CN114930464A - Sensor determination device and sensor determination method - Google Patents

Abstract

Provided are a sensor determination device and a sensor determination method, which can determine a sensor for acquiring examination data so that the person who has received a physical examination can continuously acquire the examination data conveniently, and can continuously acquire the examination data not only by the person but also by family members and the like. Inputting physical examination results of a specific person (S3); judging a specific diagnosis result obtained by performing a specific diagnosis among the physical examination results, and extracting a symptom depending on heredity or lifestyle from the specific diagnosis result (S5); a guard sensor corresponding to the extracted symptom is determined (S6). Further, the judgment of the person to be supported by the specific person is performed, and a guard sensor corresponding to the extracted symptom is determined for the judged person to be supported (S9, S11).

Description

Sensor determination device and sensor determination method

Technical Field

The present invention relates to a sensor determination device and a sensor determination method for determining a sensor for maintaining a health state in daily life when a symptom depending on heredity or living habits is extracted in an examination by a daily examination device, a health examination, or the like.

Background

Conventionally, a data analysis device that notifies a highly reliable diagnosis result has been proposed. For example, patent document 1 discloses a data analysis device that, when newly acquiring undetermined physical examination data, evaluates the relationship between the undetermined physical examination data and a predetermined symptom from judged physical examination data obtained by a doctor judging whether or not the predetermined symptom is related to the undetermined physical examination data, and notifies a patient in need of prediction diagnosis of a disease of the undetermined physical examination data.

Documents of the prior art

Patent literature

Patent document 1: international publication No. 2016/006042

Disclosure of Invention

Problems to be solved by the invention

The data analysis device can know the diagnosis result for the symptom of the person who received the physical examination based on the physical examination data. The person who has received the diagnosis result may receive guidance for improving living habits or receive treatment in a medical institution or an examination institution by regularly acquiring examination data and observing the progress. In addition, it is known that health can be further improved by carefully guarding the user in everyday life. For example, there is a service that promotes smoking prohibition and deals with hypertension using an application of a smartphone, and the effect of the service is recognized.

However, the above patent document 1 only describes the diagnosis of diseases of the person who has received a physical examination, and does not describe any information on the convenience of acquiring examination data of the person who has received a health examination. Further, there is no consideration of the examination by a person other than the person who has received the physical examination.

The present invention has been made in view of the above circumstances, and an object thereof is to provide a technique for making many people healthy using physical examination results.

Means for solving the problems

In order to achieve the above object, a sensor determination device according to claim 1 includes: an input unit for inputting a result of physical examination of a specific person; a determination unit that determines a specific diagnosis result obtained by performing a specific diagnosis among the physical examination results; a symptom extraction unit that extracts a symptom that depends on heredity or lifestyle in the specific diagnosis result; and a determination unit that determines a guard sensor corresponding to the extracted symptom.

The sensor determination device according to claim 2 is the sensor determination device according to claim 1, wherein the specific diagnosis result is a diagnosis result that is abnormal for a specific examination item at the time of the physical examination.

In the sensor determination device according to claim 3, in the above-described invention 1, the symptom extraction unit extracts the specific diagnosis result by searching a database in which the specific diagnosis result is associated with a cause thereof, and the like.

In the sensor determination device according to claim 4, in the sensor determination device according to claim 1, the guard sensor is extracted by searching a database in which the specific diagnosis result is associated with a cause thereof or the like.

The sensor determination device according to claim 5 is the sensor determination device according to claim 1, wherein the sensor determination device includes an information providing unit capable of displaying information detected by the guard sensor in a graphical form on an information terminal associated with the specific person.

The sensor determination device pertaining to claim 6 is the sensor determination device pertaining to claim 1, and includes: an inference unit that infers a health advice from a detection result of the guard sensor; and a display control unit for displaying a result obtained by the inference.

The sensor determination device according to claim 7 is the sensor determination device according to claim 1, wherein the sensor determination device includes an inference unit that infers the health advice based on a detection result of the guard sensor, and the inference unit reflects the life information corresponding to the symptom extracted by the symptom extraction unit at the time of the inference.

The sensor determination device according to claim 8 is the sensor determination device according to claim 1, wherein the sensor determination device includes a supported person determination unit that determines a supported person of the specific person, and the determination unit determines a guard sensor corresponding to the extracted symptom for the supported person determined by the supported person determination unit.

The sensor determination device according to claim 9 is the sensor determination device according to claim 8, wherein the sensor determination device includes a1 st recording unit that records inspection equipment that can be used by the specific person and the person to be supported, and the determination unit determines the guard sensor from the inspection equipment recorded in the 1 st recording unit.

The sensor determination device according to claim 10 includes, in the sensor determination device according to claim 1, a blood-related person determination unit that searches for a person having a blood-related relationship with the specific person, and the determination unit determines a guard sensor corresponding to the extracted symptom for the blood-related person searched by the blood-related person determination unit.

The sensor determination device according to claim 11 includes, in the above-described 10 th aspect, a 2 nd recording unit that records test devices usable by the specific person and the blood related person, and the determination unit determines the guard sensor from the test devices recorded in the 2 nd recording unit.

In the sensor determination device according to claim 12, in the above-described invention 1, the input unit inputs a physical examination result based on whether the specific person has received a physical examination or a medical examination.

In the sensor determination device according to claim 13, in the above-described invention 1, the input unit inputs examination data from an examination facility so that the specific person measures the health status.

The sensor determination method according to claim 14 includes the steps of: an input step of inputting a physical examination result of a specific person; a determination step of determining a specific diagnosis result obtained by performing a specific diagnosis among the physical examination results; a symptom extraction step of extracting a symptom depending on heredity or lifestyle in the specific diagnosis result; and a determination step of determining a guard sensor corresponding to the extracted symptom.

A recording medium according to claim 15, wherein a sensor determination program is recorded to cause a computer to execute the sensor determination program, the sensor determination program including: an input step of inputting a physical examination result of a specific person; a determination step of determining a specific diagnosis result obtained by performing a specific diagnosis among the physical examination results; a symptom extraction step of extracting a symptom depending on heredity or lifestyle in the specific diagnosis result; and a determination step of determining a guard sensor corresponding to the extracted symptom.

A sensor determination system according to claim 16 includes an information terminal that transmits a result obtained by inputting a physical examination result of a specific person to an information processing device having a program and executing the program, and the program includes: a determination step of obtaining a physical examination result and determining a specific diagnosis result obtained by performing a specific diagnosis; a symptom extraction step of extracting a symptom depending on heredity or lifestyle in the specific diagnosis result; and a determination step of determining a guard sensor corresponding to the extracted symptom.

Effects of the invention

According to the present invention, it is possible to provide a sensor determination device and a sensor determination method that can determine a sensor for acquiring examination data so that a person who has received a physical examination can easily and continuously acquire examination data, and that can continuously acquire examination data not only for the person but also for family members and the like.

Drawings

Fig. 1 is a block diagram showing the structure of an inference system of an embodiment of the present invention.

Fig. 2 is a table showing a list of available devices of each ID stored in the DB unit 8 in the inference system according to the embodiment of the present invention.

Fig. 3 is a graph showing an example of history data for each individual ID recorded in the DB unit 8 in the inference system according to the embodiment of the present invention.

Fig. 4 is a graph showing a change in time series of inspection data of a subject person in the inference system according to the embodiment of the present invention.

Fig. 5A is a flowchart showing the operation of the control unit in the inference system according to the embodiment of the present invention.

Fig. 5B is a flowchart showing the operation of the control unit in the inference system according to the embodiment of the present invention.

FIG. 6 is a flow diagram illustrating actions specified by a corresponding inference model in an inference system of one embodiment of the invention.

Fig. 7 is a diagram showing a case where information transmitted from the control unit is displayed on the terminal for browsing in the inference system according to the embodiment of the present invention.

Fig. 8A is a flowchart showing a modification of the operation of the control unit in the inference system according to the embodiment of the present invention.

Fig. 8B is a flowchart showing a modified example of the operation of the control unit in the inference system according to the embodiment of the present invention.

Fig. 9 is a diagram showing an example of the relationship between the input and the output of the inference model in the inference system according to the embodiment of the present invention.

Fig. 10 is a flowchart showing an example of the operation of sensor setting in the inference system according to the embodiment of the present invention.

Fig. 11 is a diagram showing another example of the relationship between the input and the output of the inference model in the inference system according to the embodiment of the present invention.

Fig. 12 is a flowchart showing another example of the operation of sensor setting in the inference system according to the embodiment of the present invention.

Detailed Description

Hereinafter, an example in which the present invention is applied to an inference system will be described as an embodiment of the present invention. The control unit of the inference system and the control unit of the inference system of the present embodiment can be used to input examination data related to the health of the user from the 1 st device or the like that can be used by the user every day in daily life, and can collect the examination data of the user. The control unit can be inputted with the diagnosis result in the diagnosis/examination means, and can collect information on physical examination received by the user.

The control unit of the inference system according to the present embodiment can collect output data of a plurality of devices and perform inference using an inference model generated by learning the collected data as training data. In addition, in the present embodiment, it is also possible to grasp an accurate health state by taking the situation of the user (subject person) into consideration, and provide customized information. That is, examination data relating to the health status is monitored every day by the 1 st device, the 2 nd device, and the like, and is collected. Further, it is possible to provide health-related information based on the collected data.

Using the historical data acquired through the monitoring, health-related advice can be displayed to the user. In addition, when presenting a suggestion, the data collected by monitoring can be input to an inference engine in which an inference model is set, and the suggestion can be displayed based on an inference result of the inference engine.

However, the examination apparatus used by the user and the family members thereof may be installed at home or at work (including school for school and the like). Examples of the examination devices installed at home and the like include an electronic sphygmomanometer, an electronic thermometer, and examination devices for stool and urine installed in a toilet. In addition to home use, various examination apparatuses are used for regular health examinations, short-term examinations, examinations during blood donations, and the like. Various kinds of examination apparatuses are also used when a user visits a medical institution. In this way, various inspection apparatuses are often used, and the inspection apparatus is often determined for each user and family member thereof. In this way, the user and his family members can acquire examination data relating to health through various examination apparatuses. In addition, the contents that can be checked by the checking device are different.

In the present embodiment, a medical examination is received by a diagnosis/examination means or the like, and when a diagnosis result is obtained, a symptom associated with the diagnosis result is extracted, an examination device capable of examining the symptom is designated, and a guard examination is continuously performed. When the examination apparatus is decided, the control section of the inference system continuously collects examination data, and if sufficient history data is collected, it outputs advice on health to the user using the inference model.

The health examination may be said to judge a specific disease or a symptom of a health state. Some diseases are suspected based on the symptoms, and the symptoms are used as a material for judging some diseases. That is, since symptoms are quantified or digitized by health examination, pathological diagnosis and clinical diagnosis are performed based on the symptoms, and as a result, it is determined whether or not some kind of guard is necessary. For example, when the body weight is simply higher than the body height, the guarding sensor can be determined in consideration of lack of exercise, excessive eating, and food preference, particularly without performing pathological diagnosis or the like. In this case, the number of steps, a questionnaire for eating, a photograph of a dish to be eaten, and the like may be used as data, and therefore, a pedometer, a user interface of an information terminal for information input, a camera, and the like may be used as a guarding sensor. Therefore, the equipment and the sensor can be determined according to the condition (weight gain), or can be determined based on a disease such as binge eating disorder, which is diagnosed by actually including other information.

The inference system according to the present embodiment determines, not only for the user himself, but also for the family members, an examination device (sensor) that continuously acquires examination data of the family members according to the situation. A specific disease or the like may develop depending on lifestyle habits, and a family member of the user himself or herself may have a lifestyle habit similar to that of the user. Therefore, in the case of a disease or the like depending on lifestyle, it is preferable that the family member also performs examination. In addition, sometimes diseases are suffered which depend on heredity. In the case of diseases depending on the inheritance, family members who preferably have a relationship of blood relationship are also examined. When an examination device for examining the person or a family member is determined, a control unit of the inference system continuously collects examination data, and when sufficient history data is collected, health-related advice is output to the user using an inference model.

This genetic consideration also includes consideration of differences in race and sex (difference in diseases that are likely to occur). The lifestyle is a concept of a normal life pattern determined according to the preference, occupation, family member constitution and other restrictions of the person. The lifestyle habits are not limited to long-term habits in a broad sense, and include short-term lifestyle habits. For example, in the case of a disease which is easily affected by a short span such as an overrun and a resting state at every moment, a lifestyle pattern in a unit of one day, two days to one week, or two weeks may be included and referred to as a lifestyle habit.

Next, the configuration of an inference system according to an embodiment of the present invention will be described with reference to fig. 1. In view of the foregoing, it is an object of the present invention to provide a system, an apparatus, and a method that can improve health or improve a disease condition by keeping a healthy state in daily life close to each individual. Therefore, the guard can be performed more efficiently by reflecting the result of the health check or the like. For example, even if a person who has good lifestyle habits and does not find any symptoms is advised, it is only troublesome. In addition, when symptoms are associated with lifestyle habits, family members and the like may have the same lifestyle habits, and it is preferable to continuously acquire examination data and observe the progress of the examination data as in the same manner as the self, and receive guidance for improving lifestyle habits or receive treatment. In addition, when the symptoms are related to genetic diseases, there is a possibility that family members having a relationship with blood causes the same symptoms, and it is preferable to continue to acquire physical examination data and observe the progress of the physical examination data as in the case of the family members, and receive guidance for improving lifestyle habits or receive treatment.

In addition, it is sometimes effective for persons other than family members to give similar instructions for improving living habits. For example, people in the same school (class), people in the same work unit, people who have the same social circle, the same interest, and gather in the same place can have the same improvement guidance because living habits are common in a broad sense or in some cases. As for whether or not such a relationship exists, as long as the family member is allowed to determine the support relationship by public information such as health insurance, or the like, the determination may be made based on information of a medical institution, information of SNS (social network service), or the like. The present invention may be configured such that the terminal can make a setting by self-declaration, and whether or not the participation status is the same work unit, school, social circle, or the like may be determined based on information such as GPS information and SNS of the terminal provided for each of the terminals, or may be self-declared.

