JP2021072851A - Information processing system and program - Google Patents

Abstract

To establish a technique for grasping a health state of a person.SOLUTION: First extraction means 111 extracts each human being present germ data for M object people matching a first condition, out of N object people. Cluster generation means 101 generates L pieces of clusters to which object people having a same possession pattern of the human being present germ belong, based on each human being present germ data for M people extracted by the first extraction means 111. Second extraction means 112 extracts each human being present germ data for K object people matching a second condition, out of N object people. Cluster expansion means 103 expands the L pieces of clusters by executing processing for causing each of the K object people to additionally belong to the cluster to which the possession pattern of each object person corresponds out of L pieces of clusters. Feature extraction means 104 extracts a feature for each of at least some of the L pieces of clusters which are expanded, based on questionnaire data.SELECTED DRAWING: Figure 2

Description

The present invention relates to information processing systems and programs.

Conventionally, in order to grasp the health condition of a subject, the human indigenous bacteria of the subject have been investigated (see, for example, Patent Document 1).
The technique described in Patent Document 1 described above supports, for example, a dietary habit necessary for realizing a preferable human resident bacterium based on a preset correlation between a human resident bacterium and a dietary habit.

Japanese Unexamined Patent Publication No. 2012-165716

However, it is not always possible to accurately grasp the health condition of the subject only by the prior art including the technique described in Patent Document 1 described above.
That is, in the human body, a large number of indigenous human bacteria exert their functions as a whole, so that a single indigenous human bacterium such as a healthy indigenous human bacterium or a sick human indigenous bacterium. It is difficult to accurately grasp the health condition of the subject only by using only.
In other words, it is necessary to consider the patterns (combinations) of multiple indigenous human bacteria existing in the subject's body.
The present invention has been made in view of such a situation, and an object of the present invention is to be able to establish a technique for grasping a person's health condition.

In order to achieve the above object, the information processing system of one aspect of the present invention is
For each of the N subjects, data including at least information on two or more human indigenous bacteria has been acquired in advance as human indigenous bacteria data, and data including at least data on health status is questionnaire data. In the state of being acquired in advance as
Among the N subjects, the first extraction means for extracting the human indigenous bacterium data for each of the M subjects (M is an integer value less than N) that meets the first condition,
Based on the human indigenous bacterium data of the M subjects extracted by the first extraction means, the cluster generation means for generating L clusters to which the subjects having the same possession pattern of human indigenous bacteria belong. ,
A second extraction means for extracting the indigenous human bacterial data of each of the N subjects, of whom K (K is an integer value of (NM) or less) that meets the second condition. When,
Based on the human indigenous bacterial data of the K subjects extracted by the second extraction means, the possession pattern of the L clusters corresponds to each of the K subjects. A cluster expansion means for expanding the L clusters by executing a process of additionally belonging to the cluster, and
A feature extraction means for extracting features from each of at least a part of the expanded L clusters based on the questionnaire data.
To be equipped.

The information processing apparatus and program corresponding to the information processing system of one aspect of the present invention are also provided as the information processing apparatus and program of one aspect of the present invention.

According to the present invention, it is possible to establish a technique for grasping a person's health condition.

It is a block diagram which shows an example of the hardware composition of the information processing apparatus which concerns on one Embodiment of this invention. It is a functional block diagram which shows an example of the functional configuration example of the information processing apparatus of FIG. It is a flowchart explaining an example of the flow of the clustering process executed by the information processing apparatus of FIG. It is a flowchart explaining an example of the flow of the user evaluation process executed by the information processing apparatus of FIG. It is a schematic diagram explaining the outline of the clustering process executed by the information processing apparatus of FIG. It is a figure which shows an example of the characteristic of each cluster. It is a schematic diagram explaining the outline of the user evaluation process executed by the information processing apparatus of FIG. It is a figure which shows an example of the display image which is displayed on the subject person and the like. It is a figure which shows the outline of an example of the functional configuration example of the information processing apparatus of FIG. 1, and is the functional block diagram which shows the example different from FIG.

Hereinafter, embodiments of the present invention will be described with reference to the drawings.
FIG. 1 is a block diagram showing a hardware configuration of an information processing device according to an embodiment of the present invention.

The information processing device 1 includes a CPU (Central Processing Unit) 21, a ROM (Read Only Memory) 22, a RAM (Random Access Memory) 23, a bus 24, an input / output interface 25, an input unit 26, and an output unit. 27, a storage unit 28, a communication unit 29, and a drive 30 are provided.
The CPU 21 executes various processes according to the program recorded in the ROM 22 or the program loaded from the storage unit 28 into the RAM 23.
Data and the like necessary for the CPU 21 to execute various processes are also appropriately stored in the RAM 23.

