JP2019211866A - Information providing apparatus, information providing method, and neural network learning method of information providing apparatus - Google Patents

Abstract

To provide an information providing apparatus capable of concisely presenting a balance state of a miRNA profile of a user.SOLUTION: An information providing apparatus 10 comprises: a first neural network 11 that is learned to output a Q value by dimensionally compressing, based on a miRNA attribute of an information provider and multidimensional miRNA information, a number of dimensions of the miRNA information to a smaller number of dimensions; and an information output unit 12 that outputs a miRNA score of a user corresponding to the Q value using the first neural network 11, based on the miRNA information of the user.SELECTED DRAWING: Figure 1

Description

  The present invention relates to an information providing apparatus, an information providing method, and a neural network learning method of the information providing apparatus.

  Conventionally, a technique for associating the state of human microRNA (miRNA) with the presence of cancer is known (see, for example, Patent Document 1). Patent Document 1 discloses a technique that relates the expression ratio of miRNA pairs to the presence of lung cancer.

Special table 2017-502699 gazette

However, the above-described conventional techniques can contribute to cancer detection using the miRNA state, but cannot contribute to cancer prevention using the miRNA state.
In recent years, it has been known that disorder of the miRNA profile promotes cancer. For this reason, the information provision service which contributes to improving the balance of the said miRNA profile of the said user by showing the disturbance of the balance of a user's miRNA profile to the said user can be considered. However, the miRNA profile is complicated because there are about 2500 types of miRNA profiles, and it is difficult for general users to understand the miRNA profile.

  The present invention has been made in view of such circumstances, and an object of the present invention is to provide an information providing apparatus, an information providing method, and an information providing apparatus capable of simply presenting the balance state of a user's miRNA profile. It is to provide a learning method for a neural network.

In order to achieve such an object, the present invention is grasped by the following configuration.
(1) In one aspect of the present invention, learning is performed such that the number of dimensions of miRNA information is reduced to a smaller number of dimensions and a Q value is output based on the miRNA attribute of the information provider and multidimensional miRNA information. An information providing apparatus comprising: a first neural network; and an information output unit that outputs the miRNA score of the user corresponding to a Q value from the miRNA information of the user using the first neural network.

(2) One aspect of the present invention is the information providing apparatus according to the configuration of (1), wherein the miRNA attribute is the age and sex of the information provider.

(3) According to one aspect of the present invention, in the configuration according to (1) or (2), the first neural network further adds the biochemical data of the information provider to perform the learning. It is.

(4) According to one aspect of the present invention, in the configuration of (3), the information output unit corresponds to the Q value using the first neural network from the miRNA information and biochemical data of the user. It is an information provision apparatus which outputs a user's miRNA score.

(5) According to one aspect of the present invention, in any one of the above configurations (1) to (4), the Q value output from the first neural network, and the food intake information for a certain period of the information provider, Further comprising a second neural network learned to output ideal eating information based on the Q value output from the user's miRNA information using the first neural network, It is an information providing device that outputs eating information recommended to the user using the second neural network.

(6) One aspect of the present invention is an information providing method for providing a miRNA score of a user by the information providing apparatus having any one of the configurations (1) to (5).

(7) One aspect of the present invention is a method for learning a neural network of an information providing apparatus configured as described in (1) above, and an information acquisition step of acquiring miRNA attributes and multidimensional miRNA information of an information provider; A learning step of learning the neural network so as to output a Q value by compressing the number of dimensions of the miRNA information to a smaller number of dimensions based on the miRNA attribute of the information provider and multidimensional miRNA information; , A learning method for a neural network of an information providing apparatus.

  According to the present invention, it is possible to provide an information providing apparatus, an information providing method, and a neural network learning method for the information providing apparatus that can simply present the balance state of the miRNA profile of the user.

It is the schematic which shows the information provision system which concerns on 1st Embodiment of this invention. It is a figure which shows the learning method of the neural network which concerns on Example 1 of the information provision apparatus of 1st Embodiment of this invention. It is a figure which shows the information provision method which concerns on Example 1 of the information provision apparatus of 1st Embodiment of this invention. It is a figure which shows the learning method of the neural network which concerns on Example 2 of the information provision apparatus of 1st Embodiment of this invention. It is a figure which shows an example of the information provision method which concerns on Example 2 of the information provision apparatus of 1st Embodiment of this invention. It is the schematic which shows the information provision system which concerns on 2nd Embodiment of this invention. It is a figure which shows the learning method of the neural network which concerns on the Example of the information provision apparatus of 2nd Embodiment of this invention. It is a figure which shows the information provision method which concerns on the Example of the information provision apparatus of 2nd Embodiment of this invention.

