System for predicting change in symptom of living body, information processing device, and method for predicting change in symptom of living body

Abstract

The purpose of the present invention is to predict a change in symptoms of an organism due to environmental factors with a small amount of data. The present invention is a biological symptom change prediction system (100) provided with an environmental sensor (11) that detects environmental factor data relating to environmental factors of a subject space, and an information processing device (60) that has a control unit that controls the environmental sensor (11), the information processing device (60), and the environmental sensor (11) detects environmental factor data relating to environmental factors of the subject space. And a control unit that converts the environmental factor data into intermediate data by means of a model that simulates biological characteristics relating to symptoms with respect to the environment, and that uses correspondence information that associates at least the intermediate data with the likelihood of changes in the symptoms with respect to the environment. A likelihood of the symptom change is predicted from the intermediate data.

Description

Technical Field

[0001] The present invention relates to a system for predicting symptom changes in an organism, an information processing apparatus, and a method for predicting symptom changes in an organism. Background Art

[0002] It is known that symptoms of humans such as asthma and allergic symptoms change due to environmental factors (e.g., temperature, humidity, CO2, PM2.5, TVOC, formaldehyde, etc.). If symptom changes in a human can be predicted to some extent based on environmental factor data, it is possible for a patient to avoid the environment, or to perform environmental control in advance to create an environment that improves the symptoms of the human.

[0003] There is known a technique for detecting a situation that may exacerbate a chronic disease and recommending an action or the like based on the detection result (e.g., see Patent Document 1). Patent Document 1 discloses a technique for detecting a situation that may exacerbate a chronic disease based on physiological data and environmental factor data, and recommending a preferable action and medication based on the detection result.

[0004] <Prior Art Documents>

[0005] <Patent Documents>

[0006] Patent Document 1: Japanese Patent No. 6987042 Summary of the Invention

[0007] <Problems to be Solved by the Invention>

[0008] However, in order to generate corresponding information for predicting symptom changes in an organism from environmental factor data by machine learning or the like, a huge amount of data is required. This is because when a human is affected by the environment, there are some internal reactions and changes, and as a result, symptoms are generated, and the symptoms rarely have a simple linear relationship with the environment.

[0009] The present invention provides a technique for predicting symptom changes in an organism due to environmental factors with less data.

[0010] <Means for Solving the Problems>

[0011] A first aspect of the present invention is a system for predicting symptom changes in an organism having an environmental sensor and an information processing apparatus, wherein

[0012] the environmental sensor detects environmental factor data related to environmental factors in a target space,

[0013] the information processing apparatus has a control unit that transforms the environmental factor data into intermediate data through a model that simulates an organism characteristic associated with symptoms with respect to the environment,

[0014] The control unit uses correspondence information that at least correlates the intermediate data with the likelihood of symptom changes with respect to the environment, and predicts the likelihood of symptom changes based on the intermediate data.

[0015] According to the first aspect of the present invention, it is possible to predict human symptom changes due to environmental factors with less data.

[0016] In the second aspect of the present invention, in the symptom change prediction system according to the first aspect,

[0017] The model simulating the biological characteristics is the Weber-Fechner law.

[0018] In the third aspect of the present invention, in the symptom change prediction system according to the first aspect,

[0019] The model simulating the biological characteristics is a model that outputs different intermediate data according to the range of values of the environmental factor data or whether the environmental factor data satisfies a condition.

[0020] In the fourth aspect of the present invention, in the symptom change prediction system according to the first aspect,

[0021] The model simulating the biological characteristics is a model that outputs intermediate data corresponding to an increase amount or a decrease amount only when the change in the environmental factor data changes in one direction of increase or decrease, or a model that outputs intermediate data that changes according to the value of the nth derivative.

[0022] In the fifth aspect of the present invention, in the symptom change prediction system according to the first aspect,

[0023] The model simulating the biological characteristics is a model that outputs intermediate data corresponding to the cumulative value of the environmental factor data, or intermediate data that is different according to the change history of the past values of the environmental factor data even when the current value of the environmental factor data is the same.

[0024] In the sixth aspect of the present invention, in the symptom change prediction system according to the first aspect,

[0025] The model simulating the biological characteristics is a model that outputs intermediate data corresponding to the duration of the environmental factor data remaining within a given range, or the number of times the environmental factor data repeats within a given range.

[0026] In the seventh aspect of the present invention, in the symptom change prediction system according to the first aspect,

[0027] The model simulating the biological characteristics is a model that outputs intermediate data that changes after a given time has elapsed since the time when the environmental factor data was generated.

[0028] In the eighth aspect of the present invention, in the symptom change prediction system according to the first aspect,

[0029] The model simulating the biological characteristics is a log function, an exponential function, or an n-th power function that takes the environmental factor data as input and the intermediate data as output.

[0030] In the ninth aspect of the present invention, in the symptom change prediction system according to any one of the first to eighth aspects,

[0031] The control unit uses corresponding information in which the environmental factor data is also correlated, and predicts the possibility of the symptom change based on the intermediate data and the environmental factor data.

[0032] In the tenth aspect of the present invention, in the symptom change prediction system according to any one of the first to ninth aspects,

[0033] The possibility of the symptom change is the possibility of deterioration or improvement of any one of allergic symptoms, asthma symptoms, meteorological diseases, infectious diseases, sleep quality decline, wakefulness decline / sleepiness, autonomic nerve disorder, debility, dementia / delirium, memory decline, motor function decline, heat stroke, motion sickness, or VR dizziness.

[0034] In the eleventh aspect of the present invention, in the symptom change prediction system according to any one of the first to tenth aspects,

[0035] The environmental factor data is a statistic obtained by statistical processing.

[0036] In the twelfth aspect of the present invention, in the symptom change prediction system according to the ninth aspect,

[0037] The control unit predicts the possibility of the symptom change based on the actually measured environmental factor data and the intermediate data, or the predicted value of the environmental factor data and the intermediate data.

[0038] In the thirteenth aspect of the present invention, in the symptom change prediction system according to any one of the first to twelfth aspects,

[0039] Using the symptom change information reported on asthma symptoms, allergic symptoms, meteorological diseases, infectious diseases, sleep quality decline, wakefulness decline / sleepiness, autonomic nerve disorder, debility, dementia / delirium, memory decline, motor function decline, heat stroke, motion sickness, or VR dizziness as teacher data, the corresponding information is generated by using a machine learning method.

[0040] In the fourteenth aspect of the present invention, in the symptom change prediction system according to the thirteenth aspect,

[0041] The control unit uses the method of machine learning to generate first corresponding information, taking the intermediate data as an explanatory variable and the symptom change information declared by multiple people as teacher data.

[0042] And the control unit uses the method of machine learning to generate second corresponding information, taking the intermediate data as an explanatory variable and the symptom change information declared by an individual as teacher data.

[0043] The control unit predicts the possibility of an individual's symptom change based on the possibilities of symptom changes predicted by the first corresponding information and the second corresponding information respectively.

[0044] In a fifteenth aspect of the present invention, in the symptom change prediction system according to the thirteenth or fourteenth aspect,

[0045] The control unit generates the corresponding information for each season, each target disease, or each allergen in allergic symptoms, and predicts the possibility of the symptom change based on the corresponding information generated for each season, each target disease, or each allergen.

[0046] In a sixteenth aspect of the present invention, in the symptom change prediction system according to any one of the first to fifteenth aspects,

[0047] The control unit displays the intermediate data and the possibility of the symptom change on the same screen.

[0048] A seventeenth aspect of the present invention is an information processing device, wherein,

[0049] The information processing device receives environmental factor data related to environmental factors of an object space from the environmental sensor.

[0050] The information processing device has a control unit that transforms the environmental factor data into intermediate data through a model that simulates the biological characteristics associated with symptoms relative to the environment.

[0051] The control unit uses at least the corresponding information that correlates the intermediate data with the possibility of symptom change relative to the environment, and predicts the possibility of the symptom change based on the intermediate data.

[0052] According to the seventeenth aspect of the present invention, it is possible to predict the symptom change of an organism caused by environmental factors with less data.

[0053] An eighteenth aspect of the present invention is a symptom change prediction method performed by a symptom change prediction system of an organism having an environmental sensor and an information processing device, wherein,

[0054] The environmental sensor detects environmental factor data related to environmental factors in the object space.

[0055] The control unit performs the following processing:

[0056] Processing of transforming the environmental factor data into intermediate data through a model that simulates biological characteristics associated with symptoms relative to the environment; and

[0057] Processing of predicting the possibility of symptom change based on the intermediate data using at least correspondence information that correlates the intermediate data with the possibility of symptom change.

[0058] According to the eighteenth aspect of the present invention, it is possible to predict symptom changes in an organism due to environmental factors with less data. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 FIG. is a diagram showing an overview of the system configuration and prediction method of an example of a human symptom change prediction system.

[0060] Figure 2 FIG. is a diagram showing a modified example of the system configuration of a human symptom change prediction system.

[0061] Figure 3 FIG. is a diagram showing an example of the system configuration of a human symptom change prediction system.

[0062] Figure 4 FIG. is a diagram showing an example of the hardware configuration of an information processing device.

[0063] Figure 5 FIG. is an example of a functional block diagram that explains the functions of the information processing device in the learning stage in a block-by-block manner.

[0064] Figure 6 FIG. is an example of a diagram showing environmental factor data acquired by an environmental factor data acquisition unit.

[0065] Figure 7 FIG. is a diagram explaining the learning stage of generating a mathematical model based on the statistic of environmental factor data, the sensory intensity (explanatory variable), and the symptom change information (target variable, teacher data).

[0066] Figure 8 FIG. is an example of a flowchart explaining the process of a learning method based on a gradient boosting decision tree.

[0067] Figure 9 FIG. is a schematic diagram of a decision tree.

[0068] Figure 10 FIG. is an example of a diagram showing the shapes of a log function, an exponential function, and an n-th function.

