Information processing apparatus, information processing method, and program for supporting health care

Abstract

To provide information useful for health management of a user.SOLUTION: Provided is a program that causes a computer to function as means of an information processing apparatus, the means being: medical insurance information acquiring means for acquiring the user's medical insurance information from each person's medical insurance information; prediction means for predicting at least one of the user's symptoms related to the secretion of female hormones and the user's constitution among pre-classified constitutions related to the secretion of female hormones based on the user's medical insurance information; and information generating means for generating information to be presented to the user, including health advice related to the secretion of female hormones of the user, based on the prediction result by the prediction means.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an information processing device, an information processing method, and a program for supporting health management. [Background technology]

[0002] A woman's menstrual cycle is said to last about 28 days on average, with periods within the cycle classified as the menstrual phase, follicular phase, ovulation phase, and luteal phase. Various symptoms appear during the luteal and menstrual phases, and these symptoms vary greatly from person to person. Against this background, a technology has been proposed that collects a user's life log data and predicts the onset of the menstrual period and symptoms based on the collected life log data (Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Application No. 2022-73115 Summary of the Invention [Problem to be solved by the invention]

[0004] In the technology disclosed in Patent Document 1, measurement data such as body temperature and basic constitution data such as BMI are measured and provided by the user as life log data. Meanwhile, in recent years, various data indicating the health status of users have become available, and there is a demand for providing information useful for health management of users by utilizing more reliable data and specialized data.

[0005] The present invention has been made in view of the above-mentioned problems, and its object is to realize a technology that can provide information useful for health management of a user. [Means for solving the problem]

[0006] In order to solve this problem, for example, the program of the present invention A program that causes a computer to function as each means of an information processing device that supports health management, the information processing device comprising: a medical insurance information acquisition means for acquiring the user's medical insurance information from the medical insurance information of each person; a prediction means for predicting at least one of the symptoms related to the secretion of female hormones of the user and the constitution of the user among pre-classified constitutions related to the secretion of female hormones based on the medical insurance information of the user; and an information generation means for generating information to be presented to the user, including health advice related to the secretion of female hormones of the user, based on the prediction result by the prediction means. [Effects of the Invention]

[0007] According to the present invention, it is possible to provide information useful for health management of a user. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram showing an example of a health management support system according to an embodiment of the present invention. [Figure 2] FIG. 1 is a block diagram showing an example of the functional configuration of an information processing apparatus according to an embodiment; [Figure 3] FIG. 1 is a block diagram illustrating an example of a functional configuration of a communication device according to an embodiment. [Figure 4] FIG. 1 is a diagram illustrating an overview of a health advice generation process according to an embodiment. [Figure 5] FIG. 10 is a diagram showing an example of presentation information related to self-care according to an embodiment; [Figure 6] FIG. 10 is a diagram showing an example of presented information related to physical constitution improvement according to an embodiment; [Figure 7] FIG. 10 is a diagram illustrating an example of selecting health advice taking into consideration symptoms and constitutions according to an embodiment. [Figure 8] 1 is a flowchart showing a series of operations related to a health advice generation process according to an embodiment; [Figure 9] FIG. 10 is a diagram illustrating an example of a question displayed on a communication terminal according to an embodiment. [Figure 10] FIG. 10 is a diagram illustrating an example of a score of an answer to a question according to an embodiment. [Figure 11] FIG. 1 is a diagram illustrating a method for identifying highly effective health advice according to an embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, the embodiments will be described in detail with reference to the accompanying drawings. Note that the following embodiments do not limit the scope of the invention as claimed, and not all combinations of features described in the embodiments are necessarily essential to the invention. Two or more of the features described in the embodiments may be arbitrarily combined. Furthermore, the same reference numerals are used for the same or similar components, and redundant explanations will be omitted.

[0010] (Configuration of Health Management Support System) First, the configuration of a health management support system according to an embodiment of the present invention will be described with reference to Figure 1. Health management support system 10 includes, for example, communication device 110 used by a user, communication device 111 used by another user, information processing device 100, and external device 101.

[0011] The communication device 110 receives information 120 transmitted from the information processing device 100. As will be described in detail later, the information 120 is, for example, a question about the user's health condition or information requesting user information. The information 121 is, for example, information related to the user's health condition, and includes, for example, an answer to the question. The information related to the user's health condition may also include the user's biological data (for example, changes in skin temperature or heart rate, and exercise history). Furthermore, the information related to the user's health condition may further include dietary data indicating when and what meals the user ate, and work data indicating when and for how many hours the user worked. The communication device 110 receives the information 120, displays it on a display unit, and accepts a response from the user. The communication device 110 transmits the information 121 (i.e., information related to the user's health condition) to the information processing device 100.

[0012] In the example of the present embodiment, a case is described in which the information processing device 100 transmits the information 120 to the communication device 110 and receives the information 121. However, the information 120 may be transmitted to the communication device 110 by another server (not shown), and the information 121 may be transmitted from the communication device 110 to the other server. In this case, the information processing device 100 can receive the information 120 and the information 121 received by the other server from the other server.