The CPU 21, ROM 22 and RAM 23 are connected to each other via the bus 24. An input / output interface 25 is also connected to the bus 24. An input unit 26, an output unit 27, a storage unit 28, a communication unit 29, and a drive 30 are connected to the input / output interface 25.
The input unit 26 is composed of a keyboard, a mouse, and the like, and inputs various information according to a user's instruction operation.
The output unit 27 is composed of a display, a speaker, or the like, and outputs an image or sound.
The storage unit 28 is composed of a hard disk or the like and stores various information data.

The communication unit 29 controls communication with another terminal (not shown) via a network, and the drive 30 is a removable medium composed of a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like. 31 is appropriately attached. The program read from the removable media 31 by the drive 30 is installed in the storage unit 28 as needed. Further, the removable media 31 can also store various data stored in the storage unit 28 in the same manner as the storage unit 28.

FIG. 2 is a functional block diagram showing an example of a functional configuration example of the information processing device 1 of FIG.
Here, in the present embodiment, the information processing apparatus 1 can execute two processes, a clustering process and a user evaluation process.
That is, the clustering process refers to a series of processes for generating and expanding a cluster from human indigenous bacterium data stored in the bacterial flora DB 200 and extracting the characteristics of the cluster.
In addition, the user evaluation process calculates the degree of belonging of the user to the cluster stored in the cluster DB 300 based on the data of the user's indigenous human bacteria. Then, it refers to a series of processes in which the improvement plan is displayed as an operator and the result is displayed on the display unit 131.
Hereinafter, an example of the functional configuration and processing flow of the information processing apparatus capable of executing such clustering processing and user evaluation processing will be described.

In the CPU 21 of the information processing device 1, the clustering unit 41 functions during the clustering process, the user evaluation unit 42 functions during the user evaluation process, and the improvement plan calculation unit 43 and the display control unit 44 function during any process. Function.
Further, in one area of the storage unit 28, a bacterial flora DB 200, a questionnaire DB 250, and a cluster DB 300 are provided. Further, the output unit 27 is provided with a display unit 131.
In the clustering unit 41, the human indigenous bacteria data extraction unit 101, the cluster generation unit 102, the cluster expansion unit 103, and the cluster feature extraction unit 104 function.
The human indigenous bacteria data extraction unit 101 functions as a cluster generation data extraction unit 111 and a cluster expansion data extraction unit 112.
In the user evaluation unit 42, the human indigenous bacteria data acquisition unit 121 and the cluster affiliation degree calculation unit 122 function.

First, the functional configuration of the clustering process will be described.
First, as a premise of the clustering process, human indigenous bacterium data is stored in the bacterial flora DB 200, and questionnaire data is stored in the questionnaire DB 250.
The human indigenous bacterium data is data including at least information on one or more types of human indigenous bacteria for each of N subjects (N is an integer value of 1 or more). For example, data showing the abundance of each of a plurality of types of indigenous human bacteria collected from the plexus stool of each of N subjects is an example of human indigenous bacterium data. Here, the amount present includes "0", that is, the case where no indigenous human bacteria are present.
Indigenous human bacteria are microorganisms (bacteria) mainly present in the human body that are commonly found in many people and do not show pathogenicity. For example, intestinal bacteria and the like are used. included.
The questionnaire data is data including at least data on the health condition of each of the N subjects. For example, for each of the N subjects who were provided with human resident bacterial data, age, gender, account information, BMI (Body Mass Index), health status, defecation, eating and drinking, lifestyle, etc. The data of the results of answering questions about mental aspects, body shape, etc. are collected as questionnaire data.
Here, each of the N subjects is given an individual ID. In the questionnaire data and the indigenous human bacterial data, the IDs of each of the N subjects are also associated with each other. That is, the questionnaire data and the human indigenous bacterium data having the same ID are the data of the same subject.

In the clustering process, only the clustering unit 41 of the information processing device 1 functions.
Here, the meanings of the terms that are the premise of the clustering process will be briefly described.
"Clustering" means dividing a set to be analyzed into subsets that satisfy predetermined conditions. "Cluster" means a subset divided by clustering.
That is, the "cluster" referred to in the present embodiment is a subset for classifying each of the possession patterns of human indigenous bacteria in, for example, N subjects.

