user's vital signs data, and the processor also performs a condition determination step: determining whether the vital signs data recorded in a time series are good or bad.

[0018] Furthermore, in the above-disclosed diagnostic aid method, in the extraction step, the selected lifestyle-related information is extracted based on the judgment result of the quality of the vital data and the retrieval result of the retrieval step.

[0019] Furthermore, in the above disclosure, the diagnostic assistance method of this invention outputs the user's changing status based on the vital data in the output step.

[0020] Furthermore, in the above-disclosed diagnostic assistance method, in the output step, if the determination result of the vital data is negative, an output message recommending that the patient visit an associated medical institution retrieved from the knowledge database based on the symptoms is provided.

[0021] Furthermore, in the above-disclosed diagnostic assistance method, during the output step, if the output of the selected lifestyle association information is requested from an external machine, only the association information that has been pre-approved by the user is output to the external machine.

[0022] Furthermore, the health assistance method disclosed herein is a health assistance method executed by a health assistance device equipped with a processor, the processor comprising the following steps: an acquisition step, acquiring sensor data sets obtained by detecting multiple items of the user's vital data and life habit information of multiple items related to the user's lifestyle, and recording them in a time sequence; an extraction step, retrieving a knowledge database and extracting health-related information associated with the vital data of specific items in the sensor data set; and an output step, outputting the health-related information and historical information of the lifestyle corresponding to the health-related information from the recording results recorded in the time sequence.

[0023] In addition, in the above disclosure, the processor in the health assistance method of this invention further includes a determination step: determining specific life data representing changes or specific tendencies in the life data of the plurality of items, and in the extraction step, performing an item retrieval based on the user's specific life data and the life habits of the user using the knowledge database.

[0024] In addition, in the above disclosure, the processor in the health assistance method further includes a symptom input step: accepting the user's symptom input, and in the extraction step, retrieving the knowledge database and extracting the health-related information based on the user's symptom input.

[0025] Furthermore, in the above disclosure, the knowledge database of the health assistance method of this invention is a recording medium that organizes and records at least one life data or lifestyle tendency related to the relationship between health and disease according to each disease.

[0026] In addition, in the above disclosure, the processor in the health assistance method of this invention further includes a detection step: detecting changes and timing of changes in the specific vital data, and in the output step, outputting historical information of the lifestyle habits including the period prior to the timing of the changes.

[0027] Furthermore, the health assistance method disclosed herein is a health assistance method executed by a health assistance device equipped with a processor, the processor comprising the following steps: an acquisition step, acquiring the output of a sensor data group that detects multiple items of vital data of a user and lifestyle information of multiple items related to the user's lifestyle, and recording the lifestyle information of the multiple items in a time sequence; and an output step, based on the recording results of the lifestyle information of the multiple items recorded in a time sequence, outputting historical information of lifestyle corresponding to changes in the vital data of a specific item of the sensor data group.

[0028] Furthermore, the health assistance method disclosed herein is a health assistance method executed by a health assistance device equipped with a processor, the processor comprising the following steps: an acquisition step, acquiring sensor data obtained from detecting the user's vital data and lifestyle information related to the user's lifestyle habits, and recording them according to a time series; and an output step, inferring the future health state by inputting the time series information of the sensor data and the time series information of the lifestyle habits into an inference model, wherein the inference model is an inference model learned using training data, and the training data labels the time series information of the lifestyle habits and the time series information of the vital data corresponding to the period in which the data was acquired with the name, symptoms, and diagnosis results of the disease that occurred.

[0029] In addition, the diagnostic aid device disclosed herein includes: an acquisition unit that acquires sensor data detected by a user and lifestyle information related to the user's lifestyle, and records them in a time sequence; an extraction unit that extracts selected lifestyle association information associated with the sensor data from the lifestyle information; and an output control unit that outputs the selected lifestyle association information and the sensor data.

[0030] Furthermore, the health assist device disclosed herein includes: an acquisition unit that acquires a set of sensor data obtained by detecting multiple items of a user's vital data and information on multiple items of the user's lifestyle habits, and records them in a time sequence; an extraction unit that searches a knowledge database and extracts health-related information associated with specific items of the vital data in the sensor data set; and an output control unit that outputs the health-related information and historical information on the lifestyle habits corresponding to the health-related information based on the recording results recorded in the time sequence.

[0031] In addition, the health assistance device disclosed herein includes: an acquisition unit that acquires the output of a sensor data set that detects multiple items of a user's vital signs and the information on multiple items of the user's lifestyle habits, and records the information on the multiple items of the lifestyle habits in a time sequence; and an output control unit that outputs historical information on lifestyle habits corresponding to changes in the vital signs of specific items in the sensor data set based on the recording results of the information on the multiple items of the lifestyle habits recorded in a time sequence.

[0032] Furthermore, the health assistance device disclosed herein includes: an acquisition unit that acquires sensor data obtained from detecting a user's vital data and lifestyle information related to the user's lifestyle habits, and records them in a time sequence; and an output control unit that infers the future health state by inputting the time sequence information of the sensor data and the time sequence information of the lifestyle habits into an inference model, wherein the inference model is an inference model learned using training data, and the training data labels the time sequence information of the lifestyle habits and the time sequence information of the vital data corresponding to the period in which the data is acquired with the name, symptoms, and diagnosis results of the disease that occurs.

[0033] Invention Effects

[0034] According to this disclosure, it enables the granular judgment of sensor data. Attached Figure Description

[0035] Figure 1 This is a schematic structural diagram of a diagnostic aid system according to one implementation method.

[0036] Figure 2 This is a block diagram illustrating the functional structure of a portable terminal according to one embodiment.

[0037] Figure 3 This diagram illustrates an example of time information recorded by the time information recording unit of a portable terminal according to one embodiment.

[0038] Figure 4This is a block diagram illustrating the functional structure of a medical system according to one implementation method.

[0039] Figure 5 This diagram illustrates an example of knowledge data registered in the knowledge database of the recording unit of a medical system according to one embodiment.

[0040] Figure 6 This is a timing diagram illustrating a summary of the processing performed by a portable terminal according to one embodiment.

[0041] Figure 7 This is a timing diagram that represents a summary of the processing performed by the portable terminal when a user inputs symptoms.

[0042] Figure 8 It means in Figure 7 This is an example of an image displayed on the display unit during processing.

[0043] Figure 9 It means in Figure 7 Another example of the image displayed on the display unit during processing.

[0044] Figure 10 This is a sequence diagram that represents the user's portable terminal and the processing of medical terminals when they visit a medical institution.

[0045] Figure 11 It means in Figure 10 This is an example of an image displayed on the doctor's terminal during processing.

[0046] Figure 12 This is a flowchart illustrating a summary of the processing performed by a portable terminal according to one embodiment.

[0047] Figure 13 This is a flowchart illustrating a summary of the processes performed by a medical system according to one embodiment. Detailed Implementation

[0048] The following describes in detail the methods for implementing this disclosure with reference to the accompanying drawings. Furthermore, this disclosure is not limited to the embodiments described below. Additionally, the figures referred to in the following description are merely schematic representations of shapes, sizes, and positional relationships to a degree sufficient for understanding the content of this disclosure. That is, this disclosure is not limited to the shapes, sizes, and positional relationships illustrated in the figures. Furthermore, in the following description, a mobile phone is used as an example of a diagnostic aid device, but tablet-type terminal devices and personal computers, etc., can also be used in addition to mobile phones.