[0013] The external device 101 is a server for a medical insurance information database. The medical insurance information database is a database that stores medical insurance information including information about each person's health checkup and / or medical treatment. The information processing device 100 can acquire the user's medical insurance information from the external device 101. Note that, in this embodiment, an example will be described in which the information processing device 100 acquires medical insurance information from the external device 101, but the information processing device 100 may have a medical insurance information database.

[0014] In the medical insurance information database (if the information processing device 100 has a medical insurance information database), information on an individual's daily health checkups and / or medical treatments is collected from medical institutions and stored as medical insurance information. The medical insurance information database may be a database constructed by a service company managing the information processing device 100 by collecting medical insurance information from health insurance societies, medical institutions, and the like. Alternatively, the medical insurance information database may be a database constructed by a company other than the service company by collecting medical insurance information from health insurance societies, medical institutions, and the like. Furthermore, the medical insurance information database may be, for example, a My Number Portal database, which stores individual medical insurance information collected and managed by a public system. For example, the medical insurance information according to this embodiment may include information on medical care obtained from health insurance societies, the Japan Health Insurance Association, mutual aid societies, national health insurance, and the Medical Care System for the Elderly. Furthermore, the medical insurance information according to this embodiment may include information on medical fees paid by medical institutions. The information on medical fees paid by medical institutions may include information on medical institutions, data on medical fee statements (receipts) for each patient, and information on medical treatments, procedures, prescriptions, tests, and the like contained in electronic medical record data. Information on medical fees from medical institutions can be obtained that indicates when and at which medical institution a patient was diagnosed with what condition, what treatment they received, and what medicines they were prescribed. Information on medical fees from medical institutions may include information on out-of-hospital prescriptions or may be linked to information on out-of-hospital prescriptions so that information on prescriptions both inside and outside the medical institution can be obtained. Information on out-of-hospital prescriptions can be obtained, for example, from DPC survey data.

[0015] The information processing device 100 executes a health advice generation process (described later) using information related to the user's health condition (information 121) and medical insurance information 140, and transmits presentation information 122 including the health advice to the communication device 110. As will be described in detail later, the information processing device 100 predicts, through the health advice generation process, symptoms related to the user's secretion of female hormones (i.e., symptoms that the user is prone to due to the secretion of female hormones) and / or the user's constitution related to the secretion of female hormones. Based on the prediction results, the information processing device 100 transmits to the communication device 110 presentation information 122 including health advice related to the user's secretion of female hormones (also simply referred to as health advice) that is tailored to the user's symptoms and constitution.

[0016] The information processing device 100 can also provide presentation information 131 including health advice for a user using the communication device 111. The communication device 111 can collect an action history 130 of the user of the communication device 111 in response to health advice and transmit it to the information processing device 100. The action history 130 in response to health advice can include vital data of the user, such as information about the user's sleep, and information about exercise such as walking, running, or other sports. Alternatively, the action history 130 in response to health advice can include information input into the communication device 111 indicating whether the user has performed the health advice (for example, information indicating that the user has eaten a meal related to the health advice).

[0017] The information processing device 100 can collect behavioral histories in response to health advice from multiple users. Based on the collected behavioral history information, the information processing device 100 can calculate the implementation rate and continuation rate for each piece of health advice and calculate the degree of effectiveness for each user. The implementation rate, continuation rate, and degree of effectiveness will be described later.

[0018] In this embodiment, the communication device 110 and the communication device 111 are, for example, smartphones. However, the communication device 110 and the communication device 111 are not limited to smartphones and may be other information terminals such as desktop computers, notebook computers, and tablet terminals. Furthermore, the communication device 110 and the communication device 111 may be wearable devices capable of collecting vital data of a user. Examples of wearable devices include smartwatches.

[0019] (Configuration of information processing device) Next, an example of the functional configuration of the information processing device 100 will be described with reference to Fig. 2. Each of the functional blocks described may be integrated or separated, and the functions described may be realized by different blocks. What is described as hardware may be realized by software, and vice versa.

[0020] The communication unit 201 includes a communication circuit that communicates with various communication devices (for example, the communication device 110 and the external device 101) via a network. The communication unit 201 receives information processed by the control unit 204 from a communication partner device (for example, the communication device 110, etc.), and transmits information processed by the control unit 204 to the communication partner device (for example, the communication device 110, etc.). The power supply unit 202 is a power supply that provides power required for the operation of the information processing device 100.

[0021] The storage unit 203 includes a non-volatile storage medium such as a hard disk or semiconductor memory, and stores various programs executed by the control unit 204 of the information processing device 100, various data used by the control unit 204, and a DB 230. The various programs may include an operating system, a framework, a library, and the like, in addition to a program for executing the health advice generation process according to this embodiment. The various data include, for example, setting values ​​of the information processing device 100 and parameter values ​​after learning of a machine learning model. The DB 230 of the storage unit 203 stores user information (e.g., user attributes, information related to the user's health condition such as answers and biometric data, behavioral history information, and data indicating the implementation status of health advice (implementation rate and continuation rate for each health advice)). The DB 230 also stores information indicating the expected effect on symptoms or health checkup values ​​when each piece of advice is implemented. As described above, some or all of the user information may be acquired from the user's communication device 110 or from another server.