The inference system shown in fig. 1 is composed of a control unit 1, a1 st device 2a, a 2 nd device 2b, a 3 rd device 3, a terminal 4, a learning unit 5, a learning delegation unit 6, an inference engine 7, a Database (DB) unit 8, a diagnosis/examination unit (including medical units) 9, and a user information unit 10. The inference system collects examination data related to the health status of the user, and inputs the collected examination data to an inference model to infer information related to health such as diseases.

In each unit of the inference system, the control unit 1 is disposed in a server, and can be connected to the 1 st device 2a, the 2 nd device 2b, the 3 rd device 3, the terminal 4, the learning unit 5, the learning delegation unit 6, the inference engine 7, the DB unit 8 (which may be expressed as a recording unit or a storage unit), the diagnosis/examination mechanism 9, and the user information unit 10 via a network such as the internet. However, the present embodiment is not limited to this configuration, and for example, 1 or more of the control unit 1, the 1 st device 2a, the 2 nd device 2b, the 3 rd device 3, the learning unit 5, the learning delegation unit 6, the inference engine 7, the DB unit 8, and the user information unit 10 may be disposed in a server, and the other may be disposed in an electronic device such as another server or a personal computer. The diagnosis/examination means 9 may also have a function of a server.

The 1 st device 2a, the 2 nd device 2b, the 3 rd device 3, and the terminal 4 may have the same functions as the control unit 1 and the same recording functions as the DB unit 8, and the control performed by the control unit 1 will be described below. For example, the control unit 1 located on the cloud may cooperate with the 1 st device 2a, the 2 nd device 2b, the 3 rd device 3, the terminal 4, and the like as the edge (terminal) to execute the control explained as being performed by the control unit 1. Since there are limitations in communication speed, hardware configuration of each edge, power consumption, and the like at the time of cooperation, optimization is often performed for each system. Here, however, the control unit 1 is described as collectively performing the following control for simplifying the description.

The control Unit 1 is a controller (processor) for controlling the information delivery system according to the present embodiment, and is assumed to be an IT device such as a server that provides files, data, and the like to another terminal via a network, and is configured by a CPU (Central Processing Unit), a memory, an HDD (Hard disk Drive), and the like. However, the control unit 1 is not limited to this configuration, and may be configured as a personal computer when constructed as a small-scale system. The control unit 1 includes various interface circuits, can cooperate with other devices, and can perform various kinds of arithmetic control by a program.

The control unit 1 receives information from each device that cooperates with each other, collates the information, generates necessary information, and provides the information to the user. The control unit 1 also has a function of outputting a request to each device in cooperation and operating each device. In the present embodiment, it is assumed that the degree of freedom of the system is high and the system is easy to use, and the device 1, such as the 1 st device 2a, or the terminal 4 of the user, and the control unit 1 can be connected by wireless communication or wired communication. As communication for this, a wireless LAN and a mobile phone communication network are assumed, and short-range wireless such as bluetooth (registered trademark) and infrared communication may be used depending on the situation. The communication unit including the communication line, the antenna, the connection terminal, and the like is not shown in fig. 1 because description thereof is complicated, but a communication unit including the communication line and the like is provided in a portion of an arrow indicating communication in the drawing.

The control unit 1 includes a communication control unit 1a, an ID determination unit 1b, an information providing unit 1c, an inference model specification determination unit 1d, an inference delegation unit 1e, a search unit 1f, and a foster determination unit 1 g. These units may be realized by software based on a CPU, a program, and the like in the control unit 1, may be realized by a hardware circuit, or may be realized by cooperation of software and a hardware circuit. As described above, the control unit 1 is configured by a processor having a CPU or the like, and realizes the functions (for example, an input unit, a determination unit, a symptom extraction unit, a determination unit, an inference unit, a supported person determination unit, a blood-related person determination unit, and the like) of the communication control unit 1a, the ID determination unit 1b, the information providing unit 1c, the inference model specification determination unit 1d, the inference delegation unit 1e, the search unit 1f, and the supported person determination unit 1 g. The number of processors is not limited to 1, and a plurality of processors may be divided to implement the functions of each unit by the coordinated operations.

In fig. 1, the respective parts in the control unit 1 cooperate with each other to exhibit their respective functions, and therefore the direction of the signal is omitted, but this will be described separately in the flowchart. For example, in S1 of fig. 5A or S61 of fig. 8A, the ID determination unit 1b collects information from the 1 st device 2a, the 2 nd device 2b, and the like for each identical user.

The communication control unit 1a has a communication line and the like, and performs transmission and reception of data and the like with the 1 st device 2a, the 2 nd device 2b, the 3 rd device 3, the terminal 4, the learning unit 5, the learning delegation unit 6, the inference engine 7, the Database (DB) unit 8, the diagnosis/examination mechanism 9, and the communication unit provided in the user information unit 10. The devices and units such as the 1 st, 2 nd, 3 rd devices 2a, 2b, 3 rd device 3 and the terminal 4 also have communication units, respectively, but they are complicated in fig. 1 and are not shown.

The communication control unit 1a controls a communication protocol, a line power supply, and a partner apparatus in cooperation with a wired LAN, a wireless LAN, and a communication line such as a mobile phone line, which are not shown, as necessary, in order to switch communication with various cooperating apparatuses. The communication control unit 1a may determine whether or not there is an input from an external cooperation device such as the 1 st to 3 rd devices 2a to 3, the diagnosis/examination mechanism 9, and the terminal 4, and start the cooperation with each part in the control unit 1. The communication control unit 1 may cooperate with the information providing unit 1c and the like by providing a function of analyzing what kind of communication the external device requests or what the external device requests. Further, the communication control unit 1 may have the following functions: the information is exchanged by appropriately communicating with the DB unit 8, the user information unit 10, the diagnosis/examination unit 9, and other servers in cooperation with the information providing unit 1c, and information at a communication destination is acquired or selected.

In order to finally determine the sensor of the guard user, the communication control unit 1 cooperates with the information providing unit 1c to perform communication for enabling the use of the sensors such as the terminal 4 and the 1 st to 3 rd devices 2a to 3 rd devices 3. Information on devices owned by the user, the living environment of the user, and other health information are acquired from the user information unit 10a and the like, and when a guard sensor corresponding to the extracted symptom is determined, communication for cooperating with these devices is performed. However, the present invention is not limited to this, and information of the diagnosis/examination means 9, the terminal 4, and the 1 st to 3 rd devices 2a to 3 rd devices 3 may be used as necessary, and therefore the communication control unit 1 may also perform communication control in this case. In this way, what kind of information is used to determine the content of communication control may be based on a rule determined by the operator who performs the service, or external devices, information, and the like to be communicated may be appropriately switched according to the declaration of the user.

The ID determination unit 1b collects information from the 1 st device 2a and the like and the diagnosis/examination means 9 for each identical user. As information, the examination data of the respective users is acquired from the 1 st device 2a, the 2 nd device 2b, and the 3 rd device 3. In addition, the physical examination results and examination data of the respective users are collected from the diagnosis/examination mechanism 9.

In order to identify individuals who have acquired information by the 1 st device 2a, the 2 nd device 2b, the 3 rd device 3, the diagnosis/examination mechanism 9, and the user information section 10, an ID is assigned to each individual. In the present embodiment, since data of each user is processed, the ID determination unit 1b manages which user receives information and to which user guidance is to be given. The decision to identify the user is made by: the 1 st device 2a, the 2 nd device 2b, and the 3 rd device 3 have a biometric authentication function, or the user inputs an ID through the terminal 4, or the user transmits an ID through a communication unit in the 1 st and 2 nd devices 2a and 2b, or the terminal 4 reads a unique code. In addition, in order to protect personal information, it is strictly managed by encrypting necessary portions, but these are general techniques, and therefore detailed description thereof is omitted.

As described later, the ID of each device may be information such as information about the model name of the device and unique information indicating which individual is stored in each device, and the information may be determined based on the type information. The functions, performances, and the like of the mounted sensors may be known from the model names, the installation locations, the usage environments, and the like may be known from the individual information, and these pieces of information may be retrieved via a network or the like. Information of similar devices can be determined if the model name is known, and latitude and longitude, indoor and outdoor, season, weather, temperature characteristics, and the like can be determined depending on the installation place and the environment, and the output information of the device can be corrected in consideration of the determination result.

The information providing unit 1c has a function of acquiring information of the user (the result acquired by another device may be referred to) in order to provide the user with accurate information. In order to perform this function, the medical examination apparatus has an input unit 1ca for inputting information from various external devices cooperating with the communication control unit 1a, and can acquire the result of the medical examination of a specific person. The determination unit 1cb is provided to determine a specific diagnosis result obtained by performing a specific diagnosis in cooperation with the contents of the physical examination result input, for example, a database or the like. The diagnostic device further includes a symptom extraction unit 1cc, and the symptom extraction unit 1cc has a function of communicating with the database unit 8, the user information unit 10, the correlation check mechanism 9, and other servers as appropriate to exchange information in cooperation with the communication control unit 1a, and acquiring or selecting information located therein, and extracts a symptom depending on heredity or lifestyle in a specific diagnosis result.

The information providing unit 1c acquires information on a device owned by the user, the living environment of the user, and other health information from the user information unit 10a and the like, and determines a guard sensor corresponding to the extracted symptom. Of course, since there is a recommendation from a medical practitioner or a sensor manufacturer in this case, information of the diagnosis/examination mechanism 9, the terminal 4, and the 1 st to 3 rd devices 2a to 3 rd devices may be used as needed. When determining a sensor by such information cooperation, the determination may be performed by a logical rule base such as a specific conditional branch or DB (database) search, or may be performed using an inference model learned using similar user information or the like.

In order to determine the guard sensor, the information providing unit 1c acquires the examination data of the user (specified by the ID) acquired from the 1 st equipment 2a and the like, the diagnosis/examination mechanism 9. When the user receives a health examination in the diagnosis/examination mechanism 9, the information providing unit 1c receives the result of the physical examination at that time. In the case where the diagnosis/examination means 9 cooperates with the control section 1, the physical examination result may be automatically transmitted from the diagnosis/examination means 9 to the control section 1. If there is no such cooperation, the user may transmit the physical examination result via the terminal 4 or the like.

When the user receives a physical examination or a medical examination in the diagnosis/examination mechanism 9 and receives the result of the physical examination at that time, the information providing unit 1c determines whether or not a specific diagnosis is made (see, for example, S3 in fig. 5A), and determines whether or not the result of the specific diagnosis is a symptom that depends on lifestyle habits or heredity. The specific diagnosis refers to a case where the physical examination data is a value different from the health status, or a case where the physical examination data is judged to be different from the health status by an inquiry or the like.

It is assumed that the above-described specific diagnosis result is not diagnosed as normal with respect to the specific examination item at the time of physical examination. For example, when a blood test is performed, as a lipid test, there are tests for total cholesterol, neutral fat, HDL cholesterol, and LDL cholesterol in blood, and reference values for determining the suspicion of lipid abnormality (hyperlipidemia) are set. Whether the measured value is normal or not can be determined by comparison with a reference value, inquiry, image examination, or the like. The coping method is also disclosed using the internet or the like in accordance with the legal person who develops the health examination business or the like, the health insurance combination, the academic society, the medical institution, the doctor or the like, the determination method thereof, and the estimated cause. Further, IT companies perform a service capable of collecting or aggregating such information and searching through the internet, and performing a search for "the symptom and the possibility of the disease". If the result of the determination is not normal, some symptom may appear.

Diagnosis that makes clear the disease that is the cause of some symptoms is called definitive diagnosis (pathological diagnosis). In addition, what kind of symptoms and what type of symptoms are estimated from an inquiry, a neuropsychological examination, an image examination, and the like are sometimes referred to as clinical diagnosis. Such estimation of diagnosis can be reduced to several candidates by following a specific logic. Meanwhile, the cause of the symptom is, for example, whether or not the symptom depends on heredity, lifestyle, or the like, and the symptom can be managed by a database or the like, for example.

The causes of symptoms may be searched for causes published on the internet, or in the system of the present embodiment, the causes of symptoms may be recorded in advance in the DB unit 9a (described later) or the DB unit 8a of the diagnosis/examination means 9 and searched for in association with each other based on the diagnosis result. That is, the symptom extraction unit that extracts a symptom depending on heredity or lifestyle can extract a symptom by searching from a database in which a specific diagnosis result, a cause thereof, and the like are associated with each other. The database can be updated at any time, and the cause of the possible symptoms can be newly traced even in the case of an unknown infectious disease or the like. These pieces of information can be specified in their relationship even if they are not recorded in the database. Examples of symptoms such as diseases obtained as a result of diagnosis are referred to as "symptoms". Therefore, abnormality of biological information due to a specific disease or the like may be considered as a part of the disease. The moiety written as a disorder may also be expressed otherwise per disease, diagnostic result, or per symptom.

In addition, since the disease state is data for obtaining findings (study results) in an upper concept, a device classified by disease state may be rewritten to a study result data acquisition device. With this device, information effective at diagnosis can be obtained from other than biological information. For example, it is also possible to change the infectious disease to be diagnosed depending on whether it is performed in a specific area. In this case, the GPS device carried by the user serves as a data acquisition device for the study results, and the visiting place can be specified. These devices are required for specific diagnosis and can therefore also be classified as disease-classified devices. In addition, data that can be referred to from the database is reference information, and a doctor makes an accurate diagnosis. As a reference for this information, it is preferable that the user receives a study.

If it is determined that the specific diagnosis is performed or not, as a result, the information providing unit 1c determines the symptoms (biological information and examination data) of the user to be collected based on the disease (see, for example, S5 in fig. 5A), and if the symptoms are determined, determines the device (the 1 st device 2a or the like) for acquiring the information related to the symptoms (see, for example, S6 in fig. 5A). When determining the device, the information providing unit 1c actively collects information from the devices (see, for example, S7). That is, the information providing unit 1c determines a device (sensor) for guarding the health state of the user, and collects information.