A specific example of the above-mentioned clustering will be briefly described. When classifying the possession patterns of Bacteria A and B, for example, "Bacteria A is high and Bacteria B is high", "Bacteria A is high and Bacteria B is low", "Bacteria A is low and Bacteria B is high", "Bacteria B is high". Four clusters are generated: "A is less and bacteria B is less."
Although one or more target persons belong to one cluster, one target person may belong to a plurality of clusters.
Here, "there is a large amount of bacteria A" means, for example, that the amount is more than a predetermined amount compared to the representative value of the amount of bacteria A possessed by people in a population that is sufficiently larger than the subject of this time. doing. In addition, "there is a small amount of bacteria B" means, for example, that the amount is less than a predetermined amount compared to the representative value of the amount of bacteria B possessed by a population having a sufficiently large number of people as compared with the subject of this time. Means.

The human indigenous bacteria data extraction unit 101 of the clustering unit 41 is provided with a cluster generation data extraction unit 111 and a cluster expansion data extraction unit 112.
The cluster generation data extraction unit 111 extracts human indigenous bacterial data for each of the N subjects, M subjects (M is an integer value less than N) that meets the first condition.
Here, the first condition is, for example, a condition that "a predetermined physical condition A (for example, diarrhea tends to occur)".
That is, the cluster generation data extraction unit 111 is, for example, M people who are in physical condition A (for example, prone to diarrhea) based on the questionnaire data stored in the questionnaire DB among the human indigenous bacterial data of N subjects. Only the human resident bacterial data of the subject is extracted from the human resident bacterial data stored in the flora DB200.

Next, the cluster generation unit 102 is a cluster to which the subjects having the same possession pattern of human indigenous bacteria belong based on the human indigenous bacterium data of M subjects extracted by the cluster generation data extraction unit 111. Is generated in L numbers (L is an integer value of 1 or more).
That is, for example, when L = 4, the cluster generation unit 102 has a large amount of bacteria A and a large amount of bacteria B, "a large amount of bacteria A but a small amount of bacteria B", and "a small amount of bacteria A but a large amount of bacteria B". It produces four clusters, "there are few bacteria A and few bacteria B".

The cluster expansion data extraction unit 112 provides data on indigenous human bacteria of K subjects (K is an integer value of (NM) or less) that meets the second condition among the N subjects. Is extracted.
Here, the second condition is a condition that "it is not a predetermined physical condition A (for example, prone to diarrhea)".
That is, since the cluster expansion data extraction unit 112 did not correspond to the M subjects with physical condition A (for example, prone to diarrhea) in the cluster generation data extraction unit 111, human resident bacterial data was extracted. Human resident bacterial data of K subjects who do not have physical condition A (for example, prone to diarrhea) are extracted from human resident bacterial data stored in the flora DB200.

The cluster expansion unit 103 is based on the human indigenous bacterial data of K subjects extracted by the cluster expansion data extraction unit 112, and L generated by the cluster generation unit 102 for each of the K subjects. The L clusters are expanded by executing the process of additionally belonging to the cluster to which the possession pattern corresponds among the clusters.
That is, the cluster expansion unit 103 refers to the physical condition A (for example, diarrhea) with respect to the L clusters generated based on the human indigenous bacterial data of M subjects who have the physical condition A (for example, diarrhea). In addition to the human indigenous bacterial data of K subjects who do not tend to), more appropriate clusters are generated and expanded.

The cluster feature extraction unit 104 extracts features for each of the L clusters expanded by the cluster expansion unit 103 based on the questionnaire data stored in the questionnaire DB 250.

Here, a method of extracting features by the cluster feature extraction unit 104 will be briefly described. That is, the cluster feature extraction unit 104 first reads out the questionnaire data of each target person stored in the questionnaire DB 250.
Then, the cluster feature extraction unit 104 extracts features from each of the created L clusters based on the questionnaire data of the subject who is in physical condition A (for example, prone to diarrhea).
Further, the cluster feature extraction unit 104 extracts features from each of the created L clusters based on the questionnaire data of the subject who is not in physical condition A (for example, prone to diarrhea).
That is, the cluster feature extraction unit 104 has a two-stage feature extraction means. As a result, the cluster feature extraction unit 104 can extract various features for each of the expanded L clusters.
Then, the cluster feature extraction unit 104 stores the information indicating each of the created L clusters and the extracted features in association with each other in the cluster DB 300.

Next, the functional configuration of user evaluation will be described.
First, as described above, it is assumed that the cluster DB 300 stores data related to the cluster.
In the user evaluation, only the user evaluation unit 42 of the information processing device 1 functions.

The human indigenous bacterium data acquisition unit 121 acquires data including information on the intestines of a user different from the N subjects as human indigenous bacterium data.

