Information processing system, information processing method, and program

Abstract

[Problem] To provide a more beneficial technology. [Solution] One aspect of the present invention provides an information processing system which comprises at least one processor, the processor being configured to execute the following steps by reading a program. In a data acquisition step, health data related to the health of a target user who is a subject of health management and context data related to behavior and / or environment of said target user are acquired, and in an output step, health management information related to the health management of the target user is outputted on the basis of the health data, the context data, and reference information. The reference information is collected in advance for selecting or generating the health management information and includes information related to a physical state and / or a mental state.

Description

Information Processing System, Information Processing Method, and Program

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

[0002] In recent years, various techniques for managing a user's health have been developed, such as those disclosed in Patent Document 1. On the other hand, development of more useful techniques is desired.

[0003] Japanese Patent Laid-Open No. 2015-8711

[0004] In view of the above circumstances, the present invention has been made to provide a more useful technique.

[0005] According to one aspect of the present invention, there is provided an information processing system including at least one processor, wherein the processor is configured to execute each of the following steps by reading a program: in a data acquisition step, acquiring health-related health data and context data relating to behavior and / or environment of a target user that is a subject of health management; in an output step, outputting health management information related to health management of the target user based on the health data, the context data, and reference information, wherein the reference information is information for selecting or generating previously collected health management information and includes information relating to a physical condition and / or a mental condition.

[0006] According to the present disclosure, a more useful technique can be provided.

[0007] It is a configuration diagram showing the information processing system 1. It is a block diagram showing the hardware configuration of a server device 2. It is a block diagram showing the hardware configuration of a user terminal 3. It is a block diagram showing a functional configuration of a server device 2 according to an embodiment. It is a flowchart showing an outline of processing executed by the information processing system 1.

[0008] Hereinafter, embodiments of the present invention will be described with reference to the drawings. Various features shown in the embodiments described below can be combined with each other.

[0009] Incidentally, the program or program product for realizing the software appearing in one embodiment may be provided as a computer-readable non-transitor-readable medium, or it may be provided so that the program or program product is launched on an external computer and its functions are realized on a client terminal (so-called cloud computing).

[0010] Furthermore, in various information processing according to one embodiment, an input and an output corresponding to the input can be realized. Here, as long as an output is obtained as a result of the input, the form of the information referenced in such information processing (hereinafter referred to as "reference information") is not limited. The reference information may be, for example, rule-based information such as a database, a lookup table, or a predetermined function (including a decision formula such as a regression equation constructed by a statistical method), or a trained model that has been pre-trained to learn the correlation between input and output, or a generative AI such as a large-scale language model that can output a desired result by inputting a prompt (these models include parameters that construct the correlation relationship between input and output) or a visual language model.

[0011] Furthermore, in one embodiment, "part" may include, for example, hardware resources implemented by a circuit in a broad sense, and the information processing of software that can be specifically realized by these hardware resources. Also, in one embodiment, various types of information are handled, and this information can be represented, for example, by the physical values ​​of signal values ​​representing voltage and current, the high or low values ​​of signal values ​​as a set of binary bits composed of 0s or 1s, or by quantum superposition (so-called qubits), and communication and calculations can be performed on a circuit in a broad sense.

[0012] Furthermore, a circuit in a broad sense is a circuit realized by combining at least an appropriate combination of circuits, circuits, processors, and memory. The processor may be a general-purpose processor or a dedicated circuit. In other words, this includes application-specific integrated circuits (ASICs), programmable logic devices (for example, simple programmable logic devices (SPLDs), complex programmable logic devices (CPLDs), and field programmable gate arrays (FPGAs)), etc.

[0013] [Embodiment] 1. Hardware configuration

[0014] This section describes a hardware configuration according to one embodiment.

[0015] 1.1 Information Processing System 1 Figure 1 is a configuration diagram representing Information Processing System 1. Information Processing System 1 comprises a server device 2 and a user terminal 3. The server device 2 and the user terminal 3 are configured to communicate with each other via a telecommunications line. Here, the system exemplified in Information Processing System 1 consists of one or more devices or components. Therefore, even a single server device 2 or user terminal 3 can be an example of a system. More specifically, Information Processing System 1 may include elements selected from the group consisting of server devices 2 and user terminals 3. Also, multiple server devices 2 or user terminals 3 may be used. Unselected elements may not be included in Information Processing System 1, but may be electrically connected to the selected elements as external elements. Here, "user" refers to a person whose health management is performed, and includes patients and healthy individuals.

[0016] 1.2 Server Device 2 Figure 2 is a block diagram showing the hardware configuration of server device 2. Server device 2 comprises a communication bus 20, a communication unit 21, a storage unit 22, and a processor 23. The communication unit 21, the storage unit 22, and the processor 23 are electrically connected within server device 2 via the communication bus 20.

[0017] The communication unit 21 preferably uses wired communication methods such as USB, IEEE 1394, Thunderbolt®, and wired LAN network communication, but may also include wireless LAN network communication, mobile communication such as 3G / LTE / 5G, and Bluetooth® communication as needed. In other words, it is more preferable to implement it as a collection of these multiple communication methods. That is, the server device 2 may communicate various information from the outside via the communication unit 21 and the network.

[0018] The storage unit 22 stores various types of information as defined above. This can be implemented, for example, as a storage device such as a solid-state drive (SSD) that stores various programs related to the server device 2 executed by the processor 23, or as memory such as random access memory (RAM) that stores temporarily necessary information (arguments, arrays, etc.) related to program calculations. The storage unit 22 stores various programs and variables related to the server device 2 executed by the processor 23.

[0019] The processor 23 performs processing and control of the overall operation related to the server device 2. The processor 23 is, for example, a Central Processing Unit (CPU). The processor 23 realizes various functions related to the server device 2 by reading predetermined programs stored in the memory unit 22. That is, information processing by software stored in the memory unit 22 is concretely realized by the processor 23, which is an example of hardware, and can be executed as each functional unit included in the processor 23. In other words, the processor 23 can execute programs so that each functional unit is performed. These will be described in more detail in the next section. Note that the processor 23 is not limited to being a single unit, and may be implemented with multiple processors 23 for each function, or a combination thereof.

[0020] The server device 2 may be on-premises or in a cloud environment. In the case of a cloud-based server device 2, for example, it may provide the above-mentioned functions and processing in the form of SaaS (Software as a Service) or cloud computing.

[0021] 1.3 User Terminal 3 Figure 3 is a block diagram showing the hardware configuration of user terminal 3. User terminal 3 comprises a communication bus 30, a communication unit 31, a storage unit 32, a processor 33, a display unit 34, and an input unit 35. The communication unit 31, storage unit 32, processor 33, display unit 34, and input unit 35 are electrically connected within user terminal 3 via the communication bus 30. The explanation of the communication unit 31, storage unit 32, and processor 33 is the same as the explanation of each part in server device 2 and will therefore be omitted.

[0022] The display unit 34 displays a graphical user interface (GUI) screen that can be operated by the user. The display unit 34 may be included in the housing of the user terminal 3 or it may be an external component. Specifically, the display unit 34 may be implemented as a display device such as a CRT display, liquid crystal display, organic EL display, or plasma display. It is preferable that these display devices be used according to the type of user terminal 3.

[0023] The input unit 35 receives operation input from the user. The operation input is transmitted to the processor 33 via the communication bus 30 as a command signal. The processor 33 can perform predetermined controls or calculations based on the transmitted command signal as needed. The input unit 35 may be included in the casing of the user terminal 3 or it may be external. For example, the input unit 35 may be implemented as a touch panel integrated with the display unit 34. When the input unit 35 is implemented as a touch panel, the user can input tap operations, swipe operations, etc. to the input unit 35. Instead of a touch panel, the input unit 35 can be a switch button, a mouse, a QWERTY keyboard, etc.

[0024] The user terminal 3 may be a general-purpose computer 3a or a mobile terminal 3b, as shown in Figure 1.

[0025] 2. Functional Configuration Next, with reference to Figure 4, the functional configurations of the information processing system 1 will be described. Figure 4 is a block diagram showing the functional configuration of a server device 2 according to one embodiment. As shown in Figure 4, the processor 23 functions as each of the illustrated functional units by executing various programs stored in the storage unit 22. That is, information processing by software stored in the storage unit 22 is concretely realized by the processor 23, which is an example of hardware, and can be executed as each of the functional units included in the processor 23. Specifically, the following functional units may be provided.

[0026] The acquisition unit 231 is configured to acquire various types of information as an acquisition step. Specifically, the acquisition unit 231 is configured to acquire information via the communication unit 21 or the storage unit 22 and to make it readable into the working memory.

[0027] The processing unit 232 is configured to perform various processes on the data received by the acquisition unit.

[0028] The output unit 233 is configured to output the data processed by the processing unit.

[0029] The display control unit 234 performs a display control step which involves processing to display various information on a display medium in a manner recognizable to the user. When using the phrase "display," it is not necessary to distinguish whether the display medium is in a local environment or whether the processing is performed to display it via a network. As a result of the processing by the display control unit 234, various information is presented to various users, for example, who are operating the user terminal 3, via the display unit 34. The various information presented is visual information such as screens, images, icons, and messages. The display control unit 234 may generate the visual information itself, or it may generate only rendering information for displaying the visual information on the display unit 34.

[0030] The calculation unit 235 is configured to perform various calculations related to the server device 2 as calculation steps. The type of calculation is not particularly limited.

[0031] 3. Information Processing Method This section describes the information processing method performed by the information processing system 1. The order of the processes included in the information processing method can be changed as appropriate, multiple processes may be executed simultaneously, and some processes may be omitted.

[0032] 3.1 Overview As described above, the information processing system 1 comprises at least one processor 23, and the processor 23 functions as the following parts by reading a program. In other words, the information processing method comprises each step of the information processing system 1. This embodiment provides one example of an information processing method. From another perspective, such a program causes a computer to execute each step of the information processing system 1. This embodiment provides one example of a program. Figure 5 is a flowchart outlining the processing performed by the information processing system 1. The steps shown in Figure 5 will be described below.

[0033] First, the acquisition unit 231, as a data acquisition step, acquires health data related to the health of the user who is the target of health management (hereinafter referred to as "target user") and context data related to their behavior and / or environment (step S001). Target users include, for example, patients, people before their first medical examination, or people for disease prevention purposes. Here, the target user's health data refers to all data related to the target user's health, including, for example, data on diseases, diet, exercise, and symptoms. Context data refers to information about the target user's behavior and / or environment, including, for example, the target user's needs, attributes, indoor / outdoor environment, presence or absence of an HMD or wearable device.

[0034] Next, the calculation unit 235 creates health management information relating to the health management of the target user based on health data, context data, and reference information (step S002). Here, the reference information is information for selecting health management information collected in advance, and includes information relating to the physical and / or mental state of the target user (hereinafter referred to as "user status information"). User status information includes information indicating the state, such as not having been examined, scheduled for examination, before examination, examined, undiagnosed, diagnosed, untreated, scheduled for treatment, undergoing treatment, treated, physical condition (good, poor, etc., as judged subjectively by the target user), lifestyle behaviors based on hobbies, preferences, personality traits, etc., tendencies regarding health management behaviors or medical behaviors, stress level, prevention status (status of lifestyle improvement, diet management status, sleep management status, stress management status, medication prevention management, scheduled regular checkups or follow-up visits, etc.), health level, or risk status. More specifically, user status information includes, for example, information relating to the target user's digestive system, mental illness, or mental health.

[0035] Furthermore, the reference information is not limited to information for selecting health management information collected in advance, but may also be used as information for generating health management information based on acquired health data and context data. For example, the calculation unit 235 may compare symptom data included in the acquired health data and lifestyle data included in the context data with generation rules included in the reference information, and generate new lifestyle improvement suggestions corresponding to the combination of symptoms and lifestyles.

[0036] Furthermore, the reference information may include a health management information template and variable parameters, and the calculation unit 235 may set the parameters according to the acquired health data and context data and generate health management information using the template. In addition, the reference information may include a statistical model or a machine learning model, and the calculation unit 235 may input health data and context data into the model to generate recommendations or risk prediction results specific to the target user as health management information.