[0022] Control unit 204 includes CPU 210, which is one or more processors, and RAM 211. CPU 210 loads a program stored in storage unit 203 into RAM 211 and executes it, thereby controlling the operation of each unit within control unit 204 and the operation of each unit of information processing device 100. Control unit 204 also executes a health advice generation process, which will be described later.

[0023] The RAM 211 includes a volatile storage medium such as a DRAM, and temporarily stores parameters and processing results for the CPU 210 to execute programs.

[0024] The medical insurance information acquisition unit 220 acquires medical insurance information of a specific user from, for example, the external device 101. The user information acquisition unit 223 acquires information related to the user's health condition (such as answers and biometric data) from the communication device 110 and stores it in the DB 230. The user information acquisition unit 223 also acquires the behavior history 130 in response to health advice from the communication device 111 and stores it in the DB 230.

[0025] In this embodiment, the user's medical insurance information and information related to the user's health condition, such as answers and biometric data, can be linked and used for the same user. That is, by linking and using the user's information with medical insurance information obtained with the involvement of experts such as doctors (instead of or in addition to answer information, which is a subjective input), highly accurate and reliable professional information can be used for prediction.

[0026] Next, the symptom prediction unit 221, constitution prediction unit 222, and presentation information generation unit 224 will be described together with an overview of the health advice generation process with reference to Fig. 4. The health advice generation process of this embodiment can use, as input data 401, the user's medical insurance information, information related to the user's health condition, user attributes such as age, and weather data. As described above, the information related to the user's health condition includes answers to questions, the user's biological data (e.g., changes in skin temperature and heart rate, exercise history), dietary data indicating when and what meals were eaten, and work data indicating when and for how many hours the user worked.

[0027] The symptom prediction unit 221 predicts the user's symptoms related to the secretion of female hormones (symptoms the user is likely to suffer from due to the secretion of female hormones) based on a part or all of the input data 401 (e.g., the user's medical insurance information and answers to questions). The symptoms related to the secretion of female hormones may include, for example, symptoms caused by excessive secretion of female hormones or symptoms caused by insufficient secretion of female hormones. More specifically, the symptoms related to the secretion of female hormones include, for example, symptoms included in premenstrual syndrome (PMS), dysmenorrhea, endometriosis, uterine fibroids, and menopausal symptoms. PMS includes, for example, irritability, drowsiness, depression, breast pain, and lower back pain, and dysmenorrhea includes, for example, headache, nausea, lower back pain, and abdominal pain, but are not limited to these examples. Furthermore, the predicted results of the symptoms related to the secretion of female hormones may include information indicating the timing and severity of the symptoms.

[0028] The symptom prediction unit 221 may predict symptoms using a machine learning model. In this case, the machine learning model may be configured in various ways. For example, the symptom prediction unit 221 may use a machine learning model that receives a part or all of the input data 401 and outputs one or more symptoms with a high prediction score among symptoms related to the secretion of female hormones (e.g., symptoms included in PMS, dysmenorrhea, and menopausal symptoms). Alternatively, the symptom prediction unit 221 may include a first machine learning model that receives a part or all of the input data 401 and outputs one or more PMS symptoms with a high prediction score, a second machine learning model that outputs one or more dysmenorrhea symptoms with a high prediction score, and a third machine learning model that outputs one or more menopausal symptoms with a high prediction score. Furthermore, the symptom prediction unit 221 may use a machine learning model that classifies each symptom into whether or not it will occur. The machine learning models in either example can be trained using training data that combines input data (e.g., part or all of the input data 401, or the medical insurance information described below) with correct answer data that indicates the correct answer for the symptom to be predicted.

[0029] In another example, the symptom prediction unit 221 may use an occurrence prediction model for any of dysmenorrhea, PMS, menopausal symptoms, etc. For example, this occurrence prediction model inputs, for example, medical insurance information (health checkup values, specific diseases included in medical insurance claim data), vital data, dietary data, and work data, and predicts whether or not dysmenorrhea, PMS, menopausal symptoms, etc., which appear in the medical insurance claim disease name, will occur within a given period of time (for example, outputs the occurrence probability). Other data, such as weather data, may also be used as input data.

[0030] Alternatively, the symptom prediction unit 221 may use a type-of-variance prediction model that predicts the type and / or frequency of symptoms such as dysmenorrhea, PMS, and menopausal symptoms. For example, this type-of-variance prediction model inputs, for example, medical insurance information (health checkup values, medication history and treatment details included in medical insurance claim data), vital signs, dietary data, and work data, and predicts whether or not symptoms such as dysmenorrhea, PMS, and menopausal symptoms listed in medical insurance claim disease names will occur within a given period (e.g., outputs the probability of occurrence). The input data may include at least one of data indicating changes in symptoms, lifestyle habits, and weight changes. Using such data makes it possible to reflect changes in condition, such as weight gain before menstruation due to swelling and increased appetite, in the prediction.