The cluster affiliation degree calculation unit 122 calculates the affiliation degree to the expanded L clusters of the user's possession pattern of human indigenous bacteria based on the user's human indigenous bacterium data, and is expanded with the calculated affiliation degree. A life improvement plan for the user is generated from the characteristics of at least a part of the L clusters.
That is, the cluster affiliation degree calculation unit 122 calculates, for example, how close the possession pattern of the user's indigenous human bacteria is to the possession pattern of the target person belonging to the expanded cluster of L in several steps. The higher the number, the higher the degree of belonging to the cluster.

The improvement plan calculation unit 43 calculates a life improvement plan for the user from the characteristics of the affiliation degree calculated by the affiliation degree calculation unit 122 and the characteristics of the L clusters for which the affiliation degree calculation degree is calculated.
Further, a specific example of the life improvement plan will be described in detail with reference to FIG. 8 and the like.
The improvement plan calculation unit 43 may execute the calculation of the life improvement plan not only for the user but also for each of the above-mentioned N target persons, for example.
Further, the life improvement plan for N target persons in the clustering unit 41 is also calculated.

The display control unit 44 executes control to display the life improvement plan generated by the improvement plan calculation unit 43 on the display unit 131.

Next, with reference to FIG. 3, the flow of the clustering process executed by the information processing apparatus 1 having such a functional configuration will be described.
FIG. 3 is a flowchart illustrating an example of a flow of clustering processing executed by the information processing apparatus of FIG.

In step S51, the cluster generation data extraction unit 111 of FIG. 2 is, for example, in physical condition A (for example, prone to diarrhea) based on the questionnaire data stored in the questionnaire DB among the human indigenous bacterial data of N subjects. ), Only the human resident bacterial data of the M subjects are extracted from the human resident bacterial data stored in the flora DB200.

In step S52, the cluster generation unit 102 includes L clusters to which the subjects having the same possession pattern of human indigenous bacteria belong, based on the human indigenous bacterium data of M subjects extracted in step S51. L is an integer value of 1 or more).

In step S53, the cluster expansion data extraction unit 112 did not correspond to the M subjects having physical condition A (for example, prone to diarrhea) in the cluster generation data extraction unit 111, so that human indigenous bacterial data Human resident bacterial data of K subjects who are not in physical condition A (for example, prone to diarrhea) for which was not extracted is extracted from human resident bacterial data stored in the flora DB200.

In step S54, the cluster expansion unit 103 has L units generated by the cluster generation unit 102 for each of the K subjects based on the human indigenous bacterial data of the K subjects extracted in step S53. The L clusters are expanded by executing the process of additionally belonging to the cluster to which the possession pattern corresponds among the clusters of.

In step S55, the cluster feature extraction unit 104 extracts features for each of the L clusters expanded in step S54 based on the questionnaire data stored in the questionnaire DB 250.

In step S56, the CPU 21 of the information processing apparatus 1 determines whether or not there is an instruction to end the process. Unless an end instruction is given, it is determined to be NO in step S56, the process is returned to step S51, and the subsequent processes are repeated.
On the other hand, when the information processing apparatus 1 gives an end instruction, it is determined in step S56 that the result is YES, and the clustering process ends.

FIG. 4 is a flowchart illustrating an example of a flow of user evaluation processing executed by the information processing apparatus 1 of FIG.

In step S61, the human indigenous bacterium data acquisition unit 121 acquires data including information on the intestines of a user different from the N subjects as human indigenous bacterium data.

In step S62, the cluster affiliation degree calculation unit 122 calculates how close the possession pattern of the user's indigenous human bacteria is to the possession pattern of the subject belonging to the L expanded clusters, and each of the expanded clusters. Calculate the degree of belonging to.

In step S63, the improvement plan calculation unit 43 calculates and outputs a life improvement plan for the user based on the degree of belonging of the user calculated in step S62.

Next, the clustering process will be described with reference to FIG.
FIG. 5 is a schematic diagram illustrating an outline of the clustering process executed by the information processing apparatus 1 of FIG.
In FIG. 5, the cluster generation unit 102 and the cluster expansion unit 103 of FIG. 2 generate clusters 511 using human indigenous bacteria data 510. Then, the cluster feature extraction unit 104 extracts the features 513 of each cluster using the questionnaire data 512.
The cluster generation unit 102 is based on the human indigenous bacterium data 510 of only the subjects having a specific disorder (here, it is prone to diarrhea), and the cluster 511 based on the possession pattern of the human indigenous bacteria of each subject. To generate.

