Immune condition prediction system, immune condition prediction method, and program

Abstract

To provide an immune state prediction system capable of predicting a future immune state by grasping not only a conventional medical examination and life habit but also a factor of the immune state and genetic information.SOLUTION: An information processing apparatus includes an acquisition unit that acquires state data including at least genetic information of a user and execution data of the user, a learning model creation unit that learns execution data of the user having the state data in association with each other and generates a learning model for predicting an immune state of the user with respect to predetermined state data, a prediction unit that outputs immune state prediction data obtained by predicting an immune state on the basis of the learning model from newly acquired state data, a difference between the immune state prediction data and execution data of the user having the immune state prediction data, and a provision unit that provides at least one of the state data, the execution data, the immune state prediction data, and the analysis data to a user and / or a third party company.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an immune status prediction system, an immune status prediction method, and a program. [Background technology]

[0002] In recent years, the average life expectancy in Japan has increased, and the declining birthrate and aging population have led to concerns about rising social security costs and the burden on the real economy. Therefore, in addition to promoting healthy life expectancy after retirement, companies are also focusing on health management while employees are still working. There is a movement to make greater use of the results of regular health checkups, including company health checkups, to predict future health conditions and contribute to improving health and preventing disease.

[0003] In order to predict the future health condition described above, accurate information to grasp various conditions is required in addition to the results of regular health checkups. Deterioration of health, or the onset of disease, is basically determined by genetic and environmental factors.

[0004] Genetic factors can be identified through genetic information, and environmental factors can be identified through condition information that indicates the individual's lifestyle, etc. In other words, by understanding the genetic and condition information, it becomes possible to more accurately predict future immune conditions, which is expected to increase healthy life expectancy and create a demand for technology that will significantly prevent medical and social opportunity losses.

[0005] For example, the inventor has disclosed a technology for predicting a user's immune status based on specified status data, based on a learning model created by learning and associating status data (sleep status, exercise status, lifestyle status, living status, work status, dietary status) which are environmental factors related to immune status with implementation data (health checkup results, immune test results) (Patent Document 1). [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Patent No. 7365736 Summary of the Invention [Problem to be solved by the invention]

[0007] However, the technology disclosed by the inventor in Patent Document 1 does not involve learning based on the user's genetic information related to genetic factors, making it difficult to predict future immune status based on genetic diseases and other conditions.

[0008] The present invention has been made in consideration of the above circumstances, and aims to provide an immune status prediction system that more accurately predicts a user's immune status from newly acquired status data based on a learning model that correlates the user's immune status data, which includes at least genetic information, with implementation data, which includes at least health checkup results, immune test results, and genetic test results. [Means for solving the problem]

[0009] The present invention provides the following solutions.

[0010] The first aspect of the present invention is a system including: an acquisition unit that acquires status data including at least genetic information from status data including a user's sleep status, exercise status, lifestyle status, working status, dietary status, and genetic information related to the immune status; and implementation data including at least the user's health check results, immune test results, and genetic test results; a learning model creation unit that associates and learns the user's experience data with the condition data, and generates a learning model that predicts the immune status of the user for the user's predetermined condition data; a prediction unit that outputs immune status prediction data that predicts an immune status based on the learning model from newly acquired status data; an analysis unit that analyzes the difference between the immune status prediction data and the implementation data of a user who has the immune status prediction data to generate analysis data; and a providing unit that provides at least one of the status data, the implementation data, the immune status prediction data, and the analysis data to a user and / or a third-party company.

[0011] According to the first invention, a learning model for predicting a future immune status can be created from condition data including at least acquired genetic information and implementation data, and a user's future immune status can be predicted from newly acquired user condition data based on the learning model. Furthermore, by comparing the predicted immune status prediction data with the predicted user's implementation data, such as health checkup results, immune test results, and genetic test results, it is possible to analyze the difference between the prediction at the time of acquiring the user's condition data and the time of acquiring the implementation data.

[0012] Additionally, at least one of status data, performance data, immune status prediction data, and analytical data may be provided to a user or a third-party company.

[0013] The second invention of the present invention is an invention related to the first invention, and provides an immune status prediction system in which the learning model creation unit updates the learning model based on the analysis data analyzed by the analysis unit.