[0031] The constitution prediction unit 222 predicts the user's constitution related to the secretion of female hormones (e.g., one of the pre-classified constitution classifications) based on some or all of the input data 401 (e.g., the user's medical insurance information and answers to questions). The pre-classified constitution classifications may include various constitution classifications, such as constitution classifications in traditional Chinese medicine and classifications based on vague symptoms. For example, traditional Chinese medicine constitution classifications may be classified into qi imbalance, blood imbalance, and water imbalance. Qi imbalance may be classified into qi deficiency (a state of insufficient qi, including lethargy, fatigue, and listlessness), qi stagnation (a state of stagnation in the flow of qi, including a heavy head, a stuffy throat, shortness of breath, abdominal bloating, and the like), and qi reversal (a state of qi reflux, including hot flashes, palpitations, sweating, and the like). Blood disorders may be classified into blood stasis (a condition in which blood flow is stagnant, including menstrual irregularities, constipation, abdominal tenderness, pigmentation, etc.) and blood deficiency (a condition in which the amount of blood is insufficient, including anemia, dry skin, hair loss, and poor circulation, etc.). Water disorders may be classified into water retention (a condition in which the balance of water is disturbed, including swelling, dizziness, headache, diarrhea, and abnormal urination, etc.) and yin deficiency (a condition in which water is deficient, including hot flashes, constipation, weight loss, hot flashes, and dry skin, etc.). The constitution prediction unit 222 is not limited to outputting one type of constitution classification, but may output multiple types of constitution classification. The constitution prediction unit 222 may classify the user's constitution into qi, blood, and water disorders, or alternatively, may classify the user's constitution into either a deficiency constitution or an excess constitution. Deficient symptoms include, for example, a constitution that is weak, thin and delicate, has a pale complexion and is prone to rough skin, while excess symptoms include, for example, a constitution that is strong, muscular and sturdy, has a good complexion and has radiant skin.

[0032] The constitution prediction unit 222 may output a classification based on vague symptoms as one type of constitution classification. For example, the types and tendencies of vague symptoms may be defined as predetermined physical condition classifications, and the constitution prediction unit 222 may output a classification based on the types and tendencies of vague symptoms based on part or all of the input data.

[0033] The constitution prediction unit 222 may predict constitutions using a machine learning model. In this case, the machine learning model may be configured in various ways. For example, the constitution prediction unit 222 may use a machine learning model that inputs part or all of the input data 401 and outputs one or more constitutions with high prediction scores among predetermined constitution classifications and classifications based on unidentified symptoms. Alternatively, the constitution prediction unit 222 may include a first machine learning model that inputs part or all of the input data 401 and outputs one or more constitutions with high prediction scores among predetermined constitution classifications, and a second machine learning model that outputs one or more constitutions with high prediction scores among classifications based on unidentified symptoms. Furthermore, the constitution prediction unit 222 may use a machine learning model that classifies each constitution as whether or not it has that constitution. Either of the machine learning models can be trained using training data that combines input data (e.g., part or all of the input data 401, or medical insurance information, etc., as described below) with correct answer data indicating the correct constitution to be predicted.

[0034] The first machine learning model for constitution classification can predict a constitution classification (output the corresponding probability) by inputting, for example, a user's medical insurance information (health checkup values, medication history and treatment details included in medical receipt data). Because medication and treatment details are determined taking into account a patient's constitution, a patient's constitution can be predicted based on the medication history and treatment details. As an example, herbal medicines may be prescribed taking into account the constitution classification in traditional Chinese medicine described above. Therefore, for a patient prescribed a herbal medicine, for example, the patient's constitution can be predicted based on information about the prescribed herbal medicine. Of course, predicting a patient's constitution from a medication history can be applied to things other than herbal medicine. For example, if a drug is generally prescribed for a specific illness or injury but is not prescribed for patients with weak stomachs, and instead a different drug is prescribed for the specific illness or injury, the patient may have a weak stomach or intestinal constitution.

[0035] The control unit 204 can generate correct answer data to be used in training the machine learning model based on the relationship between such medication history and treatment details and the patient's constitution. Based on medical insurance information (including medication history and treatment details included in medical prescription data), the control unit 204 associates a specific person to whom a specific drug has been prescribed with a specific constitution among the pre-classified constitutions according to a predetermined relationship (e.g., the relationship between prescriptions of drugs such as herbal medicines and constitutions). This allows the control unit 204 to assign correct answer data indicating a constitution to all medical insurance information for a specific person (i.e., medical insurance information including prescriptions of specific drugs and medical insurance information not including such prescriptions). Using such correct answer data, the machine learning model is trained to predict a user's constitution from each person's medical insurance information using the medical insurance information not including prescriptions of specific drugs to which correct answer data has been assigned. For example, the trained machine learning model can output the probability of belonging to one of the traditional Chinese medicine categories: qi deficiency, qi stagnation, qi reversal, blood stasis, blood deficiency, water stagnation, or yin deficiency, based on medical insurance information (including medication history and treatment details included in medical prescription data).