Then, as a result of cluster analysis of the bacterial species (genus level) of indigenous human bacteria, the cluster generation unit 102 extracts a plurality of characteristic clusters 511 to which the subject who tends to have diarrhea belongs.
Further, the cluster generation unit 102 applies the extracted plurality of clusters 510 to each of the plurality of clusters 511 based on the attributes and lifestyles of the subjects belonging to the plurality of clusters 511 based on the questionnaire data 512. Extract multiple lifestyle characteristics. At this time, among the plurality of clusters 511, the cluster 511 in which the lifestyle-related characteristics could not be found in the subject to which the subject belongs may be excluded from the plurality of clusters 511.
Next, the cluster expansion unit 103 performs the following processing using the human indigenous bacteria data 510 of the subject who is not prone to diarrhea, which was not used in the cluster generation unit 102.
That is, in the cluster expansion unit 103, the possession pattern of human indigenous bacteria according to the human indigenous bacterium data 510 of the subject who is not prone to diarrhea is the possession of the cluster target and the human indigenous bacteria generated by the cluster generation unit 102. If there are subjects with the same pattern, the subjects who are not prone to diarrhea are assigned to the cluster 511, and the process of expanding the cluster 511 is performed.
For example, it is assumed that there are a cluster of aboriginal bacteria possession pattern α (hereinafter referred to as cluster α) and a cluster of a bacterium possession pattern β (hereinafter referred to as cluster β) in a plurality of clusters 511.

Then, for example, among the N subjects, four subjects a, a subject b, a subject c, and a subject d who are prone to diarrhea have a possession pattern of human indigenous bacteria, and the subject a has a possession pattern β. It is assumed that the subject b has a possession pattern α, the subject c has a possession pattern α, and the subject d has a possession pattern β.
In this case, the cluster generation unit 102 performs a process in which the target person b and the target person c belong to the cluster α, and the target person a and the target person d belong to the cluster β.
Next, for example, among the N subjects, three subjects e, the subject f, and the subject g who are not prone to diarrhea have the possession pattern of human indigenous bacteria, and the subject e has the possession pattern α and the subject f. Is the possession pattern β, and the subject g is the possession pattern α.
In this case, the cluster expansion unit 103 adds the target person e and the target person g to the cluster α to belong to the cluster α, and adds the target person f to the cluster β to belong to the cluster α.
As a result, the target person b, the target person c, the target person e, and the target person g belong to the cluster α, and the target person a, the target person d, and the target person f belong to the cluster β. ..

FIG. 6 is a diagram showing an example of each feature of the cluster (expanded cluster) expanded by the cluster expansion unit 103.
By comparing the diarrhea-prone subjects and the non-diarrhea-prone subjects for each of the expanded clusters in the cluster feature extraction unit 104, the seven expanded clusters and five characteristics (that is, lifestyle characteristics) shown in Table 610 are shown. ) Was extracted. The features marked with * for each of the expanded clusters CL1 to CL7 are the features extracted for each of the expanded clusters.
The feature "drinking" means that you drink a lot, the feature "cigarette" means that you have a smoking habit, the feature "exercise" means that you do not have an exercise habit, and the feature "sleep time, quality of sleep" , Short sleep time, poor sleep quality, characteristic "stress" is that stress tends to accumulate.
It should be noted that specific numerical values related to the characteristics such as the amount of alcohol consumed for the characteristic "drinking" and the number of cigarettes for the characteristic "cigarette" can be freely set. For example, the amount of alcohol consumed can be freely set to 1 L or more per day, the number of cigarettes can be set to 10 or more cigarettes per day, and the amount of exercise can be freely set to 6,000 steps or more per day.
The description such as (100) described after the cluster name is, for example, the number of target persons belonging to the cluster.

The cluster feature extraction unit 104 can assign a life improvement plan to each of the expanded clusters based on the characteristics of each of the expanded clusters. For example, a cluster with the characteristic of "drinking" can be associated with a life improvement plan such as "let's reduce the amount of drinking".
The life improvement plan will be described in the explanation of the user evaluation process.
The cluster feature extraction unit 104 extracts the features of each expanded cluster and assigns a life improvement plan from those features. Then, each expanded cluster, the features extracted for the expanded cluster, and the life improvement plan given to the expanded cluster are associated with each other, and stored in the cluster DB 300 of the storage unit 28 as data related to the cluster.

FIG. 7 is a schematic diagram illustrating an outline of the user evaluation process executed by the information processing apparatus 1 of FIG.
The user evaluation unit 42 acquires user data 710 (that is, human resident bacterial data), reads out cluster data 711 (that is, data about the cluster) in the cluster DB 300 and each expanded cluster feature 712, and reads the user's data 712. Derivation of the degree of belonging to each expanded cluster of data 710 (ie, human resident bacterial data) 713.