In the case where there is a risk of infection at a particular meeting or the like, the information of the GPS or the like may be used as a guard sensor. For example, persons who often attend the same event and have the same lifestyle may be collectively subjected to the same guard. That is, when a specific patient who has participated in a certain event is determined to have a specific diagnosis result obtained by performing a specific diagnosis based on the result of examination (physical examination), if the symptom depending on the lifestyle (behavior pattern) is a symptom depending on participation of the specific event, the guard sensor corresponding to the extracted symptom may be determined. The information detected by the sensor may be biological information or information for determining behavior.

The location-specific sensor may be a terminal for using a settlement card of a public transportation or using a specific application, or may be used as a location-specific sensor even when the information is information on where electronic money is used in which shop. In these cases, the sensors to be guarded are fixed and used by many people, and if the user is specified, it can be said that the user is guarded because it is possible to detect that the user has moved to the location. The information for detecting buying can also be said to be sensed, and the information provision can also be made based thereon. In addition, if the timing of purchasing food is known, it is possible to sense whether or not regular eating life is performed, and also, it is possible to sense a life pattern.

The physical examination result does not need to be input by a medical staff, and may be input spontaneously at a terminal or the like by the person who has received the examination/diagnosis, or may be input as a blog article, a tweet, or the like on the internet, from which the examination result is obtained. In this case, the diagnosis/medical result may be input by the SNS system, or may be input by a system cooperating with the SNS system. A system for integrating the information by the AI to make judgment and input the diagnosis/treatment results by inference can also be constructed.

When the tendency of transmission of specific information is judged via the internet and there is attack news related to past infectious diseases or the like, SNS information at that time is used as training data, and it is possible to predict what kind of information will be transmitted and the disease will be prevalent in the future. Therefore, by monitoring the current SNS information, it is possible to predict the tendency of a certain diagnosis/examination, and the prediction result may be used as a specific diagnosis result.

In this way, the guard sensor may be a sensor capable of acquiring biological information and biopsy information, but is not limited to this, and may be a device for determining the movement of each object, or may be an input unit of a system for appropriately answering a questionnaire survey. It is sufficient that information at an appropriate time can be obtained on a daily basis, and if the information is time-series information, the amount of information further increases and is effective.

The input unit 1ca in the information providing unit 1c functions as an input unit for inputting the physical examination result of the specific person (see, for example, S3 in fig. 5A and S61 in fig. 8A). The input unit inputs the physical examination result based on the physical examination or the examination received by the specific person (see, for example, S3 in fig. 5A and S61 in fig. 8A). The input unit inputs examination data from the examination equipment so that the specified person measures the health condition (see, for example, S1 in fig. 5A, S23 in fig. 5B, and S67 and S71 in fig. 8A).

The judgment unit 1cb in the information providing unit 1c functions as a judgment unit that judges a specific diagnosis result obtained by performing a specific diagnosis among the physical examination results (see, for example, S3 in fig. 5A and S61 in fig. 8A). The specific determination result is a diagnosis result that is abnormal for a specific examination item at the time of physical examination. The symptom extraction unit 1cc in the information providing unit 1c functions as a symptom extraction unit that extracts a symptom depending on heredity or lifestyle in a specific diagnosis result (for example, see S5 of S5A and S61 of fig. 8A). The symptom extraction unit extracts the specific diagnosis result by searching a database in which the specific diagnosis result is associated with the cause and the like. The information providing unit 1c functions as a determination unit that determines a guard sensor corresponding to the extracted symptom (see, for example, S6 in fig. 5A, S65 and S69 in fig. 8A). The guard sensor searches and extracts a database in which the specific diagnosis result is associated with the cause thereof, etc. (see, for example, S6 in fig. 5A).

The determination unit determines a guard sensor corresponding to the extracted symptom for the person to be supported determined by the person to be supported determination unit (see, for example, S6 of fig. 5A and S65 of fig. 8A). The determination unit determines a guard sensor from the inspection devices recorded in the 1 st recording unit (see, for example, S9 and S11 in fig. 5A, and S65 and S67 in fig. 8A). The determination unit determines a guard sensor corresponding to the extracted symptom for the blood-related person searched by the blood-related person determination unit (see, for example, S13 and S15 in fig. 5A). The determination unit determines the guard sensor from the inspection devices recorded in the 2 nd recording unit (see S13 and S15 in fig. 5A).

The symptoms that depend on lifestyle or heredity are not limited to the physical examination results, but may be found from examination data that is routinely transmitted from the examination apparatus such as the 1 st apparatus 2a (see, for example, S1 and S3 in fig. 5A). In this case, as in the case where a symptom is found based on the result of physical examination by the diagnosis/examination means 9, the symptom (biological information, examination data) of the user to be collected is determined (see, for example, S5 in fig. 5A), and if the symptom is determined, the device (the 1 st device 2a, etc.) to be used for acquisition is determined (see, for example, S6 in fig. 5A). When the device is determined, the information providing unit 1c actively collects information from the devices (see, for example, S7).

The information providing unit 1c makes suggestions about the health status of the user using the acquired examination data, various information acquired from the diagnosis/examination mechanism 9, information about the owned devices stored in the DB unit 8a, profile information of the user, and the like (for example, see fig. 7). The advice related to health includes a disease currently suffered by or a disease likely to be suffered in the future, and when the health state is judged, information related to the health state is provided to the user. In addition, when determining a disease or the like of the user, information on facilities to be subjected to examination or treatment is provided to the user as necessary.

In the present embodiment, when there is no specific diagnosis result and there is a symptom associated with a lifestyle disease or a genetic disease, the guard test is started (see, for example, S7, S11, S15, and the like in fig. 5A). The information providing unit 1c displays the inspection data and the like collected in the guard inspection on a display unit of the terminal 4 (see, for example, fig. 7). The information providing unit 1c functions as an information providing unit capable of graphically displaying information detected by the guard sensor on an information terminal associated with a specific person. The information providing unit 1c functions as a display control unit capable of displaying the result of the inference.

Further, if the control unit 1 can check the health status of the user in a specific situation by making an inquiry in the diagnosis/examination means 9 about the current hospital-visiting situation, information such as prescription drugs, the past health examination result, and the like based on the ID of the user, the determination of the association with the device data becomes easy. This operation may be permitted by the user of the operation terminal 4, or may be performed by a doctor who operates (the IT device of) the diagnosis/examination mechanism 9 to allow the cooperation, and this operation or the like may be used to cope with a problem in terms of safety.

That is, the information providing unit 1c may provide the user with information relating to health, for example, information that the user accesses a facility to receive an examination or a treatment, or information that recommends a facility suitable for receiving an examination or a treatment. The information providing unit 1c acquires the inspection data transmitted from the 1 st equipment 2a and the like and the diagnosis/inspection mechanism 9. As described later, this data is inspection data (time-series information) to which time information is added, and is accumulated in a data structure that can be a graph shown in fig. 4. In the present embodiment, it is assumed that the control unit 1 provides information to the user using information from the 1 st equipment 2a and other equipment, the diagnosis/examination means 9, and the like, but a modification in which a server having the diagnosis/examination means 9 collects information in the same manner is also possible.

In addition, in order to provide such information, the information providing section 1c collects the inspection data from the 1 st device 2a, the 2 nd device 2b, and the like, and records it in the DB section 8 a. The frequency of information acquisition and the number of data may be different depending on the 1 st device 2a, the 2 nd device 2b, and the like. That is, the increase and decrease of specific health-related values obtained from various facilities are organized in time series, and the values measured by changing the facilities can be organized for each facility.

The information providing unit 1c may acquire the address of the user, the behavior pattern in the place of work, the lifestyle habits such as eating, sleeping time, and the timing of dining, etc. from the user information unit 10, or may acquire these pieces of information from information stored on the internet. The information providing unit 1c may generate information of facilities and the like provided to the user in consideration of the acquired information. The acquisition of such information can be supplemented by general or well known techniques. The information providing unit 1c may customize information of facilities and the like generated by acquiring the information. The information on the facility may be acquired as medical facility information from the diagnosis/examination facility 9.

The information providing unit 1c acquires the inspection data in the time-series mode in the specific period of the user. The acquired time-series pattern is not data obtained by only 1 measurement, but is composed of individual pieces of inspection data acquired by measurement at a plurality of different timings, and the inspection data up to the change in the pattern of the inspection data is used as information. By using a time-series pattern composed of a plurality of pieces of inspection data, the measurement device is less susceptible to errors caused by changes in measurement environment and conditions. Then, the health state of the future time (the time when the specific period is extended) from the end time of the specific period can be estimated, and the future can be predicted.

In addition, by giving the acquired time-series pattern timing information of the arrival of the user at the examination/medical institution as the label information, it is possible to generate training data. If there is an inference unit having an inference model generated by learning using the training data, it is possible to infer what has occurred at a timing (when the specific period is extended) after the specific period (period for acquiring the time-series change pattern). Further, if the name of a disease or the like of the user is known, it is possible to generate training data to which the information is added as label information. By learning using the training data, an inference model for inferring health information such as a disease can be generated. In addition, in generating the inference model used here, a specification of specific input/output information is defined and learning is performed.

Therefore, in the present embodiment, a delivery information determination unit is provided that inputs the time-series change pattern of the user's examination data to the inference unit, and the inference unit performs inference to determine delivery information at a timing after the specific period based on the inference result. Therefore, it is possible to provide a system, an apparatus, a method, a program, and the like, which are capable of delivering prediction information of timing after the time of examination acquisition of the time-series pattern.

In the present embodiment, the information providing unit 1c inputs the change pattern of the inspection data to the inference engine 7 in which the inference model generated by the learning unit 5 is set, obtains the inference result about the advice, and provides the inference result to the user corresponding to the input inspection data. This service may use personal information, and may require an appropriate level of personal information to be used in order to receive advice or the like. This means that profile information of the user is sometimes important. In addition, when the user is an infant or an elderly person, advice may be transmitted to a person who cares for the user, a caregiver, or the like. This is also effective information such as advice or the like according to information managed using the profile information of the user.

The inference model specification determining unit 1d determines the specification of the inference model to be generated when the inference delegation unit 1e delegates generation of the inference model to the learning unit 5 via the learning delegation unit 6. The control unit 1 acquires the biometric information of the user from the 1 st device 2a and the like, and accumulates the biometric information. The control unit 1 requests the learning unit 5 to generate various inference models via the learning requesting unit 6 using the stored biometric information as training data.

The inference model specification determining unit 1d determines what specification inference model is to be requested when generating the inference model. For example, as shown in fig. 4 (a) described later, when the time-series biological information is accumulated, the inference model specification determination unit 1d determines the specification of an inference model for inferring what kind of examination data (values) the user will receive treatment in the medical facility after several days. The inference model specification determining unit 1d determines, based on the time-series biological information, a specification for generating an inference model for inferring what kind of disease is currently suffered from or what kind of disease is likely to be suffered from in the future (when), and if a disease is likely to be suffered from, a recommended facility for receiving a required examination or treatment.

The inference requesting unit 1e requests the learning unit 5 via the learning requesting unit 6 to generate an inference model having the specification determined by the inference model specification determining unit 1 d. That is, when a predetermined number of pieces of biological information acquired by the 1 st device 2a or the like are accumulated, the inference requesting unit 1e requests the learning unit 5 to generate an inference model via the learning requesting unit 6, and receives the generated inference model via the learning requesting unit 6. The received inference model is sent to the inference engine 7. Further, it is preferable that the control unit 1 prepares a plurality of inference models and appropriately selects an inference model according to information to be provided to the user. Further, if the control unit 1 can directly communicate with the learning unit 5, the inference model may be directly received from the learning unit 5.

When the present disease, which may be suffered in the future (when) and further the examination and treatment are required, is found from the biological information of the user acquired by the 1 st device 2a, the 2 nd device 2b, the 3 rd device, and the diagnosis/examination means 9, the search unit 1f searches the database stored in the DB unit 8a for the examination means and the medical means having the devices required for the examination and treatment. These pieces of information may be acquired by inference using the inference engine 7, but there may be cases where these pieces of information match the accumulated data. Since there are cases as well, in the present embodiment, the search can be performed by the search unit 1 f.

The foster determination section 1g determines a foster such as a family member of the user. That is, as described above, when the information provider 1c collects physical examination data of the user from the diagnosis/examination mechanism 9, the information provider 1c may determine items to be guarded based on the diagnosis result. In this case, the foster determination section 1g determines a foster such as a family member of the user. In addition, when the user person is a person to be supported, the person to be supported may be determined. The foster person determination section 1g functions as a foster person determination section for determining a foster person of the specific person (see, for example, S9 of fig. 5A and S65 of fig. 8A).

Since many family members of the user have the same eating habits, exercise habits, life patterns, and the like as the user, there is a possibility that they suffer from diseases depending on the same life habits as the user or may develop diseases in the future (see, for example, S3 and S5 in fig. 5A). Therefore, the foster determination unit 1g determines the same inspection equipment (sensor) for guarding for the family members of the user based on the information on the family membership of the user, and the information provision unit 1c collects the inspection data (see, for example, S9 and S11 in fig. 5A). The daemon activity may also be initiated automatically or after approval by the user or a member of his family.

In addition, when it is diagnosed that the user is suffering from a genetic disease or is diagnosed as possibly having a future disease based on the result of the physical examination, the user is not limited to the user himself or herself, and family members who are related to the user may also be similarly likely to suffer from a genetic disease or a future disease. Therefore, as in the case of lifestyle diseases, the same examination device (sensor) for guard is determined for the family members of the user, and the information providing unit 1c collects examination data (see, for example, S13 and S15 in fig. 5A). The daemon may be started automatically or after approval from the user or family member having a relationship with the blood. The foster person determination section 1g may determine a person having a relationship with the individual blood of the user based on information (for example, see fig. 2) recorded in the DB section 8a or the like. In this case, the foster person determination unit 1g functions as a blood-related person determination unit that searches for a person having a blood-related relationship with the specific person (see, for example, S13 and S15 in fig. 5A).

The 1 st device 2a and the 2 nd device 2b are devices for acquiring health related information of a user, for example, vital sign information, sample information, and other examination data. The 1 st equipment 2a and the 2 nd equipment 2b are inspection equipments of a specific specification, and are equipments capable of performing an inspection of the same kind (the same kind) of health related information. The 1 st device 2a stores the category 2a1, and in addition, the 2 nd device 2b stores the category 2b 1. The category 2a1 and the category 2b1 are information related to the type, model, examination item, and the like of the device, and are transmitted together when the examination data of the user is transmitted to the control unit 1 through each device.