  DESCRIPTION OF EMBODIMENTS Hereinafter, embodiments for carrying out the present invention (hereinafter referred to as “embodiments”) will be described in detail with reference to the accompanying drawings. The same symbols are attached to the same elements throughout the description of the embodiments.

[First Embodiment]
FIG. 1 is a schematic diagram showing an information providing system according to the first embodiment. The information providing system 1 shown in FIG. 1 includes an information providing device 10 and a terminal device 20. The information providing device 10 and the terminal device 20 may send and receive information online by communication, or may input and output information offline. Hereinafter, as an example, the information providing device 10 and the terminal device 20 will be described as transmitting and receiving information online by communication.
The information providing apparatus 10 is configured as an apparatus for providing an individual's miRNA score using the individual's miRNA information.

  The miRNA score is information indicating whether the balance of the miRNA profile is good or bad. Examples of the miRNA score include miRNA score, miRNA age, miRNA deviation value, and the like. The miRNA score is a score obtained by scoring the balance of the miRNA profile with a prescribed perfect score (for example, 100 perfect score). The miRNA age expresses the balance of the miRNA profile in terms of age. The miRNA deviation value expresses the balance of the miRNA profile as a deviation value.

  Individual miRNA information is information indicating the state of the individual miRNA. There are approximately 2500 types of miRNA. The miRNA information may include information on all types of miRNA, or may include information on some types of miRNA. The miRNA information is information including information on each miRNA. The miRNA information may be any concentration of each miRNA, the number of moles, a fluorescence intensity, or a relative value corrected with another index. Logarithm expression may be sufficient as the expression method of miRNA information.

The terminal device 20 transmits information such as the user's miRNA information to the information providing device 10. The terminal device 20 may be a user terminal device or a terminal device other than the user terminal device. Instead of the terminal device 20, information such as a user's miRNA information may be transmitted from the server of the information providing organization to the information providing device 10.
The information providing apparatus 10 includes a first neural network 11 and an information output unit 12. The information output unit 12 of the information providing apparatus 10 outputs information such as the miRNA score of the user from the information such as the miRNA information of the user received from the terminal apparatus 20 using the first neural network 11. The information providing apparatus 10 transmits information such as the user's miRNA score to the terminal apparatus 20.

  The information providing apparatus 10 includes a memory and a CPU (Central Processing Unit). The function of each part of the information providing apparatus 10 is realized by the CPU provided in the information providing apparatus 10 executing a computer program. The information providing device 10 may be configured using a general-purpose computer device, or may be configured as a dedicated hardware device.

Further, an input device, a display device, or the like may be connected to the information providing device 10 as a peripheral device. Here, the input device refers to an input device such as a keyboard and a mouse. The display device refers to a CRT (Cathode Ray Tube), a liquid crystal display device or the like.
The peripheral device may be directly connected to the information providing apparatus 10 or may be connected via a communication line.
The information providing apparatus 10 may include a database related to the neural network, or may access the database provided outside via a communication line.

  The terminal device 20 may be a mobile terminal device such as a smartphone or a tablet computer (tablet PC), or a stationary terminal device (for example, a stationary personal computer). Also good.

  Next, the information providing apparatus 10 according to the first embodiment will be described with some examples.

[Example 1]
Example 1 of the information providing apparatus 10 according to the first embodiment will be described with reference to FIGS. 2 and 3. FIG. 2 is a diagram illustrating a neural network learning method according to Example 1 of the information providing apparatus 10 of the first embodiment. FIG. 3 is a diagram illustrating an information providing method according to Example 1 of the information providing apparatus 10 of the first embodiment.

<Learning stage>
With reference to FIG. 2, the learning stage according to the first embodiment will be described. The learning stage is a stage for learning the first neural network 11 used in the information providing stage described later. The learning stage of the first neural network 11 may be performed by the information providing apparatus 10 or may be performed by a computer different from the information providing apparatus 10.

  In FIG. 2, the learning stage (S100) includes three steps S101, S102 and S103. In the learning step (S100), the first neural network is configured to compress the number of dimensions of the miRNA information to a smaller number of dimensions based on the miRNA attribute of the information provider and the multidimensional miRNA information and output a Q value. Eleven learning is performed.

