JP7636166B2 - Water intake estimation device, water intake estimation method, and program - Google Patents

Description

The present invention relates to a water intake estimation device that obtains water intake using responses to a questionnaire.

Conventionally, there has been a health advice device that uses responses to a questionnaire to provide health advice. This device is a health advice device that displays advice for improving lifestyle habits, and has a lifestyle analysis questionnaire input means for inputting a group of responses to a predetermined group of questions, a means for calculating a predicted increase or decrease in health risk using the group of responses input by the lifestyle analysis questionnaire input means, an influencing response extraction means for selecting an answer that has increased the health risk from the group of responses input when an increase in health risk is predicted, and an influencing lifestyle item display means for displaying a question corresponding to the selected answer or advice associated with the question (see Patent Document 1).

Furthermore, there has conventionally been a monitoring device that monitors a subject by determining the subject's physical condition using the amount of water intake and vital data such as body temperature and blood pressure (see Patent Document 2).

JP 2014-135027 A JP 2020-052808 A

However, in the past, it was not possible to obtain fluid intake based on responses to questionnaires that included questions other than those directly asking about the amount of fluid intake. The questionnaires can also be called questionnaires.

The water intake estimation device of the first invention is a water intake estimation device that includes a raw information storage unit that stores raw information that is the basis for estimating water intake from answer information to two or more questions, including questions other than questions that directly ask about the amount of water ingested, an answer acceptance unit that accepts user answer information having answer information to two or more questions, an intake acquisition unit that acquires intake information that specifies the amount of water intake using the two or more answer information contained in the user answer information accepted by the answer acceptance unit and the raw information stored in the raw information storage unit, and an intake output unit that outputs the intake information.

With this configuration, fluid intake can be obtained based on responses to a questionnaire that includes questions other than those directly asking about the amount of fluid intake.

The fluid intake estimation device of the second invention is a fluid intake estimation device in which the two or more questions are two or more of the following types of questions compared to the first invention: beverage-related questions, which are questions about beverage addictiveness; alcohol-related questions, which are questions about alcohol addictiveness; diet-related questions, which are questions about diet-related addictiveness; and all-origin questions, which are questions about all origins.

With this configuration, an appropriate amount of fluid intake can be obtained based on responses to an appropriate questionnaire that includes questions other than those directly asking about the amount of fluid intake.

The water intake estimation device of the third invention is a water intake estimation device according to the first or second invention, further comprising a questionnaire storage unit in which two or more pieces of questionnaire information each having question information for two or more questions are stored in association with conditions related to user attribute values, a questionnaire acquisition unit that acquires questionnaire information corresponding to the conditions corresponding to the user attribute values of the user from the questionnaire storage unit, and a questionnaire output unit that transmits the questionnaire information acquired by the questionnaire acquisition unit to a user terminal, the raw information storage unit stores two or more pieces of raw information corresponding to the conditions corresponding to the user attribute values, the reception unit receives user response information corresponding to the user attribute values, and the intake acquisition unit acquires intake information using the raw information corresponding to the user attribute values corresponding to the user response information and the two or more pieces of response information contained in the user response information.

With this configuration, an appropriate amount of fluid intake can be obtained based on answers to a questionnaire that varies depending on the user's attribute values.

The fluid intake estimation device of the fourth invention is a fluid intake estimation device according to any one of the first to third inventions, in which the two or more questions have two or more types of question sets each consisting of one or more questions, the raw information storage unit stores two or more pieces of raw information corresponding to the types of questions, the intake acquisition unit acquires intake information for each type using answer information corresponding to each question of each of the two or more types and the raw information corresponding to each type, and acquires intake information using the two or more pieces of intake information.

This configuration allows an appropriate amount of fluid intake to be obtained based on responses to a questionnaire that includes questions other than those directly asking about the amount of fluid intake.

The fluid intake estimation device of the fifth invention is a fluid intake estimation device according to any one of the first to fourth inventions, in which the original information is a learning device constructed by performing a learning process using a machine learning algorithm using two or more teacher data sets having fluid intake information and answer information to two or more questions or answer-related information obtained from the answer information, and the intake acquisition unit is a fluid intake estimation device that performs a prediction process using a machine learning algorithm using two or more answer information or answer-related information obtained from two or more answer information contained in the user answer information accepted by the answer acceptance unit, and the learning unit stored in the original information storage unit, to acquire intake information.

With this configuration, appropriate fluid intake can be estimated using machine learning algorithms.

The sixth invention is a water intake estimation device according to the fifth invention, in which the machine learning algorithm is a random forest.

With this configuration, the appropriate amount of fluid intake can be estimated using a random forest algorithm.

The fluid intake estimation device of the present invention can obtain fluid intake based on responses to a questionnaire that includes questions other than those directly asking about the amount of fluid ingested.

Concept of the water intake estimation system A in the first embodiment Block diagram of the water intake estimation system A Block diagram of the water intake estimation device 2 A flowchart illustrating an example of the operation of the learning device 1. A flowchart illustrating an example of the operation of the water intake estimation device 2. A flowchart for explaining an example of the operation of the user terminal 3 A diagram showing an example of questionnaire information A diagram showing an example of the questionnaire information FIG. 13 shows the user response information management table. The figure shows the actual measurement value management table. A diagram showing the identity information management table A diagram showing an example of the output A diagram showing an example of the output Overview of the computer system Block diagram of the computer system

Below, embodiments of a water intake estimation device and the like are described with reference to the drawings. Note that components with the same reference numerals in the embodiments perform similar operations, and therefore may not be described again.

(Embodiment 1)
In this embodiment, a water intake estimation system is described that includes a water intake estimation device that acquires and outputs a water intake amount using answer information to two or more questions included in a questionnaire that includes questions other than the question that directly asks about the amount of water ingested, and raw information for obtaining the water intake amount using the answer information. Note that the questionnaire has two or more questions from, for example, beverage origin, alcohol origin, food origin, and all origin. In addition, each of the two or more questionnaires is associated with, for example, a user attribute value condition, and a different questionnaire is sent to the user terminal depending on the user attribute value.

In addition, in this embodiment, a water intake estimation system is described that has two or more types of questions and is equipped with a water intake estimation device that obtains the water intake amount using raw information for each type of question.

In addition, in this embodiment, a water intake estimation system including a water intake estimation device that acquires water intake using a machine learning algorithm is described. The machine learning is, for example, a random forest.

Figure 1 is a conceptual diagram of a water intake estimation system A in this embodiment. The water intake estimation system A includes a learning device 1, a water intake estimation device 2, and one or more user terminals 3.

The learning device 1 is a device that acquires raw information (described later) using the actual measured value of the water intake and answer information for each of two or more questions included in the questionnaire. The learning device 1 may be, for example, a personal computer, tablet terminal, smartphone, server, etc., and the type does not matter. The server may be, for example, a cloud server or an ASP server, and the type does not matter. The learning device 1 may be a standalone device or a server that receives instructions from the user terminal 3 and operates accordingly.

The water intake estimation device 2 is, for example, a so-called server. The server may be, for example, a cloud server or an ASP server, and the type does not matter. However, the water intake estimation device 2 may also be a standalone device such as a so-called personal computer, tablet terminal, smartphone, etc.

The user terminal 3 may be a personal computer, tablet terminal, smartphone, etc., and the type is not important.

The learning device 1, the water intake estimation device 2, and the user terminal 3 may be capable of communicating with each other via the Internet, a LAN, etc.