[0069] Figure 11 It is a diagram showing an example of the shapes of a step function, a sigmoid function, an IF function, and a function having values only in a specific range.

[0070] Figure 12 It is a diagram showing an example of the shape (tangent line) of the first derivative of a quadratic function.

[0071] Figure 13 It is a diagram showing an example of the relationship between time and environmental factor data (such as air pressure), and the relationship between time and intermediate data (such as the amount of physiological reaction related to meteorological diseases).

[0072] Figure 14 It is a diagram showing an example of the relationship between time and environmental factor data (such as the amount of pollen dispersal), and the relationship between time and intermediate data (such as the physiological reaction related to hay fever).

[0073] Figure 15 It is a diagram showing an example of the relationship between time and environmental factor data (such as air temperature), and the relationship between time and intermediate data (such as the amount of physiological reaction related to heat stroke).

[0074] Figure 16 It is a diagram showing an example of the relationship between time and environmental factor data (such as CO2 concentration), and the relationship between time and intermediate data (such as the amount of physiological reaction related to the decline in wakefulness).

[0075] Figure 17 It is a diagram showing an example of the relationship between time and environmental factor data (such as the amount of allergen), and the relationship between time and intermediate data (the amount of physiological reaction related to allergic symptoms).

[0076] Figure 18 It is a diagram showing an example of the relationship between time and environmental factor data (such as the amount of indoor dust), and the relationship between time and intermediate data (such as the amount of physiological reaction related to allergic symptoms).

[0077] Figure 19 It is a diagram showing the correspondence between environmental factor data (X-axis) and sensory intensity (Y-axis), and an example of a diagram showing the correspondence between environmental factor data and sensory intensity represented by two straight lines.

[0078] Figure 20 It is a diagram explaining the correspondence with the biological reaction by estimating the sensory intensity based on the environmental factor data.

[0079] Figure 21 It is an example of a functional block diagram explaining the functions of the information processing device in the prediction stage.

[0080] Figure 22This is a diagram showing the prediction stage of predicting the exacerbation risk by inputting environmental factor data and perceived intensity into the exacerbation risk prediction unit.

[0081] Figure 23 This is a diagram comparing the prediction accuracy when predicting the exacerbation risk of asthma without using perceived intensity with the prediction accuracy when predicting the exacerbation risk of asthma using perceived intensity.

[0082] Figure 24 This is a diagram showing an example of the map screen of the exacerbation risk displayed on the user terminal.

[0083] Figure 25 This is a diagram showing an example of the display of the perceived intensity and exacerbation risk screen displayed on the user terminal.

[0084] Figure 26 This is a diagram showing an example of environmental factor data and symptoms. Detailed implementation mode

[0085] Hereinafter, as an example of a method for implementing the present invention, a human symptom change prediction system and a human symptom change prediction method performed by the human symptom change prediction system will be described.

[0086] <Regarding intermediate data and human symptom changes>

[0087] The symptoms experienced by a person are affected by environmental factors. Symptoms include allergic symptoms, asthma symptoms, meteorological diseases, infectious diseases, decreased sleep quality (insomnia, waking up in the middle of the night, difficulty falling asleep, difficulty waking up), decreased wakefulness / somnolence, autonomic nervous system disorders, debility (weakness), dementia / delirium, memory loss, motor function decline, heat stroke, motion sickness, VR dizziness, etc. As described above, symptoms are not limited to diseases.

[0088] However, there is no simple linear relationship between the symptoms experienced by a person and environmental factors. The reason why it cannot be regarded as a simple linear relationship is that due to the influence of environmental factors, the human body will have some reactions and changes, and as a result, symptoms will occur. As is well known, the relationship between environmental factors and symptoms is a non-linear relationship and is very complex. Therefore, it requires a huge amount of data to create a model based on the relationship between the two through machine learning or the like.

[0089] Therefore, in the present embodiment, by using intermediate data representing the human body's response (symptoms) to environmental factors as explanatory variables, symptoms can be predicted with high precision using a better amount of data. The so-called intermediate data is a value that simulates the response related to the environmental factors that cause symptoms. Such intermediate data can be generated by a model (described later) that simulates biological characteristics. The model itself for generating intermediate data can simulate symptom characteristics. By transforming environmental factor data into intermediate data using a model that simulates biological characteristics, the accuracy of machine learning can be improved with a small number of samples.

[0090] In addition, in the present embodiment, the intermediate data is sometimes described using terms such as "sensation intensity". In addition, the change in symptoms is sometimes described using terms such as "aggravation risk".

[0091] As specific environmental factors, environmental factors related to the air quality in indoor, transportation, or outdoor areas (current situation: temperature, humidity, CO2, PM2.5, TVOC (total volatile organic compounds), formaldehyde, etc.) are known. Due to changes in environmental factors, the risk of aggravation of asthma or allergy symptoms sometimes increases. By aggravation, it means that diseases such as asthma or allergy symptoms deteriorate, cannot be improved by normal treatment, and the treatment content needs to be changed. By aggravation risk, it means the risk (possibility) of such a state occurring.

[0092] For example, a correlation between asthma and environmental factors is known. Asthma is a symptom that is considered to be caused by a very wide range of environmental factors. As environmental factors that cause asthma to worsen, PM2.5, VOC, SOx, NOx, fungi, mites, dust, strong odors / smoke, smoke, cold and dry air, hot air, etc. are known, and there are many of them.

[0093] The Ministry of Health, Labour and Welfare has announced standard values / recommended values for preferred environmental factors not only to suppress asthma.

[0094] Temperature (17°C to 28°C), humidity (40% to 70%), carbon dioxide concentration (1000 ppm or less), formaldehyde (0.08 ppm or less)

[0095] However, these standard values / recommended values are reference values for the presence or absence of health risks to the human body, and there are multiple factors that cause symptoms.

[0096] Therefore, according to experts, at present, no common countermeasures for all people with asthma or allergy symptoms have been found, and it is also difficult to determine the causes. Some patients do not have symptoms when seeing a doctor or undergoing inpatient examinations, but only have symptoms at home. In addition, self-medication at home is also said to be important.

[0097] Based on these actual situations, environmental factors that reduce asthma or allergy symptoms cannot be fully addressed by setting benchmark values for each factor. Additionally, it is considered important that the patient himself / herself can access the indoor environment, and the operability of environmental control is also important.

[0098] <Overview of the prediction method for exacerbation risk>

[0099] Figure 1 It is a diagram showing an overview of the system configuration and prediction method of an example of a human symptom change prediction system 100. The environmental device 10, the environmental sensor 11, the user terminal 70, and the information processing device 60 are communicably connected via the network N.

[0100] The environmental sensor 11 is preferably installed in each room of the building where the patient 9 with asthma or allergy symptoms lives. The environmental sensor 11 detects environmental factor data related to the environmental factors of the target space 7 where the patient 9 lives. The environmental sensor 11 can be installed only one in the building. The environmental device 10 is a device that controls the environment related to air quality, such as an air conditioner, a ventilation device, or an air purifier, etc. It is possible that the environmental device 10 has multiple functions, or it is possible that there are environmental devices 10 with each function separately.

[0101] The user terminal 70 is a terminal device that displays the map screen described later. In the user terminal 70, a Web browser or a local application is executed, and information for display on the display is received from the information processing device 60 via the network N. The patient 9 views the map screen and the like, and can grasp the environmental conditions that reduce or do not increase the exacerbation risk. The user terminal 70 can also be carried by the patient 9 and is not installed in the same space as the space where the environmental sensor 11 is installed.

[0102] The information processing device 60 is, for example, a server device that performs various information processing, provides services, and stores files. The information processing device 60 generates a mathematical model described later, and predicts the exacerbation risk by inputting the perceived intensity and environmental factor data into this mathematical model. The so-called perceived intensity is a variable representing the magnitude of the impact on a person caused by the change in the air quality environment becoming a stimulus.

[0103] (1) The environmental sensor 11 sends environmental factor data to the information processing device 60. In the learning stage of generating the mathematical model, further, the patient 9 self-reports symptom change information (such as deterioration, improvement, remission, improvement) from the user terminal 70 to the information processing device 60.

[0104] (2) The information processing device 60 inputs the perceived intensity and environmental factor data into the already generated mathematical model to predict the exacerbation risk. This mathematical model does not require vital data as described later, but uses the perceived intensity. The mathematical model is corresponding information that associates the perceived intensity with the exacerbation risk of asthma and allergy symptoms.

[0105] (3) The information processing device 60 sends a map screen with the weighted risk configured for the environmental factor data to the user terminal 70.

[0106] (4) The user terminal 70 displays the map screen, and shows in the map screen what kind of environmental settings will reduce or increase the weighted risk. By the user specifying the displayed environmental settings, the user terminal 70 sends the environmental settings to the information processing device 60.

[0107] (5) The information processing device 60 converts the environmental settings into the setting information of the environmental device 10 and sends it to the environmental device 10. Thereby, the environmental device 10 can control the air quality so that the weighted risk is reduced or not increased.

[0108] In this way, in the present invention, life data is not used in the prediction of the weighted risk. Specifically, in addition to the environmental factor data, "intermediate data (sensation intensity)" is also introduced as a variable (which can replace life data) representing the magnitude of the impact on people caused by the change in the air quality environment becoming a stimulus. Thereby, the weighted risk of symptoms can be predicted with high accuracy. In addition, by using a model that simulates the characteristics of the organism to convert the environmental factor data into intermediate data, the accuracy of machine learning can be improved with a small number of samples. Thereby, the patient 9 can avoid this environment, or can perform environmental control on the indoor environment that reduces the weighted risk.

[0109] <<Modification example of system structure>>

[0110] The environmental sensor 11 is not independent. As Figure 2 shown, the environmental sensor 11 can also be built into the indoor unit 10b. Figure 2 A modification example of the system structure of the human symptom change prediction system 100 is shown. The human symptom change prediction system 100 mainly includes one outdoor unit 10a as a heat source unit, one or more indoor units 10b as utilization units, and a remote control device (hereinafter referred to as "remote controller 12") as an input device for inputting instructions related to various settings.