  The individual miRNA attribute is an attribute of the individual that affects the miRNA information of the individual. Examples of miRNA attributes include age, sex, race, and the like. The miRNA attributes preferably include at least age and sex. The miRNA attribute may be only age and sex. The nationality may be used as information representing the race.

  The Q value is information representing the multidimensional miRNA information of the information provider input to the first neural network 11 with a smaller number of dimensions.

  Multidimensional miRNA information is information indicating the state of a plurality of types of miRNA. It is known that there are about 2500 types of human miRNAs. Therefore, the number of dimensions of miRNA information indicating the states of all types of miRNAs in humans is very large. On the other hand, it is thought that the kind of miRNA with a strong correlation with a future cancer onset risk (cancer prevention) is limited. Therefore, in the learning stage (S100), the first neural network 11 is trained to compress the dimensions of the miRNA information to a smaller number of dimensions and output a Q value.

(Step S101) As input information to be input to the first neural network 11, miRNA attributes of the information provider and multidimensional miRNA information are prepared. An information provider is a person who provides information for learning a neural network. Next, the miRNA attribute of the information provider and the multidimensional miRNA information are input to the first neural network 11. For example, the age and sex of the information provider and multidimensional miRNA information are input to the first neural network 11. By using age and gender as miRNA attributes, it is possible to learn the first neural network 11 having coefficients that differ by age and sex.

(Step S102) As a result of inputting the miRNA attribute of the information provider and the multidimensional miRNA information to the first neural network 11, the Q value is output from the first neural network 11.

(Step S103) Learning of the first neural network 11 is performed. As a neural network learning method, for example, an auto encoder (self-encoder) may be used. The auto encoder reconstructs the information provider's miRNA attributes and multidimensional miRNA information by applying reverse encoding (decoding layer) to the Q value of the output of the first neural network 11 (encoding layer). The first neural network 11 is trained to reduce the difference between the original input “miRNA attribute of the information provider and multidimensional miRNA information”. It is not necessary for a person to make meaning such as correct answer data, and a meaningful Q value can be automatically calculated.

  As an example of the learning method according to the present embodiment, self-encoding in which the first neural network 11 returns the M-dimensional (where M <N) Q value generated from the N-dimensional first miRNA information to the N-dimensional second miRNA information. And the first neural network 11 is made to learn so that the second miRNA information matches the first miRNA information.

<Information provision stage>
With reference to FIG. 3, the information provision step according to the first embodiment will be described. The information providing step is a step of providing the user's miRNA score from the user's miRNA information using the first neural network 11 learned in the learning step described above.

  In FIG. 3, the information providing step (S200) includes three steps S201, S202 and S203. In the information providing stage (S200), the information providing apparatus 10 includes the first neural network 11 that has been learned in the learning stage described above. That is, the information providing apparatus 10 is learned to compress the number of dimensions of the miRNA information to a smaller number of dimensions based on the miRNA attribute of the information provider and the multidimensional miRNA information and output the Q value. 1 neural network 11 is provided.

(Step S <b> 201) The information providing apparatus 10 receives the miRNA information of the user from the terminal device 20. The information output unit 12 inputs the user's miRNA information received from the terminal device 20 to the first neural network 11.

(Step S <b> 202) As a result of inputting the user's miRNA information to the first neural network 11, the Q value is output from the first neural network 11.

(Step S203) The information output unit 12 converts the Q value output from the first neural network 11 into a miRNA score. As a method for converting the Q value into the miRNA score, for example, a conversion table in which the miRNA score corresponding to the Q value is recorded may be provided in advance, or a function for deriving the miRNA score from the Q value may be defined in advance. Also good.

  The information providing apparatus 10 transmits the user's miRNA score converted from the Q value output from the first neural network 11 to the terminal apparatus 20. The terminal device 20 records the user's miRNA score received from the information providing device 10, and displays the user's miRNA score on the display screen in accordance with the information browsing operation by the user. Thereby, the user can browse his / her miRNA score with the terminal device 20. The miRNA score can concisely show the balance of the miRNA profile.