[0037] Health management information refers to information for managing the health of the target user, and includes recommendations for apps to use, therapeutic guidance, and information for self-health management. Subsequently, the output unit 233 outputs the health management information as an output step (step S003). Here, the output unit 233 can also provide app recommendations, therapeutic guidance, recommendations for medical institutions, and alerts based on changes in symptoms.

[0038] In this configuration, by integrating and analyzing the target user's health data and contextual data, it becomes possible to provide not only disease management but also health management information tailored to each user's living environment. As a result, it becomes possible to provide more beneficial technology compared to when contextual data is not analyzed. Furthermore, by using contextual data in addition to health data in this way, it becomes possible to present health management information that takes into account fluctuations in health status caused by the target user's behavior or environmental conditions, thereby proposing methods that are more acceptable to the target user, reducing the input burden, and suppressing inappropriate recommendations.

[0039] The calculation unit 235 may also integrate the acquired health data and context data by associating them based on an identifier associated with a common time axis or target user, and by associating events within the same period with each other. Alternatively, the calculation unit 235 may group the health data and context data by event or predetermined period and integrate them as a set of mutually associated data. The calculation unit 235 may then generate health management information by applying algorithms such as correlation analysis, regression analysis, clustering, decision tree analysis, or neural networks to the integrated data.

[0040] Such integration enables the analysis of the temporal correspondence between fluctuations in health status and lifestyle or environmental conditions, allowing for the extraction of related trends or predictability that are difficult to detect with standalone data. Furthermore, it enables the extraction of behavioral patterns before symptom onset, estimation of aggravating factors, and prediction of future risks, thereby achieving individualized optimization of health management information for target users. Additionally, analysis based on the integrated data set can improve predictive accuracy while reducing false positives compared to processing standalone data.

[0041] 3.2 Specific Examples Specific examples may be included within the scope defined in the overview above.

[0042] <Health Data> Preferably, health data includes data on the target user's illness, diet, exercise, or symptoms. Here, illness data may include diagnosis, severity of illness, stage of illness progression, medical history, medication history, prescriptions, or treatment history. Diet data may include the type of food consumed, amount consumed, time of consumption, nutrient content, allergen information, etc. Exercise data may include the type of exercise, exercise time, exercise intensity, calories burned, steps taken, heart rate, etc. Symptom data may include bowel movement status, presence or absence of symptoms such as abdominal pain, nausea, sleep disturbances, and mood swings, as well as frequency, intensity, duration, and time of onset.

[0043] These health data may be obtained through user input, acquisition from wearable devices, acquisition of data provided by healthcare institutions, or sharing from other health management applications. Furthermore, the health data is not limited to data at a single point in time, but may also be acquired as time-series data accumulated over time.

[0044] According to this aspect, comprehensively handling various types of data can improve the accuracy of health management information. Furthermore, since not only disease information but also multifaceted health data including lifestyle habits and symptom progression can be comprehensively handled, the health condition of the target user can be grasped more precisely. As a result, the suitability of health management information can be improved, and it is possible to achieve improvement in the validity of recommended content, suppression of unnecessary proposals, and realization of continuous health management support. Furthermore, by analyzing these health data in combination with context data, it is possible to provide health management information adapted to the living environment or behavioral state of the target user.

[0045] <Gastrointestinal tract> Preferably, the health data includes data relating to a gastrointestinal disease and / or a gastrointestinal condition of the target user, and the health management information is information relating to a gastrointestinal disease and / or a disease associated with a gastrointestinal condition. Here, the gastrointestinal disease may include, for example, gastritis, gastric ulcer, reflux esophagitis, irritable bowel syndrome, inflammatory bowel disease, functional dyspepsia, and the like. The data relating to a gastrointestinal condition may include the presence / absence, frequency, intensity, duration, time of onset, and the like of symptoms such as abdominal pain, abdominal bloating, bowel movement status, stool shape, diarrhea, constipation, nausea, decreased appetite, and indigestion. The health data may also include test data such as endoscopy results, blood test results, and stool test results. The health management information may include treatment policies for gastrointestinal diseases, dietary therapy proposals, medication management support, consultation guidelines for symptom exacerbation, improvement proposals for related mental conditions or lifestyle habits, and the like.

[0046] According to this aspect, in the treatment and management of gastrointestinal diseases and / or diseases associated with gastrointestinal conditions, individually optimized support can be provided based on the progression of symptoms and lifestyle habits of the target user. Furthermore, by analyzing the correlation between gastrointestinal symptoms and context data such as meals, sleep, or stress, it is possible to estimate triggers of symptoms or detect exacerbation trends at an early stage, and promote preventive intervention or appropriate consultation behavior.

[0047] <Health management information> Preferably, the health management information includes information on medical institutions and / or health management applications recommended for the target user. Here, the information on medical institutions may include clinical departments, specialized fields, locations, consultation hours, availability of online medical treatment, treatment records for target diseases, and the like. The calculation unit 235 may select or generate an appropriate medical institution for recommendation based on the health data and context data of the target user, in consideration of the target user's symptoms, severity, residential area, available time for hospital visit, and the like. In this case, the recommendation may be configured to recommend one piece of optimal health management information to the target user, may be configured as a recommendation that displays two or more pieces of health management information in parallel to prompt the target user to make a selection, or may be configured to set a recommendation order for two or more pieces of health management information according to the target user and display them in the order of the recommendation order.

[0048] The health management application may include, for example, the following applications. In addition, the applications listed below may be medical device programs (Software as Medical Device: SaMD), or may be non-medical device programs (non-SaMD) that do not fall under SaMD, without limitation. ・Applications that support recording and visualization of the user's bowel movement status, diet, exercise, sleep or symptoms ・Applications that provide digital therapeutics ・Applications that evaluate the user's health condition or assist in diagnosis ・Applications that support medication management, hospital visit management or lifestyle habit improvement

[0049] The calculation unit 235 may select an appropriate application from a plurality of health management applications according to the target user's health condition, disease type, disease stage, degree of understanding of the disease, degree of understanding of health management applications, or usage history of one or more health management applications, or may generate and recommend health management information in a form of presenting a combination of functions that are suitable for or highly acceptable to the target user.

[0050] This configuration allows for the integrated provision of health management information, including both medical institutions and health management applications, and enables the presentation and recommendation of options tailored to the target user's symptoms, living environment, and behavioral characteristics. Furthermore, it allows for the appropriate distinction between situations where a medical consultation is recommended and situations where self-management should be prioritized, thereby reducing unnecessary medical visits and preventing the worsening of conditions.

[0051] Furthermore, the calculation unit 235 may dynamically adjust the recommendation order of medical institutions or health management applications based on the target user's response history to past or most recent recommendation results. In this configuration, the recommendation order can be dynamically optimized based on the target user's response history to recommend health management information that is appropriate to the target user's latest condition or behavioral characteristics, thereby prioritizing the presentation of medical institutions or health management applications that are highly acceptable to the target user. In addition, the frequency of presenting recommendations for which no response was received in the past or most recent instance can be reduced, thereby suppressing unnecessary or inappropriate recommendations for the target user and improving the user experience. Moreover, the recommendation logic can be improved based on continuous feedback, thereby improving the accuracy and effectiveness of health management support.

[0052] <Data Sharing> Preferably, health data is configured to be shareable with medical institutions and / or health management applications. Here, sharing means making all or part of the health data transmittable via a predetermined communication protocol, which may be bidirectional or unidirectional. The shared health data may include disease information, symptom information, lifestyle information, test results, time-series data, etc. Sharing may be based on the selection of target users and may be controlled at the item level, period level, or granularity level (individual symptom events, daily summaries, weekly average values, or any granularity based on a combination thereof). Health data may also be shared after being converted to a common format, or it may be normalized to match the data format of the medical institution's electronic medical record system or health management application.

[0053] This configuration enables seamless collaboration with medical institutions and applications by allowing the sharing of health management information. Furthermore, because the health data of target users can be smoothly linked with medical institutions and health management applications, it is possible to improve the efficiency of information provision during consultations, reduce duplicate data entry, and prevent information gaps. In addition, since the scope of sharing can be controlled based on the consent and settings of the target users, it is possible to ensure privacy while enabling continuous health management.

[0054] <Needs and Attributes> Preferably, contextual data includes the needs and / or attributes of the target user. Here, user needs are not limited to information that indicates a request or demand from the user, such as the following: ・Prioritized actions (e.g., prioritizing dietary improvements, increasing exercise, etc.) ・Desired health management policies (e.g., prioritizing lifestyle improvements over drug therapy, etc.) ・Desired location or type of medical care for medical institutions (e.g., wanting online consultations, etc.) ・Priority of action policies ・Desired notification frequency or time of notification ・Desired use of health management applications (e.g., desired number of apps, frequency of use, granularity of information to input, etc.) These needs may be obtained through explicit input by the target user or may be estimated from usage history or selection history.

[0055] Furthermore, user attributes are not limited to information that defines the target user, such as the following: the target user's age, gender, residential area, medical history, disease stage, lifestyle, hobbies or preferences, and digital literacy. Attributes are not limited to fixed attributes; they may also be dynamic attributes that are updated in accordance with the progression of the disease or changes in the living environment.

[0056] This approach allows for the provision of health management information that takes into account not only the target user's health status but also their intentions and lifestyle characteristics, enabling the proposal of treatments or health management methods that are easily accepted by the target user. Furthermore, since the content presented can be adjusted according to the target user's priorities or usage patterns, it is possible to improve the rate of health management adherence and promote behavioral change.

[0057] <Wearable Devices> Preferably, health data includes biometric information obtained from a wearable device worn by the user. Health data includes, but is not limited to, biometric information that can be measured by the user using a health meter, biometric information that can be obtained from a wearable device, biometric information measured at a medical institution, etc., as shown below: ・Weight of the user ・Height of the user ・Bone density of the user ・Digestive symptoms of the user (frequency of bowel movements, presence or absence of blood in stool, stool characteristics, etc.) ・Body composition of the user (BMI, lean body mass, body fat percentage, muscle mass, skeletal muscle percentage, water content, etc.) ・Heart rate, heart rate variability, blood pressure, blood oxygen saturation, activity level, steps, sleep duration or quality of sleep ・Sweat of the user and its components ・Blood components of the user (blood glucose, cholesterol level, uric acid level, etc.)

[0058] Wearable devices may include smartwatches, activity trackers, continuous glucose monitors, heart rate sensors, sleep trackers, etc. This biometric information may be acquired automatically at regular intervals, or in real time or near real time. Furthermore, the biometric information may be stored as time-series data and analyzed in an integrated manner with other health data and contextual data.

[0059] This configuration allows for continuous and frequent monitoring of changes in the target user's health status, enabling early detection of signs of health deterioration, immediate feedback on lifestyle changes, and precise analysis of symptom progression. As a result, it becomes possible to provide support that immediately reflects changes in the target user's health status.

[0060] <Output Destination> Preferably, the output unit 233 outputs health management information in a manner that can be understood by a medical institution or healthcare professional as an output step. Here, the output may be in the form of display on a terminal of a medical institution, transmission to an electronic medical record system, output in report format, or sharing via a cloud server. The health management information may include the progression of the target user's major symptoms, an overview of lifestyle habits, fluctuations in test values, estimated triggers (factors that may cause the onset, worsening, or fluctuation of symptoms), or recommended countermeasures. The health management information may also be presented in the form of graphs, charts, lists, or summary text. Healthcare professionals may refer to this health management information to consider the treatment plan for the target user, adjust medication, provide lifestyle guidance, or determine whether additional tests are necessary.

[0061] This approach allows healthcare institutions to grasp health data and contextual data organized chronologically, without relying solely on information provided verbally by the target user. This enables faster decision-making and optimization of guidance content. Furthermore, it reduces the burden of information verification during consultations and interviews, and improves the efficiency of medical care and guidance through enhanced collaboration with healthcare institutions.

[0062] Here, medical institutions and healthcare professionals are not specifically limited to hospitals, clinics, doctors, or nurses, but may also include pharmacies or pharmacists, and may encompass facilities that target users may use and the people working at such facilities.