Figure 2 is a block diagram of the water intake estimation system A in this embodiment. Figure 3 is a block diagram of the water intake estimation device 2.

The learning device 1 includes a learning storage unit 11, a learning reception unit 12, a learning processing unit 13, and a learning output unit 14. The learning storage unit 11 includes a response storage unit 111, and an actual measurement value storage unit 112.

The water intake estimation device 2 comprises a storage unit 21, a reception unit 22, a processing unit 23, and an output unit 24. The storage unit 21 comprises a questionnaire storage unit 211, and a raw information storage unit 212. The reception unit 22 comprises a response reception unit 221. The processing unit 23 comprises a questionnaire acquisition unit 231, and an intake acquisition unit 232. The output unit 24 comprises a questionnaire output unit 241, and an intake output unit 242.

The user terminal 3 includes a terminal storage unit 31, a terminal reception unit 32, a terminal processing unit 33, a terminal transmission unit 34, a terminal reception unit 35, and a terminal output unit 36.

Various types of information are stored in the learning storage unit 11 that constitutes the learning device 1. The various types of information are, for example, answer information, actual measured values, and identification information for each of two or more pieces of original information.

The identification information is information used when acquiring two or more pieces of original information. The identification information is information that specifies the conditions of the answer information used when acquiring the original information. The identification information is information that corresponds to the acquired original information. The identification information is, for example, information that specifies the conditions related to the user attribute value. The identification information is, for example, information that identifies the type of question set. The identification information includes, for example, information that specifies the conditions related to the user attribute value and information that identifies the type of question set. The identification information is, for example, "male, female" which is a condition related to the user attribute value, and "beverage-derived, alcohol-derived, food-derived, all-derived" which is information that identifies the type of question set. The identification information is, for example, (gender = male & type of question set = beverage origin) (gender = male & type of question set = alcohol origin) (gender = male & type of question set = food origin) (gender = male & type of question set = all origins) (gender = female & type of question set = beverage origin) (gender = female & type of question set = alcohol origin) (gender = female & type of question set = food origin) (gender = female & type of question set = all origins).

Fluid intake from beverages is the amount of fluid ingested from beverages. Fluid intake from alcoholic beverages is the amount of fluid ingested from alcoholic beverages. Fluid intake from food is the amount of fluid ingested from food. Fluid intake from total sources is the amount of fluid ingested from beverages, alcoholic beverages, and food.

The answer storage unit 111 stores two or more pieces of answer information. The answer information is information that identifies the answer to the question. For example, the answer storage unit 111 stores answer information associated with an identifier. The answer information is information that identifies the user's answer to each question in the questionnaire. The user is the respondent. The answer information is usually associated with the question identifier of each question in the questionnaire. The question identifier is information that identifies the question, such as a question number or a question ID. The identifier is also a user identifier, or a day identifier, or a user identifier and a day identifier. The user identifier is information that identifies the user, such as an ID, email address, telephone number, or the ID of the terminal used by the user (for example, an IP address, a MAC address, a terminal identifier, etc.).

The answer information corresponds to, for example, the identification information. That is, the answer information may correspond to a user attribute value. The user attribute value is an attribute value of the user, such as gender, age, or occupation. The answer information may also correspond to a type identifier that identifies the type of question. The type is, for example, origin. The type may be, for example, beverage origin, alcohol origin, food origin, or all origin.

The actual measurement value storage unit 112 stores two or more actual measurement values. The actual measurement values are usually associated with answer information. The actual measurement values are usually associated with a set of answer information for each question in the questionnaire. The actual measurement values are associated with, for example, an identifier.

The actual measurement value is, for example, the amount of water intake of a user in a day. The actual measurement value is, for example, the amount of water intake of a single user in a day, and is associated with a user identifier. The actual measurement value is, for example, the amount of water intake of a single user in a day, and is associated with a user identifier and a day identifier.

The actual measurement value is associated with, for example, a type identifier. It is preferable that the actual measurement value storage unit 112 stores the actual measurement value for each origin. If the actual measurement value is the user's daily water intake, the origin may be, for example, two or more of beverage origin, alcohol origin, food origin, and all origin.

There is no restriction on the method of obtaining the actual measurement value. The actual measurement value is, for example, the daily fluid intake obtained from the user's responses to a multiple-choice questionnaire, which is a set of questions that asks the user to select the type and amount of food and drink consumed in a multiple-choice format. The actual measurement value is, for example, the daily fluid intake obtained from the user's responses to a questionnaire based on a descriptive food record method. However, the actual measurement value may be a value entered manually, etc. In other words, it is preferable that the actual measurement value is an accurate fluid intake value, but there may be some error. The actual measurement value may be a value that is considered to be roughly accurate.

The multiple-choice questionnaire above is a set of questions to determine actual fluid intake, and asks participants to select the types and amounts of food and drink they ingested each day.

The descriptive food record method involves giving subjects a record sheet to record what they have eaten and drunk over a certain period of time. The greatest advantage of the food record method is that it provides information about what they actually ate. Using responses based on the food record method, it is possible to obtain the user's actual daily fluid intake.

The learning reception unit 12 receives various instructions, information, etc. The various instructions, information, etc. are, for example, learning instructions. A learning instruction is an instruction to obtain original information. The input means for the various instructions, information, etc. may be anything, such as a touch panel, keyboard, mouse, or menu screen. The learning reception unit 12 may also receive various instructions, information, etc. from the user terminal 3.

The raw information is the information that is the basis for estimating the amount of fluid intake from the answer information to each of the two or more questions. Note that the two or more questions include questions other than those that directly ask about the amount of fluid intake. The amount of fluid intake here is the amount of fluid intake over a specified period of time. The specified period is preferably one day, but may be one week, half a day, etc.

The raw information is, for example, a learning device, which will be described later. The raw information is, for example, a correspondence table, which will be described later. The raw information is, for example, an arithmetic formula, which will be described later. The raw information is acquired by the learning processing unit 13, which will be described later.

The learning processing unit 13 acquires raw information. The process of the learning processing unit 13 is, for example, any one of the following (1) to (3). It is preferable that the learning processing unit 13 acquires a learning device by performing the following process (1).
(1) When the source information is a learning device

The learning processing unit 13 acquires two or more pairs from the learning storage unit 11. A pair is a collection of an actual value and two or more pieces of answer information. The actual value in the pair corresponds to the collection of two or more pieces of answer information in the pair. The actual value and the collection of answer information in the pair correspond to the same identifier, for example.

The learning processing unit 13 performs learning processing using the two or more acquired pairs according to a machine learning algorithm to obtain a learning device. More specifically, the learning processing unit 13, for example, provides the two or more acquired pairs to a module that performs machine learning learning processing, executes the module, and obtains a learning device. Note that the learning device may be called a classifier or a model. Furthermore, this learning device is provided to a module that performs machine learning prediction processing together with a set of two or more pieces of answer information, and is a learning device for obtaining the amount of water intake.

The learning module of the machine learning may be a random forest, a decision tree, deep learning, SVR, or the like, and the algorithm is not limited. For the machine learning, various machine learning functions such as the TensorFlow library, fastText, tinySVM, and the random forest module of the R language, and various existing libraries can be used.
(2) When the original information is a correspondence table

The learning processing unit 13 acquires two or more sets of answer information from the answer storage unit 111. The learning processing unit 13 also acquires actual measurement values corresponding to the sets of answer information from the actual measurement value storage unit 112.