[Example 2]
The second embodiment is a modification of the first embodiment described above. In Example 2, in addition to miRNA information, biochemical data is used to provide a user's miRNA score. Example 2 of the information providing apparatus 10 according to the present embodiment will be described with reference to FIGS. 4 and 5. FIG. 4 is a diagram illustrating a neural network learning method according to Example 2 of the information providing apparatus 10 of the first embodiment. FIG. 5 is a diagram illustrating an example of an information providing method according to Example 2 of the information providing apparatus 10 of the first embodiment.

<Learning stage>
With reference to FIG. 4, the learning stage according to the second embodiment will be described. For convenience of description, in order to distinguish from the first neural network 11 of the first embodiment, the second neural network is referred to as a first neural network 11a in the second embodiment. In FIG. 4, the learning stage (S100a) includes three steps S101a, S102a, and S103a.

(Step S101a) In addition to the information provider's miRNA attributes and multi-dimensional miRNA information, the information provider's biochemical data is further prepared as input information to be input to the first neural network 11a. As biochemical data, for example, data on the results of biochemical examinations of human specimens (for example, blood, urine, stool, etc.), captured images of human skin, human ultrasonic images, human X-ray images, human Data on the results of a doctor's diagnosis are included. The biochemical data of the information provider may be test result data obtained when the information provider has undergone a health examination such as a medical checkup.
Next, the miRNA attribute of the information provider, multidimensional miRNA information, and biochemical data are input to the first neural network 11a.

(Step S102a) As a result of inputting the miRNA attribute of the information provider, multidimensional miRNA information, and biochemical data to the first neural network 11a, the Q value is output from the first neural network 11a.

  In the learning stage (S100a), step S103a is the same as step S103 in the learning stage (S100) of the first embodiment described above.

<Information provision stage>
An information providing stage according to the second embodiment will be described. Examples of the information providing stage according to the second embodiment include examples 2-1 and 2-2 of the information providing stage shown below.

<Example of Information Provision Stage 2-1>
An example 2-1 of the information provision stage is the same as the information provision stage according to the first embodiment illustrated in FIG. 3 described above. However, in the example 2-1 of the information providing stage, the first neural network 11a that has been learned in the learning stage according to the second embodiment described above is used instead of the first neural network 11 in FIG. The other points are the same as the information providing stage according to the first embodiment shown in FIG.

<Example of information provision stage 2-2>
With reference to FIG. 5, Example 2-2 of the information provision stage which concerns on Example 2 is demonstrated. In the example 2-2 of the information providing stage, the miRNA score of the user is provided from the miRNA information and biochemical data of the user using the first neural network 11a that has been learned in the learning stage according to the second embodiment. It is a stage.

  In FIG. 5, the information providing stage example 2-2 (S200a) includes three steps S201a, S202a, and S203a. In the information providing stage example 2-2 (S200a), the information providing apparatus 10 includes the first neural network 11a that has been learned in the learning stage according to the second embodiment described above. That is, the information providing apparatus 10 outputs the Q value by compressing the number of dimensions of the miRNA information to a smaller number of dimensions based on the information provider's miRNA attributes, multidimensional miRNA information, and biochemical data. A learned first neural network 11a is provided.

(Step S201a) The information providing apparatus 10 receives the user's miRNA information and biochemical data from the terminal apparatus 20. The information output unit 12 inputs the user's miRNA information and biochemical data received from the terminal device 20 to the first neural network 11a.

(Step S202a) As a result of inputting the user's miRNA information and biochemical data to the first neural network 11a, the Q value is output from the first neural network 11a.

(Step S203a) The information output unit 12 converts the Q value output from the first neural network 11a into a miRNA score.

  The information providing apparatus 10 transmits the user's miRNA score, to which the Q value output from the first neural network 11a is converted, to the terminal apparatus 20. The terminal device 20 records the user's miRNA score received from the information providing device 10, and displays the user's miRNA score on the display screen in accordance with the information browsing operation by the user. Thereby, the user can browse his / her miRNA score with the terminal device 20. The miRNA score can concisely show the balance of the miRNA profile.

  The above is description of the Example of the information provision apparatus 10 which concerns on 1st Embodiment.

  According to the first embodiment described above, there is an effect that it is possible to simply present the balance state of the miRNA profile of the user.

[Second Embodiment]
FIG. 6 is a schematic diagram showing an information providing system according to the second embodiment. An information providing system 1b shown in FIG. 6 includes an information providing device 10b and a terminal device 20. The information providing apparatus 10b and the terminal apparatus 20 may transmit and receive information online by communication, or may input and output information offline. Hereinafter, as an example, the information providing device 10b and the terminal device 20 will be described as transmitting and receiving information online by communication. The information providing apparatus 10b is configured as an apparatus for providing an individual's miRNA score and recommended eating information to the individual using the individual's miRNA information. Eating information recommended for an individual is information indicating a meal for improving the balance of the miRNA profile of the individual.