[0063] <Interface> Preferably, the output unit 233 presents the target user's health management information via an interface corresponding to the target user's attributes as an output step. Here, the target user's attributes may include age, gender, disease type, disease stage, medication history, residential area, medical history, lifestyle, level of understanding, usage history, or digital literacy. Based on these attributes, the output unit 233 may change the number of display items, the length of the explanatory text, whether or not technical terms are used, whether or not charts and graphs are used, the font size, color scheme, or screen transition structure.

[0064] For example, for elderly users, the font size may be increased, the operation buttons may be simplified, and the explanatory text may be changed to simpler language. For users with medical knowledge, detailed displays of test results, statistical values, or detailed explanations including technical terms may be provided.

[0065] This configuration enables the creation of a user-friendly and easy-to-view health management system tailored to each target user. Furthermore, it allows for displaying information in a way that matches the target user's level of understanding of diseases, understanding of health management information, and operational ability with the health management application, thereby promoting information comprehension and reducing operational errors. Additionally, it provides an appropriate amount of information for each target user, improving the acceptance and continued use of health management information.

[0066] <Sharing across multiple applications> Preferably, at least one of the group consisting of health data, context data, and health management information (hereinafter referred to as "shared information") is configured to be shareable among multiple health management applications. Here, "shareable" means that all or part of the shared information can be sent and received between multiple health management applications and used as identical or associated data.

[0067] The information to be shared may include health data, contextual data, recommendations, notification history, or summary information. Sharing may be performed based on a standardized data format, and user information may be associated across applications using a common identifier. Sharing may be based on user selection and may be controlled at the item, time period, or granularity level. Furthermore, when the shared information is updated, the system may be configured to send only the differential information. This allows for maintaining consistency while reducing the communication load.

[0068] This configuration allows for consistent health management even when the target user uses multiple applications. Specifically, even when the target user uses multiple health management applications simultaneously, the consistency of shared information can be maintained, thereby preventing duplicate input and avoiding information loss or inconsistencies. Furthermore, consistent health management can be achieved while dividing roles among applications with different functions. In addition, shared information may be synchronized in real time or near real time. This can suppress inconsistencies in displayed content between applications.

[0069] <Location Information, etc.> Preferably, the calculation unit 235 generates events related to the target user's meals, exercise, or sleep based on the context data as a generation step. The acquisition unit 231 acquires the generated events as health data as a data acquisition step. Here, the context data may include location information, time information, transaction information, image data, activity level data, or communication history. Here, location information may be obtained, for example, from GPS (Global Positioning System) information installed in the terminal used by the target user. Time information may be obtained via the terminal used by the target user. Transaction information may be obtained from information on the history of monetary transactions made at commercial facilities, restaurants, sports gyms, etc. on the terminal used by the target user. In addition, image data, etc. may also be obtained via the terminal used by the target user. The method of acquiring this information is not particularly limited. The calculation unit 235 analyzes this context data, estimates the target user's behavior, and generates events.

[0070] The calculation unit 235 may, for example, generate a meal event at a restaurant if a stay at a restaurant is detected for a predetermined time or longer based on location and time information. The calculation unit 235 may also generate an exercise event at a gym or exercise facility if a stay at a gym or exercise facility is detected for a predetermined time or longer based on location and time information. Furthermore, the calculation unit 235 may generate a meal event if restaurant use is estimated based on transaction information. The calculation unit 235 may also generate an exercise event if gym or exercise facility use is estimated based on transaction information. In addition, the calculation unit 235 may generate a sleep event if bedtime or wake-up time is estimated based on image data or activity data acquired from a wearable device. The generated events may include attributes such as mealtime, exercise time, sleep time, estimated intensity, or estimated content, and may be stored in the storage unit 22 as health data and analyzed integrally with other health data and contextual data.

[0071] This configuration reduces the burden of inputting health data. Furthermore, since health-related events can be automatically generated based on contextual data and stored as health data without requiring individual input from the user, the burden of inputting health data is further reduced. Additionally, it helps prevent data entry errors and improves recording accuracy, thereby supporting continuous health management.

[0072] <Description Input> Preferably, the acquisition unit 231 acquires a description of the health or mental state (hereinafter referred to as "state description") entered by the inputter as part of the description acquisition step. The state description may be entered by voice input or text input. The person entering the state description may be the target user themselves, or a medical professional or caregiver.

[0073] Furthermore, the calculation unit 235 normalizes the acquired state description into technical terms as a first normalization step. Hereinafter, in this specification, "normalization," "conversion," or "standardization" refers to the process of arranging the acquired data into a standard format based on a predetermined terminology system, expression format, unit system, or code system. Depending on the type of input data, the object of processing, or the purpose of processing, these processes may be performed as first normalization, second normalization, conversion, or standardization. For example, first normalization refers to the process of converting a state description or the like, input in natural language, into a standard expression based on a predefined technical terminology system.

[0074] For example, in the case of medical terminology, normalization involves converting input such as "my stomach is throbbing" to "abdominal pain," and converting "I need to go to the toilet often" to "frequent urination" or "increased frequency of bowel movements." The arithmetic unit 235 may perform speech recognition processing in the case of speech input, or perform morphological analysis or semantic analysis in the case of text input, and then perform normalization by referring to a thesaurus or a technical term dictionary.

[0075] Then, as a data acquisition step, the acquisition unit 231 acquires the normalized state description as health data and stores it in the storage unit 22. When storing, it may be recorded in association with the original data before normalization, and information such as the input date and time, the type of inputter, or the reliability of the normalization process may be added. Furthermore, the normalized state description may be accumulated as time-series data and managed in association with other health data or context data. This allows it to be used for analyzing the trends of health or mental state, estimating causal relationships, or statistical processing.

[0076] This configuration allows target users to input accurate health data. Furthermore, even if target users are unfamiliar with technical terms, they can input their health or mental state using natural or medically accurate language, and this input can be treated as normalized health data. As a result, the accuracy of input is improved, and the accuracy of subsequent analysis processing or information sharing with medical institutions can be enhanced.

[0077] <Captured Images> Preferably, the acquisition unit 231 acquires captured images as an image acquisition step. Captured images may be images of information obtainable at a medical institution, which is created on paper or electronic media. Paper media may include memos, questionnaires, test results, referral letters, or prescription details. Electronic media may include data created with applications such as Excel and saved as images after output, or data that contains text information but is saved in a format that cannot be extracted as text data. The inputter may be the patient themselves, a medical professional, or a caregiver.

[0078] Furthermore, as a second normalization step, the arithmetic unit 235 normalizes the characters recognized from the acquired captured image into medical terminology. Here, second normalization refers to the process of associating the string of characters recognized from the captured image, etc., with standard medical terminology expressions based on a medical terminology dictionary or a standard code system. In detail, the arithmetic unit 235 performs character recognition processing on the acquired captured image and extracts character information from the image. Furthermore, the arithmetic unit 235 normalizes the extracted character information based on a medical terminology dictionary or a standard code system. The arithmetic unit 235 may, for example, unify variations in notation such as "WBC," "white blood cell count," or "White Blood Cell Count" and convert them into standard expressions.

[0079] The acquisition unit 231 then acquires the normalized characters as health data as a data acquisition step and stores them in the storage unit 22. When storing the data, the character information may be recorded in association with the original captured image, or information indicating the extraction position within the image or the reliability of the character recognition process may be added. Furthermore, the normalized character information may be managed by assigning an identifier based on a standard code system, or it may be stored as time-series data. In addition, the health data may be stored in association with other health data or context data.

[0080] This configuration allows for easy input of health data. Furthermore, since medical information held by the user on paper or electronic media can be captured simply by taking a photograph, the effort required for data entry is significantly reduced. Additionally, by combining character recognition and medical term normalization, the data can be utilized in a format suitable for subsequent analysis, statistical generation, or data sharing with medical institutions.

[0081] The calculation unit 235 may select from the extracted candidate strings based on their confidence level, and may request confirmation from the inputter if the confidence level is below a predetermined value. Here, confidence level refers to an index indicating the likelihood that the candidate string extracted by the character recognition process is a correct string. The confidence level may be calculated based, for example, on a probability value calculated by the character recognition model, the degree of match with a character image, the probability difference between candidate strings, or the degree of match with a dictionary. This configuration can suppress erroneous registrations caused by misrecognition in the character recognition process.

[0082] Furthermore, by ensuring the reliability of important data that could influence medical decisions, it is possible to improve safety and explainability suitable for medical use. In addition, by appropriately separating automated processing and verification processing, it is possible to achieve both processing efficiency and data quality. Here, automated processing refers to processes that automatically perform tasks such as detecting character regions from captured images, generating string candidates using character recognition models, extracting predetermined items from recognition results, and normalizing notation or converting units based on dictionaries or conversion rules. On the other hand, verification processing refers to processes that request verification from the user and accept correction input as needed.

[0083] <Notification> Preferably, the display control unit 234 notifies the target user of the outputted health management information as a notification step. The calculation unit 235 adjusts the timing or content of the notification to the target user based on the acquired context data. Then, as a notification step, the display control unit 234 notifies the target user of the outputted health management information according to the adjusted timing or content.

[0084] Here, context data may include the target user's time information, location information, activity status, sleep status, stress level, past or recent notification history, or response history to notifications. The calculation unit 235 may refer to this information and dynamically control whether or not to send notifications, the sending time, frequency, or content of notifications. For example, if it is estimated that the target user is on the move or asleep, the notification may be delayed. The calculation unit 235 may also reduce the notification frequency if there has been no response to similar notifications in the past.

[0085] Furthermore, if the target user is staying in a specific area, information on medical institutions related to that area may be given priority in notification, and if the user is estimated to be in a high stress state, a concise expression may be used instead of a detailed explanation. In addition, the notification method may be a combination of push notifications, emails, voice notifications, or in-app displays. The calculation unit 235 may also calculate a notification priority score based on each context data, and execute a notification if the score exceeds a predetermined threshold, or postpone or suppress the notification if it falls below the predetermined threshold.

[0086] This approach allows for more appropriate notifications compared to notifications that do not consider contextual data. Furthermore, because notifications can be optimized according to the target user's situation, unnecessary notifications can be suppressed and important information can be reliably conveyed. Additionally, by improving notification receptivity, the continuation of health management behaviors can be enhanced.

[0087] <Causal Indication> Health data may include data showing the progression of digestive symptoms, and context data may include data related to the target user's diet, sleep, activity, or stress. In that case, preferably, the calculation unit 235 calculates an index indicating the magnitude of the causal relationship between diet, sleep, activity, or stress and digestive symptoms based on the acquired health data and context data. Then, the output unit 233 outputs the index as health management information as an output step.

[0088] In detail, the calculation unit 235 analyzes the acquired health data and context data in correspondence on a time axis and calculates an index indicating the magnitude of the causal relationship. Here, the index indicating the magnitude of the causal relationship may include the correlation coefficient between behavior or living conditions and gastrointestinal symptoms, the probability of symptom occurrence, the risk ratio, the improvement rate, the regression coefficient, the feature importance, or the degree of influence estimated by a statistical model or machine learning model.

[0089] The calculation unit 235 may, for example, extract behavioral data for a predetermined period before and after the onset of symptoms and perform statistical analysis in correspondence with the presence or absence or severity of symptoms. Alternatively, it may perform multivariate analysis that simultaneously considers multiple contextual factors and calculate the contribution of each factor to the symptoms. Furthermore, the calculated indicators may be presented in numerical, graphical, or ranking format. For example, they may be displayed in a format such as, "The probability of developing abdominal pain after consuming a specific food is 1.8 times higher than normal."

[0090] This approach can help improve symptoms. Specifically, users can quantitatively understand the relationship between their lifestyle and symptoms, making it easier to identify factors that trigger symptoms and supporting the decision of appropriate lifestyle improvements or treatment plans. Furthermore, it can provide medical institutions with objective analysis results, thereby improving the efficiency and accuracy of medical care.

[0091] The calculation unit 235 may also calculate a confidence interval, statistical significance, or estimation precision for the calculated indicator. For example, the calculation unit 235 may also calculate a 95% confidence interval for the calculated correlation coefficient or risk ratio. Specifically, it may be displayed as "Risk ratio for abdominal pain after ingesting a specific food: 1.8 (95% confidence interval: 1.2 to 2.6)". The risk ratio is the value obtained by dividing the probability of symptom occurrence when a specific behavior or lifestyle condition is present by the probability of symptom occurrence when that condition is not present.