[0036] The presentation information generation unit 224 selects health advice based on the symptoms predicted by the symptom prediction unit 221 and / or the constitution predicted by the constitution prediction unit 222, and generates presentation information including the selected health advice. The presentation information generated by the presentation information generation unit 224 is transmitted to the communication device 110.

[0037] The presented information may include, for example, symptoms to which the user is prone (corresponding to symptoms predicted by the symptom prediction unit 221) and information on self-care recommended for the user based on the symptoms. That is, when the symptom prediction unit 221 predicts symptoms related to the secretion of female hormones in the user, the presented information includes health advice on self-care based on the predicted symptoms. For example, Fig. 5 shows an example in which first presented information including the predicted symptoms of the user and health advice on self-care recommended for the user is displayed on the communication device 110.

[0038] The first presented information includes, for example, a user symptom type 501, a type of health advice 502, an area 503 showing the user's symptoms, and an area 506 showing the details of self-care. The user symptom type is a user type (e.g., 20 types) determined according to, for example, answers to questions, and is determined according to, for example, dysmenorrhea scores, etc. The symptom types will be described later.

[0039] The type of health advice 502 may include, for example, health advice according to the user's symptoms and advice to improve physical constitution according to the user's physical constitution (described later with reference to FIG. 6).

[0040] The area 503 showing the user's symptoms includes a display 504 corresponding to predicted physical symptoms and a display 505 corresponding to predicted mental symptoms. The presentation information generation unit 224 can generate the presentation information by, for example, acquiring a predetermined representation corresponding to the prediction result obtained by the symptom prediction unit 221. The presentation information generation unit 224 may incorporate a predetermined display for each symptom type into the area 503 showing the user's symptoms, depending on the symptom type determined from the answer to the question. In this way, by displaying the user's symptoms predicted based on medical insurance information or the like, or the user's symptoms based on the symptom type corresponding to the answer to the question, the user can understand that their illness may be related to the secretion of female hormones (e.g., menstruation). In other words, for users who are unable to understand the cause of their illness or who are unable to obtain a clear diagnosis even after consulting a doctor due to the difficulty of explaining the symptoms or individual differences, the system can accurately suggest possible causes of the illness.

[0041] The presentation information generation unit 224 includes health advice for self-care according to the predicted symptoms in the area 506 showing the content of self-care. If the predicted symptoms include drowsiness or depression, the presentation information generation unit 224 includes a predetermined expression 507 according to the symptom, such as "First, take a good rest and recharge your battery."

[0042] Furthermore, when the constitution prediction unit 222 predicts the constitution of the user, the presented information includes health advice for improving the constitution based on the predicted constitution of the user and the user's medical insurance information. For example, Fig. 6 shows an example in which second presented information including predetermined items of the user's medical insurance information and health advice for improving the constitution is displayed on the communication device 110.

[0043] The second presentation information includes, for example, the user's symptom type 501, the type of health advice 602, an area 603 showing the user's measured values, and an area 605 showing health advice for improving physical constitution.

[0044] The type of health advice 602 indicates advice for improving the user's constitution. The area 603 indicating the measurement value includes, for example, the blood glucose level and hemoglobin measurement value 604 included in the user's medical insurance information.

[0045] The presentation information generating unit 224 includes advice according to the predicted constitution in the area 606 showing health advice for improving constitution. At this time, the presentation information generating unit 224 may further include an expression showing the tendency of the measurement value (low blood glucose level).

[0046] The presentation information generation unit 224 may include health advice 703 based on both predicted symptoms 701 related to the secretion of female hormones and predicted constitution 702 in the presentation information, as shown in FIG. 7. In this case, the presentation information generation unit 224 may use health advice that is predetermined according to the relationship between the symptoms and constitution, as shown in FIG. 7. The health advice 703 includes advice for improving the user's constitution, which may be the cause of the symptoms exhibited by the user. The presentation information generation unit 224 may use a machine learning model that inputs predicted symptoms 701 related to the secretion of female hormones and predicted constitution 702 and selects one or more pieces of health advice appropriate to these inputs.

[0047] 2, the following description will be given. Implementation status acquisition unit 225 acquires data indicating the implementation status of a plurality of users in response to health advice from DB 230. Note that implementation status acquisition unit 225 may also acquire data indicating the implementation status of health advice from a database external to information processing device 100. The data indicating the implementation status of health advice includes an index of the number of users who implemented the advice among those who were provided with the health advice (i.e., implementation rate), and an index of the number of users who continued to follow the advice over a predetermined period among those who were provided with the health advice (i.e., continuation rate).