In the case where the inspection data sets acquired by the 1 st apparatus 2a and the 2 nd apparatus 2b are different in inspection timing from each other, it is sufficient if an inspection capable of interpolating both data can be performed. The 1 st device 2a and the 2 nd device 2b may not check the completely same examination items, and for example, even when the heart rate is measured while the blood pressure is measured, the two data may be interpolated with each other. In fig. 1, only 3 devices, i.e., the 1 st device 2a, the 2 nd device 2b, and the 3 rd device 3, are described as devices for acquiring the examination data of the user, but the number of devices is not limited to 3, and may be 1 or 2, or may be 4 or more.

The health-related information acquired by the 1 st device 2a and the like includes various information, for example, vital sign information such as body temperature, blood pressure, and heartbeat of the user. The health-related information includes various kinds of sample information such as urine, feces, and the like, sputum, blood, and the like of the user. In the case of stool, the 1 st device 2a and the 2 nd device 2b acquire the color, shape, amount, date and time information thereof. The 1 st device 2a and the 2 nd device 2b may acquire information in accordance with an instruction from the control unit 1, may acquire information in accordance with an operation by a user, or may automatically acquire information. The 1 st apparatus 2a, the 2 nd apparatus 2b, and the 3 rd apparatus may have a color sensor, a shape sensor, a hardness sensor, an olfactory sensor, a gas component sensor, a color change detection sensor when a specific reagent is added, and the like for defecation, and may perform shape determination based on an enlarged observation image, and the like.

The 1 st device 2a and the like may collect and use a Personal Life Record (PLR) obtained by adding various activity data of daily Life such as daily Life, activities of work units/schools, meals, and physical activities to a Personal Health Record (PHR), which is information of medical and Health information, and transmit the acquired information to the control unit 1 via a communication unit (not shown) in the 1 st device 2a and the like.

When the 1 st device 2a, the 2 nd device 2b, or the like obtains information about the user, the information providing unit 1c of the control unit 1 presents the information about health to the information terminal 4 of the user. The description is made assuming that the presentation assists the behavior of the user, but various modifications are conceivable. The health-related information includes information related to recommended medical facilities, information related to daily living habits, and the like.

The 3 rd device 3 may acquire data of a person different from the user using the 1 st device 2a or the 2 nd device 2 b. The 3 rd device 3 may be newly started to be used or temporarily used by the user using the 1 st device 2a or the 2 nd device 2 b. In fig. 1, only 1 device 3 is shown, but there may be a plurality of devices, and a plurality of unspecified devices are collectively shown in fig. 1.

In addition, the 3 rd device 3 also stores the category 3a 1. The category 3a1 is information related to the type, model, examination item, and the like of the 3 rd device 3, and when the 3 rd device 3 transmits the examination data of the user to the control unit 1, category information is transmitted together.

When wearable terminals are used as the 1 st device 2a, the 2 nd device 2b, and the 3 rd device 3, vital sign information such as body temperature, heartbeat, blood pressure, electroencephalogram, line of sight, respiration, and exhalation can be obtained by bringing the wearable terminals into close contact with the skin or the vicinity of the body depending on the wearing parts of the wearable terminals. In addition, as a scale, a sphygmomanometer, and a measuring instrument for measuring the hardness of an artery indicating the hardness of an artery wall, there are cases where dedicated precision equipment is disposed in a health facility, a public bathing place, a pharmacy, a shopping center, and the like, and a professional measurer is disposed together. In such facilities, a user can easily use a measurement device at idle time or the like, and a physical condition is often managed based on a measurement result at that time. These measuring apparatuses may be the 1 st apparatus 2a, the 2 nd apparatus 2b, and the 3 rd apparatus 3.

The 1 st device 2a, the 2 nd device 2b, and the 3 rd device 3 may request the user to fill the questionnaire before and after using a dedicated terminal or the like. In such a case, the profile information and other information of the user can be specified from the description of the questionnaire. Such information collection is not limited to the 1 st device 2a and the like, and may be performed by the control unit 1. If information on when a medical institution, an examination institution, or the like is available, it can be used as time Tc information in fig. 4 (a) and 4 (b) described later.

The 1 st device 2a, the 2 nd device 2b, and the 3 rd device 3 are already associated with a specific disease, and may be a thermometer, a sphygmomanometer, or the like used under the direction of a doctor. In addition, when colors of a face, nails, and the like, facial expressions, images of an affected part, and uncomfortable voice of a throat, which are captured by a camera included in a smartphone, are collected by a microphone, the portable terminal (smartphone) can be directly used as the 1 st device 2a, the 2 nd device 2b, and the 3 rd device 3.

Recently, a simple health management device and a health information acquisition device have been developed, and these devices may be mounted on a wearable device, and such devices are often handled as peripheral devices of a smartphone instead of being independent devices, and therefore this is also assumed to be a portable terminal. In addition, even if the wearable device is not used, a simple measurement device may be installed in a place where people gather to provide a health information service. Such devices may also be used as the 1 st device 2a, the 2 nd device 2b, the 3 rd device 3.

The diagnosis/examination facility 9 is a facility where a user receives a health examination or examination, and includes, for example, a medical facility, an examination facility, and a pharmacy. The diagnosis/examination means 9 may be of a mobile type, for example, a type in which a normal medical facility and an examination facility are mounted on a car, a train, a ship, a helicopter, an unmanned aerial vehicle, or the like and the patient is reached. The control unit 1 can acquire, from a server or the like of a system that operates the diagnosis/examination mechanism 9, which medical mechanism the examination has been performed at, what kind of examination result has appeared, and the like.

Of course, the server of the diagnosis/examination means 9 includes the control unit 9B, and the control unit 9B may be the same as the control unit 1 or may share a part of the functions (for example, see fig. 8A and 8B). In this case, the control unit 9b can collect the inspection data from the 1 st equipment 2a and the like via the control unit 1 and record the data in the DB unit 8a, and further, the control unit 1 can read the data recorded in the DB unit 8 a. In addition, the user information can be acquired from the user information section 10. The control unit 9b can perform inference by the inference engine 7, and can request the learning unit 5 to generate an inference model via the learning delegation unit 6.

The diagnosis/inspection means 9 has a DB part 9a, and the DB part 9a is an electrically rewritable nonvolatile memory. The DB unit 9a records the diagnosis result and the examination result in the diagnosis/examination mechanism 9 for each individual ID. The DB unit 9a may also record medicines taken by the user, and further record information related to lifestyle habits. The DB unit 9a also records a recommendation and the like given to the user by the diagnosis/examination mechanism 9 (including a pharmacy and the like). In a pharmacy, the user purchases a medicine and receives information when the advice is to be a health state-related advice. The diagnosis/examination mechanism 9 outputs medical institution information to the control portion 1, and acquires the medical institution information, various information related to the user, from the control portion 1.

As described above, the terminal 4 is a portable information terminal and is a device for receiving information that can be confirmed by the user or a person related thereto. The information includes facilities recommended according to health information and health status. As described above, when a specific diagnosis is made based on the result of physical examination, there is information on the specific diagnosis as the information on health. In addition, when the specific diagnosis result is a symptom depending on heredity or lifestyle, there is a notification or the like indicating that a guard check is performed by the 1 st device 2a or the like for observation. When the symptom is also related to family members, the meaning is displayed.

The terminal 4 may be, for example, a smartphone or a tablet computer, and in this case, a built-in camera or a microphone may be used as the information acquisition unit. In addition, a wearable terminal and other home appliances that can cooperate with each other may be used as the terminal 4, or information may be acquired by the wearable terminal or the like. Therefore, the 1 st device 2a, the 2 nd device 2b and the terminal 4 may be the same or may be dedicated devices, respectively. The terminal 4 cooperating with the wearable terminal can also perform information acquisition and information management. Depending on the situation, the 1 st device 2a, the 2 nd device 2b, the 3 rd device 3, and the terminal 4 may be configured to have the function of the control unit 1, and may be configured to perform detection, control, and information provision in a distributed manner. The display example in the terminal 4 will be described later with reference to fig. 7.

The Database (DB) unit 8 has an electrically rewritable nonvolatile memory. The database unit 8 can record various data, and the DB unit 8a in the database unit 8 records information such as fostering relationships by ID. The DB unit 8a may be constructed according to the system of the present embodiment, and may be provided in the DB unit 9a of a medical institution or the like. Further, since the medical institution has a system dedicated to information management in a hospital or the like, it may be provided separately as in the system. Information on family membership is recorded in a user information unit 10 described later, and the DB unit 8a records information on a fostering relationship and the like for each ID based on the family membership information acquired from the user information unit 10 and information acquired from other devices (including the control unit 1). The information on the fostering relationship is information on persons in the fostering relationship, such as spouses and children of the users. In addition, information on family members having a relationship with blood causes and the like is also recorded. Lifestyle is also influenced by co-habitation or non-co-habitation, and therefore, if possible, the information may be recorded.

The DB unit 8a records a data history list of each ID as shown in fig. 3. In this list, medical information, device IDs (assumed devices, and other devices), and history data of the examination data for each acquisition date and time are recorded for each individual ID. As described above, the information providing section 1c inputs the examination data from the 1 st equipment 2a and the like, the diagnosis/examination mechanism 9 and the like, and therefore the DB section 8a records the examination data by ID. At this time, the inspection date (inspection timing), the inspection equipment (1 st equipment 2a, 2 nd equipment 2b, 3 rd equipment 3 (shown as equipment a, equipment b, equipment c in fig. 3)), and the inspection result are recorded. The data history list of each ID will be described later with reference to fig. 3.

The DB unit 8a records the available devices and the corresponding medical conditions that can be checked by the available devices by IDs. The user can use not all the inspection apparatuses (the 1 st apparatus 2a, the 2 nd apparatus 2b, the 3 rd apparatus 3, and the like), but generally only apparatuses installed in a plurality of inspection apparatuses, homes, work units, publicly available places, and the like. The DB unit 8a stores a list of devices available to the user. In addition, if the disease suffered by the user or developed in the future is known, the devices for observing the change of the respective symptoms are also different. Therefore, the DB unit 8a is stored for each device available to the user for each disease that can be dealt with. The list of available devices for each ID will be described later with reference to fig. 2.

The DB unit 8a also records how the examination is performed, what examination is used, and the like. The DB unit 8a may sort the acquired data into 5W1H, that is, WHO (WHO), WHERE (WHERE), WHEN (date and time), WHAT check, WHAT, HOW, and record the sorted data. In addition, the examination location (medical facility, examination facility, own home, work unit) and the like may be recorded.

The DB unit 8a functions as the 1 st recording unit that records inspection equipment that can be used by a specific person and a person to be supported (see, for example, fig. 2). The DB unit 8a functions as a 2 nd recording unit for recording examination equipment usable by a specific person and a blood related person (see, for example, fig. 3).

The user information unit 10 collects and records user information for each user (each ID). The user information unit 10 may collect information on the age, sex, behavior, and habit of the user and family members among the information recorded on the internet. In addition, if the user information part 10 allows viewing of data recorded in the 1 st device 2a, the 2 nd device 2b, the 3 rd device 3, the diagnosis/examination mechanism 9, the terminal 4, and the like, information may be collected from these devices. For example, if GPS information of a smartphone or the like mounted on a user can be collected, information on the behavior of each user can be collected. In addition, if purchase information based on electronic settlement can be collected, information on meals can be collected from purchased food and the like.

The user information section 10 includes a DB section 10a, and the DB section 10a is an electrically rewritable memory. As described above, since the user information unit 10 collects information on the age, sex, behavior and habit (including eating habit) of the user and family members for each individual ID, the DB unit 10a records the collected information.

The DB unit 10a may be provided in a database (DB unit) 9a in a medical institution or the like, but since the DB unit 9a is often dedicated to information management in the medical institution, it may be managed by another server or the like and used for the present service. Further, the DB unit 10a may be provided in the DB unit 8 for accumulating and holding the acquired data and for use in inference, but the DB unit 8 may be designed exclusively for information management of sensors and the like, and thus a database of daily life and basic information such as lifestyle habits and family members may be separately provided as shown here. Further, these pieces of information may be managed in different databases by being further differentiated. For example, databases of a DB (family member information) and an SNS (daily life) of health insurance may be separately managed, and these databases may be referred to as necessary to function as the merged information 10 a.

When receiving a request for creating an inference model from the inference requesting unit 1e in the control unit 1, the learning requesting unit 6 transmits a specification of the inference model and the like to the learning unit 5, and requests the inference model to be created according to the specification. The learning delegation unit 6 includes a data classification recording unit 6a, a specification setting unit 6d, a communication unit 6e, and a control unit 6 f.

The control Unit 6f is a controller (processor) that controls the inside of the learning delegation Unit 6, and assumes an IT device such as a server, which is configured by a CPU (Central Processing Unit), a memory, an HDD (Hard disk Drive), and the like, and provides files, data, and the like to other terminals via a network. However, the control unit 6f is not limited to this configuration, and may be configured as a personal computer when constructed as a small-scale system. The control unit 6f has various interface circuits, can cooperate with other devices, and can perform various kinds of arithmetic control by a program.

The data classification unit 6a has an object type a image group 6b, and training data 6c is recorded therein. The object type a image group 6B is an image group used when the inference model is generated in the learning unit 5, and includes a plurality of image groups of type a, type B …. Training data 6c is generated from the image group. That is, as shown in fig. 4, by drawing the examination data for each examination day, a graph can be drawn and the graph can be processed as an image. In addition, although the description is given here as an image in a manner that is easy to intuitively understand, it is not necessarily required to process the image, and a plurality of inspection data sets in which inspection date and time and inspection data are collected may be generated as training data, which is a change in time-series inspection data. The data record classification unit 6a records training data 6c based on the data history list recorded in the DB unit 8 a.

The specification setting unit 6d sets what kind of inference model is to be generated, based on the specification of the inference model determined by the inference model specification determining unit 1 d. In order to satisfy this specification, training data is generated from data recorded in the history list of the DB unit 8 a.