For example, for each of two or more sets of answer information, the learning processing unit 13 constructs a vector whose elements are each piece of answer information contained in each set. The learning processing unit 13 also acquires, for each set, correspondence information that associates the vector with an actual measurement value corresponding to the set of answer information that is the basis of the vector. The learning processing unit 13 then constructs a correspondence table having two or more pieces of correspondence information. Note that the correspondence information may be a set of answer information and an actual measurement value, or may be link information that associates a set of answer information and an actual measurement value, and may be any information that allows a set of answer information to be associated with an actual measurement value.
(3) When the original information is an arithmetic expression

The learning processing unit 13 acquires two or more pairs from the learning storage unit 11. Then, the learning processing unit 13 acquires an arithmetic formula that outputs the actual measurement value of each of the two or more pairs, for example, using each answer information of the set of answer information owned by each of the two or more pairs as a parameter. The learning processing unit 13 acquires the arithmetic formula, for example, by multiple regression analysis. Note that the arithmetic formula is not limited to a linear formula, but may be an equation of quadratic or higher order. Furthermore, the learning processing unit 13 may reduce the number of dimensions of a vector having each answer information as an element, for example, by principal component analysis, and then acquire the arithmetic formula using the vector.

The learning output unit 14 outputs information. For example, the learning output unit 14 outputs raw information acquired by the learning processing unit 13. It is preferable that the learning output unit 14 accumulates the raw information in the raw information storage unit 212 of the water intake estimation device 2.

In this case, output usually means storage on a recording medium, but it may also be a concept that includes display on a display, projection using a projector, printing on a printer, sound output, transmission to an external device, and handing over the processing results to other processing devices or other programs, etc.

Various types of information are stored in the storage unit 21 that constitutes the water intake estimation device 2. The various types of information include, for example, questionnaire information (described below), source information, intake information (described below), and one or more pieces of user information.

User information includes a user identifier and one or more user attribute values. The user attribute value is, for example, gender, but may also include various attribute values such as age, type of work (e.g., manual labor, white collar, clerical work, construction, etc.), height, weight, etc.

The questionnaire storage unit 211 stores one or more pieces of questionnaire information. It is preferable that the questionnaire storage unit 211 stores two or more pieces of questionnaire information in association with conditions related to user attribute values. The questionnaire information has question information for two or more questions. The questionnaire information may exist for each type identifier that identifies the type of question.

The two or more questions in the questionnaire information include one or more questions other than a question that directly asks about the amount of fluid intake. The condition related to the user attribute value may be a condition using one user attribute value (e.g., "male", "age 20 or younger"), or a condition using two or more user attribute values (e.g., "male and 50 years or older", "male and physical labor", etc.).

The raw information storage unit 212 stores one or more pieces of raw information. The raw information storage unit 212 may store two or more pieces of raw information corresponding to conditions corresponding to user attribute values.

The raw information storage unit 212 may store two or more pieces of raw information corresponding to the type of question. In other words, the raw information may be associated with a type identifier.

The original information is information that is used to estimate the amount of fluid intake from the answer information to two or more questions, including questions other than those that directly ask about the amount of fluid intake. The original information is, for example, a learning device. The learning device is information acquired by performing a learning process using a machine learning algorithm using two or more teacher data sets that have answer information to two or more questions or answer-related information obtained from the answer information, and fluid intake information. The answer-related information (for example, "1", "2") is information that corresponds to the answer information (for example, "Yes", "No") and may be called answer information. The answer information is information entered by the user, and the answer-related information is information that has a one-to-one relationship with the answer information.

The reception unit 22 receives various instructions, information, and the like. The reception unit 22 receives, for example, a questionnaire output instruction. This is an instruction to output questionnaire information. It is preferable that the questionnaire output instruction includes a user identifier or one or more user attribute values. The reception unit 22 receives, for example, one or more pieces of user answer information.

Note that, although "receiving" here typically refers to receiving information transmitted via a wired or wireless communication line, it may also be a concept that includes receiving information input from an input device such as a keyboard, mouse, or touch panel, or receiving information read from a recording medium such as an optical disk, magnetic disk, or semiconductor memory.

The answer receiving unit 221 receives user answer information having answer information for each of two or more questions. The user answer information has two or more pieces of answer information. Such answer information corresponds to a question identifier. The user answer information may have two or more pieces of answer information and a user identifier. The user answer information may have two or more pieces of answer information and one or two or more user attribute values.

The processing unit 23 performs various processes. For example, the processing unit 23 includes a questionnaire acquisition unit 231 and an intake acquisition unit 232.

The questionnaire acquisition unit 231 acquires questionnaire information from the questionnaire storage unit 211. For example, the questionnaire acquisition unit 231 acquires questionnaire information from the questionnaire storage unit 211 that corresponds to a condition that matches one or more user attribute values that are paired with a user identifier contained in the accepted questionnaire output instruction. For example, the questionnaire acquisition unit 231 acquires questionnaire information from the questionnaire storage unit 211 that corresponds to a condition that matches one or more user attribute values that are paired with a user identifier contained in the accepted questionnaire output instruction.

The intake amount acquisition unit 232 acquires intake amount information that specifies the amount of water intake, using two or more pieces of answer information contained in the user answer information accepted by the answer acceptance unit 221 and the raw information stored in the raw information storage unit 212.

The intake amount acquisition unit 232 acquires the intake amount information, for example, by using raw information corresponding to the user attribute value corresponding to the user answer information accepted by the answer acceptance unit 221 and two or more pieces of answer information contained in the user answer information.

The intake amount acquisition unit 232 acquires intake amount information for each type, for example, using answer information corresponding to each question of two or more types, which is answer information contained in the user answer information accepted by the answer acceptance unit 221, and raw information corresponding to each type, and acquires intake amount information using two or more pieces of intake amount information. Note that for each type, "for each type" refers to each type identifier. The intake amount acquisition unit 232 acquires intake amount information, for example, for all origins, beverage origins, alcohol origins, and food origins, using answer information corresponding to the questions corresponding to each origin and raw information corresponding to each origin.

The intake amount acquiring section 232 acquires the intake amount information, for example, by any one of the following methods (1) to (3).
When the source information is a learner

The intake amount acquisition unit 232 performs prediction processing using a machine learning algorithm, using two or more pieces of answer information contained in the user answer information accepted by the answer acceptance unit 221 or answer-related information obtained from each of the two or more pieces of answer information, and a learning device stored in the raw information storage unit 212, to acquire intake amount information. Note that the answer-related information is information acquired from the answer information entered by the user, and may be regarded as the same as the answer information.

The machine learning prediction module, like the learning module, may be a random forest, a decision tree, deep learning, SVR, or the like, and the algorithm is not important. Furthermore, for machine learning, various machine learning functions such as the TensorFlow library, fastText, tinySVM, and the random forest module of the R language, as well as various existing libraries, can be used.

More specifically, the intake acquisition unit 232 acquires two or more pieces of answer information contained in the user answer information accepted by the answer acceptance unit 221, or answer-related information obtained from each of the two or more pieces of answer information.

Next, the intake amount acquisition unit 232 acquires a learning device from the raw information storage unit 212. The intake amount acquisition unit 232 acquires, for example, a learning device corresponding to a user attribute value corresponding to the user response information from the raw information storage unit 212. The intake amount acquisition unit 232 also acquires, for example, a learning device corresponding to each of two or more types, for each type, from the raw information storage unit 212. The intake amount acquisition unit 232 also acquires, for example, a learning device corresponding to a user attribute value corresponding to the user response information, from the raw information storage unit 212, a learning device corresponding to each of two or more types, for each type.