  The terminal device 20 transmits information such as the miRNA information of the user to the information providing device 10b. The information providing apparatus 10b includes a first neural network 11, a second neural network 13, and an information output unit 12b. The information output unit 12 b of the information providing apparatus 10 b outputs information such as the miRNA score of the user using the first neural network 11 from the information such as the miRNA information of the user received from the terminal device 20. The first neural network 11 according to the second embodiment may be the first neural network 11 according to the first example of the first embodiment described above, or the second example of the first embodiment described above. The first neural network 11a according to FIG.

  The information output unit 12b further uses the second neural network 13 to inform the user of the Q value output using the first neural network 11 from information such as the user's miRNA information received from the terminal device 20. Output recommended eating information. The information providing apparatus 10b transmits information such as the user's miRNA score and recommended eating information to the user to the terminal apparatus 20.

  The information providing apparatus 10b has the same configuration as that of the information providing apparatus 10 according to the first embodiment, and the functions of each unit of the information providing apparatus 10b are realized by a CPU provided in the information providing apparatus 10b executing a computer program. The

  Next, an example of the information providing apparatus 10b according to the second embodiment will be described with reference to FIGS. FIG. 7 is a diagram illustrating a neural network learning method according to an example of the information providing apparatus 10b of the second embodiment. FIG. 8 is a diagram illustrating an information providing method according to an example of the information providing apparatus 10b of the second embodiment.

<Learning stage>
In the second embodiment, learning of two neural networks of the first neural network 11 and the second neural network 13 is performed. The learning method of the first neural network 11 is the first example of the first embodiment described above (the learning stage (S100) of the first neural network 11 shown in FIG. 2) or the second example (first shown in FIG. 4). Since this is the same as the learning stage (S100a) of the neural network 11a, the description thereof is omitted.

  The learning stage of the second neural network 13 according to the second embodiment will be described with reference to FIG. This learning stage is a stage for learning the second neural network 13 used in the information providing stage described later. The learning stage of the second neural network 13 may be performed by the information providing apparatus 10b, or may be performed by a computer different from the information providing apparatus 10b.

In FIG. 7, the learning stage (S100b) includes three steps S101b, S102b, and S103b. In the learning stage (S100b), the Q value output from the first neural network 11 as a result of inputting the miRNA attribute of the information provider and the multidimensional miRNA information to the first neural network 11, and the constant of the information provider Learning of the second neural network 13 is performed so that ideal eating information is output based on the eating and drinking information of the period.
The information intake of the information provider for a certain period is information about meals taken by the information provider for a certain period. In addition, the information provider may include information on the specific food component included in the meal taken for a certain period in the meal intake information, and the second neural network 13 may learn the information on the specific food component. The specific food ingredient may be a food ingredient that improves the balance of the miRNA profile.
The ideal eating information is information indicating a meal for improving the balance of the miRNA profile.

(Step S <b> 101 b) As input information to be input to the second neural network 13, the Q output from the first neural network 11 as a result of inputting the miRNA attribute of the information provider and multidimensional miRNA information to the first neural network 11. A value and information on eating and drinking for a certain period of the information provider are prepared. Next, the Q value and the information intake information of the information provider for a certain period are input to the second neural network 13.

(Step S <b> 102 b) As a result of inputting the Q value and the eating intake information of the information provider for a certain period to the second neural network 13, ideal eating information is output from the second neural network 13.

(Step S103b) The second neural network 13 is learned. As a neural network learning method, for example, reinforcement learning may be performed. Reinforcement learning does not require correct answer data as in supervised learning, so even if it takes a long time to actually acquire correct answer data for the ideal eating information of the output of the second neural network 13, You can learn between.

<Information provision stage>
In the information provision stage of the second embodiment, the miRNA score of the user and the recommended eating information for the user are provided using the first neural network 11 and the second neural network 13 that have been learned in the learning stage described above. It is a stage. In this information providing stage, the information providing apparatus 10b includes the first neural network 11 and the second neural network 13 that have been learned in the learning stage described above. That is, the information providing apparatus 10b has been learned to compress the number of dimensions of miRNA information to a smaller number of dimensions based on the miRNA attribute of the information provider and multidimensional miRNA information and output a Q value. 1 neural network 11 and a second neural network 13 learned to output ideal eating information based on the Q value output from the first neural network 11 and the eating intake information of the information provider for a certain period of time. And comprising.