[0049] [Overview of Diagnostic Support Systems]

[0050] Figure 1 This is a schematic structural diagram of a diagnostic aid system according to one implementation method. Figure 1 The diagnostic assistance system 1 shown includes a portable terminal 10 that functions as a diagnostic assistance device and a medical system 20. The portable terminal 10 and the medical system 20 are connected via a network N100 in a manner capable of bidirectional communication. This network N100 is, for example, an internet line network or a mobile telephone line network. User U1 accesses the medical system 20 using the portable terminal 10.

[0051] [Functional Structure of Portable Terminals]

[0052] Figure 2 This is a block diagram representing the functional structure of the portable terminal 10. Figure 2 The portable terminal 10 shown acquires sensor data detected by sensors such as those from a smart toilet and a weighing scale, as well as lifestyle information related to the user's habits, and records it in a time series. After extracting the correlation information associated with the sensor data from the lifestyle information, it outputs the correlation information and the sensor data. Here, the correlation information is recorded as lifestyle information related to the sensor data, but it may also include information other than lifestyle information, such as health-related information or selected lifestyle-related information. This is because, for example, when sensor data shows an elevated body temperature, or during an epidemic of infectious diseases characterized by such symptoms, by retrieving this information (which the knowledge DB242 described later can also possess) and conveying this information, it is possible to provide the user with self-restraint, symptom relief, treatment strategies, and psychological preparation.

[0053] Figure 2 The portable terminal 10 shown includes a communication unit 11, a sensor group 12, an input unit 13, a display unit 14, a recording unit 15, and a control unit 16. Furthermore, in one embodiment, the portable terminal 10 functions as a diagnostic aid or a health aid.

[0054] Under the control of the control unit 16, the communication unit 11 sends various information to the medical system 20 via the network N100 and receives various information from the medical system 20. Furthermore, the communication unit 11 receives vital information related to the user of the portable terminal 10, health information related to health status, and behavioral history related to the user's use of QR code-based electronic payments from external sensors such as smart trays or scales that are pre-connected to the portable terminal 10 via Bluetooth or Wi-Fi communication, and outputs this information to the control unit 16. Here, vital information refers to blood pressure, electrocardiogram, blood oxygen saturation, heart rate, pulse, and body temperature. Health information refers to uric acid levels, weight, and blood glucose levels. Furthermore, under the control of the control unit 16, the communication unit 11 receives environmental information about the vicinity of the portable terminal 10 from an external weather server (not shown) and outputs this information to the control unit 16. Here, environmental information includes weather-related information (sunny, cloudy, etc.), temperature, humidity, warnings (such as dryness warnings, migraine warnings), and alarms. Furthermore, a smart toilet refers to a toilet (toilet bowl) equipped with a modular urine testing sensor that can be installed in the toilet seat and a camera capable of capturing dynamic images of feces and urine. The smart toilet detects important parameters in the user's urine, such as glucose, pH, uric acid, urea, protein, red blood cells, and fecal occult blood, detecting 11 urine test indicators including uric acid, urine protein, and urine occult blood, as well as the presence or absence of fecal occult blood. These 11 items are: urine pH, urine protein, urine glucose, urine bilirubin (urobilinogen), urine ketones, urine occult blood, urine specific gravity, urine color, nitrite, urine white blood cells, and urine turbidity. The communication unit 11 is constructed using a communication module.

[0055] The sensor group 12 acquires various information related to the user of the portable terminal 10, such as vital signs, step count, and sleep information, and outputs it to the control unit 16. The sensor group 12 is composed of, for example, GPS (Global Positioning System) sensors, accelerometers, blood glucose sensors such as pulse oximeters, humidity sensors, orientation sensors, and gyroscope sensors.

[0056] The input unit 13 accepts various inputs from external operations and outputs them to the control unit 16. The input unit 13 is composed of buttons, switches, and touch panels.

[0057] Under the control of the control unit 16, the display unit 14 displays various information related to the portable terminal 10. The display unit 14 is constructed using a liquid crystal display or an organic EL display, etc.

[0058] The recording unit 15 records various information related to the portable terminal 10. The recording unit 15 includes a program recording unit 151 that records various programs executed by the portable terminal 10, a time information recording unit 152 that records time information related to the user of the portable terminal 10, and a portable terminal identification information recording unit 153 that records identification information used to identify the portable terminal 10. The recording unit 15 is constructed using volatile memory, non-volatile memory, a memory card, or an SSD (Solid State Drive), etc.

[0059] Figure 3 This diagram illustrates an example of the time information recorded by the time information recording unit 152. Here, the portable terminal 10 is able to acquire sensor data sets obtained from multiple items of vital data detected by sensors on the user, as well as lifestyle information related to multiple items of the user's lifestyle, and record them in a time sequence.

[0060] like Figure 3 As shown, the following time information is recorded in the time information K1: This time information is recorded in time sequence, which is obtained by the communication unit 11 under the control of the control unit 16, and is sensor data detected by the smart toilet, scale, etc., as well as life habit information related to the user's life habits.

[0061] The vital data (including steps) that a user can obtain varies depending on the available device. Furthermore, the portable terminal 10 involves different vital data depending on the disease or health monitoring, so it is preferable to record multiple vital data points. Similarly, it can be said that the portable terminal 10 records lifestyle habits in the same way.

[0062] The portable terminal 10 acquires sensor data sets obtained from detecting multiple vital signs of the user, as well as lifestyle information related to multiple aspects of the user's lifestyle, or records them in a corresponding manner in a time-series format. This allows for the determination of a temporal correlation between changes in vital signs caused by changes in physical condition and changes in lifestyle. Specifically, in the time-series information K1, for example, users are periodically given a questionnaire consisting of several items. Each item includes the user's lifestyle habits, such as hobbies, whether they drink alcohol, whether they smoke, and their behavioral history, as indicated by their responses.

[0063] As other examples, it is possible to analyze vital data such as steps, body temperature, pulse, brain waves, respiration, blood flow, blood pressure, weight, and composition information from excrement from sensor-based devices (such as wearable devices equipped with sensors that can communicate with smartphones, smart toilets, smart buses, smart beds (smart means having a processor and sensors, information processing unit, input / output unit), etc. (portable terminal 10, smartphones can also be equipped with sensors)) to determine smoking, drinking, dining history, eating habits, etc.

[0064] In addition, the portable terminal 10 can obtain information such as destination, frequency of outings, and time periods from GPS information. It can also analyze several pre-determined items based on the user's daily shopping results (using receipts or electronic payments), and determine changes in lifestyle habits over time for each item. Furthermore, the portable terminal 10 can determine environmental information such as climate based on the location and date / time, using online information. The behavioral history includes average annual steps, presence of occult blood in excrement, daily toilet frequency, and dietary preferences based on shopping history using payment information. For example, dietary preferences include the ratio of grains, meat, fish, and vegetables. Specifically, in the dietary preferences section of the behavioral history of time information K1 for 2017, the ratio of grains, meat, fish, and vegetables was recorded as 3:2:2:3.

[0065] When shopping history is obtained by photographing receipts, the portable terminal 10 can determine when and how much of what items were purchased by reading text or codes such as date, purchased items, quantity, amount, and location. If quantity data is unavailable, the quantity purchased can be determined based on the amount and the relationship between the average weight and amount of that item at that time. If it is an annual average, the quantity can be compared over the years. Furthermore, the daily intake can be calculated based on the period up to the purchase of the same item.

[0066] Furthermore, in addition to receipts, the portable terminal 10 can also use electronic settlement content to replace or combine receipts, and can determine the type and quantity of stored items, stored items, and cooked items through smart refrigerators and smart cookers.