The communication unit 6e has a communication line for communicating with the control unit 1 and the learning unit 5. The communication unit 6e receives a request for generation of an inference model from the control unit 1, and requests the learning unit 5 to generate an inference model.

The learning unit 5 includes an input/output modeling unit 5a, and generates an inference model by machine learning or the like in accordance with the specification from the learning delegation unit 6. The input/output modeling unit 5a includes a specification matching unit 5 b. The specification comparison unit 5b determines whether or not the specification received from the learning delegation unit 6 matches the inference model generated by the input/output modeling unit 5 a. That is, the specification comparison unit 5b defines not only the input/output relationship but also a learning method and the like to learn the "required specification" such as time, energy, and circuit configuration required for inference according to the inference model.

The inference model is generated by learning the relationship between acquired information such as biological information and biopsy information acquired and a disease, specifically, the relationship between the acquired information and a clinical department/department. The input/output modeling unit 5a has an input layer, a plurality of intermediate layers, and an output layer, as in the case of the inference engine 7, and obtains the strength of connection of neurons in the intermediate layers by learning to generate an inference model.

When such an inference model is generated, the learning committing unit 6 extracts a change pattern of the examination data acquired from the subject using the examination device in a specific time width, inputs the extracted change pattern to the inference engine 7, and generates training data in which health advice to be output at a timing after the timing of examination by the subject is set as the labeling information. Then, the learning unit 5 performs learning by using the training data to generate an inference model.

Further, the learning unit 5 can also generate an inference model that can suggest future predictions of the effect of lifestyle improvement, treatment, and medication if learning is performed using an examination data string after examination, hospital visit, and medication. In this case, the time-series data after the examination, the visit to the hospital, and the administration of the medicine are used as the starting points. In the case of advising examinations, going to the hospital, taking medicines, etc., the time-series data up to that point are utilized.

Here, deep learning will be described as an example of learning performed by the learning unit 5. The "Deep Learning (Deep Learning)" is obtained by structuring the process of "machine Learning" using a neural network in multiple layers. A "forward propagation type neural network" that transmits information from front to back to make a decision is representative. The forward propagation type neural network is the simplest, and may have 3 layers, i.e., an input layer including N1 neurons, an intermediate layer including N2 neurons given by parameters, and an output layer including N3 neurons corresponding to the number of classes to be discriminated. The neurons of the input layer and the intermediate layer, and the neurons of the intermediate layer and the output layer are connected by connection weighting, and the intermediate layer and the output layer are added with an offset value, whereby a logic gate can be easily formed.

The neural network may be 3 layers as long as it can perform simple discrimination, but a combination of a plurality of feature amounts can be learned in the machine learning process by making a plurality of intermediate layers. In recent years, the 9-152-layer structure is practical from the viewpoint of time taken for learning, determination accuracy, and energy consumption. In addition, a "convolution type neural network" may be used, which performs a process called "convolution" of the feature amount of the compressed image, operates with a minimum process, and is strong in pattern recognition. In addition, a "recurrent neural network" (fully-connected recurrent neural network) may be used, which handles more complicated information and allows information to flow in both directions in accordance with information analysis whose meaning changes in order or order.

In order to realize these techniques, a general-purpose arithmetic processing circuit such as a CPU or an FPGA (Field Programmable Gate Array) that has been conventionally used may be used. However, since the Processing of the neural network is mostly matrix multiplication, a processor called GPU (Graphic Processing Unit) or Tensor Processing Unit (TPU) dedicated to matrix calculation may be used. In recent years, "neural Network Processing Unit (NPU)" of such Artificial Intelligence (AI) -dedicated hardware is designed to be integrated and incorporated with other circuits such as a CPU, and may become a part of a processing circuit.

Further, as a method of machine learning, for example, a support vector machine, a support vector regression method, and the like are available. The learning here is a method of calculating the weight, filter coefficient, and offset of the identifier, and also a method of using a logistic regression process. In the case of having the machine decide what, one needs to teach a method of machine decision. In the present embodiment, a method of deriving image judgment by machine learning is adopted, but in addition to this, a method of applying a rule base of rules obtained by human experience/intuitive reasoning (hemristics) may be used.

The inference engine 7 has an input/output layer and a neural network similar to those of the input/output modeling unit 5a of the learning unit 5. The inference engine 7 performs inference using the inference model generated by the learning section 5. For example, the inference engine 7 inputs physical examination data of the diagnosis/examination mechanism 9, and infers whether or not a disease is present, a possible future disease, and the like. In this case, historical data of the past user may be input and inferred.

Also, the inference engine 7 can also infer whether or not it is a life style-or heredity-dependent symptom. The inference engine 7 may measure the biological information in time series by the first device 2a or the like, input the biological information, and determine an examination facility/medical facility suitable for examination, treatment, or the like of the health status of the user by inference. The inference engine 7 may also perform inference of when a medical institution will see a doctor based on the time-series biological information.

In this way, the control unit 1 can provide information on the disease of the user by the inference engine 7 in addition to the search of the DB unit 8a by the search unit 1 f. The inference engine 7 performs inference about a disease using the inference model generated by the learning unit 5. The inference model is generated by learning the relationship between acquired information such as acquired biological information and biopsy information and a disease. In this way, the control unit 1 can output guidance information to be presented by inference from the inference engine 7.

When the control unit 1 determines to guide a disease or the like once from the acquired information obtained once by searching or reasoning, there is a possibility that medical information is brought into the life unnecessarily, which hinders a healthy and safe life. Therefore, the history of acquired information (time series information) can be used a plurality of times to improve the accuracy.

The inference engine 7 functions as an inference unit that infers the health advice from the detection result of the guard sensor (see, for example, S31 in fig. 5B, S85 in fig. 7 and 8B). The inference engine 7 functions as an inference unit that infers the health advice from the detection result of the sensor (see, for example, S31 in fig. 5B and S85 in fig. 8B). The inference unit reflects the life information corresponding to the symptom extracted by the symptom extraction unit at the time of inference.

Next, a list of available devices of each ID recorded in the DB unit 8a will be described with reference to fig. 2. The list of available devices for each ID includes a list of available devices for the individual, functions thereof, and corresponding medical conditions. The personal usable device may be automatically transmitted from the 1 st device 2a, the 2 nd device 2b, the 3 rd device 3, the diagnosis/examination mechanism 9, the user information section 10, or the like, or may acquire data input by the user through a questionnaire or the like.

In the leftmost column of the table in fig. 2, individuals identified by IDs, such as the individual X and the individual Y …, are described. The right adjacent column shows devices such as the person X and the person Y that can be used at ordinary times. The right adjacent column describes the functions of the device. In 1 device, it is sometimes possible to acquire a plurality of functions, for example, a plurality of data (functions) such as the color and shape of stool, blood pressure, and pulse. Further, in the right adjacent column, there is described a disease state that can be associated with each function. By observing this table, it is possible to know which apparatus should be used to collect examination data, for example, from a disease state found by the result of physical examination.

Next, the history data recorded in the DB unit 8a will be described with reference to fig. 3. The history data is created for each individual ID for identifying one user by one. The historical data records the fostering relationship, the medical information, the equipment ID and the acquired data according to each ID.

In fig. 3, in the hurdle of the fostering relationship, if there is a fostering relationship between individuals, this meaning is recorded. For example, ID1 is a foster and ID2 is a foster (spouse) relative to ID 1. In addition, ID3 is a foster and ID4 is a foster (child) relative to ID 3. While the relationship between blood vessels is usually present in the case of children, the relationship between blood vessels can be accurately recorded because there are cases of nurses.

As the medical information, information on examination results, medicine purchase, and nursing judgment is recorded. The date of the examination was accepted and the result of the examination and the advice made at that time are recorded in the examination result in the medical information. In addition, the date of purchase, the medicine purchased, and the advice at that time are recorded in the medicine purchase in the medical information. In the section of the guard determination, when it is determined that guard is necessary in consideration of lifestyle habits and hereditary diseases by physical examination or the like, items such as lifestyle habits and heredity are recorded, and a person who is a family member is also guarded. In the example shown in fig. 3, since ID1 is determined to require the guard of lifestyle-related diseases, the guard is recorded in ID2 of the person (family member) being supported.

In addition, the device ID recorded in the history data in the DB section is an ID for identifying an inspection device used in the inspection. The device ID is recorded based on information such as category information 2a1, 2b1, 3a1, and the like. In addition, when the type information is not transmitted from the inspection device, the control unit 1 appropriately gives the device ID. As described above, when the guard determination is made, the inspection apparatus is determined according to the symptom.

In the example of the history data shown in fig. 6, the user of ID1 is determined to be on guard because there is a possibility that a particular disease is present during physical examination or the like at time t2, and a lifestyle disease or a genetic disease may be caused, or a disease may be caused. Therefore, after time t2, ID1 specifies device a and device b, and further ID2 specifies device b, and collection of inspection data is performed. That is, the ID1 acquires the check data Da (t3), Da (t4) at the date and time t3, t4 using the device a, and acquires the check data Db (t2), Db (t5) at the date and time t2, t5 using the device b. Among the history data acquired before the time t2, Da1(t1) and Dc2(t1) are used as past data for inference. Da1(t1) and Dc2(t1) are underlined in fig. 3 to show data acquired before (in the past) the decision guard check.

Similarly, the users ID3 and ID4 are determined to be guardianed because they have a specific disease, such as physical examination, at time t3, and may suffer from lifestyle-related diseases or genetic diseases, and also may develop a disease. Similarly to the case of ID1 and ID2, in the case of ID3 and ID4, data before time t3 is used as past list data, and after time t3, designated device c collects check data and guards the data.

Next, biological information (examination data) acquired in time series by the 1 st apparatus 2a and the like will be described with reference to fig. 4. In the example shown in fig. 4, in order to acquire the examination data of the user, 2 devices of the 1 st device 2a and the 2 nd device 2b are assumed. Fig. 4 illustrates biological information (examination data) acquired from 1 device out of 2 devices.

Fig. 4 is a graph created using the inspection data. As described above, the DB unit 8a records the examination data arranged in time series for each patient ID (see fig. 3), and fig. 4 shows the examination data in a graph. In fig. 4, the horizontal axis represents time T (corresponding to the acquisition date and time T1 to T9 in fig. 3), and the vertical axis represents time-series inspection data. The vertical axis represents examination data, biological data, vital sign data, and sample data, and any of these data is represented by a numerical value D of an examination output result of an apparatus performing an examination. The numerical value D is, for example, a value indicating the degree of redness of stool.

In the example shown in fig. 4 (a), as described later, the time-series data changes in a direction toward deterioration of health, and the user is going to a hospital soon. The patient in the situation shown in fig. 4 (a) can provide a result of deducing how far the patient will go to the hospital of the clinical department before time T1. In addition to this example, as shown in fig. 4 (b), even when the patient goes to the hospital and obtains vital sign data because other signs have been perceived, the information is recorded in the DB unit 8 a. However, there are also people who have vital sign data even if they have not gone to the hospital at all.

As described above, fig. 4 (a) is a case where it is estimated that a user will go to a hospital in the future. The graph shown in fig. 4 (a) shows a time-series change of examination data (device data) of a user who does not currently go to a hospital. When a specific examination result (specific information) is obtained from the time-series examination data, it is possible to obtain information on whether or not to go to a medical institution. Therefore, it is possible to guide health information that enables the user to grasp his/her health status before the user gets worse to the point of going to the hospital, based on the time-series examination data. For example, in fig. 4 (a), in the case of the examination data at time T1, it can be inferred that the medical institution is visited at time Tc when the time + Δ T has elapsed. That is, if the DB unit 8a stores examination data, medical institution information (hospital name, clinical department, date and time information), and the like, it is possible to estimate a period until the medical institution receives a medical treatment.

Fig. 4 (b) shows a case where the patient has already gone to the hospital, and is a case where the patient has deteriorated during the course of going to the hospital for a reason other than treatment. The graph shown in fig. 4 (b) is an example of receiving treatment in a hospital when a person who has gone to the hospital due to a disease has specific information at times Tc1, Tc 2. The time-series examination data shown in fig. 4 (b) can be sufficiently used for learning such a situation. This example is effective for guidance of the subject matter "a person of this value cannot usually perform treatment by himself". It is effective to provide information that can prevent further deterioration from occurring.

Fig. 4 (c) is a case where it is not necessary to go to the hospital. In this case, the examination data D is lower than a predetermined value (indicated by a broken line in the graph), and does not need to travel to the hospital. In this case, the column of the date of the inspection result is blank in the database of the DB unit 8a shown in fig. 3.

In fig. 4, time series information for each patient recorded in the DB unit 8a is shown in a graph, where the horizontal axis represents time and the vertical axis represents numerical values of acquired information. Therefore, the information becomes two-dimensional visual information. Since the two-dimensional map is obtained, the following two cases can be said. First, since the image is a graph, it is possible to perform processing in the same manner as image determination, and it is possible to easily follow an AI chip or system that is easily constructed in general, such as an inference model for image recognition, and to easily realize inference. Further, since the horizontal axis represents time, information on temporal changes in the body information can be effectively used, and prediction and the like can be easily performed. In addition, information relating to a characteristic of temporal change unique to a living body such as fluctuation or frequency can be added.

In the present embodiment, when it is assumed that inference is performed depending on future diseases such as lifestyle habits, the case where inference results are obtained by inputting time-series data (see fig. 4) to an inference model is assumed and explained. As an application example, an inference model obtained by learning specific data as training data may be used. That is, as the inference result provided to the user, an inference result obtained by inputting data selected from time-series data may be used. Alternatively, the inference result may be obtained by inputting an average value, a maximum value, a minimum value, or other values subjected to a specific operation in a predetermined period. In an unnoticed period, the body temperature may rise excessively, and in this case, there is also a risk of an infectious disease or infection of other persons, and it is important not to predict the future but to promptly notify the user promptly.

Next, the operation of the control unit 1 will be described with reference to flowcharts shown in fig. 5A and 5B. The CPU in the control unit 1 operates according to a program stored in the memory, and controls the entire inference system to execute the flow.