[0111] The outdoor unit 10a and the indoor unit 10b are called air conditioners. The outdoor unit 10a and the indoor unit 10b are connected by a refrigerant communication pipe (gas communication pipe GP), thereby forming a refrigerant circuit. In addition, in the human symptom change prediction system 100, a plurality of communication networks (network NW1, network NW2) are constructed to function as signal transmission paths between the units. The network NW2 can be wired or wireless.

[0112] The remote controller 12 is a user interface for accepting settings such as temperature and humidity. The function of the information processing device 60 can be the same as Figure 1The same.

[0113] (1) An embedded environmental sensor 11 is installed in the indoor unit 10b. The indoor unit 10b sends environmental factor data to the outdoor unit 10a.

[0114] (2) The outdoor unit 10a sends environmental factor data to the information processing device 60.

[0115] (3) The information processing device 60 inputs the perceived intensity and environmental factor data into the generated mathematical model to predict the exacerbation risk.

[0116] (4) The information processing device 60 sends a map screen with the exacerbation risk configured for the environmental factor data to the remote controller 12 via the outdoor unit 10a and the indoor unit 10b.

[0117] (5) The remote controller 12 displays the map screen, which shows what environmental settings will reduce or increase the exacerbation risk. By specifying the displayed environmental settings by the user, the remote controller 12 sends the environmental settings to the indoor unit 10b.

[0118] (6) The indoor unit 10b converts the environmental settings into setting information for the air conditioner to control its own device. Thus, the environmental device 10 can control the air quality so as to reduce or not increase the exacerbation risk.

[0119] <System Structure of Human Symptom Change Prediction System>

[0120] Next, refer to Figure 3 to describe the system structure of the human symptom change prediction system 100. Figure 3 is a diagram showing an example of the system structure of the human symptom change prediction system 100.

[0121] The human symptom change prediction system 100 provides various IoT-utilized services from administrators to general users by enabling various devices 30 such as air conditioners and lighting to communicate with the information processing device 60 on the cloud side via the network N. The edge device 80, devices 30, sensor switches 53, and user terminals 70 are set on the customer side, and the information processing device 60 is set in the cloud such as a data center or the Internet. In addition, since the edge device 80 is a device that centrally manages the devices 30 and sensor switches 53, the edge device 80 may not be provided.

[0122] Device 30 refers to all devices that consume electricity, such as environmental device 10, security device, heat source device, fire alarm, AHU (air handling unit), electricity meter, lighting, etc. Sensor switch class 53 includes various sensors such as environmental sensor 11, lights, relays, etc. Device 30 and sensor switch class 53 are communicably connected to edge device 80 via a dedicated cable or a network such as LAN. Device 30 and sensor switch class 53 can also be communicably connected to edge device 80 through wireless communication.

[0123] Device 30 and sensor switch class 53 are controlled by edge device 80. In other words, edge device 80 performs the required operations on device 30 and sensor switch class 53 to meet the purposes of device 30 and sensor switch class 53. The content of control varies according to the types of device 30 and sensor switch class 53. However, for example, when device 30 is an air conditioner, it can include all controls related to the functions of the air conditioner, such as the cooling / heating mode, set temperature, air volume, humidity, air direction, etc. that can usually be set on the air conditioner. In addition, the control also includes operation modes such as the pre-season inspection dedicated mode, microcomputer reset, operation stop, and function substitution.

[0124] Device 30 collects operation data corresponding to device 30 and mainly sends it to edge device 80 regularly. The so-called regular, for example, is once per minute, once per 10 minutes, once per 60 minutes, etc., but it can also be set by the user or information processing device 60. In addition, at the request of edge device 80 or user terminal 70, device 30 can send operation data to edge device 80. The operation data varies according to device 30. For example, in the case of an air conditioner, there are various data such as the high-pressure pressure of the refrigerant, low-pressure pressure, refrigerant temperature, fan speed, and CPU temperature of the microcomputer.

[0125] In addition, when device 30 detects an abnormality, it sends an abnormality code to edge device 80. Device 30 that detects an abnormality stops operating. Edge device 80 sends the abnormality code to information processing device 60. Regarding sensor switch class 53, the processing of edge device 80 can be the same. Sensor switch class 53, for example, regularly sends various detection information such as the detected environmental factor data to edge device 80, or sends an abnormality code.

[0126] The edge device 80 is a controller for the control device 30 and the sensor switch class 53. In the absence of the edge device 80, the information processing device 60 controls the control device 30 and the sensor switch class 53. The edge device 80 has the functions of a control device for the control device 30 and the sensor switch class 53, an information processing device that processes operation data, etc., and a communication device that communicates with the information processing device 60. For example, the edge device 80 sends an abnormal code received from the device 30 to the information processing device 60 and receives an instruction corresponding to the abnormal code from the information processing device 60. Alternatively, even if the edge device 80 does not send any information to the information processing device 60, it receives an instruction from the information processing device 60 (for example, when there is an instruction from the user terminal 70 to the information processing device 60). The edge device 80 transforms the instruction into an appropriate instruction according to the models of the device 30 and the sensor switch class 53 and sends it to the device 30 and the sensor switch class 53.

[0127] The information processing device 60 may be one or more server devices. In Figure 3 one information processing device 60 is shown, but the information processing device 60 may be divided into several according to functions. In addition, the functions of the information processing device 60 may be integrated by one server device. Alternatively, the information processing device 60 may prepare multiple information processing devices with the same functions, and the multiple information processing devices 60 process while communicating like a server cluster.

[0128] The information processing device 60 inputs the sensory intensity and environmental factor data into a mathematical model to predict the aggravation risk and provides it to the user terminal 70, etc. The information processing device 60 can not only predict the aggravation risk for each facility such as a house and a building, but also predict the aggravation risk for each area, and can also share the aggravation risk for public announcements, etc. In addition, the information processing device 60 can provide an environmental setting optimal for the aggravation risk to the user terminal 70 by using the comprehensively prepared environmental factor data and aggravation risk. In addition, the information processing device 60 may also send an instruction for the device 30 to the edge device 80 according to a predetermined schedule or operation set by the user terminal 70.

[0129] In addition, although not described in Figure 3 it, the information processing device that generates the mathematical model may exist separately from the information processing device 60. In this case, the mathematical model generated by the information processing device is imported into the information processing device 60. In the present invention, for the sake of convenience of explanation, it is assumed that the information processing device 60 generates the mathematical model.

[0130] The information processing device 60 also has a function of a Web server. The Web server responds to a request from a client software (Web client) such as a Web browser operated by a user, and provides the client with screen information described in HTML files, XML, CSS files, JavaScript (registered trademark), etc. Such an application using the Web mechanism is called a Web application.

[0131] In addition, the information processing device 60 preferably supports cloud computing. Cloud computing refers to a method of utilizing resources on the network without being aware of specific hardware resources. Cloud computing provides data and software that users have previously used on their computers to users as services via the network. The user side can use a variety of services from any terminal by preparing a web browser that operates on a personal computer, a portable information terminal, etc. and an Internet connection environment.

[0132] The user terminal 70 is a client terminal that displays various screens provided by the information processing device 60. The user terminal 70 can be used by an administrator or a general user (the patient 9 in the present invention). When the device 30 is located in a general home, the administrator can be a family member, and the patient 9 can also serve as the administrator. When the device 30 is located in a building managed by a company, the administrator is, for example, a facility manager, a caregiver, a nurse, etc.

[0133] The screens displayed by the user terminal 70 are various, including, for example, the above-mentioned map screen, an overview screen of the devices 30 and sensor switches 53 on the client side, an internal company map showing the locations where the devices 30 and sensor switches 53 are configured, and an operation screen for operating the devices 30 or sensor switches 53.

[0134] The user terminal 70 is, for example, a PC (Personal Computer), a smart phone, a tablet terminal, a PDA (Personal Digital Assistant), a wearable PC (sunglasses type, watch type, etc.), etc. Any device having a communication function and a web browser may be used. In addition, in the user terminal 70, instead of a web browser, a local application dedicated to the human symptom change prediction system 100 may be used.

[0135] <Hardware structure of information processing device>

[0136] Reference Figure 4 The hardware structure of the information processing device 60 will be described. Figure 4 is a diagram showing an example of the hardware configuration of the information processing device 60. Figure 4As shown, the information processing apparatus 60 includes a processor 221, a memory 222, an auxiliary storage device 223, an I / F (Interface) device 224, a communication device 225, and a drive device 226. In addition, each hardware component of the information processing apparatus 60 is interconnected via a bus 207.

[0137] The processor 221 includes various computing devices such as a CPU (Central Processing Unit). The processor 221 reads various programs onto the memory 222 and executes them. The processor 211 corresponds to the control unit 110 that controls or performs operations on the entire information processing apparatus 60. In addition to overall control, the control unit 110 also performs processing for estimating the sensory intensity related to human sensations. The processing for estimating the sensory intensity will be described later.

[0138] The memory 222 includes main storage devices such as a ROM (Read Only Memory) and a RAM (Random Access Memory). The processor 221 and the memory 222 form a so-called computer, and the processor 221 executes various programs read onto the memory 222.

[0139] The auxiliary storage device 223 stores various programs and various data used when the processor 221 executes various programs.

[0140] The I / F device 224 is a connection device that connects a display device 230 and an operation device 240, which are examples of external devices, to the information processing apparatus 60. The display device 230 displays the internal state of the information processing apparatus 60. When an administrator of the information processing apparatus 60 inputs various instructions to the information processing apparatus 60, the operation device 240 is used.

[0141] The communication device 225 is a communication device for communicating with the edge device 80 and the user terminal 70 via the network N.