[0067] Furthermore, the portable terminal 10 can estimate a person's preferences based on visits to recipe websites, etc. Specifically, if information such as a high frequency of searching for fish dishes in a certain year, but a high frequency of searching for meat dishes starting from a certain year, can be obtained, it is possible to determine changes in lifestyle habits over time. If such a database is used in conjunction with, for example, the portable terminal 10, effective health assistance information can be provided.

[0068] By acquiring sensor data detected by specific sensors on the user via portable terminal 10 and other means in a time sequence, as well as lifestyle information related to the user's lifestyle obtained by portable terminal 10 and other means, health-related information and changes in lifestyle information prior to this can be linked together for display and prompting.

[0069] This is because health-related information can be determined based on the aforementioned sensor data.

[0070] By organizing and extracting these relationships, users can understand the reasons and motivations behind changes in health-related data, thereby promoting improvements in their lifestyle habits.

[0071] Furthermore, because there are diseases that develop due to changes or tendencies in lifestyle (differences from the average lifestyle of many people or the lifestyle of healthy individuals), although in Figure 3 Even items not recorded in the text, but which serve as reasons, can also record information about changes in lifestyle habits and tendencies.

[0072] That is, based on the sensor data obtained by acquiring the user's life data and the results of recording the user's lifestyle information in a time series, the knowledge DB242 (described later) is retrieved, and health-related information is extracted based on their time series changes and trends (differences from the average information). Thus, not only health-related information can be output, but also information on changes in lifestyle that may be the cause can be output.

[0073] Therefore, it can not only assist in the diagnosis at the onset of the disease, but also anticipate improvements in lifestyle habits during subtle changes. The aforementioned knowledge DB242 records lifestyle habits information related to patients with specific diseases as time-series information, recording their changes (trends) and tendencies (differences from the average, etc.).

[0074] Of course, such as Figure 3 As shown, simply by having items, it's possible to know which item's information is effectively used for diagnosis, etc. Therefore, even without information on changes or trends, it's possible to selectively display lifestyle information for that item, which is also an improvement. This is because the historical information of the corresponding lifestyle can be immediately identified.

[0075] By accumulating time-series information on changes and tendencies in lifestyle habits (even if lifestyle habits remain unchanged, the same habits can still affect health depending on age), as well as time-series information on sensor data such as vital signs during the same period as these lifestyle habits, from data in a disease-free state to data in a disease-onset state, a reasoning model can be provided. This reasoning model, given inputs such as changes in lifestyle habits, tendencies, and vital signs, can infer what kind of health state the individual will experience in the future. As training data, if the time-series information on changes in lifestyle habits, tendencies, and vital signs is labeled with the name, symptoms, and diagnosis of the disease, the aforementioned reasoning model can be learned and acquired. A system that links and collaborates with such a reasoning model to a knowledge database can also be set up. In this case, it can become a system that, by inputting necessary information through communication with the knowledge database, issues health-related suggestions as output. Suggestions can be added to the annotations of the training data when generating the reasoning model, allowing the model to reason and provide suggestions, or suggestions can be generated based on the reasoning results. The suggestions are sent to the user's portable terminal 10 via the communication unit 21.

[0076] return Figure 2 The structure of the portable terminal 10 will be further explained.

[0077] The control unit 16 is implemented using a processor equipped with hardware such as an FPGA (Field-Programmable Gate Array), GPU (Graphics Processing Unit), or CPU (Central Processing Unit), and a memory serving as temporary storage for the processor. Furthermore, the control unit 16 includes an acquisition unit 161, a symptom acceptance unit 162, a retrieval unit 163, a good / bad determination unit 164, an extraction unit 165, and an output control unit 166.

[0078] The acquisition unit 161 acquires sensor data and lifestyle information from external smart toilets, scales, and sensor array 12, and records it in a time sequence in the time information recording unit 152 of the recording unit 15. The sensor data and lifestyle information each contain multiple items. Furthermore, the acquisition unit 161 acquires multiple sensor data detected by multiple sensors.

[0079] The symptom processing unit 162 processes the user's symptom input by inputting symptoms through the input unit 13.

[0080] The retrieval unit 163 determines, based on the symptoms of the user that have been received by the symptom receiving unit 162, whether it is possible to retrieve the vital data characteristics corresponding to the user's symptoms and the lifestyle characteristics that are the cause from the knowledge DB242 of the medical system 20. The knowledge DB242 consists of at least the symptoms caused by lifestyle, the treatment methods for the symptoms, and the sensor data caused by the symptoms.

[0081] The good or bad determination unit 164 determines the good or bad of the user's vital signs based on the changes in the user's sensor data over time recorded by the time information recording unit 152 of the recording unit 15.

[0082] Based on the search results retrieved from the knowledge database 242 by the retrieval unit 163 and the judgment results of the good / bad judgment unit 164, the extraction unit 165 extracts selected lifestyle habit-related information from the lifestyle habit information contained in the time information recording unit 152, that is, association information associated with sensor data. Here, association information refers to either selected lifestyle habit-related information or health-related information associated with life data of a specific item in the sensor data set and related to health. Hereinafter, when referring to either selected lifestyle habit-related information or health-related information, it will be described as association information.

[0083] The output control unit 166 displays the results of the correlation information extracted by the extraction unit 165 on the display unit 14. Specifically, the output control unit 166 displays a display image containing report information on the display unit 14. This report information is composed of a message generating vital data corresponding to symptoms and a message containing lifestyle information related to the correlation information extracted by the extraction unit 165. In addition, the output control unit 166 outputs health-related information and historical information on lifestyle habits corresponding to the health-related information based on the recording results recorded in the time-series information recording unit 152.

[0084] [Structure of the healthcare system]

[0085] Next, the functional structure of the medical system 20 will be explained. Figure 4 This is a block diagram representing the functional structure of the medical system 20. Figure 4 The medical system 20 shown includes a communication unit 21, an input unit 22, an output unit 23, a recording unit 24, and a server control unit 25.

[0086] Under the control of the server control unit 25, the communication unit 21 receives various information from the portable terminal 10 and external medical terminals used by doctors via the network N100, and sends various information to the portable terminal 10 or the doctor's terminal. The communication unit 21 is constructed using a communication module and the like.

[0087] The input unit 22 accepts various inputs from external operations and outputs them to the server control unit 25. The input unit 22 is composed of buttons, switches, and touch panels.

[0088] Under the control of the server control unit 25, the output unit 23 displays various information related to the medical system 20. The output unit 23 is constructed using a liquid crystal display or an organic EL display, etc.

[0089] The recording unit 24 records various information executed by the medical system 20. The recording unit 24 has a program recording unit 241 that records various procedures executed by the medical system 20 and a knowledge database 242 (hereinafter referred to as "knowledge DB242").

[0090] Knowledge DB242 registers and stores various types of knowledge corresponding to a patient's symptoms and condition in a systematic and organized manner. Specifically, in Knowledge DB242, symptoms that are registered or accumulated elements are stored in relation to knowledge information Q1 that indicates the correlation between those symptoms and conditions. Here, knowledge information Q1 refers to the causes, treatments, lifestyle habits, and vital information of multiple diseases corresponding to a patient's symptoms and condition.

[0091] Figure 5 This is a diagram representing an example of knowledge data registered in knowledge database DB242. For example... Figure 5 As shown, Knowledge DB242 is configured to retrieve, when a specific symptom occurs, any illness or disease (name, diagnosis) that may accompany that symptom. Furthermore, Knowledge DB242 also includes records of different causes and treatments for the illness or disease.