When the flow of the control section shown in fig. 5A, 5B is started, first, data is collected from the device (S1). Here, the CPU of the control unit 1 collects physical examination data, and the like from the 1 st apparatus 2a, the 2 nd apparatus 2b, the 3 rd apparatus 3, the diagnosis/examination mechanism 9, and the like. The collection of the physical examination data, the examination data, and the like may be performed by the control unit 1 at all times (in fig. 3, the underlined data is a result of normal collection), or the data may be collected by starting the guard in step S7 as described later. Note that if there are physical examination data, and the like transmitted from the 1 st device 2a and the like to the control unit 1, the data may be collected.

When the data is collected from the device, it is next determined whether or not the determination result of the user himself (or herself) is that new "diagnosis" information is obtained (S3). Here, the control unit 1 (information providing unit 1c) determines whether or not the user has received physical examination or examination by the diagnosis/examination means 9, and a doctor or the like has performed a specific diagnosis.

If the result of the determination in step S3 is new "diagnosis" information, the related data item is then determined based on the "diagnosis" information of the user himself (personally) (S5). Here, since a specific diagnosis is made, the control unit 1 (information providing unit 1c) extracts a symptom depending on heredity or lifestyle in association with the diagnosis. Data received from the diagnosis/examination agency 9 or the like may also be input to the inference engine 7, inferring symptoms depending on heredity or lifestyle. When a symptom is extracted, a necessary related item is determined in order to attend to the symptom, that is, in order to observe the progress.

In step S5, when the association data item is decided, it is then determined whether or not a daemon corresponding device exists in the DB with respect to the lifestyle association item (S6). As described with reference to fig. 2, it is determined whether or not there is any device that can check the items determined in step S5, among devices that are normally used by the user (individual). If the result of this determination is that there is no daemon-corresponding device in the DB, the process returns to step S1. In this case, the terminal 4 may be sent a message indicating that the device which can not be designated as the daemon user is absent, and may display the message.

If the guard-corresponding device is present as a result of the determination at step S6, guard of the principal is started (S7). Here, the control unit 1(ID determination unit 1b) specifies the corresponding device for guard (any device such as the 1 st device 2 a) determined in step S6, and collects the examination data of the user from the device. When the inspection data is collected, the inspection data is recorded as history data in the DB unit 8a (see fig. 3).

When the self guard is started, it is determined whether or not there is a person to be supported (S9). Here, the control unit 1 (the supported person determining unit 1g) searches the DB unit 8a (which may be the user information unit 10) to determine whether or not there is a person supported by the user himself. In addition, in the case where the user is the person to be supported, the person to be supported may be determined, or a family member co-resident with the user may be determined. If the result of this determination is that there is no foster person, the process returns to step S1.

If the foster person is present as a result of the determination in step S9, then a guard check of the foster person is started (S11). Here, first, the DB unit 8a (or the user information unit 10) is searched to determine whether or not the facility for checking the lifestyle-related item among the related data items determined in step S5 is used when the presence of the person to be supported is checked, and the maintenance check of the person to be supported is started when the presence of the facility is checked as a result of the search. That is, a corresponding facility for guard (any facility such as the 1 st facility 2 a) is specified, and the examination data of the person to be supported is collected from the specified facility. When the inspection data is collected, the data is recorded as history data in the DB unit 8a (see fig. 3). In addition, when the guard inspection is started, the user or the person to be supported by the user may be notified of the fact, and the collection of the inspection data may be started after permission is obtained.

When the guardian check of the foster is started in step S11, it is then determined whether or not there is a genetically related item (S13). Here, the control unit 1 determines whether or not there is a hereditary related item among the related data items determined in step S5. If no related item is found as a result of the determination, the process returns to step S1.

If the determination result in step S13 indicates that there is a genetic relationship item, a guardian test is started if there is a blood-related person other than the foster person (S15). Here, first, the DB unit 8a (or the user information unit 10) is searched to determine whether or not the device for checking the genetic related item among the related data items determined in step S5 is normally used by the blood-related person. If the result of the search is that the examination device is present, the guardian examination of the blood-related person is started. That is, a corresponding device for guardian (any device such as the 1 st device 2 a) is specified, and the examination data of the blood-related person is collected from the specified device. When the inspection data is collected, the inspection data is recorded as history data in the DB unit 8a (see fig. 3). When the guardian test is started, the user or the blood-related person of the user may be notified of the fact, and the collection of test data may be started after permission is given. When the guard check is started, the flow returns to step S1.

Returning to step S3, if there is no new "diagnosis" information as a result of the determination in this step, it is determined whether or not there is sufficient history data as the relevant data of the user himself/herself who is the subject of the determination (S21). As described above, the DB unit 8a records history data of an individual for each ID. Here, the control unit 1 determines in step S3 whether or not the history data of the user himself/herself who is the object of determination is sufficiently recorded.

If the determination result in step S21 is that sufficient history data has not been recorded, the collection of the history data of the user himself/herself is started and continued (S23). Here, the control unit 1 (information providing unit 1b) starts collection of the inspection data from the 1 st apparatus 2a or the like, and continues the collection. The selection of the examination item may be performed by the determination of the priority item in the next step S25.

When the collection of the history data is started in step S23, the priority items of the user himself and the family members are then decided according to the physical examination result of the user himself (S25). Here, the control unit 1 determines the priority order from the related data items based on the diagnosis result based on the physical examination result of the individual acquired in step S1. That is, the physical examination data received from the diagnosis/examination mechanism 9 or the like is input to the inference engine 7, and the symptoms depending on the heredity or lifestyle are inferred, and after the symptoms are extracted, the related items necessary for guarding the symptoms, that is, for observing the progress of the observation can be determined. After the related items are determined, priority items of the individual and family members are determined based on the usable devices and the corresponding medical conditions of each ID recorded in the DB unit 8 a. When the priority item is decided, the process returns to step S1.

Returning to step S21, if sufficient history data exists as a result of this determination, it is next determined whether or not a device that the user himself (personally) can use exists in the DB (S27). Here, the control unit 1 determines whether or not a device for guarding the corresponding medical condition is recorded in the DB unit 8a as a device which can be used by the user himself when the diagnosis information is to guard the corresponding medical condition. If the DB unit 8a does not store any device that can be used by the user himself/herself as a result of this determination, the process returns to step S1.

When the device that the user himself/herself (individual) can use is recorded in the DB unit 8a as a result of the determination in step S27, it is next determined whether or not the corresponding inference model can be specified (S29). There are a plurality of inference models set in the inference engine 7, and the control unit 1 selects an inference model based on data input to the inference engine 7 and the content of an output to be acquired. In this step, the control unit 1 determines whether or not there is data input to the inference engine 7 and an inference model corresponding to the acquired output result. The detailed operation in specifying the corresponding inference model will be described later with reference to fig. 6. If the determination result indicates that there is no corresponding inference model, the process returns to step S1.

In the case where the result of the determination in step S29 is that the corresponding inference model can be specified, inference is then performed using the data history (S31). Here, the control section 1 sets the specified corresponding inference model as the inference engine 7. Then, the control unit 1 inputs the history data recorded in the DB unit 8a to the inference engine 7, and acquires the inference result corresponding to the inference model.

The corresponding inference model is generated using the training data illustrated in fig. 4. When the time-series data is input to the corresponding inference model and inferred, inference is made as to which time period the patient will travel to the hospital in the future, what kind of examination results will appear, what kind of advice will be made at that time (a radical remedy known from the disease name diagnosed from the examination results, a candidate for a symptom-improving remedy known from the disease name, and a notice in daily life).

The following description is made assuming a case where an inference model is generated using time-series data (see fig. 4) and an inference result is obtained using the inference model. However, the inference can be performed in addition to the time-series data, and for example, the inference result may be obtained by inputting data selected from the time-series data to an inference model corresponding to the data. Alternatively, the inference result may be obtained by inputting an average value, a maximum value, a minimum value, or other values subjected to a specific operation in a predetermined period. During the unnoticed period, the body temperature may rise excessively, in which case a quick notification is important. In this case, if an inference model that performs inference with reference to other data is used, the accuracy of determination is improved.

When inference is made in step S31, the inference result is then output to the user himself (a person) (S33), and a supplementary suggestion of the inference result is made (S35). Here, the control unit 1 (information providing unit 1c) outputs the inference result acquired in step S31 to the terminal 4 of the user himself. Further, when transmitting the inference result, the control unit 1 also transmits a supplementary advice based on the inference result to the terminal 4. Since the inference result and the supplementary advice are displayed on the display portion of the terminal 4, the user can know the health state associated with the disease based on the physical examination result. When steps S33, S35 are executed, the process returns to step S1.

Fig. 7 is a display example of the advice in the terminal 4 of the user. Information on the physical examination result and examination data by the subsequent guard is displayed on the terminal 4 owned by the user himself. In the example shown in fig. 7, the examination data of the user himself/herself is displayed in a graph using parameters such that the horizontal axis represents a data numerical value and the vertical axis represents a frequency (number of times), white circles represent results within the normal range, and black circles represent results outside the normal range. By this display, it is clear whether or not there is a tendency to deviate from the normal numerical value. Further, for example, if the horizontal axis is time and the vertical axis is data numerical values, it is easy to know whether the trend is a recent trend or a trend that has been present from the past. If improvement or deterioration is known, the effort for improvement can be reviewed to review life and otherwise decide whether to go to the examination. In addition, the examination result of the other user may be displayed together with the examination result of the user himself/herself. By comparing with other users, it is possible to objectively determine the physical condition of the user, review the life and make an improvement effort, and determine whether to make a diagnosis.

The user' S terminal 4 may display the inference result (see S33 and S35). In this case, it is first desired that the user notices from the objective data by himself so as not to cause unnecessary anxiety. However, the behavior of the user may be detected in advance, and when there is no improvement, the inference result may be made and displayed. As the expression, for example, "such symptoms appear with a probability of good quality%". If a disease or the like is introduced based on a future examination result inferred from the learning result, the user can actually feel a bad situation at the time of the disease. The display is obtained by processing a result obtained by further searching the inference result in the database by the logic library, and is obtained based on the result of learning. Therefore, a generic concept including this is obtained that can display a result of inferring the health advice based on the detection result of the sensor.

In addition, the result of diagnosis by referring to the inference result by the doctor may be displayed on the terminal 4 of the user. That is, according to the present embodiment, it is possible to provide an apparatus, a method, and a system, each of which includes a display control unit for displaying the above-described inference result. The inference result may be obtained by inputting the time-series data as shown in fig. 4 to the inference model, or may be obtained by inputting data selected from the time-series data to the inference model corresponding to the data. Alternatively, the inference model may be input with an average value, a maximum value, a minimum value, or other values subjected to a specific operation for a predetermined period. For example, the body temperature may rise excessively during an inadvertent period, and this may be input data.

As shown in fig. 7, icons of "contents of scrutiny" and "examination request" are displayed on the terminal 4. When the "content of careful observation" is touched, detailed inspection data is displayed, and when the "inspection request" is touched, the diagnosis/inspection means 9 or the like can be requested to perform an inspection. As the "other user" described above, the same sex, the same age group, and the like may be selected. The basic information necessary for the selection may be recorded in the DB unit 8a, or may be searched by the ID to search the databases of the DB units 9a and 10a for determination. In addition, through the cooperation of the databases, people suffering from the same host disease and people with the same behavior pattern can be extracted, compared and displayed.

Next, the detailed operation of "specification of correspondence inference model" in step S29 will be described with reference to the flowchart shown in fig. 6.

When the flow designated by the corresponding inference model of fig. 6 is started, first, meaningful guard information is determined from "symptoms" (S41). As described above, in the present embodiment, a lifestyle-related or genetic disorder is extracted from the result of physical examination or the like. When a disease state is extracted, the control unit 1 determines what the inspection items (daemon information) suitable for observing the disease state are. Since appropriate examination items are recorded in the DB unit 8a in a list form according to the disease state (see fig. 2, for example), and history data is recorded in the DB unit 8a, the control unit 1 may determine the guard information based on these pieces of information.

When the daemon information is determined in step S41, available device information is next determined (S43). Here, since information on available equipment for each ID is recorded in the DB unit 8a (see fig. 2) and history data of each ID is stored in the DB unit 8a, the control unit 1 performs determination based on the information. Next, the specification of the corresponding device is determined (S45). Here, the control unit 1 makes a determination based on the specification of the corresponding equipment recorded in the DB unit 8a and the history data recorded in the DB unit 8a (for example, refer to the functional fields of fig. 2).

After the daemon information, the available device information, and the specification information of the corresponding device are determined in steps S41 to S45, the acquisition information is selected according to the frequency of use and the specification (S47). Since there are cases where a plurality of pieces of information are acquired as a result of the determination in steps S41 to S45, acquisition information is selected from these pieces of information according to the frequency of use and specifications of the device.

Next, it is determined whether an inference model exists (S49). Here, the control unit 1 determines whether or not there is an inference model generated based on the same information as the device selected in step S47. That is, when physical examination data and examination data are input and inference is performed, an inference model is specified in consideration of the purpose of inference. In this case, the specified inference model is a model that is the same as the device used by the user in the examination, and is additionally desired to infer the "disorder" as the target. Here, the control unit 1 determines whether or not the inference model exists.

In the case where the result of the determination in step S49 is that there is no predictive inference model, it is determined whether or not other functions or other devices can be selected (S51). Since there is no optimal inference model, the control unit 1 determines whether or not it is possible to select another function of the device used in the examination or another device. If the device can be selected as another device or the like as a result of the determination, the process returns to step S49.

On the other hand, if the result of the determination in step S51 is that selection is not possible, a device use suggestion or the like is made (S53). Here, the control unit 1 outputs a suggestion to use a device other than the device that the user normally uses to the terminal 4 held by the user. When the suggestion is made, as a branch in step S29, no is entered (S55).

Returning to step S49, if the result of this determination is that a predictive inference model is present, the corresponding predictive model is specified (S57). Here, the control unit 1 specifies (sets) the selected inference model in the inference engine 7. When the inference model is specified, as a branch in step S29, yes is entered (S59).