[0014] According to the second invention, in the first invention, the difference between the predicted immune status prediction data and the implementation data that is the prediction result is analyzed, and the analysis results are fed back to the learning model creation unit, thereby making it possible to improve the prediction accuracy of the learning model.

[0015] A third aspect of the present invention is an invention according to the first or second aspect of the present invention, comprising: a standardization index creation unit that creates a standardization index, which is an index for achieving a standard immune status, from the immune status prediction data, the implementation data, and the analysis data of the user; a standardized index providing unit that provides the standardized index to the user and / or the third-party company; The standardized index provides an immune status prediction system that includes at least recommendations for additional testing and / or improvement suggestions related to standardization.

[0016] According to the third invention, in the first or second invention, a standardization index is created from the user's immune status prediction data and / or implementation data, which is an index for achieving a standard immune status and includes at least recommendations for additional tests related to standardization and / or suggestions for improvement, and the created standardization index can be provided to the user and / or a third-party company.

[0017] The fourth invention of the present invention is an invention related to the first or second invention, wherein the providing unit provides an immune status prediction system that provides at least one of the status data, the implementation data, the immune status prediction data, and the analysis data to a third-party company in accordance with setting data preset by the third-party company.

[0018] According to the fourth invention, in the first or second invention, the providing unit is capable of providing at least one of status data, implementation data, immune status prediction data, and analysis data to a third-party company in accordance with setting data preset by the third-party company.

[0019] A fifth invention is an immune status prediction system, A step of acquiring status data including at least genetic information from status data including sleep status, exercise status, lifestyle status, working status, dietary status, and genetic information related to the user's immune status, and implementation data including at least the user's health check results, immune test results, and genetic test results; A step of associating and learning the user's experience data with the condition data, and generating a learning model that predicts the immune status of the user for the user's predetermined condition data; a step of outputting immune status prediction data obtained by predicting an immune status based on the learning model from the newly acquired status data; analyzing the difference between the immune status prediction data and the implementation data to generate analysis data; providing at least one of the status data, the performance data, the immune status prediction data, and the analysis data to a user and / or a third party company; The present invention provides an immune status prediction method executed on a computer system comprising:

[0020] A sixth invention is an immune status prediction system, comprising: A step of acquiring status data including at least genetic information from status data including sleep status, exercise status, lifestyle status, working status, dietary status, and genetic information related to the user's immune status, and implementation data including at least health checkup results, immune test results, and genetic test results of the user; A step of learning by associating the user's experience data with the condition data and generating a learning model that predicts the immune status of the user for the user's predetermined condition data; a step of outputting immune status prediction data obtained by predicting an immune status based on the learning model from the newly acquired status data; generating analysis data by analyzing the difference between the immune status prediction data and the implementation data; providing at least one of the status data, the performance data, the immune status prediction data, and the analysis data to a user and / or a third party company; A computer-readable program for executing the above is provided. [Effects of the Invention]

[0021] According to the present invention, an immune status prediction system, method, and program are provided that can grasp the immune status including causes, including genetic factors, and predict the future immune status, thereby enabling more effective health management. [Brief explanation of the drawings]