[0092] Lifestyle-related diseases can sometimes worsen or improve depending on lifestyle habits, and therefore are also recorded as ailments or diseases. Representative examples of such lifestyle habits are shown here, but there are also cases where changes are unique to periods of worsening, or where, even if not considered changes, there is a consistent tendency different from that of healthy individuals. For example, regarding diet, information such as "increased meat consumption" or "more meat dishes consumed" can be recorded (as a tendency, the difference from the average can be quantified), as one of the causes of developing a disease, and organized as change information or tendency information to form knowledge DB242.

[0093] Conversely, information such as "reduced meat consumption" and "meat-consuming dishes with reduced meat consumption (specific numerical targets)" can also be recorded in Knowledge DB242 as information for improving lifestyle habits (change information, tendency information) for treatment and symptom improvement. This can also be configured in Knowledge DB242 in a way that allows for changes based on race, gender, and age.

[0094] That is, Knowledge DB242 can also be a recording medium characterized by organizing and recording the correlation information of health and disease according to health obstacles and diseases. Its feature is that it records the changes and trends of the lifestyle information related to the lifestyle of patients with specific diseases as time series information.

[0095] In addition, such as Figure 5 As shown, in knowledge DB242, when the symptom is bleeding during defecation, in knowledge information Q1, the candidate disease 1 "colorectal cancer", the cause diet "high meat consumption", the age "over ○○ years old", the treatment "surgery, etc.", the lifestyle diet "meat consumption", the exercise "none", and the vital information "fecal occult blood" are matched and saved.

[0096] In addition to these, vital signs information can also include items such as body temperature, blood pressure, pulse, and weight, which are characteristics of different diseases, and can also be used to search for disease candidates. Furthermore, it can include values ​​beyond these items, such as whether they are normal or dangerous changes; for example, it can retrieve information suggesting a specific infection due to a sudden rise in body temperature.

[0097] The "lifestyle habits" section mentioned above includes information on lifestyle habits such as diet and exercise that are related to the characteristics of patients with specific diseases. For example, in cases of obesity, a high-calorie diet and insufficient exercise are common characteristics that can be recorded in knowledge database DB242.

[0098] In addition, Figure 5 The document only lists items related to "diet" or "exercise," but it could also include more detailed information. If calories are a concern, it could be structured to include specific numerical targets such as gender, age, and height in the knowledge database DB242.

[0099] Therefore, it can also be configured to include information such as the possibility of developing the disease if the calorie target is exceeded and a specific value is exceeded, or information such as the tendency for the risk of developing the disease to increase even if there is no significant deviation from the target, provided that a specific calorie value is consistently maintained.

[0100] Thus, as long as the knowledge DB242 can compare the changes in users' lifestyle information, tendencies, and how they change relative to a standard value through changes (differentiation over time), tendencies (integration over time), etc., it can also be configured to record characteristic information such as changes and tendencies of risk as described herein.

[0101] Here is an example: Knowledge DB242 is a database that organizes and records information on the relationships between health and disease that doctors, medical staff, patients, and their families can refer to when making medical decisions, categorized by each health disorder and ailment. Therefore, Knowledge DB242 is a database that organizes and records the relationship between symptoms and their treatment, management, and prescriptions according to specific regulations.

[0102] Knowledge DB242 addresses symptoms, which can sometimes refer to different conditions, diseases, or ailments. Therefore, it also compiles information on treatment methods categorized according to these conditions, as well as factors that can easily contribute to disease (race, age, gender, body shape, weight, living environment such as climate, occupational information including exercise and home-based work, and lifestyle habits such as diet, health products, and medication). This information can serve as a reference for diagnosis and treatment as needed.

[0103] Furthermore, to improve patient quality of life (QOL), the development of a Clinical Decision Support System (CDSS) is indispensable. Here, we assume that Knowledge DB242 is a recording medium that organizes and records information related to health and disease, categorized by health impairment and ailment.

[0104] However, in Figure 5 The knowledge database 242 shown contains information on various lifestyle habits related to the user's (a patient with a specific disease, ailment, or symptom, or a person in a non-disease state) and records them in a time series. The portable terminal 10 retrieves such knowledge database 242 and extracts health-related information or selects lifestyle-related information based on their time series changes and trends (differences from average information (data)). This allows it to not only obtain and output health-related information but also information on changes in lifestyle habits that may be contributing factors.

[0105] Furthermore, information related to the associated medical institutions, examination machines, equipment, medical devices, specialists, medical departments, doctors at the associated medical institutions, and the patient's medical history can be systematically and organized and stored in knowledge information Q1. In this case, since a doctor's consultation is required, the associated medical institutions (hospital name and address, specialty, whether there are specialists) are registered in knowledge information Q1. Moreover, knowledge information Q1, as an example, registers associated medical institutions, treatment methods, ingredient information, efficacy information, specialists, medical departments, side effects, dosage instructions, and doctors at the associated medical institutions for each symptom. Additionally, medical history information includes the patient's medical records and current underlying conditions, such as diabetes, anemia, and hypertension.

[0106] return Figure 4The structure of medical system 20 will be explained.

[0107] The server control unit 25 includes an acquisition unit 251, a retrieval unit 252, a determination unit 253, and a communication control unit 254.

[0108] The acquisition unit 251 acquires various information for updating the knowledge DB242 via the communication unit 21 and the network N100, and updates the knowledge DB242 with the systematized and organized state of various knowledge corresponding to the patient's symptoms and state.

[0109] Based on the user's symptoms received from the portable terminal 10, the retrieval unit 252 retrieves related information associated with the user's symptoms from the knowledge database 242.

[0110] The determination unit 253 determines whether the user's symptoms were input and communicated from the portable terminal 10 via the network N100 and the communication unit 21.

[0111] The communication control unit 254 sends the retrieval results of the related information on the user's symptoms retrieved from the knowledge DB 242 by the retrieval unit 252 to the portable terminal 10.

[0112] [Overview of portable terminal processing]

[0113] Next, a summary of the processing performed by the portable terminal 10 will be explained. Figure 6 This is a timing diagram summarizing the processing performed by the portable terminal 10. Figure 6 In the middle, starting from the top paragraph, (a) represents the sensor data of the smart toilet obtained by the portable terminal 10, (b) represents the number of steps obtained from the sensor group 12, and (c) represents the settlement information.

[0114] like Figure 6 As shown, whenever a user urinates on the toilet, the portable terminal 10 communicates with the external smart toilet to obtain sensor data (feces and urine tests) detected by the smart toilet and records it in the elapsed information recording unit 152 of the recording unit 15 according to the time sequence. In addition, the portable terminal 10 obtains the user's step count and billing information from the sensor group 12. In this case, as... Figure 6 As shown, if a user observes occult blood or bleeding in their own stool at 13:00, they can input the symptoms into the portable terminal 10.

[0115] Figure 7 This is a timing diagram summarizing the processing performed by the portable terminal 10 when a user inputs symptoms. Figure 7 In the middle, starting from the top paragraph, (a) represents the processing timing of the portable terminal 10, and (b) represents the access timing of the medical system 20. Figure 8 It means in Figure 7An example of an image displayed on the display unit 14 during processing. Figure 9 It means in Figure 7 Another example of the image displayed on the display unit 14 during processing.