[0048] The implementation status acquiring section 225 also acquires data indicating the expected effect on symptoms or health checkup values ​​when each piece of advice is implemented from the DB 230. The data indicating the effect on symptoms or health checkup values ​​is, for example, determined in advance by an administrator or the like and registered in the DB 230. The implementation status acquiring section 225 may also acquire the data indicating the effect on symptoms or health checkup values ​​from a database external to the information processing device 100.

[0049] The effectiveness calculation unit 226 calculates an index of effectiveness (also simply referred to as an effectiveness score) for each piece of advice when it is provided to a user, based on data indicating the implementation status of the health advice for multiple users and data indicating the effect on symptoms or health checkup values. When calculating the effectiveness index, the effectiveness calculation unit 226 can take into account both the implementation rate and the continuation rate, but may use only one of them. By calculating the effectiveness index (effectiveness score), health advice with an effectiveness index higher than a predetermined threshold can be selected as health advice for the user.

[0050] An example of calculating the effectiveness score in this embodiment will be described with reference to Fig. 11. The example shown in Fig. 11 shows an example of calculating the effectiveness score when advice for dietary improvement A is presented to users X and Y, and the effectiveness score when advice for sleep improvement A is presented to users X and Y. Here, the advice for dietary improvement A and the advice for sleep improvement A are advice candidates selected according to the symptoms and constitution of the user.

[0051] The effectiveness calculation unit 226 first acquires information such as the age, gender, and health checkup values ​​of each user from the DB 230 as user attributes 1102. The effectiveness calculation unit 226 also acquires data indicating the implementation status of multiple users with respect to advice from the DB 230. The implementation rate 1104 indicates the implementation rate when users with attributes in the same category as the attributes of the target users (users X and Y) are presented with advice for dietary improvement A. The continuation rate 1105 indicates the continuation rate when users with attributes in the same category as the attributes of the target users (users X and Y) are presented with advice for dietary improvement A. The improvement effect 1106 indicates the improvement effect as a result of users who received the advice for dietary improvement A and implemented the advice. Various measures can be used to represent the improvement effect. For example, the numerical value of the improvement effect may be the number of points for the improvement effect voted by users who have implemented the advice in the past, or the average value per person whose answer score improved as described above. The numerical value of the improvement effect may also represent the improvement (average value) of a specific health checkup value of users who have implemented the advice in the past. In the example shown in FIG. 11, the implementation rate 1104, continuation rate 1105, and improvement effect 1106 of users in the same category as user X who were presented with advice 1103 for dietary improvement A are 70%, 55%, and +10 points, respectively. The effectiveness calculation unit 226 multiplies the implementation rate 1104, the continuation rate 1105, and the improvement effect 1106 to calculate an index of effectiveness (effectiveness score 1107) when the advice for dietary improvement A is presented to user X. The effectiveness calculation unit 226 calculates effectiveness scores for all health advice candidates and identifies health advice 1103 having an effectiveness score that meets a predetermined criterion. The predetermined criterion may be the highest effectiveness score or an effectiveness score that exceeds a predetermined criterion. Note that the numerical values ​​of the implementation rate 1104 and the continuation rate 1105 are merely shown schematically and are illustrative. By using such an effectiveness score, it becomes possible to extract advice that is likely to be implemented by the user, that is likely to be continued by the user, and that is likely to produce an improvement effect.In the above example, the implementation rate 1104 and the continuation rate 1105 are set to use the implementation rate and continuation rate of users in the same category as the attribute of the target user. By doing so, the implementation rate and continuation rate of users with similar attributes can be used, making it possible to calculate the effectiveness score more accurately.

[0052] The presentation information generation unit 224 generates presentation information including the health advice specified according to the effectiveness score calculated by the effectiveness calculation unit 226, and transmits the generated presentation information to the user's communication device.

[0053] For example, the presentation information generation unit 224 may include the identified health advice and the reason for presenting the identified health advice in the presentation information. The reason for presenting the identified health advice corresponds to the reason for identifying the health advice, for example. If the identified health advice is identified because it has a high index of effectiveness, the presentation information generation unit 224 can display, for example, "It's very effective" in the presentation information. Furthermore, if the identified health advice is identified because it has a high index of continuity, the presentation information generation unit 224 can display, for example, "It's easy to continue" in the presentation information.

[0054] 2, the explanation will be given again. The presentation information generation unit 224 uses the behavioral history stored in the DB 230 to calculate an index of the number of users who have implemented the advice among the users who have been provided with the advice (i.e., the implementation rate of each piece of advice), and stores the index in the DB 230. Furthermore, the effectiveness calculation unit 226 uses the behavioral history stored in the DB 230 to calculate an index of the number of users who have continued to use the advice over a predetermined period among the users who have been provided with the health advice (i.e., the continuation rate of each piece of advice), and stores the index in the DB 230.