[0092] Furthermore, the calculation unit 235 may calculate a p-value for the results of the regression analysis and determine statistical significance by comparing it with a predetermined significance level (e.g., 5%). For example, it may display "The association between the food and the symptoms is statistically significant (p<0.05)." In addition, when using a machine learning model, the calculation unit 235 may calculate and present indicators of estimation accuracy such as accuracy, AUC (Area Under the Curve), F1 score, mean absolute error, or cross-validation results.

[0093] This approach allows for the presentation of the reliability or estimation accuracy of the calculated indicators, enabling target users or healthcare professionals to appropriately evaluate the validity of those indicators. Furthermore, by clearly indicating statistical significance or confidence intervals, it becomes possible to distinguish between random fluctuations and substantial correlations, thereby curbing excessive self-judgment or inappropriate behavioral changes. Moreover, by presenting the estimation accuracy, it becomes easier for healthcare institutions to utilize the data as reference information when making clinical decisions or treatment plan decisions, improving the explainability and transparency of the analysis results. As a result, the reliability of health management information is enhanced, and decision-making by target users and healthcare professionals can be supported more rationally.

[0094] <Summary for Medical Institutions> Preferably, the calculation unit 235 summarizes information regarding the health status of the target user for medical institutions based on the acquired health data and context data. The output unit 233 then outputs the summary as health management information as an output step. Here, summarization refers to the process of extracting information that is useful for medical treatment, guidance, or treatment policy decisions at a medical institution and organizing it in a predetermined format. The summary may not present all of the raw data, but may include a process of selectively extracting information that is highly relevant to medical judgment. The summary may include, for example, the progression of major symptoms, the trend of symptom exacerbation or improvement, estimated triggers, related lifestyle behaviors, changes in medication status, recommended actions, or unaddressed matters.

[0095] The calculation unit 235 may extract health data within a predetermined period and calculate the average or maximum value of symptom intensity, the frequency of occurrence, or the range of variation. The calculation unit 235 may also include an indicator showing the magnitude of the causal relationship described above. Furthermore, the calculation unit 235 may organize the information in a ranking format according to its importance. The calculation unit 235 may also select extraction items based on a summary template defined for each medical department. The summary may be output in text format, tabular format, graph format, or a structured data format that can be imported as a format used by users, locations, and terminals that may utilize the data, such as electronic medical records.

[0096] This approach facilitates explanations from the target user to the medical institution. It also reduces the burden on the target user of verbally describing their symptoms, and allows the medical institution to obtain objective, organized information before consultation. As a result, consultation times can be shortened and the accuracy of consultations can be improved.

[0097] <Viewing Permissions> Health data may be configured to be viewable by at least one of the following groups: the medical institution the user is visiting, medical institutions related to the user's health data, research institutions related to the user's health data, and the user's family and / or caregivers. In this case, preferably, the calculation unit 235 controls the viewing permissions by selecting the items, period, or granularity of the user as a viewing control step. Specifically, the calculation unit 235 identifies the data to be displayed based on the viewing permissions, and the display control unit 234 displays only the identified data.

[0098] Here, "item" refers to data types such as symptom data, medication information, diet information, test results, or location information. "Period" includes a specific day, a predetermined period, or the entire history. "Granule" refers to summary level or detailed level, aggregated values ​​or individual measurements, category units or individual event units, etc. Health data may be configured to be viewable simultaneously by multiple sources. These sources are not limited to the medical institution where the user is currently receiving treatment, but may include medical institutions, university hospitals, research institutions, or specialized clinics that provide specialized medical care or research on the user's symptoms or diseases.

[0099] The calculation unit 235 may be configured to allow different viewing conditions to be set for each viewing destination. For example, it may be configured to allow viewing of detailed data for all items for the medical institution currently being visited, to allow viewing of only anonymized aggregate values ​​or symptom trends over a predetermined period for specialized research institutions, and to allow viewing of summary information for the most recent week for family members or caregivers. Furthermore, viewing permissions may be configured to be added, changed, or suspended at any time by the target user.

[0100] This configuration allows users to access their health data to the extent they desire. Furthermore, because users can flexibly control the scope of access, they can ensure privacy while providing only the necessary information to the necessary parties. As a result, it is possible to achieve both the promotion of medical collaboration and the protection of personal information.

[0101] <Anonymization> Health data may be configured to be shareable with at least one of the following groups: the medical institution the user is visiting, medical institutions related to the user's health data, research institutions related to the user's health data, and the user's family and / or caregivers.

[0102] In that case, preferably, the calculation unit 235 removes identifiers such as name, date of birth, address, contact information, or personal identification number from the health data as a removal step. Here, removal processing refers to processing that deletes, replaces, or encodes information that can identify an individual. For example, this may include applying pseudonym processing to personal information or sensitive personal information that can identify an individual, replacing identifiers with other codes, or deleting identification information. Furthermore, as an anonymization step, the calculation unit 235 performs additional anonymization processing on the health data after identifiers have been removed. Anonymization processing may include variable weighting, aggregation of rare events, or pseudokey assignment.

[0103] Here, variable weighting refers to the process of assigning weights indicating importance or contribution to multiple data items to reduce the influence of highly identifiable variables. Aggregation of rare events refers to the process of integrating data that occurs infrequently and poses a risk of re-identification into predetermined categories. Pseudo-key assignment refers to the process of assigning identification keys that do not directly identify individuals, thereby enabling time-series tracking or statistical analysis without identifying individual users. The calculation unit 235 may change the strength of anonymization depending on the type of recipient. For example, the aggregation level may be increased for research institutions, and pseudo-keyed data may be shared with medical institutions.

[0104] This approach ensures analytical usefulness while preserving patient privacy. It also enables continuous data utilization while reducing the risk of re-identification. Furthermore, by adjusting the anonymization strength according to the recipient, it is possible to achieve the minimum necessary information disclosure, thereby promoting both medical research and clinical application while enhancing legal compliance. In addition, it enables secure data distribution in distributed or cloud environments.

[0105] <Display Mode Control> Preferably, the acquisition unit 231 acquires indicators as an indicator acquisition step, which include the attributes of the terminal user using the terminal to which health management information is output (hereinafter referred to as the "output destination terminal") and / or context data related to the output destination terminal by the terminal user. Here, the terminal user includes patients, medical professionals or caregivers, etc. The indicators may include the terminal user's settings, usage history, user attributes or operation tendencies. In addition, the context data related to the output destination terminal may include the terminal type, screen size, communication environment, frequency of use or digital literacy.

[0106] Furthermore, the calculation unit 235 adjusts the complexity of the display mode of the output terminal according to the acquired indicators as a mode adjustment step. Here, complexity is represented by the number of display items, the number of input items, the number of buttons (number of items pressed), the number of screen transitions, and the amount or content of explanation. For example, if the terminal user is a medical professional, more detailed information may be displayed, and if the user is a patient, only the main information may be displayed. Also, if it is estimated that the user has low digital literacy, the number of screen transitions may be reduced and the operation procedure may be simplified. Furthermore, based on the usage history, frequently used functions may be given priority in display.

[0107] This configuration provides a user-friendly UI for terminal users. Specifically, it enables optimal display control according to the terminal user's attributes and usage, thereby suppressing confusion due to information overload and reducing operational burden and errors. Furthermore, by appropriately differentiating the displayed content for professionals and patients, comprehension and work efficiency can be improved. Moreover, by adaptively changing the display configuration according to continuous use, the continuity of long-term health management support can be enhanced.

[0108] <Support Terminal> Preferably, the calculation unit 235 identifies a support terminal used by a support person who supports a user who uses health management information, as an identification step. Here, the user includes target users (patients, people before their first consultation, people for preventative purposes, etc.), doctors, etc. The support person includes hospital staff, caregivers, family members, or medical assistants, etc. The calculation unit 235 may identify the support terminal based on the correspondence between the user and the support person, or it may identify it based on authentication information, registration information, or pre-configuration.

[0109] The acquisition unit 231 then acquires health data and context data entered by the supporter to the identified support terminal as part of the data acquisition step. The data entered from the support terminal may include a description of the user's condition, medication status, lifestyle, behavioral information, or observational information. The input data may also be accompanied by identification information of the person who entered the data. The calculation unit 235 may also restrict the items that can be entered according to the supporter's authority and may perform consistency checks to detect incorrect or inappropriate input.

[0110] This configuration allows data to be acquired even when the user is unable to perform the task. For example, even if the user is elderly, unwell, or unable to operate the system, health data and contextual data can be acquired through a support person. Furthermore, by managing the history of proxy data entry, it is possible to clarify data entry responsibility and improve data reliability. In addition, it is possible to realize continuous health management support within medical institutions or in home care settings.

[0111] <Explanation for Target Users> Preferably, the output unit 233 outputs key points for explanation to target users as health management information as an output step. Here, target users include patients, those awaiting their first consultation, or users for preventative purposes, as described above. These key points may also be explanation support information used when medical professionals such as doctors explain to target users. Reference information may include past medical history, test results, or regional medical trends.

[0112] The calculation unit 235 extracts or generates explanatory key points based on the acquired health data, context data, and reference information. These explanatory key points may include recommended treatment options, the benefits and drawbacks of each treatment, anticipated side effects, lifestyle considerations, or guidelines for the next medical consultation. The key points may also be organized in order of importance and output in bulleted list format or visually highlighted format. Furthermore, depending on the target user's level of understanding or attributes, technical terms may be converted into simpler language before output.

[0113] This configuration makes it easier to explain things to the target user. For example, it can reduce the burden on doctors and other medical professionals when explaining things to the target user. Furthermore, by structuring and presenting the explanation content, it is possible to ensure consistency in the explanation. In addition, it can promote the target user's understanding and support the appropriate implementation of informed consent.

[0114] <Explanation for Target Users, Part 2> Preferably, the output unit 233 outputs explanatory materials as health management information, which describe the health status of the target user at a difficulty level appropriate to the attributes of the target user. Here, the attributes of the target user may include age, the stage of the disease the target user is suffering from, level of understanding, medical history, or presence or absence of medical knowledge. The calculation unit 235 generates explanatory materials based on the acquired health data, context data, and reference information, and adjusts the difficulty level of the explanatory materials according to the attributes of the target user.

[0115] Adjusting the difficulty level may include the use or non-use of technical terms, the length of the text, the level of abstraction of the explanation, the proportion of use of diagrams and tables, the addition of concrete examples, and the presentation of explanations in stages or interactively through questions. For example, the calculation unit 235 may generate concise explanatory materials that replace technical terms with simpler language and make extensive use of diagrams, tables, or illustrations for elderly target users or users with limited medical knowledge. On the other hand, the calculation unit 235 may generate explanatory materials that include detailed numerical data or comparative information on treatment options for target users with a high level of understanding of the disease.

[0116] This approach makes it easy to provide clear explanations to target users. Specifically, it allows for explanations of health conditions at an appropriate level of difficulty according to the user's attributes, thereby improving comprehension. Furthermore, it avoids confusion caused by overly technical explanations or a lack of information due to overly simplified explanations. In addition, it can enhance the user's sense of satisfaction and promote appropriate treatment choices or health management behaviors.

[0117] <Explanation for medical professionals such as physicians> Preferably, the calculation unit 235 creates interview insights for medical professionals such as physicians, which are used by information providers to medical institutions. Here, an information provider refers to an entity that provides information on medical care, pharmaceuticals, medical devices, or health management to a medical institution or medical professionals such as physicians, and includes company representatives, research institution representatives, government agency representatives, or medical-related service providers, and more specifically, includes, for example, a pharmaceutical company's MA (Medical Affairs) representative, academic representative, or pharmaceutical information representative.

[0118] Interview insights refer to key pieces of information that the information provider uses to explain, judge, or reach an agreement with a physician or other healthcare professional during an interview. The calculation unit 235 extracts information related to the physician's or other healthcare professional's area of ​​interest or treatment content based on acquired health data, contextual data, or statistical information, and generates interview insights. Interview insights may include summary text, main graphs, statistical comparison results, or explanatory slide outlines. Summary text may include key clinical trends, indicators of treatment effectiveness, or trends in side effect occurrence. Main graphs may include charts showing time series trends, group comparisons, or correlations. Explanatory slide outlines may include the order of explanation or the structure of the issues discussed during the interview.