[0116] like Figure 7 As shown, the user operates the input section 13 to input their own symptoms. For example, such as... Figure 8 As shown, the user inputs their symptoms, such as bleeding during bowel movements, into the input image P1 displayed on the display unit 14 via the input unit 13, which includes the user's step count. Furthermore, the input image P1 includes the changes in the user's step count H1, which is part of vital data detected by the sensor group 12. Additionally, the portable terminal 10 can also display changes in the user's weight, blood sugar levels, blood pressure, etc., instead of the step count H1, and the display can be changed according to the user's settings.

[0117] Next, based on the symptoms input via the input unit 13, the portable terminal 10 retrieves the corresponding vital data characteristics and lifestyle habit information from the knowledge database 242 of the medical system 20, which contain the causes corresponding to the vital data as sensor data, i.e., lifestyle habit characteristics. Furthermore, the portable terminal 10 can also retrieve associated medical institutions corresponding to the symptoms from the knowledge information contained in the knowledge database 242.

[0118] Subsequently, based on the search results retrieved from the knowledge database 242, the portable terminal 10 retrieves the vital data characteristics and causes (lifestyle characteristics) corresponding to the disease candidates retrieved from the knowledge database 242 from the time information recording unit 152, and displays a display image corresponding to the search results. Specifically, such as Figure 9 As shown, the portable terminal 10 displays image P2. This image P2 contains vital data and lifestyle information corresponding to the symptoms input by the user via the input unit 13. Specifically, as vital data, it displays a message M1 indicating a need for fecal occult blood testing since the beginning of this year; as lifestyle information, it displays a message M2 indicating a change in dietary preference (more meat consumption) since two years ago. Furthermore, in... Figure 9 In this embodiment, the portable terminal 10 only includes vital data and lifestyle information in the display image P2 and displays it on the display unit 14. However, based on search results retrieved from the knowledge database 242, if related medical institutions capable of addressing symptoms are included, the related medical institutions in the display image P2 can also be included and displayed on the display unit 14. This allows the user to understand the cause and current condition corresponding to the symptoms. Although not shown here, other health-related information that can be retrieved from the knowledge database 242 can also be displayed as needed.

[0119] Next, an overview of the portable terminal 10 and the processing of the medical terminal when a user visits a medical institution based on the displayed image will be explained. Figure 10 This is a timing diagram illustrating the portable terminal 10 and the processing overview of the medical terminal when a user visits a medical institution. Figure 10 In the middle, starting from the top paragraph, (a) represents the doctor's terminal, (b) represents the access timing of the knowledge DB242, and (c) represents the timing of the portable terminal 10. Figure 11 It means in Figure 10 This is an example of an image displayed on the doctor's terminal during processing.

[0120] like Figure 10 As shown, the doctor uses the doctor terminal 200 to input the symptoms of the user as a patient. Based on the user's symptoms, the doctor retrieves the corresponding vital data characteristics and lifestyle habit information from the knowledge database 242 of the medical system 20, which correspond to the vital data as sensor data, i.e., the causes, i.e., the lifestyle habit characteristics. The doctor then uses the doctor terminal 200 to communicate with the user's portable terminal 10, requesting the portable terminal 10 to provide the following information: based on the user's symptoms, the information on the corresponding vital data characteristics and lifestyle habit information, which correspond to the vital data as sensor data, i.e., the causes, i.e., the lifestyle habit characteristics.

[0121] Subsequently, the portable terminal 10, upon request from the doctor terminal 200, outputs pre-authorized information to the doctor terminal 200. In this case, the doctor terminal 200 displays an image corresponding to the information from the portable terminal 10. Specifically, as... Figure 11 As shown, the doctor's terminal 200 displays image P3. This image P3 contains vital data and lifestyle information corresponding to the symptoms. Specifically, the vital data includes message M3 indicating a desire for fecal occult blood testing since the beginning of this year, and the lifestyle information includes message M4 indicating a change in dietary preferences (more meat consumption) since two years ago. Therefore, the doctor can quickly diagnose the user's illness based on abnormalities in the user's vital data and changes in lifestyle habits. Furthermore, the portable terminal 10 only outputs information authorized by the user to the doctor's terminal 200, thus protecting the user's privacy. It is worth noting that, in order to determine the lifestyle habits that triggered the changes in vital data, the causal relationship is clarified by displaying time points prior to the changes.

[0122] [Processing performed on portable terminals]

[0123] Next, the processing performed by the portable terminal 10 will be explained. Figure 12 This is a flowchart illustrating a summary of the processes performed by the portable terminal 10.

[0124] like Figure 12As shown, when the user inputs information into the input unit 13 (step S101: Yes), the control unit 16 displays the home screen on the display unit 14 (step S102). After step S102, the portable terminal 10 proceeds to step S103. Conversely, if the user does not input information into the input unit 13 (step S101: No), the portable terminal 10 continues this determination.

[0125] In step S103, the acquisition unit 161 acquires sensor data and lifestyle information from the external smart toilet, scale and sensor group 12, and records them in the time information recording unit 152 according to the time sequence.

[0126] Next, if the symptom acceptance unit 162 accepts the user's symptom input via the input unit 13 (step S104: Yes), the retrieval unit 163 communicates with the knowledge DB 242 via the network N100 (step S105). After step S104, the portable terminal 10 proceeds to step S106, which will be described later. Conversely, if the symptom acceptance unit 162 does not accept the user's symptom input via the input unit 13 (step S104: No), it proceeds to step S112, which will be described later. Furthermore, in S104, the user (patient, medical practitioner) manually inputs the symptoms, but the retrieval unit 163 can also detect changes in physical condition using sensor data, or automatically determine the symptoms based on other user input or operations, such as through "text extraction" or "voice judgment." Manual input can also be done through text input, questionnaire responses, or item checks.

[0127] In step S106, the retrieval unit 163, based on the symptoms received by the symptom reception unit 162, determines whether vital signs data characteristics and lifestyle characteristics as the cause can be retrieved from the knowledge database 242. If it is determined that vital signs data characteristics and lifestyle characteristics as the cause can be retrieved from the knowledge database 242 (step S106: Yes), the portable terminal 10 proceeds to step S107, described later. Here, the retrieval unit 163 can also be used to determine only vital signs data characteristics, and as a result, determine lifestyle characteristics when providing guidance. If there is an acquisition step of the sensor data group that acquires the output of multiple items of vital signs data of the user and the lifestyle information acquisition unit 161 that acquires multiple items of lifestyle information related to the user's lifestyle, the retrieval unit 163 can also determine only whether the vital signs data is normal or abnormal. In this case, the retrieval unit 163 can also be used to compare multiple lifestyle information records in the time-series information recording unit 152 in advance with certain problems (characteristic tendencies) to find out the cause when certain problems (characteristic tendencies) exist. Furthermore, even without utilizing the knowledge DB242, the retrieval unit 163 can use the association information and program that links life data with lifestyle data to easily determine and extract historical information of lifestyle corresponding to changes in life data of a specific item based on the recording results of the aforementioned time information recording unit 152.

[0128] In step S107, the good / bad determination unit 164 determines the good / bad of the user's vital signs data based on the changes in the user's sensor data over time recorded by the time information recording unit 152. Regarding good / bad, it can also be determined whether a specific change or a specific threshold has been exceeded, or whether a trend different from the usual value continues. Here, the good / bad determination unit 164 determines the user's vital signs data as bad if the weight included in the user's vital signs data increases over time, if the number of steps included in the user's vital signs data is lower than the baseline value for the health index but the weight over time decreases, or if occult blood is detected in the vital signs data. Conversely, the good / bad determination unit 164 determines the user's vital signs data as good if the weight included in the user's vital signs data decreases over time, if the number of steps included in the user's vital signs data is higher than the baseline value for the health index and the weight over time increases, or if no occult blood is detected in the vital signs data. Furthermore, while the health assessment unit 164 uses the user's weight as the sole basis for determining the quality of vital data, it is not limited to this. It can also assess the health of vital data based on sleep logs, blood glucose levels, 11 urine test indicators, and the presence or absence of fecal occult blood. This sensor data can also be recorded in a time-series format in the menstrual information recording unit 152. The retrieval unit 163 retrieves health-related information associated with changes and anomalies in the sensor data and displays and provides corresponding prompts.