[0142] The drive device 226 is a device for setting a recording medium 250. The recording medium 250 mentioned here includes media that record information in optical, electrical, or magnetic ways, such as CD-ROMs, floppy disks, and optical disks. In addition, the recording medium 250 may also include semiconductor memories that record information electrically, such as ROMs and flash memories.

[0143] In addition, various programs installed in the auxiliary storage device 223 are installed, for example, by setting the distributed recording medium 250 in the drive device 226 and reading out the various programs recorded on the recording medium 250 by the drive device 226. Alternatively, the various programs installed in the auxiliary storage device 223 can also be installed by downloading from the network N via the communication device 225.

[0144] <Regarding Functions>

[0145] Next, refer to Figure 5 to describe in detail the functional structures of the respective devices included in the human symptom change prediction system 100. Figure 5 FIG. is an example of a functional block diagram that separately describes the functions of the information processing device 60 in the learning stage.

[0146] The information processing device 60 includes an environmental factor data acquisition unit 61, a symptom change information reception unit 62, a statistic calculation unit 63, a sensory intensity estimation unit 64, and a mathematical model generation unit 65. Each of these units included in the information processing device 60 is a function or unit realized by the control unit 110 of the information processing device 60 executing instructions of a program expanded in the memory 222.

[0147] The environmental factor data acquisition unit 61 acquires environmental factor data indicating the concentration and the like of environmental factors actually detected by the environmental sensor 11. In the present invention, the environmental factor data is set to temperature, humidity, CO2 concentration, PM2.5 concentration, TVOC concentration, and formaldehyde concentration, but this is merely an example. For example, the environmental factor data may also include pollen and dust.

[0148] The environmental factor data acquisition unit 61 may only receive the environmental factor data regularly transmitted by the environmental sensor 11, or may request the environmental sensor 11 to measure the environmental factor data and receive the environmental factor data as a response thereto. The acquisition timing is preferably at least once a day or more, and for example, it can be set to a frequency of once every few minutes to several hours.

[0149] The symptom change information receiving unit 62 receives the symptom change information input by the patient 9 at risk of exacerbation into the user terminal 70. The symptom change information is information indicating the presence or absence of symptoms such as asthma and allergic symptoms, and the intensity of the symptoms. For example, the patient 9 inputs "1" as the symptom change information for the current day when symptoms appear, and "0" when no symptoms appear. The symptom change information may also be a value other than "1" or "0", such as a numerical value from 0 to 100 or an intensity level from 3 to 5. In this way, the symptom change information not only indicates deterioration but also improvement. These numerical values correspond to symptom exacerbation, improvement, remission, or alleviation. By the patient 9 logging in to the information processing device 60, the symptom change information receiving unit 62 obtains the patient ID (able to identify the patient). The basic information about the patient 9 is pre-registered in the information processing device 60. For example, the basic information is age, gender, height, allergens (such as mold, dust, pollen), underlying diseases, etc. An allergen is an antigen that specifically reacts with the antibodies of a person suffering from asthma or allergic diseases. Generally speaking, an allergen is a causative substance that causes its allergic symptoms.

[0150] The statistic calculation unit 63 calculates the statistic of the environmental factor data by processing the environmental factor data using statistical processing. The statistic can be, for example, the maximum value of each day, the minimum value of each day, the average value of a day, the standard deviation, etc. of the environmental factor data. In addition, the statistic is not limited to these, and can also be the median, cumulative value, moving average from the past few hours to several days, etc. Calculating the statistic is to reduce the processing load of the environmental factor data, so the statistic calculation unit 63 may not be provided.

[0151] The perceived intensity estimation unit 64 generates intermediate data based on a model that simulates the characteristics of an organism, according to the statistic of the environmental factor data. As an example, in the present invention, the perceived intensity estimation unit 64 estimates the perceived intensity according to the statistic of the environmental factor data. For details about the perceived intensity, use Figure 19 、 Figure 20 to illustrate.

[0152] The mathematical model generation unit 65 uses learning data with the statistic of the environmental factor data and the perceived intensity as explanatory variables and the symptom change information as the target variable (teacher data) to generate a mathematical model for predicting the exacerbation risk based on the statistic of the environmental factor data and the perceived intensity. A mathematical model refers to a model that simplifies real-world objects and represents the relationships between various quantities in a mathematical manner according to physical laws. However, it is not required to be a strict mathematical model, and the mathematical model only needs to be able to predict the exacerbation risk based on the environmental factor data and the perceived intensity.

[0153] <Examples of environmental factor data>

[0154] Refer to Figure 6To illustrate the environmental factor data that the environmental sensor 11 can detect. Figure 6 Shows the environmental factor data acquired by the environmental factor data acquisition unit 61. Here, for ease of explanation, Figure 6 Shows the statistic of the environmental factor data. As Figure 6 Shown, the statistics of temperature (average value of a day, standard deviation, maximum value of each day, minimum value of each day), humidity, PM2.5 concentration, etc. are obtained. Figure 6 The environmental factor data is the statistic of each day, but it can also be the statistic of a shorter time.

[0155] In addition, Figure 6 Shows the symptom change information corresponding to the environmental factor data. The symptom change information is the information input by the patient 9. This symptom change information is aggravation (1), not aggravated (0).

[0156] <Generation of mathematical model>

[0157] Next, with reference to Figures 7 - 9 To illustrate the generation method of the mathematical model. Figure 7 Is a diagram showing the learning stage of generating a mathematical model based on the statistics of environmental factor data, the perceived intensity (explanatory variable), and the symptom change information (target variable, teacher data). Although Figure 5 Is the same as Figure 7 In terms of functional structure, Figure 7 The blocks are arranged along the processing flow.

[0158] S1: First, the environmental factor data acquisition unit 61 acquires the environmental factor data actually detected by the environmental sensor 11. The environmental factor data is not limited to the measured value, and can also be the predicted value. This predicted value can be provided by the meteorological bureau, etc., or can be predicted by the environmental factor data acquisition unit 61 based on the measured value.

[0159] S2: In addition, the symptom change information reception unit 62 receives the symptom change information input by the patient 9 with asthma or allergy symptoms from the user terminal 70, etc.

[0160] S3: Next, the statistic calculation unit 63 calculates the statistics of the environmental factor data (for example, the maximum value of each day, the minimum value of each day, the average value of a day, the standard deviation, etc.). Above, the environmental factor data shown in Figure 6 Is obtained.

[0161] S4: Next, the perceived intensity estimation unit 64 estimates the perceived intensity based on the statistics of the environmental factor data. In addition, when the predicted value is used for the environmental factor data, the perceived intensity is also estimated using the above predicted value. Regarding the perceived intensity, details are described using Figure 19 , Figure 20This will be described. The perceived intensity P is estimated by Equation (1).

[0162] P = k log(I / I0)……(1)

[0163] Among them, P: perceived intensity (also called perceived quantity), I: intensity of the stimulus, I0: intensity of the stimulus with a perceived intensity of 0, k: a constant inherent to the stimulus. These details will be described later.

[0164] S5: Then, the mathematical model generation unit 65 uses the statistic of the environmental factor data and the perceived intensity as explanatory variables and the symptom change information as the target variable (teacher data) to construct a mathematical model that outputs the exacerbation risk based on the statistic of the environmental factor data and the perceived intensity. When the number of types of environmental factor data is 6, the number of statistics for each environmental factor data is 4, and the number of perceived intensities for each environmental factor data is 1, 6×5 = 30 data is one sample of the learning data.

[0165] In addition, in the present invention, the statistic of the environmental factor data is used for learning. However, since the environmental factor data is also included in the perceived intensity, the mathematical model generation unit 65 can also perform learning without using the statistic of the environmental factor data (using the perceived intensity).

[0166] In addition, the process of generating a mathematical model is called machine learning. Machine learning is a technology that enables a computer to acquire learning ability like a human. It refers to a technology in which a computer autonomously generates an algorithm required for data recognition and other judgments based on previously imported learning data, and applies this algorithm to new data for prediction. The method used for machine learning can be any one of supervised learning, unsupervised learning, semi-supervised learning, reinforcement learning, and deep learning. Furthermore, it can also be a learning method that combines these learning methods, and the learning method used for machine learning is not limited.

[0167] There are various algorithms for the method of generating a mathematical model using machine learning. In the present invention, for example, the gradient boosting decision tree is described. The gradient boosting decision tree is one of the supervised learnings that combines the "gradient descent method", "Boosting (ensemble)", and "decision tree".

[0168] Figure 8 It is a flowchart showing the process of the learning method based on the gradient boosting decision tree. Figure 9 It shows a schematic diagram of a decision tree.

[0169] The mathematical model generation unit 65 calculates an initial value (S11) based on a plurality of symptom change information (teacher data) prepared as learning data. The initial value is, for example, the average value. For the sake of explanation, this average value is called the predicted value 1.

[0170] Next, the mathematical model generation unit 65 calculates, for each of the learning data, the value obtained by subtracting the average value from the symptom change information as the error 1 (S12). The error 1 is positive if the symptom change information is greater than the average value, and negative if the symptom change information is less than the average value. Here, the reason for setting the "value obtained by subtracting the average value from the symptom change information" as the error is that, for the calculation method of taking the squared error between the symptom change information and the predicted value as the error, the gradient obtained by differentiating the squared error is used for the calculation of the error. It is also possible to set the absolute value error as the calculation method of the error.

[0171] Next, the mathematical model generation unit 65 constructs a decision tree for the purpose of prediction error (S13). The number of nodes and levels of the decision tree can be limited within a preset range. This decision tree is a weak classifier (Boosting). Figure 9 The topmost tree in Figure 9 is a schematic diagram of the initially generated decision tree. Since

[0172] is a schematic diagram, the number of nodes, etc. are insufficient relative to the number of input data, but the error is classified into the leaves (ends of the tree) of such a decision tree.