[0119] The output unit 233 then outputs the generated interview insights as health management information. Output may be performed by displaying on a display unit, outputting as an electronic file (e.g., PDF format, slide format, or spreadsheet format), sending via email, or sharing via cloud. The output unit 233 may output the interview insights by dividing them into multiple components such as a summary page, a main graph page, or a discussion page. It may also output them in a format that can be edited by the information provider before the interview. Furthermore, the output unit 233 may change the display order or emphasized items based on the affiliation, areas of interest, or past interview history of the medical professional, such as a physician. It may also be configured to dynamically present additional information in response to the responses or questions entered by the medical professional, such as a physician, during the interview.

[0120] This configuration makes it easier for information providers to prepare for meetings with medical professionals such as doctors. It also reduces the burden of preparation for meetings between information providers and medical professionals. Furthermore, it improves the quality of meetings by automating the data-driven analysis of issues. In addition, it facilitates consensus building with medical professionals such as doctors and supports appropriate decision-making in medical settings.

[0121] Preferably, the calculation unit 235 causes the system to select an interview template based on physician profile information as a selection step. Here, the physician profile information may include physician type, medical department or specialty, region, areas of interest, past prescribing trends, academic conference participation history, past interview history, or previously used physician template information. Here, physician type may include private practitioners, hospital physicians, specialists, instructors, etc. Medical department may include gastroenterology, psychiatry, general internal medicine, etc. Region may include urban areas, rural areas, specific medical areas, etc. Areas of interest may include specific diseases, specific treatments, specific patient groups, or specific side effects, etc. Furthermore, an interview template refers to a template that defines the composition order, display items, emphasis items, graph format used, or explanatory structure of the interview insights. The selection of the interview template may be automatic, or the information provider may be allowed to make a selection.

[0122] The calculation unit 235 may automatically select the most suitable interview template based on this physician profile information using a predetermined rule-based or machine learning model. Alternatively, the calculation unit 235 may present multiple candidate interview templates with priority and allow the information provider to make a selection. In this case, the reason for the suitability of each interview template may be displayed. Furthermore, the interview template selection algorithm may be updated based on physician response information or interview outcome indicators obtained after the interview.

[0123] The output unit 233, as an output step, structures the interview insights using the interview template selected by the information provider and outputs them as health management information. For example, a template for specialists may be composed mainly of detailed statistical data and comparative graphs, while a template for non-specialists may be composed mainly of clinical significance and practical key points.

[0124] This approach reduces the effort required to prepare customized materials for each physician while improving the quality of consultations. Furthermore, it helps to minimize the excess or deficiency of explanations and allows for the presentation of information tailored to the physician's interests, thereby improving consultation efficiency and accelerating consensus building. Additionally, standardizing the material structure ensures consistent information delivery.

[0125] <System Integration> Preferably, the calculation unit 235 performs a conversion step to normalize the differences in items, units, or code systems between the output health management information and the medical institution's electronic medical record system or claims system. Here, conversion refers to the process of matching differences in item names, measurement units, or code systems when integrating with an external system such as an electronic medical record system or claims system.

[0126] For example, the calculation unit 235 may perform the following processes: • Associating different test item names with standard codes; • Converting different measurement units (mg, g, mmHg, etc.) to predetermined reference units; • Mapping different disease code systems (ICD code, SNOMED, ​​etc.) to a common code system; • Standardizing drug codes or medical device codes.

[0127] Furthermore, the calculation unit 235 may maintain a conversion table to accommodate different item configurations for each medical institution, and may convert the data into a data format compliant with external standards (e.g., a standardized format). Moreover, the conversion may be performed not only when outputting to a medical institution, but also when integrating data acquired from a medical institution within this system.

[0128] This configuration allows for smooth integration with medical institution systems. Furthermore, it enables consistent data integration even when data formats differ between different medical institutions. Additionally, it prevents misinterpretations caused by input errors or unit mismatches, thereby improving safety and reliability in medical settings.

[0129] <Offline Input> The information processing system 1 may further include an input assistance terminal. Here, an input assistance terminal is a terminal that has the function of receiving input of health data or context data and temporarily storing such data, even when it is not in constant communication with the server device 2. The input assistance terminal may include a smartphone, tablet, notebook computer, wearable device, or terminal within a medical institution.

[0130] The input assistance terminal may accept and collect health data or context data while offline, and transmit the data to the server device 2 when communication becomes possible. Specifically, the input assistance terminal may temporarily store the input data in local storage and manage the data by adding a timestamp, terminal identification information, or inputter identification information. When communication is restored, the input assistance terminal may extract only the unsent data and transmit it differentially, or it may transmit data for a predetermined period in batches. The input assistance terminal may also perform retransmission control until it receives confirmation of transmission completion. Furthermore, to guarantee the transmission order, it may be configured to transmit data in chronological order. In addition, encrypted communication may be used to protect the data during transmission.

[0131] Preferably, the acquisition unit 231 acquires health data or context data accumulated in the input assistance terminal at any time when communication is possible as part of the data acquisition step. If there is a conflict between the data to be acquired and data already stored in the storage unit 22, the calculation unit 235 resolves the conflict based on the conflict resolution rule, and then the acquisition unit 231 acquires the data. Here, a conflict refers to a state in which multiple different values ​​exist for the same item or the same period. Conflict resolution rules may include prioritizing the last editor, prioritizing the latest timestamp, prioritizing the input source with higher reliability, or maintaining referential consistency.

[0132] Referential consistency refers to the process of maintaining consistency so that identifiers or associations referenced by multiple data sets do not become inconsistent. For example, an update process may be performed to maintain the association between event data and corresponding symptom data. Furthermore, the calculation unit 235 may refer to the timestamp, input source identification information, inputter type, confidence score, or version number attached to each conflicting data set and determine the data to be resolved based on a predefined priority table. For example, the system may be configured to prioritize data entered from medical institution terminals, then input from support terminals, and finally input from the target user themselves.

[0133] Furthermore, the calculation unit 235 may apply multiple rules in a stepwise manner, rather than applying a single rule. For example, it may first extract candidates that can maintain referential consistency, select data with the latest timestamp from among them, and then determine whether the confidence score is above a predetermined threshold to make a final decision. In addition, the calculation unit 235 may perform consistency verification processing on the results after conflict resolution to check whether there are any inconsistencies in dependencies with other related data. If an inconsistency is detected, the calculation unit 235 may request re-resolution processing or administrator confirmation. Furthermore, the acquisition unit 231 may save the history before conflict resolution and make the change history traceable.

[0134] This configuration allows data entry to continue even in the event of communication failures or network connectivity issues. Furthermore, it maintains data integrity even when input is received from multiple terminals. Additionally, retaining an input history improves data reliability and traceability.

[0135] <Data Standardization> Preferably, the calculation unit 235 performs standardization on the acquired health data or context data using standardization means including a variable dictionary as a standardization step. Here, standardization refers to the process of unifying inconsistencies in notation, units, or event timelines for the acquired health data or context data. The variable dictionary refers to a dictionary that can be added, updated, or switched during operation, and may include a disease name dictionary, symptom dictionary, drug dictionary, unit conversion table, or event classification dictionary. The variable dictionary may be updated by an administrator or by synchronization with an external standard.

[0136] Standardization includes term normalization, unit conversion, or event time-series sorting. Term normalization is the process of unifying different notations with the same or similar meanings into a common standard expression. For example, "abdominal pain," "stomach ache," and "abdominal pain" may be unified into a single standard term. Unit conversion is the process of converting numerical data expressed in different units of measurement into a common standard unit. For example, weight may be standardized to kg, and blood glucose levels may be standardized to a predetermined standard unit. Event time-series sorting is the process of rearranging multiple events on a common time axis so that their order of occurrence or interrelationships can be understood. For example, meal events and symptom onset events may be placed on the same time axis to allow for relationship analysis.

[0137] Furthermore, the calculation unit 235 may maintain the correspondence between data before and after standardization, and may be configured to allow tracing back to the original data as needed. Specifically, the calculation unit 235 may store the correspondence between the original data before standardization and the data after standardization as association information in the storage unit 22. This association information may include dictionary information used for conversion, applied conversion rules, conversion date and time, or information about the entity that performed the conversion. This makes it possible to refer to the original data before standardization when confirming the basis for generating the analysis results or health management information in a later stage.

[0138] Furthermore, the calculation unit 235 may retain a history of the standardization process, and when re-standardization is performed after a dictionary update, it may be configured to allow comparison of the difference with past standardization results. It may also be possible to present the original data and conversion process when responding to inquiries or audits from medical institutions. Such embodiments can improve the transparency and explainability of the standardization process. Furthermore, safety and reliability in medical settings can be ensured. In addition, because the scope of impact can be understood when the dictionary is updated or conversion rules are changed, continuous improvement of the system can be facilitated.

[0139] This configuration allows for the integration of health data and contextual data from different sources or input methods into a common format. Furthermore, it facilitates subsequent analysis, display, and system integration with healthcare institutions. Additionally, it reduces analytical errors caused by inconsistencies in notation or unit differences between different data sources, thereby improving analytical accuracy and reliability.

[0140] <Statistical Information> Context data may include information about pharmaceuticals or medical devices used by the target user. In that case, preferably, the calculation unit 235 generates statistical information in the statistical generation step, which is a combination of the usage status of pharmaceuticals or medical devices indicated by the multiple context data acquired and the health status indicated by the multiple health data acquired together with the multiple context data.

[0141] In one embodiment, the context data may include quasi-drugs, health foods, supplements, etc. that are not classified as pharmaceuticals and are used by the target user. Similarly, the context data may include health devices, services, etc. that are different from medical devices and are used by the target user.

[0142] Here, the statistical generation step may classify user groups based on a predetermined period, dose, frequency of use, or start date of use, and aggregate health status indicators for each group. Health status indicators may include symptom scores, laboratory values, event frequency, recurrence rate, or improvement rate. Statistical information may include, for example, the average or distribution of symptom scores in user groups who used a specific drug or medical device for a certain period, the trend of symptom improvement by use status, the trend of health status indicators for each category of use period or amount, correlation coefficients, or regression analysis results.

[0143] Furthermore, the calculation unit 235 may generate stratified statistical information based on attributes such as age group, disease stage, or presence or absence of concomitant treatment. Here, stratification refers to the process of classifying multiple target users into multiple groups based on predetermined attributes and calculating health status indicators for each classified group. Attributes may include age group, sex, disease severity, duration of onset, medical history, lifestyle, region, or type of concomitant medication. The calculation unit 235 may also calculate the mean, median, standard deviation, distribution shape, improvement rate, deterioration rate, or probability of occurrence for each stratified group. In addition, group comparisons may be performed, and significance tests or regression analyses may be conducted.

[0144] The output unit 233 then outputs the generated statistical information as health management information as an output step. The statistical information may be output as a graph, heat map, distribution chart, time-series trend chart, or summary text. Specifically, the output unit 233 may output a line graph showing trends by usage period, a bar graph showing comparisons by usage status, a histogram showing the distribution of symptom intensity, or a dashboard format displaying multiple indicators in a list.

[0145] Furthermore, the output unit 233 may narrow down the displayed items according to the user's attributes. For example, detailed statistical indicators and group comparison results may be displayed for healthcare professionals, while only summary information or trends in simple terms may be displayed for target users. The output unit 233 may also set thresholds for predetermined indicators and highlight or warn if a change exceeding the threshold is detected. Furthermore, it may be configured to allow transitions to related detailed data based on the displayed statistical information.

[0146] This approach allows for a visual and intuitive understanding of statistical information. Furthermore, it enables the presentation of information at an appropriate level of detail tailored to the user's perspective, reducing the burden of understanding and supporting decision-making. Additionally, it facilitates rapid response by allowing for immediate recognition of significant changes.

[0147] Furthermore, this approach allows for the statistical understanding of the relationship between the use of pharmaceuticals or medical devices and health status. It also provides reference information for selecting therapeutic drugs or medical devices by visualizing trends at the population level. Moreover, it supports the creation of evidence based on real-world clinical data and assists in optimizing treatment strategies according to the attributes of target users. In addition, it can streamline decision-making in medical institutions or research institutions.