[0129] Furthermore, since sensor data is time-series information, information such as changes corresponding to time, long durations, and the continuation of specific states can also be obtained. Therefore, the retrieval unit 163 can also retrieve information such as when such a state occurred or when it began. This timing information can also be displayed / prompted. Additionally, in health guidance and diagnostic assistance, it is important to determine whether the changes in sensor data are caused by lifestyle habits, aging, or a combination of both; therefore, lifestyle habit information can be displayed / prompted. Alternatively, the feature may be that it outputs the aforementioned health-related information along with information on changes in the aforementioned lifestyle habits prior to that point.

[0130] Furthermore, in order to retrieve diseases exhibiting a predisposition based on changes and tendencies in vital data, the retrieval unit 163 can also search the knowledge database 242 to extract health-related information associated with the vital data of a specific item and output historical information on corresponding lifestyle habits. As health-related information, it is envisioned to provide guidance such as "Because there is a tendency towards ○, you need to pay attention." In this case, if the aforementioned tendency is improved through improvements in lifestyle habits such as diet, sleep, and exercise, this relationship is also recorded in the knowledge database 242, thus enabling guidance such as "Please pay attention to insufficient exercise."

[0131] Additionally, changes in vital data and the timing of those changes can be detected. In the event of a change in specific vital data, historical information about the lifestyle habits that led to the change is output, covering the period prior to the timing of the change.

[0132] Subsequently, based on the search results retrieved by the retrieval unit 163 from the knowledge database 242 and the judgment results of the condition determination unit 164, the extraction unit 165 extracts the association information related to vital data from the lifestyle information contained in the menstrual information recording unit 152 (step S108). Specifically, based on the symptom-related search results retrieved by the retrieval unit 163 from the knowledge database 242 and the vital data judgment results of the condition determination unit 164, the extraction unit 165 selects changes in dietary tendencies (more meat consumption) related to fecal occult blood tests from the lifestyle information contained in the menstrual information recording unit 152 and extracts them as association information.

[0133] Next, the output control unit 166 displays the results of the correlation information extracted by the extraction unit 165 on the display unit 14 (step S109). Specifically, the output control unit 166 displays a display image P2 containing report information (refer to the above-described image). Figure 9 The report information, displayed on display unit 14, is generated from message M1, which generates vital data corresponding to the symptoms, and message M2, which extracts lifestyle information related to the symptoms extracted by extraction unit 165. In this case, output control unit 166 can also recommend medical institutions corresponding to the symptoms by displaying a message on display unit 14 suggesting a visit to the medical institution corresponding to the location information of portable terminal 10, when multiple related medical institutions corresponding to the symptoms are found in the search results retrieved from knowledge database 242 by retrieval unit 163. Of course, output control unit 166 can also connect to medical system 20 to schedule appointments for users at the recommended medical institutions. Here, other health-related information that can be retrieved from knowledge database 242 can also be displayed.

[0134] Next, the output control unit 166 outputs the useful information obtained by the retrieval unit 163 from the knowledge database 242 (step S110). Here, useful information is suggestion information, which is useful information corresponding to symptoms, their improvement, prevention of infection, etc., such as multiple candidate diseases, multiple medical institutions that the user can treat, etc. The doctor sees this. In addition, the process from S105 to S110 is explained in an easy-to-understand way by dividing it into several steps, but the following health assistance can also be performed: The sensor data obtained by obtaining the user's vital data and the results of recording the user's lifestyle information in a time series are used as input, the knowledge database 242 is retrieved, and the health-related information associated with the above sensor data is extracted (the required sensor information varies depending on the disease. For example, body temperature is important in influenza, but it is rare for there to be a direct relationship with weight, etc.), and the information on changes in the above-mentioned lifestyle habits before this is also output. For example, if information such as getting the flu after going to a crowded place can be obtained, one will be careful not to take precautions when going out. One can also pay attention to future life, family members and colleagues. To generate a reasoning model that has been trained using time-series information on lifestyle habits and time-series information on life data from the period corresponding to which the data was obtained, labeled with the name, symptoms, and diagnosis of the disease that occurred, this data can also be used. At this time, by inputting the time-series information of the aforementioned sensor data and the time-series information of the aforementioned lifestyle habits, it is possible to infer what kind of health state one will develop in the future and make recommendations. After step S110, the portable terminal 10 proceeds to step S111, which will be described later.

[0135] In step S111, if the user ends the operation of the portable terminal 10 (step S111: Yes), the portable terminal 10 returns to step S101. Conversely, if the user does not end the operation of the portable terminal 10 (step S111: No), the portable terminal 10 returns to step S103.

[0136] In step S106, if the retrieval unit 163 is unable to retrieve life data features and lifestyle habit features as the cause from the knowledge DB242 (step S106: No), the portable terminal 10 proceeds to step S110, which will be described later.

[0137] In step S112, the portable terminal 10 performs processing in other modes, such as the mode corresponding to the application stored in the portable terminal 10. After step S112, the portable terminal 10 proceeds to step S111.

[0138] [Medical System Processing]

[0139] Next, the processing performed by the medical system 20 will be explained. Figure 13This is a flowchart that represents a summary of the processes performed by the medical system 20.

[0140] like Figure 13 As shown, the determination unit 253 determines whether a user's symptom input communication has occurred from the portable terminal 10 via the network N100 and the communication unit 21 (step S201). If the determination unit 253 determines that a user's symptom input communication has occurred from the portable terminal 10 (step S201: Yes), the medical system 20 proceeds to step S202, which will be described later. Conversely, if the determination unit 253 determines that there is no user symptom input communication from the portable terminal 10 (step S201: No), the medical system 20 proceeds to step S201, which will be described later.

[0141] Next, the retrieval unit 252 inputs the user's symptoms received from the portable terminal 10 into the knowledge database 242 (step S202), retrieves useful information from the knowledge database 242, and outputs the useful information (step S203). Here, useful information refers to useful information corresponding to the symptoms, such as multiple candidate diseases, multiple treatment methods, multiple surgical methods, and past medical history information.

[0142] Next, the determination unit 253 determines whether vital signs data characteristics and lifestyle characteristics as the cause can be retrieved from the knowledge database 242 based on the user's symptoms input via the portable terminal 10 (step S204). If the determination unit 253 determines that vital signs data characteristics and lifestyle characteristics as the cause can be retrieved from the knowledge database 242 based on the user's symptoms input via the portable terminal 10 (step S204: Yes), the medical system 20 proceeds to step S205, which will be described later. Lifestyle characteristics can be just items, or they can include more detailed characteristics from the items. Alternatively, they can be information about the "changes (changes over time)" or "tendencies (continuities over time)" of the lifestyle habits shown in the item. This allows for more detailed information filtering. For example, if information is provided when there are changes in lifestyle habits or deviations from the average situation compared to a situation where there are no problems with lifestyle habits, the persuasiveness of the information is increased. In contrast, if the determination unit 253 determines that it is impossible to retrieve vital data characteristics and lifestyle characteristics as the cause from the knowledge DB 242 based on the user's symptoms input via the portable terminal 10 (step S204: No), the medical system 20 proceeds to step S206, which will be described later.