[0173] (i) The mathematical model generation unit 65 calculates the entropy based on the ratio of correct answers to wrong answers in the learning data before classification. The mathematical model generation unit 65 can also use the Gini coefficient instead of entropy.

[0174] (ii) The mathematical model generation unit 65 calculates the entropy for each branch based on the ratio of correct answers to wrong answers in each branch when classified according to any one attribute.

[0175] (iii) The mathematical model generation unit 65 calculates the weighted average of the entropy in (ii). This weighted average can be the ratio of the number of data classified into each branch to the number of the original data multiplied.

[0176] (iv) The mathematical model generation unit 65 adopts the attribute with the largest difference (gain) in entropy between (i) and (iii) as the root attribute.

[0177] (v) The structure below the root is also determined by processing (i) to (iv).

[0178] Next, the mathematical model generation unit 65 uses the error 1 to calculate a new predicted value (S14). Here, it is set as "error 1", but "error n" increases through repetition. Since the error 1 is classified into the leaves of the decision tree for each sample of the learning data, it is possible to calculate the predicted value 1 using the error 1 for each sample of the learning data. In the case where multiple errors are classified into one leaf, the average of the errors included in the leaf is the error 1.

[0179] If the new predicted value is set as Predicted Value 2, then "Predicted Value 2 = Predicted Value 1 + Learning Rate × Error 1". The learning rate is a value less than 1 and is a hyperparameter that determines the degree to which the error is corrected in a single decision tree. The learning rate is appropriately determined, for example, to be 0.05 to 0.3 or the like. By repeatedly performing the operation of "obtaining the error, multiplying it by the learning rate, and adding them", the accuracy is gradually improved.

[0180] Next, the mathematical model generation unit 65 calculates the error based on the symptom change information as the teacher data and the predicted value 2 (S15). The mathematical model generation unit 65 calculates the error from the predicted value 2 for the symptom change information of all the prepared learning data. The error calculated based on the predicted value 2 is called Error 2.

[0181] The mathematical model generation unit 65 repeatedly executes steps S13 to S15 until the error is calculated a certain number of times or the error is less than the threshold value (S16). As shown in the second tree and the third tree in Figure 9 , the mathematical model generation unit 65 classifies the previous nearest error through a new decision tree, and calculates predicted values 3, 4... n and errors 3, 4... n that utilize the error. Since the error also changes due to the repetition of the process, the structure of the decision tree also automatically changes. The n decision trees created in this way are the mathematical model of the present invention. The prediction of the weighted risk using the n decision trees in the prediction stage will be described later.

[0182] As various frameworks for implementing gradient boosting decision trees in an information processing device, LightGBM (Light Gradient Boosting Machine, lightweight gradient boosting machine), XGBoost (eXtreme Gradient Boosting, extreme gradient boosting), Catboost (Category Boosting, category boosting), etc. are known. The mathematical model generation unit 65 can also use these frameworks.

[0183] In addition, since predicting the weighted risk through gradient boosting decision trees is a so-called regression problem (using continuous values and predicting other values based on one or more numerical values), the algorithms that can be used are not limited to gradient boosting decision trees. As algorithms that can be used for regression, there are various algorithms such as linear regression (multiple regression), logistic regression, neural network, Bayesian linear regression, SVM regression, ridge regression, lasso regression, Poisson regression, etc.

[0184] For example, deep learning is an algorithm that, after predicting XYZ based on the input data ABC, adjusts the weights between neural networks by the error backpropagation method to reduce the error from the teacher data.

[0185] <The amount of physiological response relative to the environment based on a model simulating biological characteristics>

[0186] A model simulating biological characteristics that transforms environmental factor data into intermediate data will be described in detail. Simulating biological characteristics means estimating the influence on a person (physiological response amount, behavior, etc.) from environmental factor data. In addition, Weber and Fechner's law, which is one of such models, will be described in detail later.

[0187] The environmental factor data is transformed into intermediate data through the following models representing non - linear relationships. That is, the control unit 110 generates intermediate data related to the amount of physiological response relative to the environment based on these models simulating biological characteristics. The following models are all non - linear processing with quantitative information.

[0188] (i) A model that outputs intermediate data corresponding to the ratio of the values of environmental factor data (logarithmic function, exponential function, n - th power function)

[0189] This model is suitable for representing the relationship between the amount of dust and asthma symptoms, etc. The change corresponding to the ratio of values means that when the environmental factor data increases at a certain ratio, the value of the intermediate data also increases at a given ratio. In Figure 10 (a) - Figure 10 (c), an example of the shapes of the logarithmic function 331, exponential function 332, and n - th power function 333, which are examples of this model, is shown.

[0190] (ii) A model that outputs different values of intermediate data according to the range of the values of environmental factor data or whether the environmental factor data satisfies a condition (step function, Sigmoid function, IF function, function having values only in a specific range)

[0191] This model is suitable for representing the relationship between sweating, tremors caused by temperature, or the relationship between temperature and the activity level of immune cells, etc. In addition, this model is suitable for representing the relationship between temperature and humidity and heat stroke, and the relationship between the amount of dust and coughing or sneezing, etc. In Figure 11 (a) - Figure 11 (d), an example of the shapes of the step function 334, Sigmoid function 335, IF function 336, and function having values only in a specific range 337, which are examples of this model, is shown. In addition, the IF function 336 is a function that takes a certain value when the environmental factor data satisfies a given condition and takes another certain value when it does not satisfy the given condition.

[0192] (iii) A model that outputs intermediate data corresponding to the change pattern of environmental factor data rather than the absolute value (n - th derivative (slope, acceleration), function having values only for changes in one direction)

[0193] This model is suitable for representing physiological responses that are not noticeable when the temperature changes slightly, or physiological responses such as burns caused by exposure to high temperatures that do not recover even when the temperature returns to normal. In addition, this model is suitable for representing the relationship between air pressure and meteorological diseases, or the relationship between acceleration and motion sickness, etc. In Figure 12 An example of the shape (tangent) of the first derivative 338 of a quadratic function is shown.

[0194] Figure 13 Figures (a) and (b) of Figure 13 show the relationship between time and environmental factor data (e.g., air pressure). Figure 13 Figure (b) of

[0195] (iv) A model that outputs intermediate data corresponding to the cumulative value of environmental factor data, or intermediate data that varies depending on the change history (hysteresis) of the past values of environmental factor data even when the current values of environmental factor data are the same

[0196] This model is suitable for representing the relationship between the intake of pollen and the amount of antibodies, or the relationship between CO2 concentration and blood oxygen concentration, etc. In addition, this model is suitable for representing the relationship between the amount of pollen scattered and hay fever, or the relationship between temperature and humidity and heat stroke, etc.

[0197] Figure 14 Figures (a) and (b) of Figure 14 show the intermediate data corresponding to the cumulative value of environmental factor data. Figure 14 Figure (a) of

[0198] Figure 15 Figures (a) and (b) of Figure 15(a) shows the relationship between time and environmental factor data (such as air temperature). Figure 15 (b) shows the relationship between time and intermediate data (such as the amount of physiological reactions related to heatstroke). For example, the environmental factor data is set as air temperature, and the intermediate data is set as the amount of physiological reactions related to heatstroke. Even if the air temperature starts to decrease, the amount of physiological reactions does not immediately decrease (time t1). Additionally, even if the air temperature decreases to the same temperature, the amount of physiological reactions does not decrease to the same value (time t2). Therefore, this model is suitable for representing the relationship between the amount of pollen scattering and hay fever, or the relationship between temperature and humidity and heatstroke, etc.

[0199] (v) A model that outputs intermediate data corresponding to the duration of the continuously given range of environmental factor data or the number of times the environmental factor data is repeatedly given within a range

[0200] This model is suitable for representing the habituation to temperature. In addition, this model is suitable for representing the relationship between the number of allergen intakes and the amount of immune response (allergic reaction), etc.

[0201] Figure 16 (a) and (b) are diagrams for explaining intermediate data corresponding to the duration and continuously measured values of continuously measured environmental factor data. Figure 16 (a) shows the relationship between time and environmental factor data (such as CO2 concentration). Figure 16 (b) shows the relationship between time and intermediate data (such as the amount of physiological reactions related to the decline in wakefulness). For example, the environmental factor data is set as CO2 concentration, and the intermediate data is set as the amount of physiological reactions related to the decline in wakefulness. When the time during which CO2 is above a given concentration continues for a certain period or more, the amount of physiological reactions increases (time T1). When the time during which CO2 is below a given concentration continues for a certain period or more, the amount of physiological reactions decreases (time T2). Therefore, this model is suitable for representing symptoms caused by the duration and continuously measured values of continuous exposure to environmental factor data.

[0202] Figure 17 (a) and (b) are diagrams for explaining intermediate data corresponding to the number of times of measuring environmental factor data. Figure 17 (a) shows the relationship between time and environmental factor data (such as the amount of allergen). Figure 17 (b) shows the relationship between time and intermediate data (the amount of physiological reactions related to allergic symptoms). For example, the environmental factor data is set as the amount of allergen, and the intermediate data is set as the amount of physiological reactions related to allergic symptoms. Regarding the amount of physiological reactions, even if the amount of allergen is the same, the reaction for the second time is larger than that for the first time. Therefore, this model is suitable for representing symptoms caused by the number of times of exposure to environmental factor data.

[0203] (vi) A model that outputs intermediate data that changes after a given time has elapsed since the time when the environmental factor data is generated

[0204] The model is suitable for representing relationships such as delayed runny nose after inhaling pollen. In addition, the model is suitable for representing relationships such as the immune response being delayed after contact with bacteria.