[0148] <Comparison Information> If the context data includes information on pharmaceuticals or medical devices used by the target user as described above, preferably the calculation unit 235 generates comparison results of statistical information for each medical institution, each region, or each attribute of the target user as a comparison generation step.

[0149] Here, the comparative generation step refers to the process of comparing statistical information calculated for multiple groups and calculating differences, ratios, ranks, or trend differences. For example, the symptom improvement rates calculated for each medical institution may be compared, and the difference or relative ratio of improvement rates may be calculated. Alternatively, the recurrence rates after drug use in each region may be compared.

[0150] The calculation unit 235 may compare the statistical information grouped based on these attributes and determine the difference between groups, ranking, or statistical significance. Furthermore, the calculation unit 235 may calculate the comparison results as difference values, percentage changes, risk ratios, odds ratios, or statistical significance indicators. In addition, the combination of comparison targets may be automatically selected, and if a difference exceeding a predetermined threshold is detected, it may be extracted as a highlighting target.

[0151] The output unit 233 then outputs the generated comparison results as health management information as an output step. The comparison results may be output as a bar graph, radar chart, heat map, ranking display, or summary text. For example, they may be output as a ranking display that ranks the improvement rates for each medical institution, a heat map that displays the incidence rate for each region in different colors, a radar chart that shows the risk ratio by attribute, or a line graph that shows the trend over time.

[0152] Furthermore, the output unit 233 may highlight differences when the difference between the comparison targets exceeds a predetermined threshold, and may also add a warning message. In addition, the output unit 233 may be configured to allow transitions from the displayed comparison results to related detailed statistical information or the original data. Furthermore, the output unit 233 may adjust the display granularity according to the attributes of the user. For example, detailed statistical indicators including difference values, confidence intervals, or significance information may be displayed for healthcare professionals, while only trend explanations or summary information in easy-to-understand language may be displayed for target users. In addition, stratification conditions or analysis methods may also be displayed for research institutions. Furthermore, the output unit 233 may be configured to allow the user to select comparison conditions, periods, or attributes, and may dynamically regenerate the comparison results in response to changes in selections.

[0153] This configuration allows for a visual and intuitive understanding of the comparison results. Furthermore, it enables immediate recognition of significant differences, supporting rapid decision-making. Additionally, it allows for display tailored to the user's expertise or purpose, reducing the burden of understanding while improving the accuracy of decision-making.

[0154] Furthermore, this approach allows for the understanding of the relationship between the use of pharmaceuticals or medical devices and health status for each comparison group. It also supports the optimization of treatment strategies or medical device selection by visualizing trend differences between medical institutions or regions. Moreover, clarifying differences based on attributes can promote the realization of personalized medicine and support rational decision-making in medical institutions or research institutions.

[0155] <Notification Control> The information processing system 1 may further include a database linking the above-mentioned statistical information with information on adverse events. Here, adverse events include all undesirable or unintended signs, such as suspected side effects of pharmaceuticals, malfunctions of medical devices, a rapid deterioration trend in health status, an increase in the incidence rate of adverse events under predetermined conditions, or fluctuations in health indicators that are judged to be statistically abnormal.

[0156] In that case, preferably, the calculation unit 235 determines, as a determination step, whether the generated statistical information corresponds to an adverse event. The determination conditions may include exceeding a predetermined threshold, the degree of deviation from the past average, the result of an anomaly detection by regression analysis, or an anomaly score calculated by a machine learning model. For example, the calculation unit 235 may determine that an adverse event has occurred or is likely to occur if the incidence rate of side effect-related symptoms increases by a predetermined percentage or more in a particular drug use group, or if the frequency of abnormal events increases statistically significantly in a medical device use group.

[0157] Then, as a notification step, the processing unit 232 immediately notifies of the adverse event if it determines that an adverse event has occurred or is likely to occur, and also notifies statistical information other than the adverse event in a digest format. Here, immediate notification may include notifications with high priority, highlighted notifications, or automatic transmission to designated contacts. Furthermore, the recipients of the notification may include medical institutions, research institutions, target users, or designated administrators, and the notification content may include the detected abnormality, scope of impact, recommended countermeasures, or reference statistical information. In addition, the notification history may be recorded and used for analysis of recurrence trends or for audit response.

[0158] This approach allows for the rapid identification of serious incidents. Furthermore, it enables early detection of adverse events based on statistical information, thereby improving medical safety. In addition, by distinguishing between normal and emergency information in notifications, information can be disseminated according to its importance, ensuring the reliable sharing of important information while suppressing an overload of unnecessary notifications.

[0159] More preferably, the following specific examples can be considered.

[0160] Information processing system 1 is, for example, a digital health platform that collects and analyzes health data and contextual data to provide appropriate health management information in order to support the health management of users (patients) with digestive diseases and / or diseases related to digestive conditions.

[0161] This information processing system 1 consists of the following main components: Server device 2 acquires, processes, analyzes, and outputs health data. User terminal 3 is a device in which the user inputs data and receives health management information, and includes a desktop computer 3a, a smartphone, and / or a mobile terminal 3b. User terminal 3 may be a wearable device or may be installed in a medical institution.

[0162] The acquisition unit 231 acquires health data and / or contextual data as an acquisition step. This data may include audio data, text data, image data, and metadata (such as the date and time of the meeting and participant information).

[0163] The storage unit 22 of the server device 2 stores health data and context data. It can also store the user's health history, AI analysis results, and local community data. The processor 23 performs data analysis, generates health management information, and processes data in real time, providing appropriate feedback. The server device 2 can be operated in both cloud-based and on-premise environments, and by strengthening data linkage with medical institutions, it can improve the efficiency of medical support.

[0164] The user terminal 3 has the following main components: The communication unit 31 communicates with the server device 2 to acquire health management information. The storage unit 32 stores the user's health data and past medical history. The processor 33 runs the health management application and processes the user's input data. The display unit 34 can visually display health management information. The display unit 34 can also provide an adaptive UI (simple mode / detailed mode / accessibility support, etc.) according to user attributes. The input unit 35 supports touchscreen, voice input, keyboard input, etc., allowing the user to record symptoms and lifestyle habits.

[0165] In information processing system 1, users can easily understand their own health status and take appropriate action through user terminal 3.

[0166] The information processing system 1 has three functions: acquisition, analysis, and output, and performs the following information processing: The acquisition unit 231 acquires health data and context data from the user terminal 3. The calculation unit 235 analyzes the health data and context data. The output unit 233 provides health management information to the user terminal 3.

[0167] This functional configuration makes it possible to understand the user's health status and provide appropriate health management information.

[0168] The information processing system 1 of the present invention can constitute a "Digital GI Health Platform". In such an embodiment, the information processing system 1 can build an ecosystem that realizes comprehensive health management by linking with the systems of hospitals, clinics, local governments, companies, and digital health companies, centering on users (patients) suffering from digestive diseases (e.g., inflammatory bowel disease (IBD), irritable bowel syndrome (IBS), fatty liver disease (MASH / MASLD), gastroesophageal reflux disease (GERD), non-erosive gastroesophageal reflux disease (NERD), upper gastrointestinal disorders, constipation, diarrhea, fecal incontinence, designated intractable diseases of the digestive system, rare diseases of the digestive system, and / or malignant tumors of the digestive system) and / or diseases related to the condition of the digestive system (including diseases related to the onset, exacerbation, and progression of the condition of the digestive system, and including, but not limited to, sarcopenia, obesity, and / or mental illnesses such as schizophrenia, depression, major depressive disorder, anxiety disorder, bipolar disorder, autism spectrum disorder, and autism).

[0169] Information processing system 1 can consist of (1) collaboration between users (patients) and medical institutions (hospitals, clinics, and home healthcare), (2) a "Digital GI Health Platform" for data collection and analysis, and (3) elements of health management support in collaboration with companies, local governments, and research institutions.

[0170] (1) Regarding collaboration between users (patients) and medical institutions (hospitals, clinics, and home healthcare), for example, users (patients) can manage their health in real time while collaborating with doctors through hospitals, clinics, and home healthcare. Specifically, Information Processing System 1 collects examination data from hospitals and clinics in real time, which users (patients) can use as health management information. In addition, Information Processing System 1 can record the health status of users (patients) at home and recommend a doctor's examination as needed.

[0171] (2) Regarding the "Digital GI Health Platform" for data collection and analysis, the information processing system 1, as a data analysis platform specializing in disease management of digestive diseases and / or diseases related to digestive conditions, can collect and integrate user (patient) health data (symptoms, diet, exercise, treatment history), contextual data (living environment, stress level, activity level), and medical treatment data from medical institutions (examination results, drug prescriptions, test data). By analyzing this data, the information processing system 1 can recommend health management apps and digital treatments suitable for patients, provide personalized therapeutic guidance for disease management, and optimize treatment policies at hospitals and clinics.

[0172] (3) Regarding health management support in collaboration with companies, local governments, and research institutions, Information Processing System 1 can collaborate with the systems of companies, local governments, and research institutions to enhance health management support for users (patients) with digestive diseases and / or diseases related to digestive conditions. Furthermore, by collaborating with the systems of lifestyle companies, Information Processing System 1 can provide health support not only from the perspective of treatment but also from the perspective of prevention and lifestyle improvement for users (patients).

[0173] This document describes a configuration for self-care support as one embodiment of the "Digital GI Health Platform" that can be configured by Information Processing System 1. Information Processing System 1 is an all-in-one digital health platform that allows users (patients) with digestive diseases and / or diseases related to digestive conditions to centrally manage not only symptoms but also diet, exercise, psychotherapy, and medication prescriptions. This enables users (patients) to achieve more effective health management and self-management while receiving guidance from specialists.

[0174] The information processing system 1 has a "personalized" data infrastructure, and the calculation unit 235 comprehensively analyzes the user's (patient's) health status, behavioral data, and lifestyle data, and the output unit 233 can provide an optimal health management plan.

[0175] Information processing system 1 can record and visualize symptoms. Specifically, it records daily symptoms such as "frequency of abdominal pain," "number of bowel movements," and "food content" entered by the user (patient), and visualizes this data, making it easier to understand changes in symptoms. Furthermore, information processing system 1 can support the improvement of symptoms of digestive diseases by providing information on diet and nutrition guidance and exercise support.

[0176] For users (patients) with gastrointestinal disorders such as IBD and IBS, or diseases related to gastrointestinal conditions such as schizophrenia, stress affects their symptoms. Therefore, information processing system 1 can incorporate psychotherapy, cognitive behavioral therapy, and simple psychotherapy. Specifically, information processing system 1 can analyze the correlation between stress and symptoms and recommend appropriate care.

[0177] Information processing system 1 can manage test results digitally by linking with hospital and clinic systems.

[0178] Information processing system 1 can provide health data to doctors, nutritionists, health coaches, etc., allowing users (patients) to receive care plans from specialists.

[0179] [Other] With respect to the information processing system 1 according to the above embodiment, the following embodiments may be adopted.

[0180] The collected data may be managed in an integrated manner. For example, information processing system 1 may aggregate and store health data or context data acquired from multiple health management applications, medical institution systems, wearable devices, or external services on a predetermined server. This data may be organized by target user and managed as an integrated database.

[0181] The calculation unit 235 may perform statistical analysis, trend analysis, or correlation analysis, etc., based on multiple data stored in the integrated database. For example, it may estimate trends or risk factors related to the health status of the target user by combining and analyzing lifestyle data, health status data, and medical usage data obtained from multiple applications or services.

[0182] This approach allows for the integrated management of data collected across multiple applications or services. Furthermore, it enables analysis based on large amounts of data collected throughout the entire ecosystem, leading to more advanced health analytics or healthcare management support.

[0183] At least one of the devices included in the information processing system 1 may be located outside of Japan. For example, the server device 2 or the server may be located outside of Japan, while the user terminal 3 is located in Japan. Similarly, a user may access the server device 2 located in Japan from outside of Japan using their user terminal 3. In either case, the information processing system 1 may include a server device 2 equipped with a processor and a terminal (user terminal 3) that can access the server device 2. This configuration allows for a more convenient user experience through various management methods.