[0022] [Figure 1]FIG. 1 is a basic overview of an immune status prediction system 1 according to an embodiment of the present invention. [Figure 2] FIG. 2 is a basic configuration diagram of an immune status prediction system 1 according to an embodiment of the present invention. [Figure 3] FIG. 3 is a diagram showing a learning model generation processing flow executed by the immune status prediction system 1 according to the embodiment of the present invention. [Figure 4] FIG. 4 is an example of a display screen of the sleep state data of the state data 102 acquired by the computer 3, which is displayed on the user terminal 2. [Figure 5] FIG. 5 is an example of a display screen of the genetic polymorphism test results of the condition data 102 acquired by the computer 3, which is displayed on the user terminal 2. [Figure 6] FIG. 6 shows an example of a display screen of the immunoassay results of the implementation data 103 acquired by the computer 3, displayed on the user terminal 2. In FIG. [Figure 7] FIG. 7 is a diagram showing the immune status prediction data creation process flow executed by the immune status prediction system 1 according to the embodiment of the present invention. [Figure 8] 10 is an example of a display screen of immune status prediction data 104 predicted by a computer 3 and displayed on a user terminal 2. [Figure 9] FIG. 9 is a diagram showing an outline of the analysis process executed by the immune status prediction system 1 according to the embodiment of the present invention and a flow of the analysis process. [Figure 10] FIG. 10 shows an example of an analysis display screen of the analysis data 105 created by the computer 3 and displayed on the user terminal 2. [Figure 11] FIG. 11 is a diagram showing an outline of the learning model improvement process executed by the immune status prediction system 1 according to the embodiment of the present invention and a flow of the learning model improvement process. [Figure 12] FIG. 12 is a diagram showing the flow of a selective data providing process executed by the immune status prediction system 1 according to an embodiment of the present invention. [Figure 13] FIG. 13 is a configuration diagram of the standardized index creation and provision process executed by the immune status prediction system 1 according to the embodiment of the present invention. [Figure 14]FIG. 14 is a diagram showing the flow and outline of the standardized index creation and provision process executed by the immune status prediction system 1 according to the embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0023] The best mode for carrying out the present invention will be described below with reference to the drawings. However, these are merely examples, and the technical scope of the present invention is not limited to these.

[0024] [Overview of immune status prediction system 1] 1 is a diagram for explaining an overview of an immune status prediction system 1 according to an embodiment of the present invention. The overview of the immune status prediction system 1 will be explained based on FIG.

[0025] As shown in FIG. 1, an immune status prediction system 1 according to an embodiment of the present invention is a computer system that includes a user terminal 2 (2A, 2B) and a computer 3 and is used to predict immune status.

[0026] The user terminal 2 of the immune status prediction system 1 according to an embodiment of the present invention is, for example, a terminal for sending and receiving data to a computer 3, and may be an electronic terminal such as a personal computer, laptop computer, smartphone or tablet terminal, or a wearable terminal such as a head-mounted display such as smart glasses or a smart watch, and in this embodiment, is one or more personal computers.

[0027] Furthermore, the computer 3 of the immune status prediction system 1 according to an embodiment of the present invention is, for example, an on-premise server or an on-premise computing system, or a cloud server or a cloud computing system, and in this embodiment is a cloud computing system.

[0028] It is also assumed that there may be a plurality of users 4 and third-party companies 5.

[0029] The computer 3 of the immune status prediction system 1 according to an embodiment of the present invention may be connected to the user terminal 2 via a network 6 such as a public line network in a data communication manner, and may transmit and receive necessary data and information.

[0030] The computer 3 of the immune status prediction system 1 according to the embodiment of the present invention includes an acquisition module 201 that acquires at least user attribute data 101 (111), status data 102 (112), and implementation data 103 from a user terminal 2 (2A, 2B); a learning model creation module 202 that creates a learning model 10 for generating data to predict future immune status from the status data 102 and the implementation data 103; a prediction module 203 that predicts an immune status from newly acquired status data 112 based on the learning model 10 and outputs the predicted immune status data 104; and a providing module 204 that provides at least the output immune status prediction data 104 to a user 4 and / or a third-party company 5, thereby enabling prediction of future immune status through processing performed by each of them.

[0031] Here, the user attribute data 101 (111) refers to data including at least attribute data such as the user's age, gender, height, weight, hobbies, educational background, work history, and family composition, and the provision module 204 may provide the user attribute data 111 together with the immune status prediction data 104 to the user 4 and / or third-party company 5.

[0032] The status data 102 (112) includes at least genetic data of the user, such as the entire genome sequence, gene polymorphisms, and gene expression levels, and further includes at least sleep status data, such as sleep time in a predetermined period, sleep depth, and frequency of waking up during sleep, exercise status data, such as number of steps, exercise frequency, and exercise time, lifestyle status data, such as smoking frequency, drinking frequency, and alcohol amount, living status data, such as active hours and sleeping hours, work status data, such as working hours and work content, and dietary status data, such as meal content, snack frequency, calorie intake, and nutritional balance.