Next, the intake amount acquiring unit 232 provides two or more pieces of answer information or two or more pieces of answer-related information and the learning device to a module that performs machine learning prediction processing, executes the module, and acquires the intake amount information. The intake amount acquiring unit 232 acquires the intake amount information, for example, by type.
(2) When the original information is a correspondence table (2-1) When using one vector that is most similar to a vector obtained from user response information

The intake acquisition unit 232 constructs a vector whose elements are each piece of information contained in two or more pieces of answer information contained in the user answer information accepted by the answer acceptance unit 221 or answer-related information obtained from each of the two or more pieces of answer information.

Next, the intake amount acquisition unit 232 searches the correspondence table for a vector that is most similar to the vector. The intake amount acquisition unit 232 acquires the actual measurement value that is paired with the most similar vector as intake amount information.

The intake amount acquiring unit 232 acquires the intake amount information by the above-mentioned process, for example, using a correspondence table corresponding to user attribute values. The intake amount acquiring unit 232 acquires the intake amount information by the above-mentioned process, for each type, for example, using a correspondence table corresponding to each of two or more types. The intake amount acquiring unit 232 acquires the intake amount information by the above-mentioned process, for each type, for example, using a correspondence table corresponding to user attribute values and corresponding to each of two or more types.
(2-2) When using two or more vectors that meet the conditions

The intake acquisition unit 232 constructs a vector whose elements are each piece of information contained in two or more pieces of answer information contained in the user answer information accepted by the answer acceptance unit 221 or answer-related information obtained from each of the two or more pieces of answer information.

Next, the intake amount acquisition unit 232 determines two or more vectors that are included in each correspondence information in the correspondence table and that satisfy the approximation condition for the vector constructed by the intake amount acquisition unit 232. Next, the intake amount acquisition unit 232 acquires actual measurement values that are paired with each of the two or more vectors.

Next, the intake amount acquisition unit 232 acquires intake amount information using the two or more acquired actual measured values. Note that the intake amount acquisition unit 232 acquires, for example, a representative value (e.g., average value, median) of the two or more acquired actual measured values as the intake amount information. For example, the intake amount acquisition unit 232 calculates a weighted average of the two or more acquired actual measured values using the actual measured values and the degree of approximation, and acquires this value as the intake amount information. Note that the approximation condition is, for example, that the distance between the two vectors is equal to or less than a threshold value or is less than a threshold value.

The intake amount acquiring unit 232 acquires the intake amount information by the above-mentioned process, for example, using a correspondence table corresponding to user attribute values. The intake amount acquiring unit 232 acquires the intake amount information by the above-mentioned process, for each type, for example, using a correspondence table corresponding to each of two or more types. The intake amount acquiring unit 232 acquires the intake amount information by the above-mentioned process, for each type, for example, using a correspondence table corresponding to user attribute values and corresponding to each of two or more types.
(3) When the original information is an arithmetic expression

The intake acquisition unit 232 constructs a vector whose elements are each piece of information contained in two or more pieces of answer information contained in the user answer information accepted by the answer acceptance unit 221 or answer-related information obtained from each of the two or more pieces of answer information.

The intake amount acquisition unit 232 acquires the calculation formula, which is the raw information, from the raw information storage unit 212. The intake amount acquisition unit 232 provides the constructed vector to the calculation formula, executes the calculation formula, and acquires the intake amount information.

The output unit 24 outputs various types of information. The various types of information include, for example, questionnaire information and intake amount information.

Here, output usually means transmission to the user terminal 3, but it may also be a concept that includes display on a display, projection using a projector, printing on a printer, sound output, storage on a recording medium, and delivery of the processing results to other processing devices or other programs, etc.

The questionnaire output unit 241 transmits the questionnaire information acquired by the questionnaire acquisition unit 231 to the user terminal 3.

The intake output unit 242 outputs the intake information acquired by the intake acquisition unit 232.

Here, output usually means transmission to the user terminal 3, but it may also be a concept that includes display on a display, projection using a projector, printing on a printer, sound output, storage on a recording medium, and delivery of the processing results to other processing devices or other programs, etc.

The terminal storage unit 31 constituting the user terminal 3 stores various types of information. The various types of information are, for example, a user identifier and one or more user attribute values.

The terminal reception unit 32 receives various instructions and information. The various instructions and information are, for example, answer information, a questionnaire output instruction, and a transmission instruction. The transmission instruction is an instruction to transmit intake amount information. The transmission instruction includes user answer information. The transmission instruction includes, for example, a user identifier. The transmission instruction includes, for example, one or more user attribute values.

The means for inputting various instructions and information can be anything, such as a touch panel, keyboard, mouse, or menu screen.

The device processing unit 33 performs various types of processing. For example, the various types of processing are to convert the instructions, information, etc. accepted by the device accepting unit 32 into a data structure for instructions, information, etc. to be transmitted. For example, the various types of processing are to convert the information received by the device receiving unit 35 into a data structure for output.

The terminal transmission unit 34 transmits various instructions, information, etc. to the water intake estimation device 2. The terminal transmission unit 34 transmits instructions, information, etc. configured by the terminal processing unit 33 to the water intake estimation device 2.

The terminal receiving unit 35 receives various types of information, etc. For example, the terminal receiving unit 35 receives questionnaire information or intake information from the water intake estimation device 2.

The terminal output unit 36 outputs various information, etc. For example, the terminal output unit 36 outputs questionnaire information or intake amount information.

The learning storage unit 11, the response storage unit 111, the actual value storage unit 112, the storage unit 21, the questionnaire storage unit 211, the raw information storage unit 212, and the terminal storage unit 31 are preferably non-volatile recording media, but can also be realized using volatile recording media.

The process by which information is stored in the learning storage unit 11, etc. is not important. For example, information may be stored in the learning storage unit 11, etc. via a recording medium, information transmitted via a communication line, etc. may be stored in the learning storage unit 11, etc., or information inputted via an input device may be stored in the learning storage unit 11, etc.

The learning acceptance unit 12 and the terminal acceptance unit 32 may be realized by a device driver for an input means such as a touch panel or a keyboard, or control software for a menu screen. The learning acceptance unit 12 may also be realized by a wireless or wired communication means.

The learning processing unit 13, processing unit 23, questionnaire acquisition unit 231, intake acquisition unit 232, and device processing unit 33 can usually be realized by a processor, memory, etc. The processing procedures of the processing unit 23, etc. are usually realized by software, and the software is recorded in a recording medium such as a ROM. However, they may also be realized by hardware (dedicated circuitry). The processor may be, for example, a CPU, MPU, GPU, etc., and the type is not important.

The learning output unit 14 and the terminal output unit 36 may or may not include output devices such as a display or a speaker. The learning output unit 14 and the like may be realized by driver software for an output device, or driver software for an output device and an output device, etc. The learning output unit 14 may also be realized by wireless or wired communication means.

The reception unit 22, the response reception unit 221, and the terminal reception unit 35 are typically realized by wireless or wired communication means, but may also be realized by means of receiving broadcasts.

The output unit 24, questionnaire output unit 241, intake output unit 242, and terminal transmission unit 34 are typically implemented using wireless or wired communication means, but may also be implemented using broadcasting means.

The terminal reception unit 32 can be realized by a device driver for an input means such as a touch panel or keyboard, or control software for a menu screen, etc.

The terminal output unit 36 may or may not include an output device such as a display or speaker. The terminal output unit 36 may be realized by driver software for an output device, or by a combination of driver software for an output device and an output device, etc.