[0205] Figure 18 Figures (a) and (b) are diagrams for explaining intermediate data corresponding to the measured environmental factor data after a lapse of time from when the environmental factor data was measured. Figure 18 Figure (a) shows the relationship between time and environmental factor data (such as the amount of indoor dust), Figure 18 Figure (b) shows the relationship between time and intermediate data (such as the amount of physiological response related to allergic symptoms). For example, the environmental factor data is set as the amount of indoor dust, and the intermediate data is set as the amount of physiological response related to allergic symptoms. The amount of physiological response is roughly proportional to the amount of house dust, but changes slightly delayed (a delay of time T) from the moment when the amount of house dust changes. Therefore, the model is suitable for representing symptoms that occur after a lapse of time from exposure to environmental factor data.

[0206] <Regarding the sensory intensity>

[0207] Next, Weber's and Fechner's laws are described in detail as one of the models for simulating biological characteristics. Through Weber's and Fechner's laws, the sensory intensity is obtained as an example of the above intermediate data. That is, the present invention introduces "sensory intensity" as a variable representing the magnitude of the influence that a person may receive when a change in the air quality environment becomes a stimulus. The sensory intensity is estimated based on the Weber-Fechner law proposed by Weber and Fechner, according to the air quality environment data.

[0208] Weber's - Fechner's law is a law that expresses the intensity of a stimulus felt by a person using a mathematical expression, and it is said to be approximately applicable to all five senses. The sensory intensity P is estimated according to the statistic of the environmental factor data as shown in Equation (1). When estimating the sensory intensity based on the air quality environment data, I, I0, and k in Equation (1) are determined as follows.

[0209] "The intensity of the stimulus I" uses the statistic of the environmental factor data.

[0210] "The intensity of the stimulus at which the sensory intensity is 0 (the intensity of the stimulus at which the stimulus starts to be felt) I0" uses the average value of the environmental factor data. The reason for using the average value is as follows.

[0211] It is known that people have the characteristic of adapting to the surrounding environment. This adaptation progresses towards the average state of the surrounding environment. Considering these circumstances, in the present invention, the average value is used as the intensity of the stimulus I0 at which the stimulus starts to be felt.

[0212] Regarding the "intrinsic constant k of stimulation", different values are set for each sense. However, in the present invention, it is used as a weighting coefficient to make the differences in the degrees of influence caused by different ranges and units of the available values of environmental factor data (such as temperature, humidity, CO2, PM2.5, TVOC, formaldehyde, etc.) consistent, and is determined for each environmental factor. The determination method uses the environmental factor data as the explanatory variable and the weighted risk as the target variable to create an approximation formula, and is obtained as the constant that minimizes the approximation error.

[0213] Figure 19 (a) and (b) of Figure 19 are graphs showing the correspondence between environmental factor data (X-axis) and sensory intensity (Y-axis). Figure 19 (a) of Figure 19 is obtained by forming the following formula (2) into a curve graph.

[0214] Y = klogX + α......(2)

[0215] Among them, k and α can be appropriately designed constants.

[0216] In addition, formulas (1) and (2) are examples, and the correspondence between stimulation and sensory intensity can be expressed by formula (3) for example.

[0217] Y = logI......(3)

[0218] I is the statistic of environmental factor data / the average value per day.

[0219] In addition, the sensory intensity can also be obtained by methods other than logarithms. Figure 19 (b) of Figure 19 represents the correspondence between stimulation and sensory intensity with two straight lines. In this way, the sensory intensity only needs to be saturated in the region with a larger stimulation compared to the region with a smaller stimulation. The correspondence between stimulation and sensory intensity can also be represented by three or more straight lines.

[0220] Figure 20 is a graph for explaining the correspondence with biological responses by estimating the sensory intensity based on environmental factor data. In Figure 20 of Figure 20 , the surrounding environment A and the human side (inside the organism) B are shown separately.

[0221] Surrounding environment A: A person feels stimulation due to environmental changes such as temperature changes, humidity changes, air quality changes, and odor changes.

[0222] Human side (inside the organism) B: According to Weber-Fechner's law, the greater the stimulation, the more saturated it is. That is, a person perceives the sensory intensity rather than the magnitude of the stimulation. And the sensory intensity changes in form and is manifested as various biological responses (changes in heart rate, blood pressure, respiratory rate, etc.). Therefore, it can be known that the sensory intensity is information that can replace biological data.

[0223] <Prediction of exacerbation risk>

[0224] Next, a prediction method for predicting the exacerbation risk based on the environmental factor data and the perceived intensity using the mathematical model generated by the mathematical model generation unit 65 will be described.

[0225] <<Regarding functions>>

[0226] Figure 21 This is an example of a functional block diagram that separately describes the functions of the information processing device 60 in the prediction stage. In addition, in the Figure 21 description, the differences from Figure 5 will be mainly described. The information processing device 60 includes an environmental factor data acquisition unit 61, a statistic calculation unit 63, a perceived intensity estimation unit 64, and an exacerbation risk prediction unit 66. These units of the information processing device 60 are functions or units implemented by the control unit 110 of the information processing device 60 executing instructions of a program expanded in the memory 222.

[0227] Among them, the exacerbation risk prediction unit 66 corresponds to the mathematical model. The exacerbation risk prediction unit 66 uses the correspondence information that correlates the intermediate data with the possibility of symptom change, and predicts the possibility of symptom change based on the intermediate data. In the present invention, the exacerbation risk prediction unit 66 outputs the exacerbation risk based on the environmental factor data (actual measurement, forecast) and the perceived intensity estimated based on the environmental factor data. The possibility of symptom change represents the degree of certainty of symptom deterioration or improvement. Taking the exacerbation risk as an example, when the symptom change information input by the user is 1 (exacerbated) or 0 (not exacerbated), the predicted value of the possibility of symptom change also takes a value in the range of 0 to 1. The closer the predicted value is to 1, the more likely the symptom will change in the worse direction, and the closer the predicted value is to 0, the more likely the symptom will change in the better direction. The exacerbation risk unit 66 can predict the degree of change in symptoms. When the forecast value is used in the environmental factor data, the perceived intensity is also estimated using the forecast value. The exacerbation risk is the value predicted by the exacerbation risk prediction unit 66 for the self-reported symptom change information.

[0228] Figure 22 This is a diagram showing the prediction stage in which the environmental factor data and the perceived intensity are input to the exacerbation risk prediction unit 66 to predict the exacerbation risk. In addition, in the Figure 22 description, the differences from Figure 7 will be mainly described. Regarding steps S1, S3, and S4, they can be the same as Figure 7 .

[0229] S6: The exacerbation risk prediction unit 66 takes the statistic of the environmental factor data and the perceived intensity estimated based on the statistic as input data, and outputs the exacerbation risk.

[0230] The prediction using the gradient boosting decision tree will be described. The exacerbation risk prediction unit 66 inputs the input data into all the decision trees created in the learning phase respectively. Figure 9 There are three decision trees, and for each decision tree, the input data is classified into one leaf of the decision tree. An error is stored in each leaf. For example, assume that errors 1 to 3 are classified into Figure 9 the leaves 321 to 323 indicated by the dotted ○ in

[0231] The predicted value of the exacerbation risk = average + learning rate × error 1 + learning rate × error 2 + learning rate × error 3

[0232] Thus, in the gradient boosting decision tree, the final predicted value is the value obtained by adding all of the average calculated in the learning phase and the errors 1 to errors n multiplied by the learning rate.

[0233] The final predicted value = average + learning rate × error 1 + learning rate × error 2 + …… + learning rate × error n

[0234] When the symptom change information in the teacher data is exacerbated (1) or not exacerbated (0), the predicted value is a value between 0 and 1. It is appropriate for the exacerbation risk prediction unit 66 to convert the predicted value by multiplying it by 100 and display it as a percentage.

[0235] <Improvement in Prediction Accuracy Based on the Use of Sensory Intensity>

[0236] Refer to Figure 23 to describe the effect of using sensory intensity. Figure 23 This is a graph comparing the prediction accuracy of predicting the exacerbation risk of asthma without using sensory intensity and the case of using sensory intensity for prediction. The prediction accuracy without using sensory intensity is 61.1%, while in contrast, the prediction accuracy in the case of using sensory intensity is improved to 73.3%.

[0237] <Variant Example in the Learning Phase>

[0238] It is known that there are large individual differences in symptom change information. This means that in the learning phase, it is more effective for the mathematical model generation unit 65 to generate a mathematical model for each individual. The mathematical model generation unit 65 generates a mathematical model (an example of the first corresponding information) for all patients who declare symptom change information, and also generates a mathematical model for each individual (an example of the second corresponding information).

[0239] The exacerbation risk prediction unit 66 uses a mathematical model for multiple people (e.g., all patients) to predict the exacerbation risk, and uses an individual mathematical model to predict the exacerbation risk. The exacerbation risk prediction unit 66 makes it easy for each individual to grasp the exacerbation risk on the current day by providing one or more of the two predicted exacerbation risks, the higher of the two predicted exacerbation risks, or the average of the two predicted exacerbation risks to the individual.

[0240] In addition, since allergens are factors that become environmental factors according to seasons such as pollen, it is effective for the mathematical model generation unit 65 to generate a mathematical model for each season. In addition, since allergens vary depending on the individual, it is effective for the mathematical model generation unit 65 to generate a mathematical model for each allergen. The allergens of patient 9 are registered in the information processing device 60. The mathematical model generation unit 65 groups patients 9 with the same allergen and generates a mathematical model based on the reported symptom change information and environmental factor data. In addition, since the diseases (underlying diseases) for which symptoms are likely to appear vary depending on the individual, it is effective for the mathematical model generation unit 65 to generate a mathematical model for each target disease. The diseases of patient 9 are registered in the information processing device 60. The mathematical model generation unit 65 groups patients 9 with the same disease and generates a mathematical model based on the reported symptom change information and environmental factor data.

[0241] When sufficient environmental factor data is obtained, it is also possible to generate a mathematical model for each user attribute (e.g., gender, age), region (e.g., prefecture, city, town, village). Thereby, an improvement in the prediction accuracy of the exacerbation risk can be expected.

