JP7145729B2 - Analysis processing device, analysis processing method, and machine learning device - Google Patents

Description

The present invention relates to an analysis processing device, an analysis processing method, and a machine learning device for analyzing the effects of near-infrared rays on skin and/or physical condition.

A person's physical condition is greatly affected by the surrounding environment, and in physical condition management, it is necessary to consider various factors such as the temperature, weather, and atmospheric pressure at that time. Techniques for supporting physical condition management in consideration of such surrounding environments have been conventionally known.

For example, Patent Literature 1 describes a physical condition management support device that acquires information about the user's surrounding environment and estimates the user's physical condition, thereby enabling easy input related to physical condition management.

JP 2017-182350 A

By the way, studies have shown that near-infrared rays contained in sunlight have an adverse effect on human health. In particular, in dermal fibroblasts, it is known to reduce the production of versican, a heavy biological component that plays a variety of roles in skin tissue formation, maintenance and repair. ing.

However, it has not yet been fully understood what kind of conditions exposure to near-infrared rays brings to the skin and physical conditions of individuals.

SUMMARY OF THE INVENTION It is an object of the present invention to provide an analysis processing apparatus for analyzing the influence of the amount of near-infrared rays on the skin and physical condition.

In order to solve the above problems, the present invention provides an analysis processing device for analyzing the effects of near-infrared rays on the skin and/or physical condition,
Acquisition means for acquiring near-infrared data consisting of multiple items of item information including area, time of measurement and near-infrared amount, and user data consisting of multiple items of item information including area, acquisition time and answer;
analysis processing means for performing analysis processing using the near-infrared data and user data related to a common area;
The analysis process is characterized by including a process of calculating an analysis result based on the input near-infrared data and user data.

The present invention also provides an analysis processing method for analyzing the effects of near-infrared rays on the skin and/or physical condition,
a step of acquiring near-infrared data consisting of multiple items of item information including area, time of measurement and near-infrared amount, and user data consisting of multiple items of item information including area, acquisition time and answer;
A computer executes a step of analyzing and processing using the near-infrared data and user data related to a common area,
The analysis process is characterized by including a process of calculating an analysis result based on the input near-infrared data and user data.

Further, the present invention is a machine learning device for machine learning the influence of near infrared rays on the skin and / or physical condition,
Acquisition means for acquiring near-infrared data consisting of multiple items of item information including area, time of measurement and near-infrared amount, and user data consisting of multiple items of item information including area, acquisition time and answer;
learning processing means for performing learning processing using the near-infrared data and user data,
The learning process includes updating parameters for an impact prediction model for predicting the impact on skin and/or health based on the near-infrared data and user data that have been input. characterized by comprising

With such a configuration, the near-infrared data and user data can be used to analyze and predict effects on skin and/or health.

In a preferred embodiment of the present invention, conversion processing means for converting the item information about the area into predetermined item information,
The analysis process is characterized by using the near-infrared data and the user data associated with the area based on the item information given by the conversion process.
By adopting such a configuration, it becomes possible to correspond to each region and perform analysis and prediction for each region.

In a preferred embodiment of the present invention, the near-infrared data includes terrestrial near-infrared data measured on the ground surface and reflected light infrared data obtained by measuring reflected light on the ground surface.

In a preferred embodiment of the present invention, the analysis process is based on a combination of one or more items included in the input near-infrared data and one or more items of input user data, and the item It is characterized by calculating the correlation of
With such a configuration, it is possible to analyze the correlation and use it for creating a prediction model and designing a learning device.

In a preferred embodiment of the present invention, user data for generating the user data using data including information about the timing of responding to questionnaires and/or interviews, and in which response items to questions with a specified period are associated with specified periods. comprising generating means,
The user data is generated by using the information on the response time and the exposure time obtained by using the specified period as the acquisition time, and the response item to the time-specified question as the answer.
By adopting such a configuration, it becomes possible to analyze the influence of the amount of near-infrared rays, etc., taking into consideration the period and time.

A preferred embodiment of the present invention is characterized in that the analysis processing is further performed using meteorological data.
By adopting such a configuration, it becomes possible to analyze the influence of the amount of near-infrared rays, etc., taking weather conditions into account.

In a preferred embodiment of the present invention, based on the analysis result, using the near-infrared amount input for each region, prediction means is provided for predicting the degree of influence on the skin and/or health based on the near-infrared amount for each region. characterized by
With such a configuration, it is possible to predict the influence of the amount of near-infrared rays.