Next, an example of the operation of the water intake estimation system A will be described. First, an example of the operation of the learning device 1 will be described using the flowchart in FIG. 4.

(Step S401) The learning processing unit 13 assigns 1 to counter i.

(Step S402) The learning processing unit 13 judges whether or not to acquire the i-th raw information. If the i-th raw information is to be acquired, the process proceeds to step S403, and if the i-th raw information is not to be acquired, the process ends.

The learning processing unit 13 determines whether to acquire the i-th original information, for example, depending on whether the i-th identification information exists in the learning storage unit 11. Note that if the identification information in the learning storage unit 11 is, for example, (gender = male & type of question set = beverage origin) (gender = male & type of question set = alcohol origin) (gender = male & type of question set = food origin) (gender = male & type of question set = all origins) (gender = female & type of question set = beverage origin) (gender = female & type of question set = alcohol origin) (gender = female & type of question set = food origin) (gender = female & type of question set = all origins), the counter i can be 1 to 8.

(Step S403) The learning processing unit 13 assigns 1 to counter j.

(Step S404) The learning processing unit 13 judges whether or not the jth set of answer information exists. If the jth set of answer information exists, the process proceeds to step S405, and if the jth set of answer information does not exist, the process proceeds to step S410.

The jth set of answer information is associated with an identifier, for example. The identifier is a user identifier, a day identifier, or a user identifier and a day identifier.

(Step S405) The learning processing unit 13 acquires the jth set of answer information. Note that the answer information acquired here may not be the entire jth set of answer information. In other words, if a question corresponds to any of two or more types, the learning processing unit 13 acquires only the answer information corresponding to the question of the type corresponding to the ith original information.

(Step S406) The learning processing unit 13 constructs a vector using the set of answer information acquired in step S405.

(Step S407) The learning processing unit 13 acquires the actual measurement values that are paired with the set of answer information acquired in step S405 from the actual measurement value storage unit 112.

(Step S408) The learning processing unit 13 creates a record having the vector obtained in step S406 and the actual measurement value obtained in step S407, and temporarily stores the record in a buffer (not shown).

(Step S409) The learning processing unit 13 increments the counter j by 1. Return to step S404.

(Step S410) The learning processing unit 13 obtains two or more records from a buffer (not shown) and obtains raw information using the two or more records. The learning processing unit 13 obtains a learning device, for example, by machine learning prediction processing.

(Step S411) The learning processing unit 13 stores the raw information acquired in step S410. When acquiring two or more pieces of raw information, the learning processing unit 13 stores the raw information in association with the identification information. The raw information may be stored in the learning storage unit 11, for example, but is not limited thereto.

(Step S412) The learning processing unit 13 increments the counter i by 1. Return to step S402.

Next, an example of the operation of the water intake estimation device 2 will be described using the flowchart in Figure 5.

(Step S501) The reception unit 22 determines whether or not a questionnaire output instruction has been received. If a questionnaire output instruction has been received, the process proceeds to step S502. If a questionnaire output instruction has not been received, the process proceeds to step S504. Here, the reception unit 22 determines whether or not a questionnaire output instruction has been received from the user terminal 3.

(Step S502) The questionnaire acquisition unit 231 acquires questionnaire information corresponding to the questionnaire output instruction received in step S501 from the questionnaire storage unit 211. The questionnaire acquisition unit 231 acquires, for example, one or more user attribute values corresponding to the user identifier included in the questionnaire output instruction from the storage unit 21, and acquires questionnaire information corresponding to the one or more user attribute values from the questionnaire storage unit 211.

(Step S503) The questionnaire output unit 241 outputs the questionnaire information acquired in step S502. Return to step S501. Note that the questionnaire output unit 241 transmits the questionnaire information to the user terminal 3, for example.

(Step S504) The answer receiving unit 221 judges whether or not user answer information has been received. If user answer information has been received, the process proceeds to step S505, and if user answer information has not been received, the process returns to step S501. Note that here, the receiving unit 22 judges, for example, whether or not user answer information has been received from the user terminal 3.

(Step S505) The intake acquisition unit 232 assigns 1 to counter i.

(Step S506) The intake acquisition unit 232 determines whether the i-th question type exists. If the i-th question type exists, the process proceeds to step S507, and if the i-th question type exists, the process proceeds to step S511.

(Step S507) The intake acquisition unit 232 acquires two or more pieces of answer information corresponding to the type of the i-th question from the user answer information. The intake acquisition unit 232 uses the two or more pieces of acquired answer information to construct a vector.

(Step S508) The intake acquisition unit 232 acquires raw information corresponding to the i-th question type from the raw information storage unit 212.

(Step S509) The intake amount acquisition unit 232 acquires the water intake amount using the vector constructed in step S507 and the raw information acquired in step S508. The intake amount acquisition unit 232, for example, performs a machine learning prediction process using the vector constructed in step S507 and the raw information acquired in step S508 to acquire the water intake amount.

(Step S510) The intake acquisition unit 232 increments the counter i by 1. Return to step S506.

(Step S511) The intake acquisition unit 232 uses one or more water intake amounts acquired in step S509 to construct the intake information to be output.

(Step S512) The intake output unit 242 outputs the intake information acquired in step S511. Return to step S501.

Here, the intake output unit 242 transmits, for example, the intake information acquired in step S511 to the user terminal 3.

In the flowchart in Figure 5, processing ends when the power is turned off or an interrupt occurs to end processing.

Next, an example of the operation of the user terminal 3 will be explained using the flowchart in FIG. 6.

(Step S601) The terminal reception unit 32 determines whether or not a questionnaire output instruction has been received. If a questionnaire output instruction has been received, the process proceeds to step S602; if a questionnaire output instruction has not been received, the process returns to step S601.

(Step S602) The device processing unit 33 configures a questionnaire output instruction to be output. The device transmission unit 34 transmits the configured questionnaire output instruction to the water intake estimation device 2.

The device processing unit 33, for example, reads out the user identifier from the device storage unit 31 and generates a questionnaire output instruction having that user identifier.

(Step S603) The terminal receiving unit 35 determines whether or not questionnaire information has been received. If questionnaire information has been received, the process proceeds to step S604; if not, the process returns to step S603.

(Step S604) The device processing unit 33 constructs questionnaire information to be output from the questionnaire information received in step S603. The terminal output unit 36 outputs the questionnaire information.

(Step S605) The terminal reception unit 32 determines whether or not answer information has been received from the user. If answer information has been received, the process proceeds to step S606; if answer information has not been received, the process proceeds to step S607.

(Step S606) The device processing unit 33 associates the answer information received in step S605 with the question identifier and temporarily stores it in a buffer (not shown). Return to step S605.

(Step S607) The terminal reception unit 32 determines whether or not a transmission instruction has been received from the user. If a transmission instruction has been received, the process proceeds to step S608; if a transmission instruction has not been received, the process returns to step S605.

(Step S608) The device processing unit 33 reads two or more pieces of answer information from the buffer and composes user answer information. Note that the user answer information includes, for example, a user identifier.

(Step S609) The terminal transmission unit 34 transmits the user response information constructed in step S608 to the water intake estimation device 2.

(Step S610) The terminal receiving unit 35 determines whether or not intake information has been received from the water intake estimation device 2. If intake information has been received, the process proceeds to step S611, and if intake information has not been received, the process returns to step S610.

(Step S611) The device processing unit 33 uses the intake amount information received in step S610 to construct the intake amount information to be output. The terminal output unit 36 outputs the intake amount information. Return to step S601.