[0033] The implementation data 103 includes at least health checkup data of an actual health check at a specified timing (specified period) of the user having the status data 102, immune test data of an actual immune test, treatment data indicating that the user actually received treatment, and genetic test data which is at least the test results of genome sequences, specific gene polymorphisms, and gene expression levels.

[0034] The user attribute data 101 (111), condition data 102 (112), implementation data 103, and immune status prediction data 104 may be linked to the user attribute data and stored inside the computer 3, or may be stored outside the computer 3.

[0035] As shown in Figure 1, the immune status prediction system 1 according to an embodiment of the present invention first generates a learning model 10 using a learning model creation module 202 from user attribute data 101 and status data 102 acquired by an acquisition module 201. Next, the acquisition module 201 of the immune status prediction system 1 according to the embodiment of the present invention acquires, for example, status data 112 input by the user 4 as new status data via the user terminal 2B or the like. Furthermore, the prediction module 203 predicts a future immune status from the status data 112 based on the learning model 10 and outputs the predicted immune status data 104. The output immune status prediction data 104 is provided to the user 4 and / or a third-party company 5 by the provision module 204, thereby enabling the immune status prediction system 1 according to the embodiment of the present invention to predict a future immune status.

[0036] The above is a basic overview of the immune status prediction system 1 according to the embodiment of the present invention.

[0037] [Basic configuration of immune status prediction system 1] 2 is a diagram illustrating the basic configuration of the immune status prediction system 1 according to the embodiment of the present invention. The basic configuration of the immune status prediction system 1 according to the embodiment of the present invention will be described with reference to FIG.

[0038] The computer 3 of the immune status prediction system 1 according to the embodiment of the present invention includes a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a RAM (Random Access Memory), a ROM (Read Only Memory), etc. as a control unit 300. The control unit 300 cooperates with a storage unit 310 to realize an acquisition module 201, a learning model creation module 202, a prediction module 203, and a provision module 204.

[0039] The user terminal 2 is assumed to have, as an input unit 320, the functions necessary to operate the computer 3 communicably connected via the network 6. Examples of input devices include an LCD display that provides a touch panel function, a keyboard, a mouse, a pen tablet, hardware buttons on the device, and a microphone for voice recognition. The present invention is not particularly limited in its functions depending on the input method.

[0040] The computer 3 includes a storage unit 310 for data storage, such as a hard disk, semiconductor memory, recording medium, or memory card. The data may be stored in a cloud service, a database, or the like.

[0041] The above is the basic configuration of the immune status prediction system 1. Hereinafter, the immune status prediction system 1 according to the embodiment of the present invention will be described in detail based on the above basic outline and basic configuration.

[0042] [Learning model generation process] Fig. 3 is a diagram showing the flow of a learning model generation process executed by the immune status prediction system 1 according to an embodiment of the present invention. Fig. 4 is an example of a display screen of sleep status data in the status data 102 acquired by the computer 3, displayed on the user terminal 2. Fig. 5 is an example of a display screen of gene polymorphism test results in the status data 102 acquired by the computer 3, displayed on the user terminal 2. Fig. 6 is an example of a display screen of immune test results in the implementation data 103 acquired by the computer 3, displayed on the user terminal 2. The learning model generation process realized by the immune status prediction system 1 will be described with reference to Figs. 3 to 6.

[0043] As shown in FIG. 3 , the acquisition module 201 of the immune status prediction system 1 according to an embodiment of the present invention includes at least genetic data of the user, such as the entire genome sequence, gene polymorphisms, and gene expression levels, and further includes status data 102 including at least sleep status data, such as sleep duration for a predetermined period, sleep depth, and frequency of waking up during sleep, exercise status data, such as number of steps, exercise frequency, and exercise duration, lifestyle status data, such as smoking frequency, drinking frequency, and alcohol intake, living status data, such as activity hours and sleeping hours, work status data, such as working hours and work content, and dietary status data, such as meal content, snack frequency, calorie intake, and nutritional balance. At least the implementation data 103 including at least health checkup data of an actual health checkup, immune test data of an actual immune test, treatment data indicating actual treatment, and genetic test data which is the test results of at least genome sequences, specific gene polymorphisms, and gene expression levels, is obtained at a predetermined timing (predetermined period) for the user having the status data 102 (step S401).