ADVANTAGE OF THE INVENTION According to this invention, the analysis processing apparatus for analyzing the influence of the amount of near-infrared rays with respect to skin and physical conditions can be provided.

It is a figure which shows the system configuration|structure of the processing system which concerns on Embodiment 1 of this invention. 3 is a hardware configuration diagram of a terminal device according to Embodiment 1 of the present invention; FIG. 1 is a hardware configuration diagram of an analysis processing device according to Embodiment 1 of the present invention; FIG. 4 is a processing flowchart for acquiring near-infrared data and user data according to Embodiment 1 of the present invention. It is a figure which shows an example of questionnaire data, period designation|designated data, and user data which concern on Embodiment 1 of this invention. 4 is a processing flowchart relating to analysis processing according to Embodiment 1 of the present invention. It is an example of a screen display of the prediction screen classified by area which concerns on Embodiment 1 of this invention. It is a hardware block diagram of the machine-learning apparatus based on Embodiment 2 of this invention. FIG. 10 is a processing flowchart relating to learning processing according to Embodiment 2 of the present invention. FIG.

<Embodiment 1>
A processing system according to the first embodiment of the present invention will be described below with reference to the drawings. The embodiments shown below are examples of the present invention, and the present invention is not limited to the following embodiments, and various configurations can be adopted.

Although the configuration, operation, etc. of the processing system will be described in the present embodiment, a method, processing apparatus, computer program, recording medium, etc. having the same configuration can also achieve the same effect. Also, the program may be stored in a recording medium. Using this recording medium, the program can be installed in a computer, for example. Here, the recording medium storing the program may be a non-transitory recording medium such as a CD-ROM.

<Configuration of processing system>
Referring to FIG. 1 showing the configuration in one embodiment, the processing system is embodied as processing system 1 .

This processing system 1 comprises an analysis processing device 2, a terminal device 3, a web server 4 and a communication network NW. The analysis processing device 2 cooperates with the terminal device 3 via the communication network NW, and is configured to enable data input of information for analysis processing and data input via the terminal device 3 . Also, the analysis processing device 2 is configured to be able to communicate with the satellite data providing server SS via the communication network NW, and acquires satellite data from the satellite data providing server SS.

Based on the display processing from the terminal device 3, the web server 4 displays the web page based on the analysis processing result of the analysis processing device 2, and transmits the display processing result.

The communication network NW includes an IP (Internet Protocol) network such as the Internet. The communication network NW accommodates the analysis processing device 2, the terminal device 3, and the satellite data providing server SS, respectively, and the analysis processing device 2, the terminal device 3, and the satellite data providing server SS perform data communication via the communication network NW. are assigned an IP address for each. In the following description, the intervention of the communication network NW will be omitted unless it is unclear.

The terminal device 3 can adopt a single configuration or a composite configuration including a computer terminal (including a smart phone terminal, a personal computer and a tablet terminal).

More specifically, the terminal device 3 in the processing system 1 includes hardware and functional components, as illustrated in FIG. That is, each terminal device 3 includes, as hardware components, an arithmetic device (CPU (Central Processing Unit)) 11 and a main storage device (RAM (Random Access Memory)) 12 as a working memory.

Each terminal device 3 includes an auxiliary storage device 13 such as an HDD, SSD, or flash memory that rewritably stores an OS (Operating System), application programs, and various information (including data), a communication control unit 14, and a NIC. (Network Interface Card) or other communication interface (IF) unit 15, a display control unit 16, a display unit 17, an information input/designation unit 18, and the like.

In order to logically implement the functional configuration of each terminal device 3, a web browser, a terminal control program, and the like are installed in the auxiliary storage device 13 as application programs. In each terminal device 3, when the power is turned on or an instruction from a user (user) is triggered, the arithmetic unit (CPU) 11 develops the application program in the main storage device (RAM) 12 and executes it.

The analysis processing device 2 has a data communication function and includes hardware and functional components as illustrated in FIG. That is, the analysis processing device 2 includes, as hardware components, an arithmetic device (CPU (Central Processing Unit)) 21 and a main storage device (RAM (Random Access Memory)) 22 as a working memory.

The analysis processing device 2 includes an auxiliary storage device 23 such as an HDD, SSD, or flash memory that rewritably stores an OS (Operating System), application programs, and various types of information (including data), a communication control unit 24, and a NIC. A communication interface (IF) unit 25 such as (Network Interface Card) is further provided.