In the flowchart in Figure 6, processing ends when the power is turned off or an interrupt occurs to end processing.

The specific operation of the water intake estimation system A in this embodiment will be described below. A conceptual diagram of the water intake estimation system A is shown in Figure 1.

Now, it is assumed that the learning storage unit 11 of the learning device 1 stores two or more pieces of questionnaire information including the questionnaire information shown in Figures 7 and 8. The questionnaire information in Figure 7 corresponds to information "male" that specifies a condition related to a user attribute value. The questionnaire information in Figure 8 corresponds to information "female" that specifies a condition related to a user attribute value. It is also assumed that each question in the questionnaire information corresponds to a type identifier. Here, it is assumed that the type identifier is one of "beverage-derived," "alcohol-derived," "food-derived," and "all-derived."

In this situation, assume that many users have inputted answer information to the questionnaire information, and as a result, a large number of sets of answer information are stored in the learning storage unit 11 in association with user identifiers. An example of such a large number of sets of answer information is the user answer information management table shown in FIG. 9. The user answer information management table is a table having "user identifier", "user attribute value", "question identifier", and "type identifier". In this case, the "question identifier" ranges from "1" to "40". Also, there are 10 questions for each type identifier. Also, the first record in FIG. 9 indicates that the user with user identifier "U001" is a "male" and has input answer information "3" ... "5", "3" ... "5", "1" ... "4", "3" ... "3".

Also, assume that the actual measured values of many users are stored in the learning storage unit 11 in association with user identifiers. Note that the actual measured values here are the amount of water intake per day.

As described above, the learning processing unit 13 may obtain actual measurement values for each type identifier, for example, from the user's responses to a multiple-choice questionnaire. The learning processing unit 13 may also obtain actual measurement values for each type identifier from the user's responses to a questionnaire based on a descriptive food record method. Furthermore, the learning processing unit 13 may obtain actual measurement values that are input by the user and that are associated with the user identifier. In other words, the method of obtaining the actual measurement management table is not important.

As a result of the above processing, the actual measurement storage unit 112 stores the actual measurement management table shown in Fig. 10. The actual measurement management table is a table showing the correspondence between user identifiers, type identifiers, and water intake amounts. The water intake amounts are, for example, _a001 , _a002 , ..., _b001 , ..., _c001 , ..., _d001 , _d002 , ..., and these values are, for example, numerical values in milliliters.

Then, the learning processing unit 13 of the learning device 1 performs a machine learning learning process for each user identifier (male, female) and each type identifier (beverage-derived, alcohol-derived, food-derived, all-derived) using the user response information management table shown in FIG. 9 and the actual measured values in the actual measured value management table shown in FIG. 10, by the process described with reference to FIG. 5, and obtains a learning device. In other words, the learning processing unit 13 performs a machine learning learning process for each user identifier and each type identifier, and obtains eight learning devices. The learning processing unit 13 then associates each of the eight learning devices with identification information having a user identifier and a type identifier, and stores them in the raw information storage unit 212 of the water intake estimation device 2.

Through the above process, the raw information management table shown in FIG. 11 is stored in the raw information storage unit 212 of the water intake estimation device 2. The raw information management table has eight records, each having an "ID", "user identifier", "type identifier", and "raw information". Here, "ID" is information that identifies the record. "Raw information" is an identifier (e.g., file name) of the file of the machine learning (e.g., random forest) learning device. Note that the actual file is assumed to exist in the raw information storage unit 212. Furthermore, the "user identifier" and "type identifier" may be collectively referred to as identification information.

Furthermore, it is assumed that the questionnaire storage unit 211 stores two or more pieces of questionnaire information including the questionnaire information in Figures 7 and 8.

Furthermore, the storage unit 21 stores a user information management table (not shown) that manages two or more pieces of user information each having a user identifier and one or more user attribute values (including gender).

In this situation, it is assumed that the user inputs a questionnaire output instruction to the user terminal 3. Then, by the process described in FIG. 6, the user terminal 3 accepts the questionnaire output instruction and transmits a questionnaire output instruction including the user identifier to the water intake estimation device 2.

Next, the reception unit 22 of the water intake estimation device 2 receives the questionnaire output instruction. The questionnaire acquisition unit 231 then acquires a user attribute value (here, "male") corresponding to the user identifier included in the questionnaire output instruction from the user information management table in the storage unit 21, and acquires questionnaire information corresponding to the user attribute value from the questionnaire storage unit 211. Next, the questionnaire output unit 241 transmits the questionnaire information to the user terminal 3.

Next, the user terminal 3 receives and outputs the questionnaire information. An example of such output is shown in FIG. 12.

Let us assume that the user inputs answer information for each question in the questionnaire information in FIG. 12 and selects the "Send" button 1201. Then, the user terminal 3 transmits user answer information, which includes a user identifier and two or more pieces of answer information, to the water intake estimation device 2.

Next, the response receiving unit 221 of the water intake estimation device 2 receives the user response information from the user terminal 3.

Next, the intake amount acquisition unit 232 acquires the learning device paired with the user attribute value "male" from FIG. 11 for each type identifier. Then, the intake amount acquisition unit 232 acquires two or more pieces of answer information corresponding to each type identifier from the user answer information for each type identifier, and configures a vector using the two or more pieces of answer information. Next, the intake amount acquisition unit 232 provides the vector and the learning device corresponding to the type identifier for each type identifier to a machine learning prediction module, executes the prediction module, and acquires intake amount information for each type identifier. Such intake amount information is intake amount information for each of beverages, alcoholic beverages, meals, and total intakes. Next, the intake amount acquisition unit 232 adds up the four pieces of intake amount information to acquire intake amount information "1215 milliliters" indicating the user's daily water intake.

Next, the output unit 24 transmits the intake amount information to the user terminal 3. The output unit 24 may transmit information containing the intake amount information to the user terminal 3. Such information is, for example, a character string, and is a character string in which the acquired intake amount information is substituted for the variable <intake amount information> of a template (here, "Your average daily water intake is <intake amount information>").

Next, the user terminal 3 receives and outputs the intake amount information. An example of such output is shown in FIG. 13.

As described above, according to this embodiment, water intake can be estimated based on responses to a questionnaire that includes questions other than those directly asking about the amount of water ingested.

In addition, in this embodiment, the appropriate amount of fluid intake can be estimated based on answers to a questionnaire that varies depending on the user's attribute values.

In addition, this embodiment can estimate the appropriate amount of water intake for each source.

Furthermore, in this embodiment, the appropriate amount of fluid intake can be estimated using machine learning algorithms such as random forest.

The processing in this embodiment may be realized by software. This software may be distributed by software download or the like. This software may also be recorded on a recording medium such as a CD-ROM and distributed. This also applies to the other embodiments in this specification. The software that realizes the water intake estimation device 2 in this embodiment is the following program. In other words, this program:
The program causes a computer that can access a raw information storage unit in which raw information that is the basis for estimating fluid intake from answer information to two or more questions, including questions other than those that directly ask about the amount of fluid ingested, to function as an answer accepting unit that accepts user answer information having answer information to the two or more questions, an intake amount acquiring unit that acquires intake information that specifies the amount of fluid intake using two or more answer pieces of answer information contained in the user answer information accepted by the answer accepting unit and the raw information stored in the raw information storage unit, and an intake amount output unit that outputs the intake amount information.

Figure 15 also shows the appearance of a computer that executes the programs described in this specification to realize the learning device 1 and water intake estimation device 2 of the various embodiments described above. The above-mentioned embodiments can be realized by computer hardware and a computer program executed thereon. Figure 15 is an overview of this computer system 300, and Figure 16 is a block diagram of system 300.