[0184] In one embodiment, a functional unit implemented by the processor 23 of the server device 2 is described, but at least a part of this may be implemented as a functional unit implemented by another server. Alternatively, it may be implemented as a functional unit implemented by the processor 33 of the user terminal 3. Furthermore, the various types of information described in the above example may be stored not only in the storage unit 22 of the server device 2, but also distributedly on other external devices using blockchain technology or the like.

[0185] In one embodiment, personalization of health management information can be enhanced. Specifically, health management information can be tailored based on the user's past medical history, preferences, and lifestyle tendencies to provide more appropriate advice. For example, a user with allergies to certain foods may be configured to receive a meal plan that does not contain those allergens.

[0186] In one embodiment, health management information can be provided using a voice interface. For example, health management information can be output using speech synthesis technology to provide appropriate health guidance to visually impaired or elderly users. Alternatively, it may be linked with a smart speaker, allowing users to obtain health information using voice commands.

[0187] In one embodiment, health management information can be made multilingual. For example, users can be allowed to select from multiple languages ​​such as Japanese, English, and French, and the system can be configured to output health management information in each language. This makes it applicable to foreign users and users who use the system overseas.

[0188] In one embodiment, a dynamic alert system can be implemented using AI. For example, by analyzing biometric information acquired from a wearable device, if an abnormality in heart rate or a sudden change in blood pressure is detected, a warning notification can be sent to the user or a designated medical institution. This enables the early detection of health risks.

[0189] In one embodiment, health data can be managed using blockchain technology. For example, it can be used to prevent tampering when sharing data between medical institutions, and to enhance privacy protection by allowing users to manage their own access rights to the data.

[0190] In one embodiment, end-to-end encryption technology can be introduced to enhance security when sharing health data. For example, by adopting a zero-trust architecture and ensuring that healthcare institutions can access data only from authenticated devices, security risks can be reduced.

[0191] In one embodiment, the methods for outputting health management information can be diversified. For example, multiple output methods can be combined and provided, such as smartphone push notifications, email, voice notifications using smart speakers, and automatic registration to electronic medical records. This allows users to obtain information using the most suitable method.

[0192] In one embodiment, when providing health management information, it is possible to consider the treatment trends of medical institutions in the user's residential area, local dietary habits, and the prevalence of infectious diseases. This makes it possible to provide optimal health management for health risks specific to the region.

[0193] In one embodiment, health data collection and analysis are performed on a cloud-based system, enabling real-time collaboration with medical institutions. For example, by integrating with hospital and clinic systems, doctors can access the latest health data during consultations, enabling more precise medical care.

[0194] In one embodiment, health management information can be linked to the user's behavioral habits to provide timely health advice. For example, if a user tends to eat at night, the system can be configured to recommend meals suitable for digestion based on that habit.

[0195] In one embodiment, data can be integrated across different platforms by collaborating not only with medical institutions but also with health management applications. This makes it possible to achieve consistent health management even when users are using multiple apps.

[0196] In one embodiment, the provision of health management information can take into account the user's stress level and mental health status. For example, it may be possible to link this information with psychotherapy data to suggest advice for stress reduction and relaxation methods.

[0197] In one embodiment, by anonymizing users' health management data and sharing it with research institutions and public organizations, it is possible to contribute to medical research utilizing health big data. This makes it possible to contribute to disease prevention and the development of new treatments.

[0198] In one embodiment, AI can be used to analyze a user's health data and automatically set optimal health goals. For example, based on past exercise data and dietary trends, it can suggest achievable fitness plans and adjustments to nutritional balance.

[0199] In one embodiment, sharing health management information with family members and caregivers can enhance health support within the home. For example, family members can monitor the health status of elderly users in real time and coordinate with medical institutions as needed.

[0200] In one embodiment, when providing health management information, user feedback can be collected and the AI ​​can continuously make improvements. For example, by having the user evaluate their satisfaction with the advice provided and learning from that data, it becomes possible to provide more accurate health management information.

[0201] In one embodiment, users who share information about a specified individual may be given an incentive. Here, the information about the specified individual is not limited to and may include health management information, information about individual hobbies and preferences, information about diseases they suffer from, etc. The incentive may be, for example, points usable in the system described in this disclosure, a means of payment equivalent to money, or money itself. This can encourage users to share their private information.

[0202] Furthermore, they may be provided in the following embodiments.

[0203] (1) An information processing system comprising at least one processor, wherein the processor is configured to perform the following steps by reading a program, the data acquisition step of acquiring health data relating to the health of a target user subject to health management and context data relating to the behavior and / or environment, and the output step of outputting health management information relating to the health management of the target user based on the health data, the context data and reference information, wherein the reference information is information for selecting or generating the health management information collected in advance, and includes information relating to the physical and / or mental state.

[0204] This configuration allows for the provision of more beneficial technology.

[0205] (2) An information processing system as described in (1) above, wherein the health data includes data relating to the disease, diet, exercise, or symptoms of the target user.

[0206] In this manner, the accuracy of health management information can be improved by comprehensively handling various types of data.

[0207] (3) An information processing system as described in (2) above, wherein the health data includes data relating to the digestive diseases and / or digestive conditions of the target user, and the health management information is information relating to diseases related to the digestive diseases and / or digestive conditions.

[0208] This approach allows for individually optimized support in the treatment and management of gastrointestinal diseases.

[0209] (4) An information processing system described in any one of (1) to (3) above, wherein the health management information includes information about medical institutions and / or health management applications recommended to the target user.

[0210] This approach makes it possible to provide health management information that includes both medical institutions and health management apps, allowing for more appropriate options to be presented to the target users.

[0211] (5) An information processing system as described in (4) above, wherein the health data is configured to be shareable with the medical institution and / or the health management application.

[0212] This approach enables seamless collaboration with medical institutions and apps by allowing the sharing of health data.

[0213] (6) An information processing system according to any one of (1) to (5) above, wherein the context data includes the needs and / or attributes of the target user.

[0214] This approach allows for the proposal of treatment and health management methods that are easily accepted by the target users.

[0215] (7) An information processing system according to any one of (1) to (6) above, wherein the health data includes biometric information obtained from a wearable device worn by the target user.

[0216] This configuration allows for support that immediately reflects changes in the target user's health status.

[0217] (8) An information processing system according to any one of (1) to (7) above, wherein in the output step, the health management information is output in a manner that can be understood by a medical institution or medical professional.

[0218] This approach allows for increased efficiency in medical treatment and guidance through enhanced collaboration with medical institutions.

[0219] (9) An information processing system according to any one of (1) to (8) above, wherein in the output step, the health management information of the target user is presented via an interface corresponding to the attributes of the target user.

[0220] This configuration makes it possible to create a health management system that is easy to view and use for each target user.

[0221] (10) An information processing system according to any one of (1) to (9) above, wherein at least one of the group consisting of health data, context data, and health management information is configured to be shareable among multiple health management applications.

[0222] This configuration allows for consistent health management even when the target user uses multiple apps.

[0223] (11) An information processing system according to any one of (1) to (10) above, wherein the information processing system is further configured to perform the following steps: in the generation step, it generates events relating to the target user's diet, exercise, or sleep based on the context data; and in the data acquisition step, it acquires the generated events as health data.

[0224] This configuration can reduce the burden of inputting health data.

[0225] (12) An information processing system described in any one of (1) to (11) above, wherein the information processing system is further configured to perform the following steps: in the explanation acquisition step, an explanation of a health or mental state entered by an inputter is acquired; in the first normalization step, the acquired explanation is normalized into technical terms; and in the data acquisition step, the normalized explanation is acquired as health data.

[0226] This configuration allows the target user to input accurate health data.

[0227] (13) An information processing system as described in any one of (1) to (12) above, wherein the information processing system is further configured to perform the following steps: an image acquisition step in which an image is acquired; a second normalization step in which characters recognized from the acquired image are normalized into medical terms; and a data acquisition step in which the normalized characters are acquired as health data, wherein the image is an image of information obtainable at a medical institution, which is created on paper and / or electronic media, and the paper media includes memos, questionnaires or test results.

[0228] This configuration allows for easy input of health data.

[0229] (14) An information processing system described in any one of (1) to (13) above, wherein the information processing system is further configured to perform the following steps, wherein in the notification step, it notifies the target user of the outputted health management information and adjusts the timing or content of the notification based on the acquired context data.

[0230] This approach allows for more appropriate notification.

[0231] (15) An information processing system according to any one of (1) to (14) above, wherein the health data includes data showing the progression of digestive symptoms, the context data includes data relating to the target user's diet, sleep, activity, or stress, and in the output step, based on the acquired health data and the context data, outputs an index indicating the magnitude of the causal relationship between the diet, sleep, activity, or stress and the digestive symptoms as health management information.

[0232] This approach can help improve symptoms.

[0233] (16) An information processing system according to any one of (1) to (15) above, wherein the output step summarizes information regarding the health status of the target user for medical institutions based on the acquired health data and the context data, outputs the summary as health management information, and the summary includes the progression of major symptoms, estimated triggers, or recommended actions.

[0234] This configuration makes it easier for the target user to provide explanations to medical institutions.

[0235] (17) An information processing system according to any one of (1) to (16) above, wherein the health data is configured to be viewable by at least one of the following groups: a medical institution where the target user is receiving treatment, a medical institution related to the target user's health data, a research institution related to the target user's health data, and the target user's family and / or caregivers, and in the viewing control step, the viewing authority is controlled by the item, period or granularity selected by the target user.

[0236] In this configuration, health data can be made accessible to the target user to the extent desired.

[0237] (18) An information processing system according to any one of (1) to (17) above, wherein the health data is configured to be shareable with at least one of the following groups: a medical institution where the target user is receiving treatment, a medical institution related to the target user's health data, a research institution related to the target user's health data, and the target user's family and / or caregivers, and in the removal step, identifiers are removed from the health data, and in the anonymization step, variable weighting, aggregation of rare events or pseudokeying is performed on the health data after the identifiers have been removed.

[0238] This configuration makes it possible to ensure the usefulness of the analysis while preserving patient privacy.

[0239] (19) An information processing system according to any one of (1) to (18) above, wherein the information processing system is further configured to perform the following steps: an indicator acquisition step in which an indicator is acquired including the attributes of a terminal user using the terminal to which the health management information is output and / or context data relating to the terminal by the terminal user; and a manner adjustment step in which the complexity of the display manner of the terminal is adjusted according to the acquired indicator, the complexity being represented by the number of display items, the number of input items, the number of buttons, the number of screen transitions, the amount of explanation or the content of the explanation.

[0240] According to this embodiment, a user-friendly UI can be provided.

[0241] (20) An information processing system according to any one of (1) to (19) above, wherein the information processing system is further configured to perform the following steps: in the identification step, it identifies a support terminal used by a supporter who supports a user who uses the health management information; and in the data acquisition step, it acquires the health data and context data input by the supporter to the identified support terminal.

[0242] In this configuration, data can be acquired even when the user is unable to perform the task.

[0243] (21) An information processing system according to any one of (1) to (20) above, wherein the output step outputs key points for explanation to the target user as health management information, the reference information includes past medical history, test results or regional medical trends, and the key points include recommended treatment options, the advantages and disadvantages of treatment or guidelines for the next visit.

[0244] This configuration makes it easier to explain the concept to the target user.

[0245] (22) An information processing system according to any one of (1) to (21) above, wherein the output step outputs explanatory materials describing the health status of the target user at a difficulty level corresponding to the attributes of the target user as health management information, wherein the attributes include age, the stage or level of understanding of the disease the target user is suffering from.

[0246] This configuration makes it easy to provide explanations that are easy for the target users to understand.

[0247] (23) An information processing system according to any one of (1) to (22) above, wherein the output step outputs interview insights for physicians to be used by information providers to medical institutions as health management information, and the interview insights include summary text, main graphs or explanatory slide outlines.

[0248] This configuration makes it easier to prepare for a consultation with a doctor.

[0249] (24) The information processing system described in (23) above, wherein the information processing system is further configured to perform the following steps: in the selection step, it causes the user to select an interview template based on physician profile information; and in the output step, it outputs the interview insights using the interview template selected by the information provider.