  The method of providing the user's miRNA score using the first neural network 11 is the first example of the first embodiment described above (information providing step (S200) by the first neural network 11 shown in FIG. 3) or implementation. Since it is the same as Example 2 (Example 2-1 or Example 2-2 of the information providing stage), description thereof is omitted.

  With reference to FIG. 8, the information provision step by the second neural network 13 according to the second embodiment will be described. In FIG. 8, the information provision stage (S200b) includes two steps S201b and S202b.

(Step S201b) The information output unit 12 performs the information providing stage (S200 in FIG. 3) of Example 1 of the first embodiment described above or the information providing stage of Example 2 (Example 2-1 or Example 2 of the information providing stage). The Q value output from the first neural network 11 or 11a is input to the second neural network 13 in the same manner as in (-2).

(Step S202b) As a result of inputting the Q value to the second neural network 13, eating information recommended to the user is output from the second neural network 13. The information providing apparatus 10 includes the information providing stage (S200 in FIG. 3) of Example 1 of the first embodiment described above or the information providing stage (Example 2-1 or Example 2-2 of the information providing stage) of Example 2. Similarly, the user's miRNA score converted from the Q value output from the first neural network 11 or 11a and the eating information recommended for the user output from the second neural network 13 are transmitted to the terminal device 20. The terminal device 20 records the user's miRNA score received from the information providing apparatus 10 and the eating information recommended for the user, and displays the user's miRNA score and the eating information recommended for the user according to the information browsing operation by the user. Display on the screen. Thereby, the user can browse his / her miRNA score and eating information recommended for himself / herself by the terminal device 20. The miRNA score can concisely show the balance of the miRNA profile. Moreover, the information which shows the meal for improving the balance of the said miRNA profile of the said user can be shown with the eating information recommended to the user.

  The above is description of the Example of the information provision apparatus 10b which concerns on 2nd Embodiment.

  According to the second embodiment described above, it is possible to simply present the balance state of the user's miRNA profile and to present information indicating a meal for improving the balance of the user's miRNA profile. The effect that it can be obtained.

  As mentioned above, although this invention was demonstrated using embodiment, it cannot be overemphasized that the technical scope of this invention is not limited to the range as described in the said embodiment. It will be apparent to those skilled in the art that various modifications or improvements can be added to the above embodiment. Further, it is apparent from the description of the scope of claims that embodiments with such changes or improvements can be included in the technical scope of the present invention.

1, 1b Information providing system 10, 10b Information providing device 11, 11a First neural network 12, 12b Information output unit 13 Second neural network 20 Terminal device

Claims (7)

A first neural network that has been trained to compress the number of dimensions of miRNA information to a smaller number of dimensions based on the miRNA attribute of the information provider and multidimensional miRNA information and to output a Q value;
An information output unit that outputs the miRNA score of the user corresponding to the Q value from the miRNA information of the user using the first neural network;
An information providing apparatus comprising: The miRNA attribute is the age and sex of the information provider,
The information providing apparatus according to claim 1. In the first neural network, the learning is performed by further adding biochemical data of the information provider.
The information providing apparatus according to claim 1 or 2. The information output unit outputs a miRNA score of the user corresponding to a Q value using the first neural network from the miRNA information and biochemical data of the user.
The information providing apparatus according to claim 3. A second neural network learned to output ideal eating information based on the Q value output from the first neural network and the eating information of the information provider for a certain period of time;
The information output unit outputs eating information recommended to the user using the second neural network from the Q value output using the first neural network from the miRNA information of the user.
The information providing apparatus according to any one of claims 1 to 4. By the information provision apparatus of any one of Claim 1 to 5,
An information providing method for providing a miRNA score of a user. A learning method for a neural network of the information providing apparatus according to claim 1,
An information acquisition step of acquiring miRNA attributes of the information provider and multidimensional miRNA information;
A learning step of learning the neural network so as to output a Q value by compressing the number of dimensions of the miRNA information to a smaller number of dimensions based on the miRNA attribute of the information provider and multidimensional miRNA information;
A method for learning a neural network of an information providing apparatus including:

Images