[0242] <Example of presenting exacerbation risk>

[0243] Figure 24 It is a display example of the map screen 300 of the exacerbation risk displayed on the user terminal 70. The map screen 300 mainly has a mode selection bar 301 and a map display bar 302. The mode selection bar 301 has a recommendation button 303, a mold & mite prevention button 304, an energy saving button 305, and a decision button 306.

[0244] · The recommendation button 303 is a button that displays the environmental settings recommended by showing the comprehensive mold & mite prevention property and energy saving property.

[0245] · The mold & mite prevention button 304 is a button that displays the environmental settings for suppressing mold and mites based on at least one of the mold index or the mite index.

[0246] · The energy saving button 305 is a button that displays the environmental settings recommended based on the energy saving property.

[0247] · The decision button 306 is a button for accepting the case of controlling the environmental equipment with the environmental settings set by the patient 9.

[0248] The map display bar 302 displays three maps A to C. This is an example, and the maps A to C can also be displayed one by one. The three maps A to C respectively show the current environmental conditions 308 to 310.

[0249] · Map A represents an area with a high weighted risk corresponding to the set temperature and set humidity. The area with a low weighted risk is divided into two. Correspondingly to the temperature and humidity of the map screen original data, the area with a weighted risk below the first threshold is represented by blue (an example), and the area below the second threshold is represented by red (an example). The map screen original data comprehensively calculates the environmental factor data and the weighted risk data. Since the map screen original data is discrete data, the screen generation unit 73 performs processing such as interpolation and coloring between points.

[0250] · Map B represents an area with a low weighted risk corresponding to the CO2 concentration and the PM2.5 concentration. The area with a low weighted risk is divided into two. Correspondingly to the CO2 concentration and the PM2.5 concentration of the map screen original data, the area with a weighted risk below the first threshold is represented by blue (an example), and the area below the second threshold is represented by red (an example). Here, the first threshold < the second threshold.

[0251] · Map C represents an area with a low weighted risk corresponding to the formaldehyde concentration and the TVOC concentration. The area with a low weighted risk is divided into two. Correspondingly to the formaldehyde concentration and the TVOC concentration of the map screen original data, the area with a weighted risk below the first threshold is represented by blue (an example), and the area below the second threshold is represented by red (an example).

[0252] Therefore, the user can easily judge what temperature and humidity are appropriate to set the air conditioner.

[0253] In addition, it can also be configured that the information processing device 60 displays the map screen on the display device 230 instead of the user terminal 70 displaying the map screen.

[0254] Figure 25 This is a display example of the perceived intensity and weighted risk screen 310 displayed on the user terminal 70. The perceived intensity and weighted risk screen 310 displays a message 311 such as "The weighted risk of allergic symptoms is as follows", the weighted risk 312, and the influence degree 313 of the environmental factors related to the weighted risk.

[0255] The user can confirm the displayed exacerbation risk 312 and visually grasp the environmental factors related to the exacerbation risk. In addition, the sensation intensity and exacerbation risk screen 310 display environmental factors 314 whose degree of influence related to the exacerbation risk is above the threshold. Thus, the user knows which environmental factors should be adjusted.

[0256] <More detailed descriptions of environmental factor data and symptoms>

[0257] Figure 26 Examples of environmental factor data and symptoms are shown in (a) and (b) of. Figure 26 (a) of represents environmental factor data that can be detected by environmental sensors. As environmental factor data, in addition to temperature, humidity, pollen, mold, mites, there are also radiant temperature, air pressure, dust (quantity, suspended concentration), air flow (wind speed, air volume), CO2, oxygen (concentration), sound (sound pressure, volume, frequency, rhythm), odor (intensity), acceleration · slope (environmental factor data when taking a vehicle), droplets · steam · smoke (environmental factor data related to infectious diseases), etc. In the present invention, these can be raw data for predicting the possibility of symptom changes.

[0258] Figure 26 (b) of shows symptoms caused by environmental factor data. As symptoms, in addition to allergies, there are also meteorological diseases, infectious diseases, sleep quality, autonomic nerve disorders, dementia / delirium, frailty / fatigue, memory decline / improvement, wakefulness / sleepiness, heat stroke, motor function, motion sickness, and VR dizziness, etc. In the present invention, these can also be symptom changes predicted by a mathematical model. When learning the mathematical model, the user reports the presence or absence and degree of these symptoms as teacher data.

[0259] <Main effects>

[0260] As described above, in the present invention, life data is not used in the prediction of exacerbation risk. In addition, by introducing "sensation intensity" as a variable representing the magnitude of the influence that a person may receive due to changes in the air quality environment becoming a stimulus, life data can be replaced, and the exacerbation risk of symptoms can be predicted with high precision. In addition, by transforming environmental factor data into intermediate data using a model simulating biological characteristics, the accuracy of machine learning can be improved with a small number of samples.

[0261] <Other application examples>

[0262] As described above, the best mode for implementing the present invention has been described using examples, but the present invention is not limited to such examples, and various modifications and substitutions can be made without departing from the gist of the present invention.

[0263] For example, the information processing device 60 and the environmental sensor 11 may also be configured as a non-separate system, and the information processing device 60 and the environmental sensor 11 may be integrated. In this case, the environmental sensor 11 can display the predicted exacerbation risk based on the environmental factor data of the set space on a liquid crystal display or the like.

[0264] Similarly, when the environmental sensor 11 is built into the indoor unit 10b of the air conditioner, any one of the indoor unit 10b, the outdoor unit 10a, or the remote controller 12 can display the predicted exacerbation risk based on the environmental factor data of the space on the remote controller 12.

[0265] In addition, in the present invention, life data is not required for the prediction of the exacerbation risk, but the information processing device 60 may also use the sensory intensity and life data to predict the exacerbation risk.

[0266] In addition, the present embodiment is not limited to the prediction of human symptoms, and can also be used for the prediction of symptoms of animals such as pets, livestock such as cows and pigs, and farmed fish.

[0267] In addition, Figure 5 、 Figure 21 Structural examples such as etc. are structural examples divided according to the main functions to make it easier to understand the processing performed by the information processing device 60. The technology of the present invention is not limited by the division method and name of the processing unit. The processing of the information processing device 60 can also be divided into more processing units according to the processing content. In addition, it can also be divided in such a way that one processing unit includes more processing.

[0268] In addition, the device group described in the embodiment only represents one of the multiple computing environments for implementing the embodiments disclosed in this specification. In a certain embodiment, the information processing device 60 includes a plurality of computing devices such as a server cluster. The plurality of computing devices are configured to communicate with each other via any type of communication link including a network, a shared memory, etc., and implement the processing disclosed in this specification.

[0269] Each function of the present invention described above can be implemented not only by software processing based on program execution, but also by one or more processing circuits. Here, the "processing circuit" in this specification includes devices such as a processor programmed to execute each function by software like a processor implemented by an electronic circuit, an ASIC (Application Specific Integrated Circuit), a DSP (Digital Signal Processor), an FPGA (Field Programmable Gate Array), and existing circuit modules, which are designed to execute each function described above.

[0270] <Reason for generating effect>

[0271] · The first mode of the present invention is "having a control unit that transforms the environmental factor data into intermediate data through a model that simulates the biological characteristics related to the symptoms relative to the environment.

[0272] The control unit uses correspondence information that at least correlates the intermediate data with the possibility of symptom change relative to the environment, and predicts the possibility of symptom change based on the intermediate data". Therefore, even if there is a complex correspondence relationship rather than a simple linear relationship between the symptoms generated by a person and environmental factors, it is possible to create correspondence information that correlates the intermediate data with the possibility of symptom change relative to the environment with a smaller number of samples of learning data.

[0273] · The second mode of the present invention is "the model that simulates the biological characteristics is the Weber-Fechner law". Therefore, it is possible to appropriately transform the magnitude of the possible influence on a person when the change in the air quality environment becomes a stimulus into intermediate data, and to create correspondence information that correlates the intermediate data with the possibility of symptom change relative to the environment with a smaller number of samples of learning data.

[0274] · The third mode of the present invention is "the model that simulates the biological characteristics is a model that outputs different intermediate data according to the range of values of the environmental factor data or whether the environmental factor data satisfies a condition". Therefore, it is possible to represent the relationship between sweating, tremors caused by temperature, or the relationship between temperature and the activity level of immune cells, etc. with intermediate data, and to create correspondence information that correlates the intermediate data with the possibility of symptom change relative to the environment with a smaller number of samples of learning data.

[0275] · The fourth mode of the present invention is "a model simulating biological characteristics is a model that outputs the intermediate data corresponding to the increase amount or decrease amount only when the change in the environmental factor data changes in only one of the increase or decrease directions, or a model that outputs the intermediate data that changes according to the value of the nth derivative". Therefore, it is possible to represent with the intermediate data physiological reactions that are not noticed when the temperature changes little, physiological reactions where burns do not recover even when the temperature returns after being burned by high temperature, the relationship between air pressure and meteorological diseases, or the relationship between acceleration and motion sickness, and it is possible to create correspondence information that correlates the intermediate data with the possibility of symptom changes with respect to the environment with a smaller number of samples of learning data.

[0276] · The fifth mode of the present invention is "a model simulating biological characteristics is a model that outputs the intermediate data corresponding to the cumulative value of the environmental factor data, or a model that outputs the intermediate data that is different according to the change history of the past values of the environmental factor data even when the current value of the environmental factor data is the same". Therefore, it is possible to represent with the intermediate data the relationships such as the relationship between the intake amount of pollen and the amount of antibodies, the relationship between CO2 concentration and blood oxygen concentration, the relationship between the amount of pollen scattered and hay fever, or the relationship between temperature and humidity and heatstroke, and it is possible to create correspondence information that correlates the intermediate data with the possibility of symptom changes with respect to the environment with a smaller number of samples of learning data.