[0044] The acquisition module 201 may also acquire user attribute data 101 including at least attribute data such as the user's age, sex, height, weight, hobbies, educational background, work history, family structure, etc. Furthermore, information related to genes, such as whether or not blood relatives have a specific genetic disease, may be acquired as user attribute data.

[0045] Furthermore, the genetic data and genetic testing data herein may be genetic polymorphism data obtained from a Genome-Wide Association Study (GWAS) or exome analysis, and are particularly preferably genetic information on immune cells related to immune status.

[0046] Next, the learning model creation module 202 of the immune status prediction system 1 according to an embodiment of the present invention learns in association with the practice data 103 of the user having the acquired status data 102, and generates a learning model 10 that predicts the immune status of the user based on the specified status data (step S402).

[0047] Here, the learning model 10 may be generated by adding the implementation data 103 as annotation data to the state data 102. The annotation data is training data for training a machine learning model, and the method for adding the annotation data is not particularly limited, and the data may be added manually or by using an automated tagging tool such as an annotation tool.

[0048] Furthermore, by referring to the respective predetermined periods of the user's condition data 102 and implementation data 103, the intervals of the predetermined periods may be associated and learned.

[0049] In addition, when the learning model creation module 202 correlates and learns the above-mentioned status data 102 and implementation data 103, it may also correlate and learn the user attribute data 101 of the user, for example, by correlating the user's age and gender as status data or implementation data.

[0050] Learning by associating the status data 102 with the implementation data 103, for example, by associating the sleep status of the user for a predetermined period (see the date in FIG. 4) as shown in the sleep status data that is the status data 102 in FIG. 4, the gene polymorphism test results that are the user's genetic information that are the status data 102 in FIG. 5, and the immune test results that are the implementation data 103 of the user shown in FIG. 6 and indicate the immune status, can improve the prediction accuracy of the immune test results for the future period indicated by the actual measurement date in FIG. 6 based on the tendency of the sleep status for a predetermined period and the user's genetic information.

[0051] In this way, by using learned data for predicting future immune status from at least the acquired status data 102 and implementation data 103, it is possible to generate a learning model 10 that can mechanically predict status for a huge number of patterns.

[0052] The above is the learning model generation process executed by the immune status prediction system 1 according to the embodiment of the present invention.

[0053] [Immune status prediction data creation process] Fig. 7 is a diagram showing the immune status prediction data creation process flow executed by the immune status prediction system 1 according to an embodiment of the present invention. Fig. 8 is an example of a display screen of the immune status prediction data 104 predicted by the computer 3 and displayed on the user terminal 2. The immune status prediction data creation process realized by the immune status prediction system 1 will be described with reference to Figs. 7 and 8.

[0054] As shown in FIG. 7, the acquisition module 201 of the immune status prediction system 1 according to the embodiment of the present invention acquires at least the status data 112 of the user 4 (step S411).

[0055] It is preferable that the status data 112 includes at least genetic data such as the entire genome sequence of user 4, gene polymorphisms, and gene expression levels, sleep status data of user 4 for a predetermined period, exercise status data, lifestyle habit status data, living status data, work status data, and dietary status data, but it does not necessarily have to include genetic data such as the entire genome sequence, gene polymorphisms, and gene expression levels.

[0056] Furthermore, when acquiring the status data 112, the acquisition module 201 may also acquire the user attribute data 111 of the user 4.

[0057] Next, the prediction module 203 of the immune status prediction system 1 predicts the future immune status of the user 4 from the acquired status data 112 based on the learning model 10, and outputs it as immune status prediction data 104 (step S412).

[0058] The prediction module 203 may output immune state prediction data from the acquired user attribute data 111 and state data 112 based on the learning model 10.

[0059] 8, the immune status prediction data 104 is output as predicted values ​​of, for example, the white blood cell count, B cell count, and NK cell count related to the immune status for a predetermined period of time. Here, the predetermined period may be, for example, a future period during which the user 4 will measure implementation data related to the immune status.

[0060] The output immune status prediction data 104 is provided to the user 4 and / or the third-party company 5 by the providing module 204 of the immune status prediction system 1 (step S413).