The analysis processing device 2 is a processing device for analyzing and processing the influence of near-infrared rays on the skin on the earth's surface, using the amount of near-infrared rays as satellite data acquired from the satellite data providing server SS. Below, the amount of near-infrared rays reflected from the ground is obtained by measuring the amount of near-infrared rays reflected from the ground by the satellite SA in outer space, and the amount of reflected near-infrared rays provided to the analysis processing device 2 via the satellite data providing server SS, skin and / Alternatively, a case in which analysis processing is performed using questionnaire data stored in a database DB as data relating to physical condition will be exemplified.

Here, in addition to the amount of reflected near-infrared rays, one or more of ground near-infrared amounts obtained by measuring near-infrared amounts on the ground, and meteorological data relating to temperature, humidity, wind speed, and the like may be used. In addition to/or instead of the questionnaire data, one or more of measurement data obtained by measuring the user's skin condition, interview data by doctors, beauty advisors, etc., questionnaire answers, measurement results, and interview results are associated. Analytical processing may be performed using the data obtained.

<Functional components of analysis processing device>
The analysis processing device 2 includes, as functional components, storage means 201, near-infrared data generation means 202, conversion processing means 203, user data generation means 204, acquisition means 205, analysis processing means 206, prediction means 207 and databases DB1-4.

In order to logically implement the functional components described above in the analysis processing device 2, an analysis processing program is installed in the auxiliary storage device 23 as an application program. Then, in the analysis processing device 2, when the power is turned on, the arithmetic unit (CPU) 21 develops this processing program in the main storage device (RAM) 22 and executes it.

<Acquisition of near-infrared data>
FIG. 4(a) is a processing flowchart for acquiring near-infrared data. First, in step S11, the storage means 201 receives satellite data obtained via the satellite data providing server SS, and stores it in the database DB1. The satellite data is associated with measurement date and time and location information. In this embodiment, the satellite data is provided from the satellite data providing server SS in the form of an image file. For example, there are observation data obtained from LANDSAT satellites, PLEIADES satellites, and the like. Satellite data in the wavelength region of the NIR (Near InfraRed) band are acquired by these.

In step S12, the near-infrared data generating means 202 analyzes the satellite data stored in the database DB1, calculates the amount of near-infrared rays for each region, and stores the calculated amount in the database DB2. Then, in step S13, near-infrared data consisting of a plurality of items of item information including the calculated amount of near-infrared rays, an area based on one piece of satellite data information, and a measurement time based on the measurement date and time of the satellite data is obtained. The conversion processing means 203 converts the position information as item information related to the area associated with the satellite data into predetermined item information for analysis, and the item information related to the area item of the near-infrared data is set. .

The area to be converted may be local or prefectural level, or may be set in municipality or smaller units. The amount of near-infrared light for the entire area or a predetermined area included in the satellite data is obtained by arithmetic processing using the amount of near-infrared light at each point included in the satellite data. Similarly, using a plurality of satellite data of corresponding measurement dates and times belonging to a certain area, the amount of near-infrared rays at each point in time in each area is arithmetically processed. The near-infrared data generating means 202 calculates the amount of near-infrared rays for each region at each point in time using one or more satellite data, and utilizes the results for analysis processing.

<Acquisition of user data>
FIG. 4(b) is a processing flowchart for acquiring user data. First, in step S21, the storage means 201 receives the questionnaire data and stores it in the database DB3. FIG. 5(a) is a diagram showing an example of questionnaire data stored in the database DB3. The questionnaire data is associated with the questionnaire response time (year/month, year/month/day, etc.), regional information, and answers to questions. Regional information may be, for example, the location of the venue where the questionnaire data was conducted, the location of the user (questionnaire respondent), or information selected and entered as an answer to a question asking the region to which the user belongs. may be

Furthermore, some or all of the questions in the questionnaire may be period-specified questions in which a period past the date and time of the questionnaire (response time) is specified and the user is asked to answer. For example, in the form of "Please select from the following skin problems that have occurred in the past two months." We will accept responses for periods earlier than the time period) in a multiple-choice format or a multiple-choice format.

Period specification data for specifying the period is associated with the period specification question and stored in the database DB3. FIG. 5B is a diagram showing an example of period designation data. For example, for the questionnaire with the questionnaire ID "1810", there are questions with a specified period of 2 months (Questions 3-1 to 4-2 in the example shown) and questions with a specified period of 24 months ( Problems 5-1 to ) in the illustrated example are included.

As described above, the questionnaire data is associated with the meta-items and response items related to the response time of the questionnaire, and the region information.

The user data generation means 204 uses the questionnaire data to generate user data in which the exposure time obtained by using the information on the response time and the specified period is the acquisition time, and the response items to the time specified questions are the answer items. .