[0055] The symptom type determination unit 227 determines the symptom type based on the user's answer to the question. The symptom types are conceptual classifications of typical symptoms related to the menstrual cycle, among those related to the secretion of female hormones, and may be, for example, 20 predetermined types. The symptom types are classified into, for example, throbbing type, exhaustion type, ..., and no symptoms. For example, the user of the communication device 110 transmits an answer to the question shown in FIG. 9 to the information processing device 100. The question includes, for example, a question 901 regarding the presence and severity of dysmenorrhea symptoms and the presence and severity of painkillers taken. The answer to the question is selected by the user from one or more options selected from options 902. The symptom type determination unit 227 can determine the symptom type using, for example, a predetermined score table shown in FIG. 10 and predetermined rule-based logic. The score table 1000 is a table that determines, for each question, a score 1002 for each question content 1001. The symptom type determination unit 227 identifies a score corresponding to the user's answer from the score table 1000 and calculates the score. The symptom type determination unit 227 determines a symptom type based on the score for a specific question and the answers to other questions. In the example of this embodiment, the operation of the symptom type determination unit 227 is described using a score table and rule-based logic. However, the symptom type determination unit 227 may also be operated by a machine learning model that inputs a user's answer to a question and outputs a symptom type. Such a machine learning model can be trained using training data that combines input data including the user's answer and correct answer data that indicates the correct answer for the predicted symptom type.

[0056] (Configuration of communication device) Furthermore, an example of the configuration of a communication device will be described with reference to Fig. 3. Fig. 3 shows an example of the functional configuration of communication device 110 and communication device 111 according to this embodiment. Note that each of the functional blocks described may be integrated or separated, and the functions described may be realized by different blocks. Also, what is described as hardware may be realized by software, and vice versa.

[0057] The communication unit 301 includes, for example, a communication circuit, and communicates with the information processing device 100 via mobile communication such as LTE, or via wireless communication such as wireless LAN, to send and receive the necessary data.

[0058] The operation unit 303 includes buttons and a touch panel provided on the communication device, and accepts operations for a GUI displayed on the display unit 305. The display unit 305 includes a display panel such as an LCD or OLED, and displays GUIs for various operations.

[0059] The storage unit 306 includes a nonvolatile memory such as a semiconductor memory, and stores set user information, programs executed by the control unit 302, and the like.

[0060] The control unit 302 includes a CPU 310, which is one or more processors, and a RAM 311. For example, the CPU 310 executes a program recorded in the storage unit 306, causing the control unit 302 to control the operation of each unit in the communication device 110.

[0061] (A series of operations in the health advice generation process in the information processing device) Next, a series of operations in the health advice generation process in the information processing device will be described with reference to Fig. 8. Note that each operation described in this series of operations is realized by CPU 210 of control unit 204 expanding a program stored in storage unit 203 into RAM 211 and executing it, thereby causing each unit of control unit 204 described above to function.

[0062] In S801, the control unit 204 transmits information (e.g., information 120) for acquiring information (e.g., information 121) related to the above-mentioned health condition to the communication device 110. In S802, the user information acquisition unit 223 acquires information related to the health condition (e.g., answers to questions and biometric data) from the communication device 110. The user information acquisition unit 223 stores the acquired information related to the health condition in the DB 230. In S803, the medical insurance information acquisition unit 220 acquires the user's medical insurance information from the external device 101.

[0063] In S804, the symptom prediction unit 221 predicts the user's symptoms related to the secretion of female hormones using the user's medical insurance information, etc., for example, using the machine learning model described above. The symptoms related to the secretion of female hormones include, for example, symptoms related to the menstrual cycle. In S805, the constitution prediction unit 222 predicts the user's constitution related to the secretion of female hormones using the user's medical insurance information, etc., for example, using the machine learning model described above. The constitution related to the secretion of female hormones includes, for example, constitution related to the menstrual cycle.

[0064] In S806, the presentation information generation unit 224 extracts one or more health advice (i.e., health advice candidates, for example, the above-mentioned advice for improving diet A and advice for improving sleep A) based on, for example, at least one of the user's predicted symptoms related to the secretion of female hormones and the user's constitution related to the secretion of female hormones.

[0065] In S807, the effectiveness calculation unit 226 multiplies the implementation status and effect of each piece of health advice to calculate an effectiveness score for each piece of health advice, as described above. In S808, the presentation information generation unit 224 identifies health advice whose effectiveness score satisfies a predetermined condition (for example, is equal to or greater than a predetermined value, or has the highest value), and generates presentation information including the identified health advice. The generated presentation information may be, for example, the presentation information described with reference to FIG. 5 or FIG. 6, or may be presentation information including the health advice 703 described above with reference to FIG. 7. The presentation information generation unit 224 transmits the generated presentation information to the communication device 110. The control unit 204 then terminates the series of operations of the health advice generation process.