[0061] In this way, by using the immune status prediction data creation process to output immune status prediction data 104 based on the learning model 10 from the acquired status data 112, it becomes possible to predict the future immune status of the user from the status data for a specified period of time.

[0062] The immune status prediction data creation process executed by the immune status prediction system 1 according to the embodiment of the present invention has been described above.

[0063] [Analysis Processing] Fig. 9 is a diagram showing an overview and flow of the analysis process executed by the immune status prediction system 1 according to an embodiment of the present invention. Fig. 10 is an example of an analysis display screen of the analysis data 105 created by the computer 3 and displayed on the user terminal 2. The analysis process executed by the immune status prediction system 1 will be described with reference to Figs. 9 and 10.

[0064] As shown in Figure 9, the acquisition module 201 of the immune status prediction system 1 acquires immune status prediction data 104 of user 4 whose immune status was predicted in the above-mentioned immune status prediction data creation process, and implementation data 113 related to the immune status of user 4 measured over a specified period of time (step S421).

[0065] It is desirable that the predetermined period of the implementation data 113 relating to the immune status of user 4 measured during that period be data measured during a period that includes the period predicted by the immune status prediction data 104. Furthermore, when obtaining the immune status prediction data 104 and the implementation data 113 of user 4, user attribute data 111 of user 4 may also be obtained.

[0066] Furthermore, if the immune status prediction data 104 has already been stored in the memory unit 310 of the immune status prediction system 1, this may be used regardless of the acquisition module 201.

[0067] Next, the analysis module 205 of the immune status prediction system 1 analyzes the difference between the acquired immune status prediction data 104 and the implementation data 113, and outputs the result as analysis data 105 as shown in FIG. 10 (step S422).

[0068] Here, the analysis of the difference between the immune status prediction data 104 and the implementation data 113 refers to at least an analysis of the causes of the discrepancy, including the passage of time between the prediction and the actual situation, that occurs at the time when the implementation data 113 was generated and the time when the status data 112 used to create the immune status prediction data 104 was generated.

[0069] For example, as shown in Figure 10, the results of an analysis of the difference between the actual measured values ​​of white blood cell count, B cell count, and NK cell count in the immune test results of user 4's implementation data 113 and the predicted values ​​of the same immune-related items in the immune status prediction data 104 are shown, and the analysis result shows that the cause of the discrepancy is that treatment was started after the immune status prediction data 104 was presented.

[0070] The method for analyzing the cause is not particularly limited, and for example, the cause may be analyzed using a rule-based or model-based method based on machine learning, or the cause may be analyzed using a method such as manual input or an automated tagging tool such as an annotation tool.

[0071] When the analysis module 205 of the immune status prediction system 1 determines that the implementation data 113 required for analysis is insufficient, it may create request data requesting tests and data necessary or recommended for analysis, for example, from among health checkup data from an actual health check, immune test data from an actual immune test, treatment data indicating actual treatment received, and genetic test data that is at least the test results of genome sequences, specific gene polymorphisms, and gene expression levels, at a predetermined timing (predetermined period) for the user. The created request data is provided to the user 4 and / or third-party company 5 by the provision module 204.

[0072] Next, the providing module 204 of the immune status prediction system 1 provides the output analysis data 105 to the user 4 and / or the third-party company 5 (step S423).

[0073] The analysis process performed by the immune status prediction system 1 according to this embodiment of the present invention analyzes the difference between the user's implementation data and immune status prediction data, making it possible to understand the changes, including their causes, from the time of status prediction to the time of measurement of the implementation data, thereby contributing to more effective health management.

[0074] The above is the analysis process executed by the immune status prediction system 1 according to the embodiment of the present invention.

[0075] [Learning model improvement processing] 11 is a diagram showing an overview of the learning model improvement process executed by the immune status prediction system 1 according to an embodiment of the present invention and a flow of the learning model improvement process. The learning model improvement process executed by the immune status prediction system 1 will be described with reference to FIG.

[0076] As shown in Figure 11, the learning model creation module 202 of the immune status prediction system 1 learns from analysis data 105 that analyzes the difference between the immune status prediction data predicted based on the learning model 10 and the implementation data that is the result of the immune status prediction data, according to the causes of the discrepancy between the prediction and the actual situation, and updates the learning model 10 (step S431).