For example, in step S22, a period-specified question is acquired for each specified period from the questionnaire data, the exposure period is estimated using the meta-information regarding the response time of the questionnaire and the specified period of the period-specified question, and answer items for each exposure period are acquired. (step S23).

Then, in step S24, the conversion processing means 203 converts the item information related to the region associated with the questionnaire data into predetermined item information for analysis. In step S25, the user data generating means 204 acquires user data consisting of a plurality of item information including area, exposure time (acquisition time), and answer, and stores it in database DB4.

When using measurement results and interview results related to skin and/or physical condition, the user data may include measurement values and question answer items instead of or in addition to answer items. When the measurement results are used, the date of measurement corresponds to the time of acquisition, and the location of the user, the region where the user belongs or works, and the location of measurement corresponds to the region. When using the interview results, the acquisition time corresponds to the time of answering the interview, the time of past exposure specified by the contents of the interview, etc. etc. correspond to regions. Moreover, the user data does not necessarily have to be obtained by processing the data, and the data itself regarding the skin and/or physical condition stored in the database DB may be used.

FIG. 5(c) is a diagram showing an example of user data by exposure period estimated by the period designation data and the response period item of the questionnaire data. For example, the upper part shows user data that aggregates period-specified questions (questions 3-1 to 4-2 in the example shown) that specify the period two months ago from the response time item (October 2018) of the questionnaire data. This is an example, and the lower part is an example of user data obtained by aggregating period-specified questions (problems 5-1 to 5-1 in the illustrated example) in which a period of 24 months is specified. Here, the dates included in the date items of the questionnaire data are ignored in the calculation, but the exposure time may be estimated by taking these into account.

Here, the area associated with the questionnaire data does not necessarily need to be converted, and the area associated with the questionnaire data is assumed to be a predetermined area that is the purpose of the conversion process, and the item information related to the area of the satellite data (Positional information) may be converted. In addition, in the illustrated example, user data is aggregated separately for each estimated exposure time, but such data processing is not necessarily required.

<Analysis processing>
FIG. 6 is a processing flowchart relating to analysis processing. In step S31, the acquisition means 205 acquires near-infrared data consisting of a plurality of items of item information including the area, measurement time, and near-infrared amount stored in the database DB2, and the area, acquisition time, and answer stored in the database DB4. Acquire user data consisting of item information of multiple items including.

Analysis processing means 206 performs analysis processing using near-infrared data and user data relating to a common area, and calculates an analysis result. In this embodiment, as shown in step S32, based on a combination of one or more items included in the input near-infrared data and one or more items in the input user data, items are analyzed as Calculate the correlation.

Based on the obtained correlation, for example, a prediction formula for calculating the degree of influence based on the input amount of near-infrared rays can be set. The prediction unit 207 uses the near-infrared amount input for each region to predict the degree of influence on the skin and/or health based on the input near-infrared amount. The amount of near-infrared rays input by the prediction means 207 may be a predicted future amount of near-infrared rays in each region, or may be a measured value of reflected near-infrared amount or terrestrial near-infrared amount.

<Display processing>
The web server 4 has, as a functional component, display means 401 for displaying a web page based on the analysis processing result of the analysis processing device 2 based on the display processing from the terminal device 3 and transmitting the display processing result. Prepare. The display unit 401 performs display processing of the region-specific prediction screen and transmits the processing result, and the terminal device 3 displays the region-specific prediction screen based on the processing result.

FIG. 7 is a screen display example of the region-specific prediction screen. The prediction screen W1 for each region displays the "beautiful skin index" for each region on the map based on the input amount of near-infrared rays. In this embodiment, the beautiful skin index is treated as one of the skin condition items, and the beautiful skin index defined in advance according to the near-infrared level is used for displaying the regional prediction screen W1.

<Embodiment 2>
Next, a second embodiment of the present invention will be described with reference to FIGS. 8 and 9. FIG. In this embodiment, the machine learning device 6 is configured to include learning means 208 instead of the analysis processing means 206 . It should be noted that the same reference numerals are used for the same configurations as in the first embodiment described above, and the description thereof will be simplified.

FIG. 8 is a hardware configuration diagram of the machine learning device 6. As shown in FIG. Also, FIG. 9 is a processing flowchart relating to the learning processing. In this embodiment, as in the first embodiment, a predetermined area is associated using storage means 201, near-infrared data generation means 202, conversion processing means 203, and user data generation means 204. The obtained near-infrared data and user data are stored in databases DB2 and DB4.