[0250] This approach reduces the effort required to prepare materials optimized for each individual doctor while improving the quality of consultations.

[0251] (25) An information processing system described in any one of (1) to (24) above, wherein the information processing system is further configured to perform the following steps, the conversion step of which the output health management information is converted to normalize the differences in items, units or code systems with the electronic medical record system or claims system of the medical institution.

[0252] This configuration allows for integration with the systems of medical institutions.

[0253] (26) An information processing system according to any one of (1) to (25) above, wherein the information processing system further comprises an input assistance terminal, the input assistance terminal accepts and accumulates the input of health data or the context data when offline, the data acquisition step acquires the health data or the context data accumulated in the input assistance terminal at any time when communication is possible, and if there is a conflict, the conflict is resolved based on a conflict resolution rule before acquisition, the conflict resolution rule includes the last editor, timestamp, or reference consistency.

[0254] This configuration allows data entry to proceed even in the event of communication failures or other issues.

[0255] (27) An information processing system according to any one of (1) to (26) above, wherein the information processing system is further configured to perform the following steps, the standardization step being to perform standardization on the acquired health data or context data using standardization means including a variable dictionary, the standardization including term normalization, unit conversion or event time series alignment.

[0256] This configuration allows for the unification of health data and contextual data, which may differ in their source and input method, into a common format, facilitating subsequent analysis, display, and system integration.

[0257] (28) An information processing system according to any one of (1) to (27) above, wherein the context data includes information on pharmaceuticals or medical devices used by the target user, the statistical generation step generates statistical information on the usage status of pharmaceuticals or medical devices indicated by the multiple context data obtained and the health status indicated by the multiple health data obtained together with the multiple context data, and the output step outputs the generated statistical information as health management information.

[0258] This approach allows for the statistical understanding of the relationship between the use of pharmaceuticals or medical devices and health status.

[0259] (29) An information processing system as described in (28) above, wherein the information processing system is further configured to perform the following steps: in the comparison generation step, it generates comparison results of the statistical information for each medical institution, each region, or each attribute of the target user; and in the output step, it outputs the generated comparison results as health management information.

[0260] In this configuration, the above relationship can be understood for each comparison target.

[0261] (30) An information processing system as described in (28) or (29) above, wherein the information processing system further comprises a database linking the statistical information and adverse event information, and the information processing system is configured to perform the following steps: in the determination step, it determines whether the generated statistical information corresponds to the adverse event, and the adverse event includes at least suspected side effects of a drug or malfunction of a medical device; and in the notification step, if it is determined that the adverse event has occurred or is likely to occur, it immediately notifies the adverse event and notifies the statistical information other than the adverse event in a digest format.

[0262] This configuration allows for the rapid identification of serious incidents.

[0263] (31) An information processing system according to any one of (1) to (30) above, comprising a server device equipped with the processor and a terminal capable of accessing the server device.

[0264] According to this configuration, the information processing system can be implemented in various ways.

[0265] (32) An information processing method comprising each of the steps described in any one of (1) to (30) above, which is performed by a processor.

[0266] According to this embodiment, one embodiment of the information processing method can be provided.

[0267] (33) A program that causes a computer to perform any one of the steps described in (1) to (30) above.

[0268] According to this embodiment, one embodiment can be provided in the form of a program. Of course, this is not limited to this.

[0269] Finally, while various embodiments relating to this disclosure have been described, these are presented as examples only and are not intended to limit the scope of the invention. These novel embodiments can be implemented in a variety of other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their variations are included in the scope and spirit of the invention, as well as in the claims and their equivalents.

[0270] 1: Information processing system, 2: Server device, 3: User terminal, 3a: Computer, 3b: Mobile terminal, 20: Communication bus, 21: Communication unit, 22: Storage unit, 23: Processor, 30: Communication bus, 31: Communication unit, 32: Storage unit, 33: Processor, 34: Display unit, 35: Input unit, 231: Acquisition unit, 232: Processing unit, 233: Output unit, 234: Display control unit, 235: Calculation unit, AI: Generation, S001: Step, S002: Step, S003: Step

Claims

1. An information processing system comprising at least one processor, wherein the processor is configured to perform the following steps by reading a program: in a data acquisition step, it acquires health data relating to the health of a target user subject to health management, and context data relating to the behavior and / or environment; and in an output step, it outputs health management information relating to the health management of the target user based on the health data, the context data and reference information, wherein the reference information is information for selecting or generating the health management information collected in advance, and includes information relating to the physical and / or mental state.

2. An information processing system according to claim 1, wherein the health data includes data relating to the disease, diet, exercise, or symptoms of the target user.

3. An information processing system according to claim 2, wherein the health data includes data relating to the digestive diseases and / or digestive conditions of the target user, and the health management information is information relating to diseases to which the digestive diseases and / or digestive conditions are related.

4. An information processing system according to any one of claims 1 to 3, wherein the health management information includes information about medical institutions and / or health management applications recommended to the target user.

5. An information processing system according to claim 4, wherein the health data is configured to be shareable with the medical institution and / or the health management application.

6. An information processing system according to any one of claims 1 to 5, wherein the context data includes the needs and / or attributes of the target user.

7. An information processing system according to any one of claims 1 to 6, wherein the health data includes biometric information obtained from a wearable device worn by the target user.

8. An information processing system according to any one of claims 1 to 7, wherein the output step outputs the health management information in a manner that can be understood by a medical institution or medical professional.

9. An information processing system according to any one of claims 1 to 8, wherein in the output step, the health management information of the target user is presented via an interface corresponding to the attributes of the target user.

10. An information processing system according to any one of claims 1 to 9, wherein at least one of the group consisting of health data, context data, and health management information is configured to be shareable among a plurality of health management applications.

11. An information processing system according to any one of claims 1 to 10, wherein the information processing system is further configured to perform the following steps: in the generation step, generate events relating to the target user's diet, exercise, or sleep based on the context data; and in the data acquisition step, acquire the generated events as health data.

12. An information processing system according to any one of claims 1 to 11, wherein the information processing system is further configured to perform the following steps: an explanation acquisition step in which an explanation of a health or mental state entered by an inputter is acquired; a first normalization step in which the acquired explanation is normalized into technical terms; and a data acquisition step in which the normalized explanation is acquired as health data.

13. An information processing system according to any one of claims 1 to 12, wherein the information processing system is further configured to perform the following steps: an image acquisition step of acquiring a captured image; a second normalization step of normalizing characters recognized from the acquired captured image into medical terms; a data acquisition step of acquiring the normalized characters as health data; and the captured image is an image of information obtainable at a medical institution, which is created on paper and / or electronic media, and the paper media includes memos, questionnaires or test results.

14. An information processing system according to any one of claims 1 to 13, wherein the information processing system is further configured to perform the following steps: in the notification step, notify the target user of the outputted health management information and adjust the timing or content of the notification based on the acquired context data.

15. An information processing system according to any one of claims 1 to 14, wherein the health data includes data showing the progression of digestive symptoms, the context data includes data relating to the target user's diet, sleep, activity, or stress, and in the output step, based on the acquired health data and the context data, an index indicating the magnitude of the causal relationship between the diet, sleep, activity, or stress and the digestive symptoms is output as health management information.

16. An information processing system according to any one of claims 1 to 15, wherein the output step summarizes information regarding the health status of the target user for a medical institution based on the acquired health data and the context data, outputs the summary as health management information, and the summary includes the progression of major symptoms, estimated triggers, or recommended actions.

17. An information processing system according to any one of claims 1 to 16, wherein the health data is configured to be viewable by at least one of a group consisting of a medical institution where the target user is receiving treatment, a medical institution related to the target user's health data, a research institution related to the target user's health data, and the target user's family and / or caregivers, and in the viewing control step, the access rights are controlled by an item, period, or granularity selected by the target user.

18. An information processing system according to any one of claims 1 to 17, wherein the health data is configured to be shareable with at least one of a group consisting of a medical institution where the target user is receiving treatment, a medical institution related to the target user's health data, a research institution related to the target user's health data, and the target user's family and / or caregivers, and in the removal step, identifiers are removed from the health data, and in the anonymization step, variable weighting, aggregation of rare events or pseudokey assignment is performed on the health data after the identifiers have been removed.

19. An information processing system according to any one of claims 1 to 18, wherein the information processing system is further configured to perform the following steps: an indicator acquisition step in which an indicator is acquired including the attributes of a terminal user using the terminal to which the health management information is output and / or context data relating to the terminal by the terminal user; a mode adjustment step in which the complexity of the display mode of the terminal is adjusted according to the acquired indicator, the complexity being represented by the number of display items, the number of input items, the number of buttons, the number of screen transitions, the amount of explanation, or the content of the explanation.

20. An information processing system according to any one of claims 1 to 19, wherein the information processing system is further configured to perform the following steps: an identification step, which identifies a support terminal used by a supporter who supports a user who uses the health management information; and a data acquisition step, which acquires the health data and context data input by the supporter to the identified support terminal.

21. An information processing system according to any one of claims 1 to 20, wherein the output step outputs key points for explanation to the target user as health management information, the reference information includes past medical history, test results, or regional medical trends, and the key points include recommended treatment options, the advantages and disadvantages of treatment, or guidelines for the next visit.

22. An information processing system according to any one of claims 1 to 21, wherein the output step outputs explanatory materials describing the health status of the target user at a difficulty level corresponding to the attributes of the target user as health management information, and the attributes include age, the stage or level of understanding of the disease the target user is suffering from.

23. An information processing system according to any one of claims 1 to 22, wherein the output step outputs a physician interview insight for use by an information provider to a medical institution as the health management information, and the interview insight includes a summary text, a main graph, or an outline of an explanatory slide.

24. The information processing system according to claim 23, wherein the information processing system is further configured to perform the following steps: in the selection step, it causes the system to select an interview template based on physician profile information; and in the output step, it outputs the interview insights using the interview template selected by the information provider.

25. An information processing system according to any one of claims 1 to 24, wherein the information processing system is further configured to perform the following steps, the conversion step being to perform a conversion that normalizes the differences in items, units, or code systems between the output health management information and the electronic medical record system or claims system of a medical institution.

26. An information processing system according to any one of claims 1 to 25, wherein the information processing system further comprises an input assistance terminal, the input assistance terminal receives and stores the health data or the context data when offline, the data acquisition step acquires the health data or the context data stored in the input assistance terminal at any time when communication is possible, and if there is a conflict, the conflict is resolved based on a conflict resolution rule before acquisition, the conflict resolution rule includes the last editor, timestamp, or reference consistency.

27. An information processing system according to any one of claims 1 to 26, wherein the information processing system is further configured to perform the following steps: a standardization step, in which the acquired health data or context data is standardized using standardization means including a variable dictionary, the standardization includes term normalization, unit conversion or event time-series sorting.

28. An information processing system according to any one of claims 1 to 27, wherein the context data includes information on pharmaceuticals or medical devices used by the target user, the statistical generation step generates statistical information of the usage status of pharmaceuticals or medical devices indicated by a plurality of acquired context data and the health status indicated by a plurality of health data acquired together with the plurality of context data, and the output step outputs the generated statistical information as health management information.

29. An information processing system according to claim 28, wherein the information processing system is further configured to perform the following steps: in the comparison generation step, it generates comparison results of the statistical information for each medical institution, each region, or each attribute of the target user; and in the output step, it outputs the generated comparison results as health management information.

30. An information processing system according to claim 28 or claim 29, wherein the information processing system further comprises a database linking the statistical information and information on adverse events, and the information processing system is configured to perform the following steps: In the determination step, it determines whether the generated statistical information corresponds to the adverse event, the adverse event includes at least suspected side effects of a drug or malfunction of a medical device, and in the notification step, if it is determined that the adverse event has occurred or is likely to occur, it immediately notifies the adverse event and notifies the statistical information other than the adverse event in a digest format.

31. An information processing system according to any one of claims 1 to 30, comprising: a server device equipped with the processor; and a terminal capable of accessing the server device.

32. An information processing method comprising each step described in any one of claims 1 to 30, which is performed by a processor.

33. A program that causes a computer to perform each of the steps described in any one of claims 1 to 30.

Images