The human indigenous bacterium data acquisition unit 121 acquires the human indigenous bacterium data 710 of the user to be evaluated. The human indigenous bacterium data 710 is preferably data in the same format as the above-mentioned human indigenous bacterium data acquisition unit 112.
The cluster affiliation degree calculation unit 122 reads the acquired human indigenous bacteria data 710 and the data related to the clusters of the respective expanded clusters generated by the clustering unit 41 from the cluster DB 300 of the storage unit 28, and the user to be evaluated. The human indigenous bacterium data 710 is calculated to which expanded cluster 711 has a high degree of belonging.
In order to determine the degree of affiliation, the cluster affiliation degree calculation unit 122 determines, for example, how close the possession pattern of the user's human indigenous bacteria is to the possession pattern of a certain cluster.

FIG. 8 is a diagram showing an example of display on the display unit 131 by the user evaluation process.
Five life improvement plans are displayed on the display 810. For these life improvement plans, for example, among the clusters CL1 to CL7 shown in FIG. 6, which life improvement plan is displayed according to the degree of belonging of each user to each cluster, and the number of stars recommended. It is decided whether to do it.

In the example of FIG. 8, when the characteristics of "drinking", "cigarette", and "exercise" of FIG. 6 are important elements for improving life, the display 810 of FIG. "Let's reduce the amount and frequency of drinking" on the upper left, "Let's walk 8,000 steps a day" on the upper right of the display 810, "Recommendation" As two stars, "Let's refrain from smoking" in the upper part of the display 810 The life improvement plan is displayed.

Next, when the characteristics of "exercise", "sleep time, sleep quality", and "stress" in Fig. 6 are factors for improving life, the "recommendation level" is displayed as 4 stars on the upper right of 810. "Let's walk 8,000 steps a day", "Let's reduce stress" on the lower right of the display 810 in Fig. 8, "Recommendation" As two stars, "Adjust sleep" in the lower part of the display 810 in Fig. A life improvement plan called "Let's go" is displayed.

Although one embodiment of the present invention has been described above, the present invention is not limited to the above-described embodiment, and modifications, improvements, etc. within the range in which the object of the present invention can be achieved are included in the present invention. Is.
For example, the function of the clustering process is not particularly limited to the above-described embodiment. Therefore, another embodiment different from the above-described embodiment will be described below with reference to FIG.
FIG. 9 is a diagram showing an outline of an example of a functional configuration example of the information processing device 1 of FIG. 1, and is a functional block diagram showing an example different from that of FIG. Note that in FIG. 9, the description of the output unit 27, the improvement plan calculation unit 43, the display control unit 44, the bacterial flora DB 200, the questionnaire DB 250, and the like in FIG. 2 is omitted.
In FIG. 9, the clustering unit 41 also functions as a learning unit. That is, the clustering unit 41 in FIG. 9 has a learning function of updating the cluster DB 300 by using the user's indigenous human bacterial data acquired by the user evaluation unit 42.
Specifically, the user's indigenous human bacterial data acquired by the user evaluation unit 42 is also input to the clustering unit 41, and the life improvement plan for the user, which is the output of the user evaluation unit 42, is also the clustering unit. It is input to 41. In this way, by feeding back the user's human indigenous bacteria data and the processing result acquired by the user evaluation unit 42 to the clustering unit 41, the user's human indigenous bacteria data is also clustered by the clustering unit 41. The cluster DB 300 can be updated by performing the process.
In this case, it is preferable to update the questionnaire DB 250 by acquiring the same questionnaire data as the questionnaire data stored in the questionnaire DB 250 for the user evaluated by the user evaluation unit 42.

In the above-described embodiment, the functions of the clustering unit 41 and the user evaluation unit 42 are included in the CPU 21 of the information processing device 1, but the present invention is not limited to this.
For example, the information processing device 1 may be connected to a network, and the user terminals (personal computer, tablet terminal, smartphone, etc.) connected to the network may have the function of the user evaluation unit 42. In this case, it is preferable that the user terminal reads the data of the cluster DB in the storage unit 28 of the information processing device 1 via the network during the user evaluation process on the user terminal.

Further, for example, as the display of the life improvement plan for the user, in the above-described embodiment, it is displayed as character information as shown in FIG. 8, but the display is not limited to this. A plurality of improvement elements in the life improvement plan may be displayed in a diagram like a radar chart based on the "recommendation level".

Further, for example, as the content of the question in the questionnaire data, in the above-described embodiment, in addition to the age, gender, and BMI, the question was about the health condition, defecation, eating and drinking, lifestyle, mental aspect, body shape, etc. You may ask such a question.
First, for example, the question may be "Is there any health condition?"
Questions regarding defecation may include, for example, "prone to constipation (no defecation for 3 days or more)", "prone to diarrhea (may have mud-like stools or water-like stools)" and the like.
Questions about eating and drinking include, for example, "frequency of eating out", "frequency of eating out", "skipping breakfast", "like spicy foods", "like soy foods", "like sweet foods", and "salty foods". It may be "I like things", "I like greasy things", "I like meat", "I like natto and soy milk", "I like dairy products" and so on.