In this way, in the flow of the control unit in fig. 5A, 5B, and 6, when the physical examination result is input from the diagnosis/examination means 9 or the like (see S1), it is determined whether or not there is a specific diagnosis result obtained by performing a specific diagnosis in the physical examination result (see S3). Then, lifestyle-related or hereditary symptoms in the specific diagnosis result are extracted, and examination items (related data items) for observing the symptoms are determined (see S5). When the examination items are determined, it is determined whether or not the examination can be performed by the examination apparatus used by the user (see S6), and if the examination can be performed, the apparatus starts the guard examination (see S7).

In the case of lifestyle diseases, since family members (nursed persons) of the user may suffer from or develop diseases in the future, the guard check is started in the same manner as the user (see S9 and S11). Similarly, in the case of a genetic disease, since there is a possibility that a person who is blood-related to the user may also suffer from the disease or may develop the disease in the future, the guard test is started in the same manner as the user (see S13 and S15).

In the present embodiment, the description has been simplified to specify a sensor and start acquiring data when diagnosis and onset of disease are expected. However, the present invention is not limited to this, and the user may contract with an equipment sales company or the like at a time of purchasing equipment mounted with a sensor, at a time of hand, at a time of installation, or the like, and may acquire data and accumulate data. In data transmission and data accumulation, it is sometimes necessary to contract for electricity charges, communication charges, usage amount of a recording memory, and the like. In many cases, it is easier to accept the expert's description at the same time as the purchase or the sign-in, to select data items within the scope of approval in consideration of the health status of the person and to determine a settlement method for payment in a lump. Of course, these contracts may be set in the user's mobile terminal or information terminal. Further, the data may be accumulated by determining the storage period, the storage amount, and the like of the data. In this way, when data reference is made by tracing back to a specific data acquisition timing using already recorded data, the expression "daemon start" is also used.

As described above, in the present embodiment, the guard inspection of the user himself is performed not only based on the physical examination result of the user himself, but also the guard inspection of the family members such as the supported person. Therefore, the examination data can be continuously acquired not only by the person who has received the physical examination but also by the family member such as the foster, and advice concerning the health status can be made to the family member of the user.

That is, the control unit of the inference system according to the present embodiment receives input of examination data measured in daily life by the 1 st device or the like or a diagnosis result in a diagnosis/examination institution (see S1), determines a device for examination so that examination data (sensor) can be continuously acquired every day when a specific symptom or sign of the symptom is present (see S6), and collects examination data from the determined device (see S7). When the specific symptom is related to the lifestyle, information is collected on family members having the same lifestyle, such as spouses and children (fosters) (see S9 and S11). In addition, in the case where a specific symptom is genetically related, information is collected on family members (fosters) having a blood relationship (see S13 and S15).

Next, a modified example of the operation of the control unit will be described with reference to the flowcharts shown in fig. 8A and 8B. This flow is realized by the CPU provided in the control unit 9b in the diagnosis/inspection means 9 operating in accordance with a program stored in the memory and controlling the entire inference system. In the example shown in fig. 5A and 5B, when the user receives a physical examination or the like, the main processing is to perform a new "diagnosis". In the example shown in fig. 8A and 8B, when a new "diagnosis" is made by physical examination or the like, the diagnosis/examination mechanism 9 performs a guard examination.

When the flow of the control unit shown in fig. 8A and 8B is started, it is first determined whether new "diagnosis" information is acquired (S61). In the diagnosis/examination mechanism 9, a doctor may make a diagnosis to confirm a new disease or the like by examination data, inquiry, or the like at the time of physical examination or examination. In this step, the control unit 9b determines whether or not information indicating that a new diagnosis is made by a doctor or the like is input. When the doctor records the information in the electronic medical record, the doctor may automatically notify the control unit 9b of the information.

When it is determined that new "diagnosis" information is acquired as a result of the determination in step S61, it is next determined whether lifestyle habits are important and nursing is recommended for family members (S63). If the cause of the diagnosed disease is lifestyle habit and treatment is performed, lifestyle improvement may be performed. In the case where lifestyle habits are greatly related to diseases, not only the person who has received a diagnosis but also family members may have lifestyle habits similar to those of the person. Therefore, in this step, the control unit 9b determines whether or not lifestyle habits are important when searching for the cause of a disease or performing treatment, and determines whether or not to recommend a guard check including the family members of the individual who has received the diagnosis when lifestyle is important.

In the case where the result of the determination in step S63 is a guard check of the recommended family member, it is next determined whether the available device of the individual/family member is in the DB (S65). Regarding the disease condition related to "diagnosis" acquired in step S61, the control section 9b determines from the record of the DB section 8a through the control section 1 as to whether or not the inspection device used in the guard inspection for observing the passing state is available for the user himself or herself or a family member. As described above, as shown in fig. 2, the DB unit 8a stores devices that can be used for each ID.

In the case where the device is recorded in the DB as a result of the determination in step S65, collection of personal history is then started inclusively including family members (S67). Here, the control unit 9b collects, by the control unit 1, inspection data of individuals and family members from available inspection devices (any of the 1 st device 2a, the 2 nd device 2b, the 3 rd device 3, and the like) recorded in the DB unit 8a, and records the data in the DB unit 8a (see fig. 3). When the collection of the history data is started, it returns to step S61.

On the other hand, in the case where the device is not recorded in the DB as a result of the determination in step S65, or in the case where the guard check of family members is not recommended as a result of the determination in step S63, it is next determined whether there is a device available to the user himself or herself in the DB (S69). As a result of the determination in step S65, the DB unit 8a does not store any check device used for the guard check of the user himself or herself and the family member, and as a result of the determination in step S63, the guard check of the family member is not required. Devices that the user himself or herself can use are sometimes recorded in the DB unit 8 a. Therefore, the control unit 9b determines whether or not the DB unit 8a is recorded as a usable device of the user himself.

If the result of the determination in step S69 is that a device that can be used for an individual is recorded in the DB, then collection of individual history is started (S71). Here, the control unit 9b collects the inspection data of the user himself/herself from the available inspection devices (any of the 1 st device 2a, the 2 nd device 2b, the 3 rd device 3, and the like) recorded in the DB unit 8a, and records the inspection data in the DB unit 8a (see fig. 3). When the collection of the history data is started, the process returns to step S61.

On the other hand, in the case where the device that the user himself or herself can use is not recorded in the DB as a result of the determination in step S69, a device use suggestion is made next (S73). Since the personal inspection device for performing the guard inspection is not recorded in the DB unit 8a, the control unit 9b can suggest what kind of device the user himself uses via the terminal 4. In addition, when the family member guard check is recommended in step S63, it is only necessary to suggest what kind of device the family member uses, and the suggestion is made via the terminal 4 (if it is for the family member, the terminal for the family member). When the recommendation is made, return is made to step S61.

If the new "diagnosis" information is not acquired as a result of the determination in step S61, it is determined whether a sufficient amount of data has been accumulated (S81). As described above, since the guard check is started in step S67 or S71, the DB unit 8a records history data for each ID. Here, the control unit 9b determines whether or not sufficient history data of the user himself/herself, or the user himself/herself and the family member, who is the object of determination in step S63 is accumulated. If a sufficient amount of data has not been accumulated as a result of the determination, the process returns to step S61 to continue the accumulation of data.

If a sufficient amount of data has been accumulated as a result of the determination in step S81, it is next determined whether or not a corresponding inference model can be specified (S83). There are a plurality of inference models set in the inference engine 7. The control unit 9b determines whether or not an optimal inference model that can correspond to the medical condition of the user himself or a family member can be selected from the plurality of inference models, taking into account the medical condition, the examination device, and the like, based on the data input to the inference engine 7 and the content of the output to be acquired. In the case where the inference model cannot be specified, the flow returns to step S61.

In the case where the inference model can be specified as a result of the determination in step S83, inference is then performed using the data history (S85). Here, the control section 9b sets the corresponding inference model designated in step S83 to the inference engine 7. Then, the control unit 9b inputs the history data recorded in the DB unit 8a to the inference engine 7, and acquires an inference result based on the corresponding inference model.

When the inference is performed in step S85, the inference result is output to the person (S87), and a supplementary suggestion of the inference result is made (S35). Here, the control unit 9b outputs the inference result acquired in step S31 to the terminal 4 owned by the individual (user). When the inference result is transmitted, the control unit 9b also transmits a supplementary advice based on the inference result to the terminal 4. Since the inference result and the supplementary advice are displayed on the display portion of the terminal 4, the user can know the health state associated with the disease based on the physical examination result. In steps S87 and S89, the controller 9b may display the inference result on the terminals of the family members, instead of being limited to individuals. When steps S87, S89 are executed, the process returns to step S61.

As described above, in the modified example of the operation of the control unit, when a doctor makes a new diagnosis in physical examination, medical examination, or the like (see "yes" at S61), when a disease state related to the diagnosis relates to a lifestyle habit, it is determined whether or not a guard check is recommended for a family member, not only by the user himself (S63). Lifestyle diseases and the like are not limited to the user himself, and family members may have the lifestyle diseases, and therefore the scope of the lifestyle diseases is extended to family members to acquire examination data and to reason for health conditions. That is, in the present modification, the medical examination data can be continuously acquired for family members and the like, as well as for the person who has received the medical examination.

In this modification, genetic disorders are not described. However, it is needless to say that, in the same manner as the flowchart shown in fig. 5A, in the case of a hereditary disease, a guard check may be recommended for family members having a relationship with blood.

Next, an example of inference in the inference engine 7 will be described with reference to fig. 9. The inference shown in fig. 9 shows an example of a case where inference is performed in consideration of information of family members, not only of the user himself. In this modification, the sensor information 21a and the examination result 21b are input to the input layer 7a of the inference engine 7. As 1 trend of the recent deep learning, there is machine learning in which specific data and other kinds of data are combined, and it is called multi-pattern learning that uses a plurality of different pieces of information. In the present embodiment, it is assumed that an inference model obtained by learning so that a correct result appears by inputting, in addition to the sensor information 21a, other information 21b as training data is used.

The sensor information 21a is inspection data collected by the control unit 1(ID determination unit 1b) from the designated inspection apparatuses (1 st apparatus 2a, etc.) (S6, S7, S11, S15 in fig. 5A, and S65 to S71 in fig. 8A). The examination results 21b are the examination results of the person and/or the family member and/or the medical history of the family member. The examination result 21b may be extracted from the ID history data recorded in the DB unit 8a, or may refer to the data recorded in the user information unit 10.

When the sensor information 21a and the examination result 21b are input to the input layer 7a, the intermediate layer 7b of the inference model performs inference and outputs an inference result 23a to the output layer 7 c. Family member information is taken into account in the inference result 23 a. That is, since the information is input and the inference is performed not only by the examination data and the examination result of the person but also by the examination data and the examination result of the family member, the inference including the status of the family member can be performed. For example, in the case of lifestyle-related diseases, although family members show disorders of lifestyle-related diseases, there is a possibility that inference is made that the potential lifestyle-related diseases of oneself is high in the case that oneself does not show disorders of lifestyle-related diseases.

As described above, the inference model shown in fig. 9 is input not only by the person himself but also by data of family members (data that may change depending on the constitution or the like affected by genetics, lifestyle habits, environment, and the like), and therefore, it is possible to perform highly accurate inference. Further, the advice can be made not only by the person but also by the family members. For example, information that a close person such as "being a constitution which easily becomes good quality" also becomes a reference may be included.

As shown in fig. 9, an inference model capable of inputting various data is also effective in inferring an infectious disease. For example, in the case of a local disease or a disease affected by the environment, which may be more likely to occur when entering a specific region, it is sometimes important to pay attention to the state of a symptom ranging from a specific slightly hot state to an acute high-hot state. The following countermeasures can be taken: the physical strength is enhanced before deterioration based on time-series data of body temperature and entry information (which can be acquired by a GPS or the like mounted on the mobile terminal) to a specific area. In a health examination or a hospital visit, there are cases where no symptom appears before deterioration, and in order to detect such a symptom, it is sufficient to determine the wearable thermometer as a guard sensor. When the patient is first taken to a hospital and examined, the system according to the present embodiment is characterized in that: a medical examination result of a specific person is inputted, a specific diagnosis result that is suspected is determined, a symptom that depends on heredity (which may be easily affected by the race) or lifestyle (which may be a disease that does not deteriorate when resting quietly) is extracted, and a determination unit that determines a guarding sensor corresponding to the symptom is prepared.

Next, an outline of the setting (sensor determination) of the inspection equipment in the present embodiment will be described with reference to fig. 10 and 11. Fig. 10 shows the input-output relationship of inference in the inference engine 7, and fig. 11 is a flowchart showing the action of setting of the inspection apparatus.

The operation of the sensor setting (setting of the inspection equipment) will be described with reference to a flowchart shown in fig. 10. When the sensor setting operation shown in fig. 10 is started, health check information is acquired first (S91). Here, the control unit 1 acquires information when the doctor has performed the health examination during the physical examination or the examination (corresponding to S61 in fig. 8A). If the health check information cannot be acquired, the control unit 1 enters a standby state until it is acquired.

When the health check information is acquired, it is next determined whether it is a specific diagnosis (S93). Here, the control unit 1 determines whether or not the diagnosis is the specific diagnosis based on the information acquired in step S91. The specific diagnosis is to determine a disease such as lifestyle-related disease by an inquiry or the like when physical examination data has a value different from a healthy state. The processing in step S93 corresponds to the processing in S3 of fig. 5A and S61 of fig. 8A. If no specific diagnosis is made, the flow ends.

When it is determined that the diagnosis is specific in step S93, symptoms depending on lifestyle habits and the like are then extracted (S95). As a cause of specific diagnosis, symptoms such as lifestyle-related diseases may occur. Here, if a symptom depending on the lifestyle habit occurs, the control portion 1 extracts the symptom. The extraction of the symptom corresponds to the processing in S5 of fig. 5A and S61 of fig. 8A. In addition, not only lifestyle habits but also hereditary symptoms may be extracted, and lifestyle and hereditary symptoms may be extracted.

The lifestyle habits are not limited to long-term habits in a broad sense, and include short-term lifestyle habits. For example, in the case of a disease which is easily affected by a short span such as overload work or a state of rest, a life pattern in a unit of one day, two days to one week or two weeks may be included and referred to as a lifestyle habit. A situation in which sleep is insufficient due to a nursing care, an emergency disaster, an evacuation life, and a work of a family member has a large influence on health, and therefore, even a short period of time is referred to as a lifestyle habit herein.