[0066] As described above, in the above-described embodiment, the information processing device 100 acquires a user's medical insurance information from each person's medical insurance information, and predicts at least one of the user's symptoms related to the secretion of female hormones and the user's constitution from pre-classified constitutions related to the secretion of female hormones based on the user's medical insurance information. Furthermore, based on the prediction results, presentation information including health advice related to the user's secretion of female hormones is generated. By predicting symptoms related to the secretion of female hormones and / or pre-classified constitutions related to the secretion of female hormones using the user's medical insurance information, more reliable data and specialized data can be utilized to enable individual users to more accurately understand their health status related to the secretion of female hormones. Furthermore, by generating presentation information including health advice related to the secretion of female hormones, information can be provided to help users spend periods affected by the secretion of female hormones (e.g., specific periods in the menstrual cycle) more comfortably. In other words, it is possible to provide information useful for managing the user's health.

[0067] In the above embodiment, the medical insurance information according to the present embodiment has been described as an example of information collected from a health insurance association, a medical institution, etc. In addition to this example, the medical insurance information according to the present embodiment may include information provided to the user by a medical institution, etc., and information provided by the user to the information processing device 100 via a communication device (by manual input or image capture, etc.).

[0068] The invention is not limited to the above-described embodiment, and various modifications and variations are possible within the scope of the gist of the invention. [Explanation of symbols]

[0069] 100... information processing device, 110, 111... communication device, 220... medical insurance information acquisition unit, 221... symptom prediction unit, 222... constitution prediction unit, 224... presentation information generation unit

Claims

1. A program that causes a computer to function as each means of an information processing device that supports health management, the information processing device comprising: a medical insurance information acquisition means for acquiring the user's medical insurance information from the medical insurance information of each person; a prediction means for predicting at least one of the symptoms related to the secretion of female hormones of the user and the constitution of the user among pre-classified constitutions related to the secretion of female hormones based on the medical insurance information of the user; and information generation means for generating information to be presented to the user, including health advice related to the user's secretion of female hormones, based on the prediction results by the prediction means.

2. The program according to claim 1 , wherein the health advice includes advice based on the predicted symptoms of the user when the prediction means predicts symptoms related to the secretion of female hormones of the user.

3. 2. The program according to claim 1, wherein the health advice includes advice for improving the user's physical constitution based on the predicted physical constitution of the user and the user's medical insurance information when the prediction means predicts the user's physical constitution.

4. 2. The program according to claim 1, wherein the information generating means generates the presentation information including the advice based on the predicted symptoms of the user and the predicted constitution of the user.

5. The program according to claim 1, wherein the prediction means predicts the user's constitution from the user's medical insurance information by executing a machine learning model that predicts the user's constitution using the user's medical insurance information.

6. The system further comprises a correct answer data generating means for assigning correct answer data to a plurality of pieces of medical insurance information of a person who has been prescribed a specific drug by associating the person with a specific constitution among the pre-classified constitutions according to a predetermined relationship; The program of claim 5, wherein the machine learning model is trained to predict the user's constitution from each person's medical insurance information using medical insurance information that does not include prescriptions for the specific drug and that has correct answer data.

7. the specific medicine includes a specific herbal medicine; The program according to claim 6, characterized in that the machine learning model is trained to predict the user's constitution using medical insurance information to which the correct answer data is assigned based on a specific herbal medicine.

8. further comprising a user information acquisition means for acquiring information related to a health condition of the user from a communication device associated with the user; The program described in claim 1, characterized in that the prediction means predicts at least one of the user's symptoms related to the secretion of female hormones and the user's constitution from among constitutions pre-classified in relation to the secretion of female hormones, further based on information related to the user's health condition.

9. the information related to the user's health condition includes an answer by the user to a question; 9. The program according to claim 8, wherein the presented information further includes information on a symptom type determined in accordance with the answer by the user, and information on symptoms related to the symptom type.

10. an implementation status acquisition means for acquiring data indicating the implementation status of the advice provided to each of a plurality of users and data indicating the expected effect on the evaluation items of the health status when the advice is implemented; a calculation means for calculating, for each piece of advice, an index of effectiveness when each piece of advice is provided to a user, based on data indicating the implementation status of the advice by a plurality of users and data indicating the effect on the evaluation items; 2. The program according to claim 1, wherein the information generating means generates presentation information including advice selected according to the calculated index of effectiveness.

11. An information processing device for supporting health management, a medical insurance information acquisition means for acquiring the user's medical insurance information from the medical insurance information of each person; a prediction means for predicting at least one of the symptoms related to the secretion of female hormones of the user and the constitution of the user among pre-classified constitutions related to the secretion of female hormones based on the medical insurance information of the user; and an information generation means for generating information to be presented to the user, including health advice related to the secretion of female hormones of the user, based on the prediction result by the prediction means.

12. An information processing method executed by an information processing device that supports health management, comprising: obtaining the user's medical insurance information from the respective person's medical insurance information; predicting at least one of the symptoms related to the secretion of female hormones of the user and the constitution of the user among pre-classified constitutions related to the secretion of female hormones based on the medical insurance information of the user; and generating information to be presented to the user, including health advice related to the secretion of female hormones of the user, based on the prediction result in the prediction step.

Images