[0077] The analytical data 105 used in the learning model improvement process may be analytical data 105 stored in the memory unit 310 of the immune status prediction system 1, or external analytical data may be acquired via the acquisition module 201 using a user terminal 2 via the network 6. The external analytical data includes at least the user attribute data, condition data, implementation data, and immune status prediction data used in the analysis.

[0078] According to the learning model improvement process executed by the immune status prediction system 1 of this embodiment of the present invention, it is possible to improve the prediction accuracy of the learning model 10 by learning using analysis data 105 that analyzes predictions based on the learning model 10 and the actual situation.

[0079] The above is the learning model improvement process executed by the immune status prediction system 1 according to the embodiment of the present invention.

[0080] [Selective data provision processing] 12 is a diagram showing the flow of the selective data provision process executed by the immune status prediction system 1 according to the embodiment of the present invention. The selective data provision process executed by the immune status prediction system 1 will be described with reference to FIG.

[0081] As shown in Figure 12, the provision module 204 of the immune status prediction system 1 extracts at least the relevant data from the user attribute data 101 (111), status data 102 (112), implementation data 103 (113), immune status prediction data 104, and analysis data 105 based on extraction conditions preset by the third-party company 5 (step S441).

[0082] The extraction conditions may be, for example, conditions for limiting extraction to various data related to a specific genetic disease, and conditions may be set such that the user attribute data, such as personal information related to the user, at the time of extraction is limited to the user attribute data of only the user who has been authorized to provide the data to the third-party company 5 at the time of acquisition.

[0083] Next, the providing module 204 of the immune state prediction system 1 provides the data extracted according to the extraction conditions to the third-party company 5 (step S442).

[0084] In this way, by providing the data to the third-party company 5 based on the setting data that the third-party company 5 has set in advance, it becomes possible to accumulate, for example, trends in the information that the third-party company 5 requires.

[0085] The above is the selective data providing process executed by the immune status prediction system 1 according to the embodiment of the present invention.

[0086] [Standardized index creation and provision processing] Fig. 13 is a configuration diagram of the standardized index creation and provision process executed by the immune status prediction system 1 according to an embodiment of the present invention. Fig. 14 is a diagram showing the flow and overview of the standardized index creation and provision process executed by the immune status prediction system 1 according to an embodiment of the present invention. The standardized index creation and provision process executed by the immune status prediction system 1 will be described with reference to Figs. 13 and 14.

[0087] 13, the standardized index creation process executed by the immune status prediction system 1 according to the embodiment of the present invention is realized by a computer 3, a user terminal 2, and a network 6 connecting the computer 3 and the user terminal 2. The above-mentioned hardware configuration is similar to the basic configuration, so a description thereof will be omitted. The control unit 300 of the computer 3 in the immune status prediction system 1 according to the embodiment of the present invention cooperates with a memory unit 310 to realize a standardized index creation module 206 and a standardized index provision module 207.

[0088] As shown in Figure 14, the standardized index creation module 206 of the immune status prediction system 1 according to an embodiment of the present invention generates a standard model 20 for grasping a standard status from the status data 102 and the implementation data 103 (step S451).

[0089] Here, the standard model 20 may be generated by adding the user attribute data 101 in addition to the condition data 102 and the implementation data 103. Here, the standard model 20 may be the average value and / or median value of a healthy or ideal health state (immune state). For example, a standard model for a user with a genetic disease may be generated from genetic information in the condition data of the user with the genetic disease.

[0090] Next, the standardized index creation module 206 of the immune status prediction system 1 detects differences from the standard model 20 from the analytical data 105 based on the standard model 20, and creates a standardized index 106 that includes suggested improvement items for approximating the standard model 20 (step S452).

[0091] Furthermore, the improvement suggestions created by the standardized index creation module 206 may include not only suggestions for improving the user's immune status, but also testing suggestions to understand the user's status in more detail.

[0092] In this case, instead of the analysis data 105 used to create the standardized index 106, the standardized index may be created using newly acquired implementation data.