[0143] In step S205, the communication control unit 254 sends the results retrieved from the knowledge database 242 to the portable terminal 10 or the doctor's terminal. Specifically, the communication control unit 254 sends the search results, which include vital data characteristics corresponding to the corresponding disease and lifestyle characteristics as the cause, to the portable terminal 10 or the doctor's terminal based on the user's symptoms. In this case, it is preferable for the user to obtain the aforementioned... Figure 9 Information such as messages M1 and M2. That is, this is because changes in vital information can be obtained as a reference, possibly caused by changes in previous lifestyle habits. Even when lifestyle habits remain unchanged, changes in age such as aging, and other causes can be studied, thus narrowing down the focus of health maintenance and diagnosis. Therefore, it can be displayed only when lifestyle habits have changed, or it can be prompted as reference information when lifestyle habits have not changed. Information earlier than the time when symptoms are noticed or when data changes are observed is important. Changes in lifestyle habits after the onset of symptoms are generally related to the onset of those symptoms, so such constraints can be set. After step S205, the medical system 20 returns to step S201.

[0144] In step S206, the communication control unit 254 sends a "no" message to the portable terminal 10 or the doctor's terminal, indicating that no information corresponding to the user's symptoms could be retrieved from the knowledge database 242. After step S206, the medical system 20 returns to step S201.

[0145] According to one embodiment described above, the output control unit 166 displays the results of the correlation information extracted by the extraction unit 165 and the sensor data on the display unit 14, thus enabling high-granularity judgment of the sensor data.

[0146] In addition, according to one embodiment, the extraction unit 165 selects and extracts the association information related to the sensor data from the lifestyle information recorded by the time information recording unit 152 based on the search results retrieved by the retrieval unit 163. Therefore, it is possible to select and extract high-granularity lifestyle information corresponding to symptoms from multiple lifestyle information.

[0147] In addition, according to one embodiment, the output control unit 166 displays a display image P2 containing report information on the display unit 14. This report information is generated by a message M1 that generates vital data corresponding to symptoms and a message M2 that extracts related information about lifestyle habits from the extraction unit 165. Therefore, the user can understand the content caused by lifestyle habits.

[0148] In addition, according to one embodiment, the good or bad determination unit 164 determines the good or bad of the user's vital data based on the time change of the user's sensor data recorded in the time information recording unit 152, so that it is easy to grasp the timing when the vital data has changed.

[0149] In addition, according to one embodiment, the extraction unit 165 extracts the association information related to vital data from the lifestyle information contained in the time information recording unit 152 based on the search results retrieved from the knowledge DB 242 by the retrieval unit 163 and the judgment results of the good or bad determination unit 164. Therefore, it is possible to trace back from the time when the user's vital data changed to determine the user's lifestyle caused by symptoms.

[0150] In addition, according to one embodiment, the output control unit 166 outputs the user's changing status based on life data, so that the user can intuitively understand their own situation.

[0151] In addition, according to one embodiment, when the determination result of the vital data by the good or bad determination unit 164 is determined to be bad, the output control unit 166 outputs a message from the retrieval unit 163 that recommends seeking medical treatment at a medical institution based on the symptoms retrieved from the knowledge DB242, so that the user can know the medical institution corresponding to the symptoms.

[0152] Various inventions can be formed by appropriately combining the multiple constituent elements disclosed in the diagnostic assistance system of one embodiment of the present disclosure described above. For example, several constituent elements may be deleted from all the constituent elements described in the diagnostic assistance system of the embodiment of the present disclosure described above. Furthermore, the constituent elements described in the diagnostic assistance system of the embodiment of the present disclosure described above may be appropriately combined.

[0153] Furthermore, in the diagnostic assistance system of one embodiment of this disclosure, the term "section" can be replaced with "unit," "circuit," or the like. For example, the control section can be replaced with a control function or a control circuit.

[0154] Furthermore, the program executed by the diagnostic assistance system according to one embodiment of the present disclosure is provided as file data recorded in an installable or executable form on a computer-readable recording medium such as a CD-ROM, floppy disk (FD), CD-R, DVD (Digital Versatile Disk), USB medium, or flash memory.

[0155] Alternatively, the program executed by the diagnostic assistance system according to one embodiment of the present disclosure may also be configured to be stored on a computer connected to a network such as the Internet and provided by downloading it via the network.

[0156] Furthermore, in the flowchart descriptions of this specification, terms such as "first," "after," and "continue" are used to explicitly indicate the sequential relationship between steps. However, the order of processes required to implement this invention is not uniquely determined by these terms. That is, the order of processes in the flowcharts described in this specification can be changed without contradiction. Additionally, the program is not limited to simple branching processes; it is also possible to comprehensively determine more decision items and branch them. In this case, artificial intelligence techniques such as machine learning can be used to encourage users to perform manual operations repeatedly for learning. Furthermore, it is also possible to learn from the operating patterns of multiple experts and perform deep learning by incorporating more complex conditions.

[0157] The above description of several embodiments of this application is based on the accompanying drawings. However, these are illustrative, and the invention can be implemented in various modifications and variations based on the knowledge of those skilled in the art, with the embodiments described in the disclosure section of this invention as the primary example.

[0158] Note that this technology can also adopt the following structure.

[0159] (Note 1)

[0160] A program that causes a diagnostic aid device equipped with a processor to perform the following steps: The acquisition steps involve acquiring sensor data detected by the sensor and information about the user's lifestyle habits, and recording them in a time series. The extraction step involves extracting selected lifestyle habit association information associated with the sensor data, chosen from the lifestyle habit information; and The output step outputs the selected lifestyle association information and the sensor data.

[0161] (Note 2)

[0162] A program that causes a processor-equipped health assistive device to perform the following steps: The acquisition steps involve acquiring sensor data sets obtained by detecting multiple vital signs data of the user, as well as lifestyle habit information related to multiple items of the user's lifestyle habits, and recording them in a time series. The extraction step involves searching a knowledge database to extract health-related information associated with specific items in the sensor data set, specifically those related to health. The output step involves outputting the health-related information and historical information about lifestyle habits corresponding to the health-related information from the recording results recorded according to the time series.

[0163] (Note 3)

[0164] A program that causes a processor-equipped health assistive device to perform the following steps: The acquisition steps involve acquiring the output of sensor data sets that detect multiple vital signs of the user, as well as lifestyle information related to multiple aspects of the user's lifestyle, and recording the lifestyle information of these multiple aspects in a time sequence; and The output step involves outputting historical information about lifestyle habits corresponding to changes in the vital data of a specific item in the sensor data set, based on the recording results of the lifestyle habit information of the multiple items recorded in a time series.

[0165] (Note 4)

[0166] A program that causes a processor-equipped health assistive device to perform the following steps: The acquisition steps involve acquiring sensor data obtained from detecting the user's vital signs and lifestyle information related to the user's daily habits, and recording them in a time-series format; and The output step involves inputting the time-series information of the sensor data and the time-series information of the lifestyle into the inference model to infer what kind of health state the person will become in the future. The inference model is a training model that has been trained using the time-series information of the lifestyle and the time-series information of the life data corresponding to the period when the data was obtained, labeled with the name of the disease, symptoms and diagnosis results.