Examples of lifestyle-related questions may be, for example, "current smoking status", "past and current drinking status", "are you exercising / sports regularly", and the like.
Mental questions include, for example, "I don't want to eat anything. I've lost my appetite.", "I don't feel well when my family and friends bald me." I think I have the same ability as other people. ”,“ I can't concentrate on things. ”,“ I'm depressed. ”,“ I've lost my concentration. ”,“ I can't sleep easily. ”“ Stress builds up. It may be "easy" or the like.
In addition, as a question regarding body shape, for example, "overweight / obesity" may be used.

In addition, the answers to the above questions other than the questions "age", "gender", "BMI", and "is there any health condition?" Are "yes", "no", or "applicable". , "Not applicable" can be answered in two stages, but you may be asked to answer in three or more stages. For example, in the case of three stages, one of "Yes", "No", "Neither", or "Applicable", "Not applicable", or "Neither can be said" may be selected.
Regarding the "current smoking situation", you may ask to choose from three answers: "smoke", "do not smoke", and "have smoked in the past but do not smoke now".
Regarding the "current drinking situation", you may be asked how many days a week you drink, that is, 0 to 7 days.

Further, in the above-described embodiment, the questionnaire data is used as the attribute information of the target person for the explanation, but the description is not particularly limited to this.
That is, the attribute information acquired from the target person is not limited to the questionnaire data. For example, information such as medical data of the subject and basic demographic information (for example, from Tokyo) may be obtained from the subject.
Furthermore, this information may be obtained in any way, not just by questioning as in the embodiments described above.

Here, the series of processes described above can be executed by hardware or software.
In other words, the functional configuration of FIG. 2 is merely an example and is not particularly limited.
That is, it suffices if the information processing system is provided with a function capable of executing the above-mentioned series of processes as a whole, and what kind of functional block is used to realize this function is not particularly limited to the example of FIG. Further, the location of the functional block is not particularly limited to FIG. 2, and may be arbitrary. The functional blocks of the information processing device 1 may be distributed to a plurality of servers, or may be provided in a terminal device.
Further, one functional block may be configured by a single piece of hardware, a single piece of software, or a combination thereof.

When a series of processes are executed by software, the programs constituting the software are installed on a computer or the like from a network or a recording medium.
The computer may be a computer embedded in dedicated hardware.
Further, the computer may be a computer capable of executing various functions by installing various programs, for example, a general-purpose smartphone or a personal computer in addition to an information processing device.

The recording medium containing such a program is not only composed of a removable medium (not shown) distributed separately from the device main body in order to provide the program to the player, but also is preliminarily incorporated in the device main body to the player. It is composed of the provided recording media and the like.

In the present specification, the steps for describing a program recorded on a recording medium are not necessarily processed in chronological order, but also in parallel or individually, even if they are not necessarily processed in chronological order. It also includes the processing to be executed.
Further, in the present specification, the term of the system means an overall device composed of a plurality of devices, a plurality of means, and the like.

In other words, the information processing apparatus to which the present invention is applied can take various embodiments having the following configurations, including the information processing apparatus as the embodiment of FIG. 2 described above.
That is, the information processing system to which the present invention is applied is
For each of the N subjects, data including at least information on two or more human indigenous bacteria has been acquired in advance as human indigenous bacteria data, and data including at least data on health status is questionnaire data. In the state of being acquired in advance as
Among the N subjects, the first extraction means (for example, FIG. 2) for extracting the human indigenous bacterial data for each of the M subjects (M is an integer value less than N) that meets the first condition. Data extraction unit 111) for cluster generation and
Based on the human indigenous bacterium data of the M subjects extracted by the first extraction means, a cluster generation means for generating L clusters to which subjects having the same possession pattern of human indigenous bacteria belong ( For example, the cluster generator 102) in FIG. 2 and
A second extraction means for extracting the human indigenous bacterial data of each of the N subjects, K (K is an integer value of (NM) or less) that meets the second condition. (For example, the cluster expansion data extraction unit 112 in FIG. 2) and
Based on the human indigenous bacterial data of the K subjects extracted by the second extraction means, the possession pattern of the L clusters corresponds to each of the K subjects. A cluster expansion means (for example, cluster expansion unit 103 in FIG. 2) that expands the L clusters by executing a process of additionally belonging to the cluster, and
A feature extraction means (for example, the cluster feature extraction unit 104 in FIG. 2) that extracts features from each of at least a part of the expanded L clusters based on the questionnaire data.
An information processing device equipped with the above is sufficient.