In FIG. 15, computer system 300 includes computer 301, which includes a CD-ROM drive, keyboard 302, mouse 303, and monitor 304.

In FIG. 16, in addition to a CD-ROM drive 3012, computer 301 includes an MPU 3013, a bus 3014 connected to the CD-ROM drive 3012 etc., a ROM 3015 for storing programs such as a boot-up program, a RAM 3016 connected to the MPU 3013 for temporarily storing instructions for application programs and providing temporary storage space, and a hard disk 3017 for storing application programs, system programs, and data. Although not shown here, computer 301 may further include a network card that provides connection to a LAN.

A program that causes the computer system 300 to execute the functions of the water intake estimation device 2 of the above-mentioned embodiment, etc., may be stored on the CD-ROM 3101, inserted into the CD-ROM drive 3012, and then transferred to the hard disk 3017. Alternatively, the program may be sent to the computer 301 via a network (not shown) and stored on the hard disk 3017. The program is loaded into the RAM 3016 when executed. The program may be loaded directly from the CD-ROM 3101 or the network.

The program does not necessarily have to include an operating system (OS) or third-party programs that cause the computer 301 to execute the functions of the water intake estimation device 2 of the above-described embodiment. The program only needs to include instructions that call appropriate functions (modules) in a controlled manner to obtain the desired results. How the computer system 300 operates is well known, and a detailed description will be omitted.

In the above program, the steps of transmitting information and receiving information do not include processing performed by hardware, such as processing performed by a modem or interface card in the transmission step (processing that is performed only by hardware).

The computer that executes the above program may be a single computer or multiple computers. In other words, centralized processing or distributed processing may be performed. In other words, the water intake estimation device 2, etc. may be a standalone device or may be composed of two or more devices.

It goes without saying that in each of the above embodiments, two or more communication means present in one device may be physically realized by a single medium.

In addition, in each of the above embodiments, each process may be realized by centralized processing in a single device, or may be realized by distributed processing in multiple devices.

The present invention is not limited to the above-described embodiment, and various modifications are possible, and it goes without saying that these are also included within the scope of the present invention.

As described above, the fluid intake estimation device of the present invention has the effect of being able to obtain fluid intake based on responses to questionnaires that include questions other than those directly asking about the amount of fluid intake, and is useful as a server or the like that estimates fluid intake.

REFERENCE SIGNS LIST 1 Learning device 2 Water intake estimation device 3 User terminal 11 Learning storage unit 12 Learning reception unit 13 Learning processing unit 14 Learning output unit 21 Storage unit 22 Reception unit 23 Processing unit 24 Output unit 31 Terminal storage unit 32 Terminal reception unit 33 Terminal processing unit 34 Terminal transmission unit 35 Terminal reception unit 36 Terminal output unit 111 Answer storage unit 112 Actual measurement value storage unit 211 Questionnaire storage unit 212 Raw information storage unit 221 Answer reception unit 231 Questionnaire acquisition unit 232 Intake acquisition unit 241 Questionnaire output unit 242 Intake output unit

Claims (10)