When the symptom is extracted, family member search is then performed (S97). Here, the control unit 1 retrieves the family member of the person from the DB unit 8 a. As described above, the DB unit 8a stores information on the person himself and family members such as the person being supported. The family member search corresponds to the processing in S9 of fig. 5A and S65 of fig. 8A. In the case where the family member is not found as a result of the family member search, the process proceeds to the next step S99 as the principal alone.

When the family member is searched and the family member is found, the family member sensor is set (S99). Here, the control unit 1 sets a checking device for the family member (sensor for the family member) for performing a guard check of the family member. When the sensor is set, the control section 1 (information providing section 1c) collects the check data of the family member from the check device (from the device specified as the sensor out of the 1 st device 2a, the 2 nd device 2b, and the 3 rd device 3). In addition to the family members, personal examination data may be collected. The sensor settings correspond to S11 in fig. 5A and S67 in fig. 8A. When the inspection device (sensor) for the family member is set, the flow is terminated.

Thus, the flow of sensor setting shown in fig. 10 has the following steps: a step (S91) for inputting a physical examination result of a specific person; a step (S93) for determining a specific diagnosis result obtained by performing a specific diagnosis among the physical examination results; a symptom extraction step (S95) of extracting a symptom depending on heredity and/or lifestyle in a specific diagnosis result; and a step (S97) for determining a guard sensor corresponding to the life information corresponding to the extracted symptom. Therefore, in the present embodiment, not only the person who has received the physical examination but also the family member or the like can determine the sensor for acquiring the physical examination data so that the physical examination data can be continuously acquired.

In addition, the following steps may be added to the flow of sensor setting: detecting ID information of a specific person; and advising the family members determined according to the ID information to acquire information of the guard sensor.

Next, an example of inference in the inference engine 7 will be described with reference to fig. 11. The inference results in an inference that takes into account the information of the family members. In this modification, the examination result 21c is input to the input layer 7a of the inference engine 7. The examination result 21c is, for example, a result of examination performed by a doctor during physical examination and examination as in S61 of fig. 8A. Note that, in step S91 in fig. 10 and step S1 in fig. 5A, the examination result 21c is the acquired data or the like. Of course, the physician's 168 diagnostic results may also be entered.

When the examination result 21c is input to the input layer 7a, the intermediate layer 7b of the inference model performs inference, and outputs an inference result 23b to the output layer 7 c. The inference result 23b is a sensor for determining the degree of influence of the family member and outputting the setting. The inference result 23b takes into account the influence of the family members. That is, reasoning is performed in consideration of family membership, not only of the examination result of the person. For example, in the case of lifestyle-related diseases, when a family member shows a lifestyle-related disease but the person does not show a lifestyle-related disease, there is a possibility that an inference that the person is highly likely to have a potential lifestyle-related disease may be made.

As described above, the inference model shown in fig. 11 infers not only the person but also the degree of influence of the family member, and thus can make an accurate inference.

Next, another example of the sensor setting will be described with reference to a flowchart shown in fig. 12. In this example, steps S91, S93, and S95 are the same as the flowchart of fig. 10, and steps S97 and S99 are replaced with step S98. Therefore, the description will be centered on step S98.

When the health check information is acquired (S91), a specific diagnosis result is determined (S93), and lifestyle-dependent symptoms are extracted (S95). When the symptom is extracted, the guard sensor is then decided (S98). The control unit 1 sets an inspection device (sensor for family members) for the person to perform the self-guardian inspection. When the sensor is set, the control unit 1(ID determination unit 1b) collects the inspection data of the person from the inspection device (the device designated as the sensor from among the 1 st device 2a, the 2 nd device 2b, and the 3 rd device 3). Of course, as shown in fig. 10, examination data of family members may be collected in addition to the principal person. In addition, the present invention is not limited to lifestyle, and a sensor may be determined by extracting a hereditary symptom. The information on the health examination in step S91 is not limited to the diagnosis by a doctor during physical examination or examination, and may be information from an examination apparatus used by the user on a daily basis. When the inspection device (sensor) for the person is set, the present flow is ended.

Thus, the flow of sensor setting shown in fig. 12 has the following steps: a step (S91) for inputting a physical examination result of a specific person; a step (S93) for determining a specific diagnosis result obtained by performing a specific diagnosis among the physical examination results; a symptom extraction step (S95) of extracting a symptom depending on heredity and/or lifestyle in a specific diagnosis result; and a step (S98) for determining a guard sensor corresponding to the life information corresponding to the extracted symptom. Therefore, when a diagnosis is made based on examination data, physical examination, and medical examination in daily life, a sensor for acquiring the examination data can be determined so that the examination data can be continuously acquired.

As described above, in one embodiment and the modification thereof of the present invention, the physical examination result of a specific person is input (for example, S3 in fig. 5A), a specific diagnosis result obtained by performing a specific diagnosis among the physical examination results is determined, a symptom depending on heredity or lifestyle habit among the specific diagnosis result is extracted (for example, S5 in fig. 5A), and a guard sensor corresponding to the extracted symptom is determined (for example, S6 in fig. 5A). Therefore, for the person who has received the physical examination, a sensor for acquiring the examination data can be determined so that the examination data can be continuously acquired.

In one embodiment and a modification thereof of the present invention, a person to be supported of a specific person is determined, and a guard sensor corresponding to the extracted symptom is determined for the determined person to be supported (see, for example, S9 and S11 in fig. 5A). Therefore, not only for the person himself, but also for the family member and the like, the sensor for acquiring the inspection data can be determined so that the inspection data can be continuously acquired.

In one embodiment and a modification thereof of the present invention, the control unit 1 and the like are information processing devices having a program and executing the program, and the program includes the steps of: a determination step (see, for example, S3 in fig. 5A) of acquiring a physical examination result and determining a specific diagnosis result obtained by performing a specific diagnosis; a symptom extraction step (for example, refer to S5 of fig. 5A) of extracting a symptom depending on heredity or lifestyle in a specific diagnosis result; and a determination step (see, for example, S6 in fig. 5A) of determining a guard sensor corresponding to the extracted symptom. Then, the information processing apparatus transmits a result of the physical examination result of the specific person being input to the information terminal (for example, the terminal 4 in fig. 1). The information processing apparatus may be a server having the control unit 1, or may be a server in another unit such as the diagnosis/examination unit 9. According to the system including the information processing device, an enterprise performing health examination or the like can transmit information based on the health examination result of the specific person and the data collected by the guard sensor to the information terminal, and the specific person can easily confirm the information related to health.

In the embodiment and the modification of the present invention, the guardian examination is performed not only on the person who has received the diagnosis but also on the person who is supported or the blood related person. However, the guardian examination may be performed only on the person concerned, or may be performed only on the person to be supported or the blood related person.

In the embodiment and the modification of the present invention, the control unit 1 is explained as an IT device including a CPU, a memory, an HDD, and the like. However, in addition to being configured by software by a CPU and a program, a part or all of each unit may be configured by a hardware circuit, or a hardware configuration such as a gate circuit generated from a program language described in a hardware description language (Verilog), or a hardware configuration using software such as a DSP (Digital Signal Processor) may be used. They may of course also be combined appropriately.

The control unit 1 is not limited to the CPU, and may be any element that functions as a controller, and the processing of each unit may be performed by 1 or more processors configured as hardware. For example, each unit may be a processor configured as an electronic circuit, or each circuit unit in a processor configured as an integrated circuit such as an FPGA (Field Programmable Gate Array). Alternatively, the processor including 1 or more CPUs may read and execute a computer program recorded in a recording medium to execute the functions of the respective units.

In many parts of the present embodiment, the description has been made as an improvement of a health management system using biological information. However, in addition to the health management system, unexpected situations may occur in a research site, an examination site, and a work site in the scientific and industrial fields, and the present embodiment can be applied to an examination apparatus and the like used in these fields. In addition, when recording images and sounds using a camera or a smartphone, if an unknown object performs some kind of inference on the image and sound recording, a previous inference model cannot be used, and a new inference model is necessary. As described above, it is sometimes desired to acquire data of an unknown object or the like and use the acquired data, and it is needless to say that the present embodiment can be applied to these applications.

In addition, in the technique described in the present specification, the control mainly described in the flowchart may be set by a program in many cases, and may be stored in a recording medium or a recording unit. The method of recording to the recording medium or the recording unit may be recorded at the time of product shipment, may be performed using a distributed recording medium, or may be downloaded via the internet.

In addition, although the operations in the present embodiment are described using the flowchart in one embodiment of the present invention, the order of the processing procedures may be changed, arbitrary steps may be omitted, steps may be added, and specific processing contents in the steps may be changed.

In the operation flows in the claims, the description, and the drawings, the description is made using words such as "first", "next", and the like in order for convenience, but the description does not mean that the operations are necessarily performed in this order in a portion not specifically described.

The present invention is not limited to the above embodiments, and can be embodied by modifying the components in the implementation stage without departing from the gist thereof. In addition, various inventions can be formed by appropriate combinations of a plurality of constituent elements disclosed in the above embodiments. For example, several components may be deleted from all the components disclosed in the embodiments. Further, the constituent elements of the different embodiments may be appropriately combined.

Description of the reference symbols

1: a control unit; 1 a: a communication control unit; 1 b: an ID determination unit; 1 c: an information providing unit; 1 d: a reasoning model specification determining section; 1 e: an inference commission unit; 1 f: a search unit; 1 g: a foster person determination section; 2 a: 1, equipment; 2a 1: category information; 2 b: a 2 nd device; 2b 1: category information; 3: a 3 rd device; 3a 1: category information; 4: a terminal; 5: a learning unit; 5 a: an input/output modeling unit; 5 b: a specification comparison unit; 6: a learning committing unit; 6 a: a recording unit; 6 b: an object type A image group; 6 c: training data; 6 d: a specification setting unit; 6 e: a communication unit; 6 f: a control unit; 7: an inference engine; 8: a DB part; 8 a: a history list of each ID; 9: a diagnostic/inspection mechanism; 9 a: a DB part; 9 b: a control unit; 10: a user information section; 10 a: and a DB part.

Claims (16)

1. A sensor determination device, characterized in that,

the sensor determination device includes:

an input unit for inputting a result of physical examination of a specific person;

a determination unit that determines a specific diagnosis result obtained by performing a specific diagnosis among the physical examination results;

a symptom extraction unit that extracts a symptom that depends on heredity or lifestyle in the specific diagnosis result; and

and a determination unit configured to determine a guard sensor corresponding to the extracted symptom.

2. The sensor determination device according to claim 1,

the specific diagnosis result is a diagnosis result that is abnormal for a specific examination item at the time of the physical examination.

3. The sensor determination device according to claim 1,

the symptom extraction unit extracts the specific diagnosis result by searching a database in which the specific diagnosis result is associated with a cause thereof, and the like.

4. The sensor determination device according to claim 1,

the guard sensor is extracted by searching a database in which the specific diagnosis result is associated with the cause thereof and the like.

5. The sensor determination device according to claim 1,

the sensor determination device includes an information providing unit capable of graphically displaying information detected by the guard sensor on an information terminal associated with the specific person.

6. The sensor determination apparatus according to claim 1,

the sensor determination device includes:

an inference unit that infers a health advice from a detection result of the guard sensor; and

and a display control unit for enabling display of a result obtained by performing the inference.

7. The sensor determination device according to claim 1,

the sensor determination device has an inference unit for inferring a health advice based on a detection result of the guard sensor,

the inference unit reflects the life information corresponding to the symptom extracted by the symptom extraction unit at the time of the inference.

8. The sensor determination device according to claim 1,

the sensor determination device has a supported person determination unit that determines a supported person of the specific person,

the determination unit determines a guard sensor corresponding to the extracted symptom for the person to be supported determined by the person to be supported determination unit.

9. The sensor determination apparatus according to claim 8,

the sensor determination device has a1 st recording part for recording the inspection equipment which can be used by the specific person and the fostered person,

the determination unit determines the guard sensor from the inspection devices recorded in the 1 st recording unit.

10. The sensor determination apparatus according to claim 1,

the sensor determination device includes a blood-related person determination unit that searches for a person having a blood-related relationship with the specific person,

the determination unit determines a guard sensor corresponding to the extracted symptom for the blood-related person retrieved by the blood-related person determination unit.

11. The sensor determination apparatus according to claim 10,

the sensor determination device comprises a 2 nd recording unit for recording the examination equipment which can be used by the specific person and the blood vessel,

the determination unit determines the guard sensor from the inspection devices recorded in the 2 nd recording unit.

12. The sensor determination device according to claim 1,

the input unit inputs a result of physical examination based on the physical examination or examination received by the specific person.

13. The sensor determination device according to claim 1,

the input unit inputs examination data from an examination device so that the specific person measures the health status.

14. A sensor determination method is characterized in that,

the sensor determination method includes the steps of:

an input step of inputting a physical examination result of a specific person;

a determination step of determining a specific diagnosis result obtained by performing a specific diagnosis among the physical examination results;

a symptom extraction step of extracting a symptom depending on heredity or lifestyle in the specific diagnosis result; and

a determination step of determining a guard sensor corresponding to the extracted symptom.

15. A recording medium having a sensor determination program recorded thereon for causing a computer to execute the sensor determination program, the sensor determination program having the steps of:

an input step of inputting a physical examination result of a specific person;

a determination step of determining a specific diagnosis result obtained by performing a specific diagnosis among the physical examination results;

a symptom extraction step of extracting a symptom depending on heredity or lifestyle in the specific diagnosis result; and

a determination step of determining a guard sensor corresponding to the extracted symptom.

16. A sensor determination system, characterized in that,

the sensor determination system comprises an information terminal for transmitting a result of a physical examination of a specific person to an information processing device having a program and executing the program,

the procedure has the following steps:

a determination step of obtaining a physical examination result and determining a specific diagnosis result obtained by performing a specific diagnosis;

a symptom extraction step of extracting a symptom depending on heredity or lifestyle in the specific diagnosis result; and

a determination step of determining a guard sensor corresponding to the extracted symptom.

Images