[0093] The standardized index providing module 207 of the immune status prediction system 1 includes: Next, the standardized index providing module 207 of the immune status prediction system 1 provides the created standardized index 106 to the user 4 and / or the third-party company 5 (step S453).

[0094] According to the standardized index creation and provision process of the immune status prediction system 1, it is possible to present to the user 4 at least an index for achieving a healthy immune status.

[0095] The above is the standardized index creation and provision process executed by the immune status prediction system 1 according to the embodiment of the present invention.

[0096] Although the embodiments of the present invention have been described above, the present invention is not limited to these embodiments. Furthermore, the effects described in the embodiments of the present invention are merely a list of the most preferable effects resulting from the present invention, and the effects of the present invention are not limited to those described in the embodiments of the present invention. [Explanation of symbols]

[0097] 1. Immune status prediction system 2, 2A, 2B User terminal 3. Computer 4 users 5 Third party companies 6 Network 10 Learning Model 20 Standard Model 101,111 User attribute data 102,112 Status Data 103,113 Implementation data 104 Immune status prediction data 105 Analysis Data 106 Standardized indicators 201 Acquisition Module 202 Learning Model Creation Module 203 Prediction Module 204 Provided Modules 205 Analysis Module 206 Standardized Index Creation Module 207 Standardized Index Providing Module

Claims

1. an acquisition unit that acquires status data including at least genetic information from status data including sleep status, exercise status, lifestyle status, living status, work status, dietary status, and genetic information related to the immune status of a user, and implementation data including at least health checkup results, immune test results, and genetic test results of the user; a learning model creation unit that associates and learns the user's experience data with the condition data, and generates a learning model that predicts the immune status of the user for the user's predetermined condition data; a prediction unit that outputs immune status prediction data that predicts an immune status based on the learning model from newly acquired status data; an analysis unit that analyzes the difference between the immune status prediction data and the implementation data of a user who has the immune status prediction data to generate analysis data; An immune status prediction system comprising: a providing unit that provides at least one of the status data, the implementation data, the immune status prediction data, and the analysis data to a user and / or a third-party company.

2. The immune status prediction system according to claim 1 , wherein the learning model creation unit updates the learning model based on the analysis data analyzed by the analysis unit.

3. a standardization index creation unit that creates a standardization index, which is an index for achieving a standard immune status, from the immune status prediction data, the implementation data, and the analysis data of the user; a standardized index providing unit that provides the standardized index to the user and / or the third-party company; The immune status prediction system according to claim 1 or 2, wherein the standardization index includes at least a recommendation for additional testing related to standardization and / or an improvement suggestion.

4. The immune status prediction system of claim 1 or claim 2, wherein the providing unit provides at least one of the status data, the implementation data, the immune status prediction data, and the analysis data to the third-party company in accordance with setting data preset by the third-party company.

5. A step of acquiring status data including at least genetic information from status data including sleep status, exercise status, lifestyle status, working status, dietary status, and genetic information related to the user's immune status, and implementation data including at least the user's health check results, immune test results, and genetic test results; A step of associating and learning the user's experience data with the condition data, and generating a learning model that predicts the immune status of the user for the user's predetermined condition data; a step of outputting immune status prediction data obtained by predicting an immune status based on the learning model from the newly acquired status data; generating analysis data by analyzing a difference between the immune status prediction data and the implementation data of a user who has the immune status prediction data; providing at least one of the status data, the performance data, the immune status prediction data, and the analysis data to a user and / or a third party company; 1. A method for predicting immune status, comprising:

6. A step of acquiring status data including at least genetic information from status data including sleep status, exercise status, lifestyle status, working status, dietary status, and genetic information related to the user's immune status, and implementation data including at least health checkup results, immune test results, and genetic test results of the user; A step of learning by associating the user's experience data with the condition data and generating a learning model that predicts the immune status of the user for the user's predetermined condition data; a step of outputting immune status prediction data obtained by predicting an immune status based on the learning model from the newly acquired status data; generating analysis data by analyzing the difference between the immune status prediction data and the implementation data of a user who has the immune status prediction data; providing at least one of the status data, the performance data, the immune status prediction data, and the analysis data to a user and / or a third party company; A computer-readable program for executing the above.

Images