Further, an acquisition means for acquiring data including information on the intestines of a user different from the N subjects as human indigenous bacterium data (for example, human indigenous bacterium data acquisition unit 121 in FIG. 2) and
An affiliation degree calculation means (for example, the cluster affiliation degree calculation unit 122 in FIG. 2) for calculating the degree of affiliation with respect to at least a part of the L clusters based on the user's indigenous human bacterial data.
Improvement plan calculation means (for example, FIG. 2) for calculating a life improvement plan for the user based on the characteristics of the affiliation degree and the affiliation degree of the affiliation degree calculation means among the L clusters. Improvement plan calculation unit 43) and
Can be further prepared.

1 ... Information processing device, 21 ... CPU, 28 ... Storage unit, 41 ... Clustering unit, 42 ... User evaluation unit, 43 ... Improvement plan calculation unit, 44 ... Display Control unit, 101 ... Extraction unit, 102 ... Cluster generation unit, 103 ... Cluster expansion unit, 104 ... Cluster feature extraction unit, 111 ... Cluster generation data extraction unit, 112 ... Data extraction unit for cluster expansion, 121 ... Human resident bacterial data acquisition unit, 122 ... Cluster affiliation degree calculation unit, 200 ... Bacterial flora DB, 250 ... Questionnaire DB, 300 ... Cluster DB

Claims (4)

For each of the N subjects, data including at least information on two or more human indigenous bacteria has been acquired in advance as human indigenous bacteria data, and data including at least data on health status is questionnaire data. In the state of being acquired in advance as
Among the N subjects, the first extraction means for extracting the human indigenous bacterium data for each of the M subjects (M is an integer value less than N) that meets the first condition,
Based on the human indigenous bacterium data of the M subjects extracted by the first extraction means, the cluster generation means for generating L clusters to which the subjects having the same possession pattern of human indigenous bacteria belong. ,
A second extraction means for extracting the indigenous human bacterial data of each of the N subjects, of whom K (K is an integer value of (NM) or less) that meets the second condition. When,
Based on the human indigenous bacterial data of the K subjects extracted by the second extraction means, the possession pattern of the L clusters corresponds to each of the K subjects. A cluster expansion means for expanding the L clusters by executing a process of additionally belonging to the cluster, and
A feature extraction means for extracting features from each of at least a part of the expanded L clusters based on the questionnaire data.
Information processing system equipped with. An acquisition means for acquiring data including information on the intestines of a user different from the N subjects as human indigenous bacterium data, and
An affiliation degree calculation means for calculating the affiliation degree to at least a part of the L clusters based on the human indigenous bacterium data of the user, and an affiliation degree calculation means.
An improvement plan calculation means for calculating a life improvement plan for the user based on the characteristics of the affiliation degree and the affiliation degree of the affiliation degree calculation means among the L clusters.
The information processing system according to claim 1, further comprising. For each of the N subjects, data including at least information on two or more human indigenous bacteria has been acquired in advance as human indigenous bacteria data, and data including at least data on health status is questionnaire data. In the state of being acquired in advance as
On the computer
Among the N subjects, the first extraction step of extracting the human indigenous bacterium data for each of the M subjects (M is an integer value less than N) that meets the first condition,
Based on the human indigenous bacterium data of the M subjects extracted by the first extraction means, a cluster generation step of generating L clusters to which the subjects having the same possession pattern of human indigenous bacteria belong. ,
Among the N subjects, K subjects (K is an integer value of (NM) or less) that meet the second condition are subjected to the second extraction step of extracting the respective human indigenous bacterial data. When,
Based on the human indigenous bacterial data of the K subjects extracted by the second extraction means, the possession pattern of the L clusters corresponds to each of the K subjects. A cluster expansion step to expand the L clusters by executing an additional process to belong to the cluster, and
A feature extraction step for extracting features from at least a part of the expanded L clusters based on the questionnaire data, and a feature extraction step.
A program that executes processing including. On the computer
An acquisition step of acquiring data including information on the intestines of a user different from the N subjects as human indigenous bacterium data, and
A affiliation degree calculation step for calculating the affiliation degree to at least a part of the L clusters based on the user's indigenous human bacterial data, and a affiliation degree calculation step.
An improvement plan calculation step for calculating a life improvement plan for the user based on the characteristics of the affiliation degree and the affiliation degree of the affiliation degree calculation means among the L clusters.
The program according to claim 3, wherein the process including the above is further executed.

Images