a questionnaire storage unit in which two or more pieces of questionnaire information each having question information for two or more questions are stored in association with conditions related to user attribute values;
a raw information storage unit that stores two or more pieces of raw information corresponding to conditions corresponding to user attribute values, the raw information being two or more pieces of raw information that are used to estimate fluid intake from answer information to each of the above questions, the answer information including two or more types of questions among beverage-related questions that are questions about beverage habituation, alcohol-related questions that are questions about alcohol habituation, diet-related questions that are questions about dietary habituation, and all-origin questions that are questions about all origins;
a questionnaire acquisition unit that acquires questionnaire information corresponding to a condition corresponding to a user attribute value of a user from the questionnaire storage unit;
a questionnaire output unit that transmits the questionnaire information acquired by the questionnaire acquisition unit to a user terminal of the user;
an answer receiving unit that receives user answer information corresponding to a user attribute value, the user answer information being a user answer to the questionnaire information transmitted by the questionnaire output unit ;
an intake acquisition unit that acquires intake information for identifying a water intake amount by using two or more pieces of answer information included in the user answer information accepted by the answer acceptance unit and raw information corresponding to the user attribute value corresponding to the user answer information;
and an intake output unit that outputs the intake information ,
The raw information is
A learning device constructed by performing a learning process using a machine learning algorithm using two or more pieces of teacher data having answer information to two or more questions and water intake information;
or a correspondence table having two or more pieces of correspondence information that associate a vector having answer information for each of two or more questions as elements with an actual measured value that is a daily water intake;
or an arithmetic formula that outputs an actual measurement value using answer information for each of two or more questions as a parameter,
The intake amount acquisition unit is
performing a prediction process using a machine learning algorithm by using two or more pieces of answer information included in the user answer information accepted by the answer accepting unit and the learning device, thereby obtaining the intake amount information;
Alternatively, a vector is constructed having two or more pieces of answer information contained in the user answer information accepted by the answer accepting unit as elements, and after constructing the vector, a vector that is most similar to the vector is searched for in the correspondence table, and an actual measurement value paired with the most similar vector is obtained as the intake amount information, or two or more vectors that satisfy an approximation condition for the vector are determined, and an actual measurement value paired with each of the two or more vectors is obtained, and a representative value of the two or more actual measurement values is obtained as the intake amount information.
Alternatively, a water intake estimation device that constructs a vector having two or more pieces of answer information contained in the user answer information accepted by the answer accepting unit as elements, applies the vector to the arithmetic formula, executes the arithmetic formula, and obtains intake information . a raw information storage unit that stores raw information that is the basis for estimating a fluid intake amount from answer information to at least two types of questions among beverage-related questions that are questions about beverage habituation, alcohol-related questions that are questions about alcohol habituation, diet-related questions that are questions about dietary habituation, and all-related questions that are questions about all origins;
an answer receiving unit that receives user answer information having answer information to each of two or more questions including the two or more types of questions;
an intake acquisition unit that acquires intake information for identifying a water intake amount by using two or more pieces of answer information included in the user answer information accepted by the answer acceptance unit and the raw information;
and an intake output unit that outputs the intake information,
The raw information is a learning device constructed by performing a learning process using a machine learning algorithm using two or more pieces of teacher data having answer information to each of the two or more questions and water intake amount information,
The intake amount acquisition unit is
The water intake estimation device performs a prediction process using a machine learning algorithm using two or more pieces of answer information contained in the user answer information accepted by the answer accepting unit and the learning device, and obtains the intake information. The water intake estimation device of claim 1, wherein the two or more questions include four or more types of questions, including beverage-related questions regarding beverage habituation, alcohol-related questions regarding alcoholic beverage habituation, diet-related questions regarding dietary habituation, and all -related questions regarding all origins. The water intake estimation device of claim 2, wherein the two or more questions include four or more types of questions, including beverage-related questions regarding beverage habituation, alcohol-related questions regarding alcoholic beverage habituation, diet-related questions regarding dietary habituation, and all-related questions regarding all origins. The two or more questions include two or more types of question sets each including one or more questions,
The raw information storage unit includes:
Two or more pieces of source information corresponding to the type of question are stored,
The intake amount acquisition unit is
5. The water intake estimation device according to claim 1, wherein intake information is obtained for each of the two or more types of questions using answer information corresponding to each of the two or more types and raw information corresponding to each of the types, and the intake information is obtained using the two or more pieces of intake information. The water intake estimation device according to claim 1 or 2 , wherein the machine learning algorithm is a random forest. a questionnaire storage unit storing two or more pieces of questionnaire information each having question information for each of two or more questions in association with a condition related to a user attribute value; a raw information storage unit storing two or more pieces of raw information corresponding to conditions corresponding to user attribute values, the raw information being used to estimate a fluid intake from answer information to two or more questions including two or more types of questions selected from beverage-derived questions related to beverage habituation, alcohol-derived questions related to alcohol habituation, diet-derived questions related to dietary habituation, and all-origin questions related to all origins; and the raw information storage unit storing two or more pieces of raw information corresponding to conditions corresponding to user attribute values; a questionnaire acquisition unit, a questionnaire output unit, an answer acceptance unit, an intake acquisition unit, and an intake output unit,
a questionnaire acquisition step in which the questionnaire acquisition unit acquires questionnaire information corresponding to a condition corresponding to a user attribute value of a user from the questionnaire storage unit;
a questionnaire output step in which the questionnaire output unit transmits the questionnaire information acquired by the questionnaire acquisition unit to a user terminal;
an answer receiving step in which the answer receiving unit receives user answer information corresponding to a user attribute value, the user answer information being user answer information to the questionnaire information transmitted by the questionnaire output unit ;
an intake acquisition step in which the intake acquisition unit acquires intake information for identifying a water intake amount, using two or more pieces of answer information included in the user answer information accepted in the answer acceptance step and raw information corresponding to a user attribute value corresponding to the user answer information ;
The intake output unit includes an intake output step of outputting the intake information,
The raw information is
A learning device constructed by performing a learning process using a machine learning algorithm using two or more pieces of teacher data having answer information to two or more questions and water intake information;
or a correspondence table having two or more pieces of correspondence information that associate a vector having answer information for each of two or more questions as elements with an actual measured value that is a daily water intake;
or an arithmetic formula that outputs an actual measurement value using answer information for each of two or more questions as a parameter,
In the intake acquisition step,
performing a prediction process using a machine learning algorithm by using two or more pieces of answer information included in the user answer information accepted by the answer accepting unit and the learning device, thereby obtaining the intake amount information;
or forming a vector having two or more pieces of answer information included in the user answer information received by the answer receiving unit as elements;
After constructing the vector, a vector that is most similar to the vector is searched for in the correspondence table, and an actual measurement value paired with the most similar vector is obtained as the intake information, or two or more vectors that satisfy an approximation condition for the vector are determined, an actual measurement value paired with each of the two or more vectors is obtained, and a representative value of the two or more actual measurement values is obtained as the intake information.
Alternatively, a method for estimating water intake includes constructing a vector having two or more pieces of answer information contained in the user answer information accepted by the answer accepting unit as elements, applying the vector to the arithmetic formula, executing the arithmetic formula, and obtaining intake information . A water intake estimation method implemented by a raw information storage unit that stores raw information that is a basis for estimating water intake from answer information to two or more types of questions among beverage-related questions that are questions about beverage habituation, alcohol-related questions that are questions about alcohol habituation, dietary-related questions that are questions about dietary habituation, and all-origin questions that are questions about all origins, a response receiving unit, an intake acquisition unit, and an intake output unit,
an answer receiving step in which the answer receiving unit receives user answer information having answer information to each of two or more questions including the two or more types of questions;
an intake acquisition step in which the intake acquisition unit acquires intake information for identifying a water intake amount by using two or more pieces of answer information included in the user answer information accepted by the answer acceptance unit and the raw information;
The intake output unit includes an intake output step of outputting the intake information,
The raw information is a learning device constructed by performing a learning process using a machine learning algorithm using two or more pieces of teacher data having answer information to each of the two or more questions and water intake information,
In the intake acquisition step,
The water intake estimation device performs a prediction process using a machine learning algorithm using two or more pieces of answer information contained in the user answer information accepted by the answer accepting unit and the learning device, and obtains the intake information. a questionnaire storage unit in which two or more pieces of questionnaire information each having question information for two or more questions is stored in association with a condition related to a user attribute value, and a raw information storage unit in which two or more pieces of raw information corresponding to a condition corresponding to a user attribute value are stored, the raw information storage unit storing two or more pieces of raw information that are used as a basis for estimating a water intake amount from answer information to two or more questions including two or more types of questions selected from beverage origin questions that are questions about beverage habituation, alcohol origin questions that are questions about alcohol habituation, diet origin questions that are questions about diet habituation, and all origin questions that are questions about all origins;
a questionnaire acquisition unit that acquires questionnaire information corresponding to a condition corresponding to a user attribute value of a user from the questionnaire storage unit;
a questionnaire output unit that transmits the questionnaire information acquired by the questionnaire acquisition unit to a user terminal of the user;
an answer receiving unit that receives user answer information corresponding to a user attribute value, the user answer information being a user answer to the questionnaire information transmitted by the questionnaire output unit ;
an intake acquisition unit that acquires intake information for identifying a water intake amount by using two or more pieces of answer information included in the user answer information accepted by the answer acceptance unit and raw information corresponding to the user attribute value corresponding to the user answer information;
A program for causing an intake output unit to function as an intake output unit that outputs the intake information,
The raw information is
A learning device constructed by performing a learning process using a machine learning algorithm using two or more pieces of teacher data having answer information to two or more questions and water intake information;
or a correspondence table having two or more pieces of correspondence information that associate a vector having answer information for each of two or more questions as elements with an actual measured value that is a daily water intake;
or an arithmetic formula that outputs an actual measurement value using answer information for each of two or more questions as a parameter,
The intake amount acquisition unit is
performing a prediction process using a machine learning algorithm by using two or more pieces of answer information included in the user answer information accepted by the answer accepting unit and the learning device, thereby obtaining the intake amount information;
or forming a vector having two or more pieces of answer information included in the user answer information received by the answer receiving unit as elements;
After constructing the vector, a vector that is most similar to the vector is searched for in the correspondence table, and an actual measurement value paired with the most similar vector is obtained as the intake information, or two or more vectors that satisfy an approximation condition for the vector are determined, an actual measurement value paired with each of the two or more vectors is obtained, and a representative value of the two or more actual measurement values is obtained as the intake information.
Or a program for causing the computer to function as follows: constructing a vector having two or more pieces of answer information contained in the user answer information accepted by the answer accepting unit as elements, applying the vector to the arithmetic formula, executing the arithmetic formula, and obtaining intake amount information . a computer that can access a raw information storage unit that stores raw information that is a basis for estimating fluid intake from answer information to at least two types of questions among beverage origin questions that are questions about beverage habituation, alcohol origin questions that are questions about alcohol habituation, diet origin questions that are questions about diet habituation, and all origin questions that are questions about all origins;
an answer receiving unit that receives user answer information having answer information to each of two or more questions including the two or more types of questions;
an intake acquisition unit that acquires intake information for identifying a water intake amount by using two or more pieces of answer information included in the user answer information accepted by the answer acceptance unit and the raw information;
A program for causing an intake output unit to function as an intake output unit that outputs the intake information,
The raw information is a learning device constructed by performing a learning process using a machine learning algorithm using two or more pieces of teacher data having answer information to each of the two or more questions and water intake amount information,
The intake amount acquisition unit is
A program for causing the computer to function as performing prediction processing using a machine learning algorithm using two or more pieces of answer information contained in the user answer information accepted by the answer accepting unit and the learning device, and obtaining the intake amount information.

Images