<Learning processing>
Acquisition means 205 acquires near-infrared data consisting of a plurality of items of item information including region, time of measurement and near-infrared amount from database DB2, and acquires a plurality of items of item information including region, acquisition time and answer from database DB4. Acquire user data consisting of

Then, as shown in step S41 of FIG. 9, a combination of near-infrared data and user data including corresponding area and time items is accepted as teacher data. The learning means 208 performs learning processing using the input near-infrared data and user data, and in step S42, an impact prediction model for predicting the degree of impact on skin and/or health based on the near-infrared data. , update the parameters.

<Display processing>
The prediction means 207 uses the near-infrared amount and the influence degree prediction model input for each region to perform the influence degree prediction on the skin and/or health for each region based on the input near-infrared amount.

Using the prediction result of the prediction means 207, the web server 4 performs display processing of the web page based on the analysis processing result of the analysis processing device 2 based on the display processing from the terminal device 3, and displays the display processing result. Send. The terminal device 3 displays the regional prediction screen based on the display processing result.

1 processing system 11 arithmetic unit (CPU)
12 main memory (RAM)
13 Auxiliary storage device 14 Communication control unit 15 Communication interface (IF) unit 16 Display control unit 17 Display unit 18 Information input/designation unit 2 Analysis processing unit 21 Arithmetic unit (CPU)
22 main memory (RAM)
23 Auxiliary storage device 24 Communication control unit 25 Communication interface (IF) unit 201 Storage unit 202 Near-infrared data generation unit 203 Conversion processing unit 204 User data generation unit 205 Acquisition unit 206 Analysis processing unit 207 Prediction unit 208 Learning unit 3 Terminal device 4 Web server 401 Display means DB1 to DB4 Database NW Communication network SA Artificial satellite SS Satellite data providing server

Claims (7)

An analysis processing device for analyzing the effects of near-infrared rays on skin and/or physical condition,
Acquisition means for acquiring near-infrared data consisting of multiple items of item information including area, time of measurement and near-infrared amount, and user data consisting of multiple items of item information including area, acquisition time and answer;
analysis processing means for performing analysis processing using the near-infrared data and user data related to a common area;
In the analysis process , based on a combination of one or more items included in the input near-infrared data and one or more items of input user data, a correlation of items is calculated as an analysis result,
Further, a prediction means for predicting the degree of influence on the skin and/or health based on the near-infrared amount for each region, using the near-infrared amount input for each region based on the analysis result. Analytical processor. conversion processing means for converting the item information about the area into predetermined item information;
2. The analysis processing apparatus according to claim 1, wherein said analysis processing uses said near-infrared data and user data associated with regions based on item information given by said conversion processing. 3. The analysis processing apparatus according to claim 1, wherein said near-infrared data includes terrestrial near-infrared data measured on the ground surface and reflected light infrared data obtained by measuring reflected light on the ground surface. User data generation means for generating the user data using data that includes information about the timing of responding to questionnaires and/or medical interviews and that associates a specified period with an answer item for a specified period question,
Claims 1 to 3, wherein the user data is generated with the exposure time obtained by using the information on the response time and the specified time period as the acquisition time, and the response item to the time-specified question as the answer. 4. The analysis processing device according to any one of 3 . 5. The analytical processing device according to claim 1 , wherein said analytical processing is further performed using meteorological data. A machine learning device for machine learning the effects of near-infrared rays on the skin and / or physical condition,
Acquisition means for acquiring near-infrared data consisting of multiple items of item information including area, time of measurement and near-infrared amount, and user data consisting of multiple items of item information including area, acquisition time and answer;
learning processing means for performing learning processing using a combination of the near-infrared data and user data , including the corresponding area and time items, as teacher data;
The learning process includes updating parameters for an impact prediction model for predicting the impact on skin and/or health based on the near-infrared data and user data that have been input. including
The machine learning device , wherein the influence degree prediction model outputs an influence degree prediction on the skin and/or health for each region based on the amount of near-infrared rays input for each region . An analysis processing method for analyzing the effects of near-infrared rays on skin and/or physical condition,
a step of acquiring near-infrared data consisting of multiple items of item information including area, time of measurement and near-infrared amount, and user data consisting of multiple items of item information including area, acquisition time and answer;
A computer executes a step of analyzing and processing using the near-infrared data and user data related to a common area,
In the analysis process , based on a combination of one or more items included in the input near-infrared data and one or more items of input user data, a correlation of items is calculated as an analysis result,
Furthermore, based on the analysis result, the computer executes a step of predicting the degree of impact on skin and / or health based on the near-infrared amount for each area, using the near-infrared amount input for each area. analysis processing method.

Images