[0277] · The sixth mode of the present invention is "a model simulating biological characteristics is a model that outputs the intermediate data corresponding to the duration of the environmental factor data remaining within a given range, or the number of times the environmental factor data repeats within a given range". Therefore, it is possible to represent with the intermediate data the relationships such as the adaptation to temperature, the relationship between the number of times of allergen intake and the amount of immune response (allergic reaction), etc., and it is possible to create correspondence information that correlates the intermediate data with the possibility of symptom changes with respect to the environment with a smaller number of samples of learning data.

[0278] · The seventh mode of the present invention is "a model simulating biological characteristics is a model that outputs the intermediate data that changes after a given time has elapsed since the time when the environmental factor data is generated". Therefore, it is possible to represent with the intermediate data relationships such as a runny nose that is delayed after inhaling pollen, or a relationship where the immunity takes effect with a delay after contact with bacteria, and it is possible to create correspondence information that correlates the intermediate data with the possibility of symptom changes with respect to the environment with a smaller number of samples of learning data.

[0279] · The eighth aspect of the present invention is that "the model simulating the characteristics of an organism is a log function, an exponential function, or an nth-degree function that takes the environmental factor data as input and the intermediate data as output", so the relationship between the amount of dust and asthma symptoms, etc. can be represented by the intermediate data, and the corresponding information that correlates the intermediate data with the possibility of symptom changes with respect to the environment can be created with a smaller number of samples of learning data.

[0280] · The ninth aspect of the present invention is that "the control unit uses the corresponding information that also correlates the environmental factor data, and predicts the possibility of the symptom change based on the intermediate data and the environmental factor data", so the possibility of symptom changes can be predicted not only based on the intermediate data but also based on the environmental factor data.

[0281] · The tenth aspect of the present invention is that "the possibility of symptom change is the possibility of deterioration or improvement of any one of allergic symptoms, asthma symptoms, meteorological diseases, infectious diseases, decreased sleep quality, decreased wakefulness / sleepiness, autonomic nerve disorders, debility, dementia / delirium, memory decline, motor function decline, heat stroke, motion sickness, or VR dizziness", so the possibility of changes in various symptoms can be predicted.

[0282] · The eleventh aspect of the present invention is that "the environmental factor data is a statistic obtained by statistical processing", so the statistical processing rather than the environmental factor data itself can be transformed into the intermediate data, and since the corresponding information correlates this intermediate data with the possibility of symptom changes with respect to the environment, the prediction accuracy can be improved.

[0283] · The twelfth aspect of the present invention is that "the possibility of the symptom change is predicted based on the actually measured environmental factor data and the intermediate data, or the predicted value of the environmental factor data and the intermediate data", so the possibility of symptom changes can be predicted not only based on the actually measured environmental factor data and the intermediate data but also based on the predicted value of the environmental factor data and the intermediate data.

[0284] · The thirteenth aspect of the present invention is that "using the intermediate data as an explanatory variable and the symptom change information reported for asthma symptoms, allergic symptoms, meteorological diseases, infectious diseases, decreased sleep quality, decreased wakefulness / sleepiness, autonomic nerve disorders, debility, dementia / delirium, memory decline, motor function decline, heat stroke, motion sickness, or VR dizziness as teacher data, the corresponding information is generated using a machine learning method", so the corresponding information that has learned the correspondence between the explanatory variable and the teacher data can be generated, and the possibility of these symptom changes can be predicted using this corresponding information.

[0285] · The fourteenth aspect of the present invention is to "predict the likelihood of an individual's symptom change based on the first correspondence information for multiple people and the second correspondence information for an individual", so it is possible to generate the correspondence information for multiple people and for an individual respectively. Since the likelihood of symptom change is predicted using two pieces of correspondence information respectively, it is possible to emphasize the one with a higher risk and provide it to each person.

[0286] · The fifteenth aspect of the present invention is to "predict the likelihood of the symptom change based on the correspondence information generated for each season, each target disease, or each of the allergens", so it is possible to generate and predict the likelihood of symptom change for each season, each target disease, or each allergen.

[0287] · The sixteenth aspect of the present invention is to "display the intermediate data and the likelihood of the symptom change on the same screen", so it is easy to grasp how much likelihood of symptom change there is with respect to the current intermediate data.

[0288] This application claims the priority based on Japanese Patent Application No. 2022-187732 filed with the Japan Patent Office on November 24, 2022, and incorporates the entire contents of Japanese Patent Application No. 2022-187732 into this application.

[0289] Reference Signs Explanation

[0290] 10: Environmental Equipment

[0291] 11: Environmental Sensor

[0292] 60: Information Processing Device

[0293] 70: User Terminal

[0294] 100: Human Symptom Change Prediction System.

Claims

1. A symptom change prediction system for an organism, which is a symptom change prediction system for an organism having an environmental sensor and an information processing device. Among them, the environmental sensor detects environmental factor data related to environmental factors in the target space. The information processing device has a control unit, and this control unit transforms the environmental factor data into intermediate data through a model that simulates the organism characteristics associated with symptoms relative to the environment. The control unit uses at least corresponding information that correlates the intermediate data with the possibility of symptom change relative to the environment, and predicts the possibility of the symptom change based on the intermediate data.

2. The symptom change prediction system for an organism according to claim 1, wherein the model that simulates the organism characteristics is the Weber-Fechner law.

3. The symptom change prediction system for an organism according to claim 1, wherein the model that simulates the organism characteristics is a model that outputs different intermediate data according to the range of values of the environmental factor data or whether the environmental factor data satisfies a condition.

4. The symptom change prediction system for an organism according to claim 1, wherein the model that simulates the organism characteristics is a model that outputs the intermediate data corresponding to the increase amount or decrease amount only when the change of the environmental factor data changes in one of the increase or decrease directions, or a model that outputs the intermediate data that changes according to the value of the nth derivative.

5. The symptom change prediction system for an organism according to claim 1, wherein the model that simulates the organism characteristics is a model that outputs the intermediate data corresponding to the cumulative value of the environmental factor data, or a model that outputs different intermediate data according to the change history of the past values of the environmental factor data even when the current values of the environmental factor data are the same.

6. The symptom change prediction system for an organism according to claim 1, wherein the model that simulates the organism characteristics is a model that outputs the intermediate data corresponding to the duration of the environmental factor data remaining within a given range of values, or the number of times the environmental factor data repeats within a given range of values.

7. The symptom change prediction system for an organism according to claim 1, wherein the model that simulates the organism characteristics is a model that outputs the intermediate data that changes after a given time has elapsed since the time when the environmental factor data is generated.

8. The symptom change prediction system for an organism according to claim 1, wherein the model that simulates the organism characteristics is a log function, exponential function or nth function that takes the environmental factor data as input and the intermediate data as output.

9. The symptom change prediction system for an organism according to any one of claims 1 to 8, wherein the control unit uses corresponding information that also correlates the environmental factor data, and predicts the possibility of the symptom change based on the intermediate data and the environmental factor data.

10. The symptom change prediction system for an organism according to claim 1, wherein The possibility of the symptom change is the possibility of deterioration or improvement of any one of allergic symptoms, asthma symptoms, meteorological diseases, infectious diseases, decreased sleep quality, decreased wakefulness / sleepiness, autonomic nerve disorders, debility, dementia / delirium, memory decline, motor function decline, heat stroke, motion sickness, or VR dizziness.

11. The system for predicting symptom changes of an organism according to claim 1, wherein the environmental factor data is a statistic obtained by statistical processing.

12. The system for predicting symptom changes of an organism according to claim 9, wherein the control unit predicts the possibility of the symptom change based on the actually measured environmental factor data and the intermediate data, or the predicted value of the environmental factor data and the intermediate data.

13. The system for predicting symptom changes of an organism according to claim 1, wherein the control unit uses the intermediate data as an explanatory variable, uses the symptom change information reported on asthma symptoms, allergic symptoms, meteorological diseases, infectious diseases, decreased sleep quality, decreased wakefulness / sleepiness, autonomic nerve disorders, debility, dementia / delirium, memory decline, motor function decline, heat stroke, motion sickness, or VR dizziness as teacher data, and uses a machine learning method to generate the corresponding information.

14. The system for predicting symptom changes of an organism according to claim 13, wherein the control unit uses the intermediate data as an explanatory variable and the symptom change information reported by multiple people as teacher data, and uses a machine learning method to generate first corresponding information, uses the intermediate data as an explanatory variable and the symptom change information reported by an individual as teacher data, and uses a machine learning method to generate second corresponding information, and the control unit predicts the possibility of an individual's symptom change based on the possibilities of symptom changes predicted by the first corresponding information and the second corresponding information respectively.

15. The system for predicting symptom changes of an organism according to claim 13 or 14, wherein the control unit generates the corresponding information for each season, each target disease, or each allergen of each allergic symptom, and predicts the possibility of the symptom change based on the corresponding information generated for each season, each target disease, or each allergen.

16. The system for predicting symptom changes of an organism according to any one of claims 1 to 8, wherein the control unit displays the intermediate data and the possibility of the symptom change on the same screen.

17. An information processing device, wherein the information processing device receives environmental factor data related to environmental factors of an object space from an environmental sensor, the information processing device has a control unit that transforms the environmental factor data into intermediate data through a model that simulates the biological characteristics associated with symptoms relative to the environment, and the control unit predicts the possibility of the symptom change based on the intermediate data using at least the corresponding information that correlates the intermediate data with the possibility of symptom changes relative to the environment.

18. A method for predicting symptom changes, which is a method for predicting symptom changes performed by a symptom change prediction system of an organism having an environmental sensor and an information processing device, wherein, the environmental sensor detects environmental factor data related to environmental factors of the target space, the control unit performs the following processing: processing of transforming the environmental factor data into intermediate data through a model that simulates the organism characteristics associated with symptoms relative to the environment; and processing of predicting the possibility of symptom changes based on the intermediate data using at least corresponding information that correlates the intermediate data with the possibility of symptom changes relative to the environment.

Images