[0167] Explanation of reference numerals in the attached figures

[0168] 1. Diagnostic Assistance System

[0169] 10 Portable Terminals

[0170] 11, 21 Ministry of Communications

[0171] 12 sensor groups

[0172] Input sections 13 and 22

[0173] 14 Display Section

[0174] Records Department, 15, 24

[0175] 16 Control Department

[0176] 20. Healthcare System

[0177] 25 Server Control Department

[0178] 151, 241 Program Recording Department

[0179] 152 Time Information Recording Department

[0180] 153 Portable Terminal Identification Information Recording Department

[0181] 161,251 Acquired Department

[0182] 162 Symptom Handling Department

[0183] 163,252 Retrieval Department

[0184] 164. Good or Bad Judgment Department

[0185] 165 Extraction Section

[0186] 166 Output Control Unit

[0187] 200 Doctor Terminal

[0188] 241 Program Recording Department

[0189] 242 Knowledge Database

[0190] 253 Judgment Department

[0191] 254 Communications Control Department

Claims

1. A diagnostic assistance method, wherein the diagnostic assistance method is executed by a diagnostic assistance device having a processor, wherein, The processor includes the following steps: The acquisition steps involve acquiring sensor data detected by the sensor and information about the user's lifestyle habits, and recording them in a time series. The extraction step involves extracting selected lifestyle-related information that is associated with the sensor data, chosen from the lifestyle information. as well as The output step outputs the selected lifestyle association information and the sensor data.

2. The diagnostic assistance method according to claim 1, wherein, The sensor data and the lifestyle information each include multiple items. In the obtaining step, Acquire data from multiple sensors detected by multiple sensors. In the extraction step, Based on the items contained in the sensor data representing characteristic tendencies from the multiple sensor data, specific behavioral history information is selected from the user's multiple behavioral history information, and this specific behavioral history information is extracted as the selected lifestyle association information.

3. The diagnostic assistance method according to claim 2, wherein, The diagnostic aid device can access a knowledge database consisting of at least symptoms caused by lifestyle habits, treatment methods for the symptoms, and sensor data related to the symptoms. The processor also performs the following steps: The symptom acceptance step involves accepting the user's input of symptoms; and The retrieval step involves retrieving sensor data features and lifestyle characteristics associated with the reported symptoms from the knowledge database. In the extraction step, Based on the search results of the aforementioned search steps, extract the information related to the selected lifestyle habits.

4. The diagnostic assistance method according to claim 3, wherein, In the output step, Report information is generated based on the correlation information and the sensor data. Output the selected lifestyle habit association information and the report information.

5. The diagnostic assistance method according to claim 4, wherein, The sensor data includes at least the user's vital signs data. The processor also performs a good or bad determination step: determining whether the life data recorded according to the time series is good or bad.

6. The diagnostic assistance method according to claim 5, wherein, In the extraction step, Based on the determination of the quality of the life data and the retrieval results of the retrieval steps, the information related to the selected lifestyle habits is extracted.

7. The diagnostic assistance method according to claim 6, wherein, In the output step, Output the user's changed status based on the said life data.

8. The diagnostic assistance method according to claim 7, wherein, In the output step, If the determination result of the vital data is negative, a message is output suggesting that the patient visit an associated medical institution retrieved from the knowledge database based on the symptoms.

9. The diagnostic aid method according to claim 8, wherein, In the output step, If the user requests the output of the selected lifestyle association information from an external machine, only the association information that has been pre-approved by the user will be output to the external machine.

10. A health assistance method, wherein the health assistance method is performed by a health assistance device having a processor, wherein, The processor includes the following steps: The acquisition steps involve acquiring sensor data sets obtained from detecting multiple vital signs of the user, as well as lifestyle information related to multiple aspects of the user's lifestyle, and recording them in a time sequence. The extraction step involves searching a knowledge database to extract health-related information associated with the life data of specific items in the sensor data set. as well as The output step outputs the health-related information and historical information on lifestyle habits corresponding to the health-related information from the recording results recorded according to the time series.

11. The health assistance method according to claim 10, wherein, The processor further includes a determination step: determining the representation changes and specific life data with specific tendencies in the life data of the multiple items. In the extraction step, Item retrieval based on the user's specific biometric data and the user's lifestyle habits is performed using the knowledge database.

12. The health assistance method according to claim 10, wherein, The processor also includes a symptom input step: accepting the user's symptom input. In the extraction step, The knowledge database is retrieved based on the user's symptom input, and the health-related information is extracted.

13. The health assistance method according to claim 10, wherein, The knowledge database is a recording medium that organizes and records at least one life data or lifestyle tendency related to the relationship between health and disease for each disease.

14. The health assistance method according to claim 10, wherein, The processor further includes a detection step: detecting changes in the specific life data and the timing of these changes. In the output step, The output contains historical information about the lifestyle habits during the period prior to the timing of the change.

15. A health assistance method, wherein the health assistance method is performed by a health assistance device having a processor, wherein, The processor includes the following steps: The acquisition steps involve acquiring the output of sensor data sets that detect multiple vital signs of the user, as well as lifestyle information related to the user's lifestyle habits for multiple items, and recording the lifestyle information for the multiple items in a time sequence. as well as The output step involves taking the recorded results of the lifestyle habit information of the multiple items recorded in a time series and outputting historical information of lifestyle habits corresponding to the changes in the life data of a specific item in the sensor data set.

16. A health assistance method, wherein the health assistance method is performed by a health assistance device having a processor, wherein, The processor includes the following steps: The acquisition steps involve acquiring sensor data obtained from detecting the user's vital signs and information about the user's lifestyle habits, and recording them in a time sequence. as well as The output step involves inferring the future health status by inputting the time-series information of the sensor data and the time-series information of the lifestyle into the inference model. The inference model is a learning model based on training data. The training data labels the time-series information of the lifestyle and the time-series information of the life data corresponding to the period in which the data is obtained with the name, symptoms and diagnosis results of the disease.

17. A diagnostic aid device, wherein, The diagnostic aid device includes: The acquisition unit acquires sensor data detected by the user and information about the user's lifestyle habits, and records it in a time sequence. The extraction unit extracts selected lifestyle-related information associated with the sensor data, chosen from the lifestyle information. as well as The output control unit outputs the selected lifestyle association information and the sensor data.

18. A health assistive device, wherein, The health assistive device includes: The acquisition unit acquires sensor data sets obtained by detecting multiple vital signs of the user and lifestyle information related to multiple aspects of the user's lifestyle, and records them in a time sequence. The extraction unit searches a knowledge database to extract health-related information associated with specific items in the sensor data set and related to health. as well as The output control unit outputs the health-related information and historical information of lifestyle habits corresponding to the health-related information from the recording results recorded according to the time series.

19. A health assistive device, wherein, The health assistive device includes: The acquisition unit acquires the output of sensor data groups that detect multiple items of the user's vital signs, as well as the life habit information of multiple items related to the user's lifestyle, and records the life habit information of the multiple items in a time sequence. as well as The output control unit outputs historical information about living habits corresponding to changes in the vital data of a specific item in the sensor data set, based on the recording results of the living habit information of the multiple items recorded in a time sequence.

20. A health assistive device, wherein, The health assistive device includes: The acquisition unit acquires sensor data obtained from detecting the user's vital signs and information about the user's lifestyle habits, and records them in a time sequence. as well as The output control unit infers the future health status by inputting the time-series information of the sensor data and the time-series information of the lifestyle into the inference model. The inference model is a learning model based on training data. The training data labels the time-series information of the lifestyle and the time-series information of the life data corresponding to the period when the data is obtained with the name, symptoms and diagnosis results of the disease.

Images