WO2022124189A1 - 生理関連情報出力装置、学習装置、学習情報の生産方法、および記録媒体 - Google Patents
生理関連情報出力装置、学習装置、学習情報の生産方法、および記録媒体 Download PDFInfo
- Publication number
- WO2022124189A1 WO2022124189A1 PCT/JP2021/044233 JP2021044233W WO2022124189A1 WO 2022124189 A1 WO2022124189 A1 WO 2022124189A1 JP 2021044233 W JP2021044233 W JP 2021044233W WO 2022124189 A1 WO2022124189 A1 WO 2022124189A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- information
- learning
- sound
- unit
- physiology
- Prior art date
Links
- 230000005906 menstruation Effects 0.000 title claims abstract description 69
- 238000004519 manufacturing process Methods 0.000 title claims 3
- 230000003187 abdominal effect Effects 0.000 claims abstract description 112
- 230000035479 physiological effects, processes and functions Effects 0.000 claims description 177
- 238000012545 processing Methods 0.000 claims description 68
- 238000010801 machine learning Methods 0.000 claims description 33
- 210000001015 abdomen Anatomy 0.000 claims description 23
- 208000002193 Pain Diseases 0.000 claims description 16
- 238000004422 calculation algorithm Methods 0.000 claims description 14
- 230000002175 menstrual effect Effects 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 8
- 239000000203 mixture Substances 0.000 claims description 4
- 208000005171 Dysmenorrhea Diseases 0.000 claims description 3
- 238000000034 method Methods 0.000 description 57
- 230000003821 menstrual periods Effects 0.000 description 23
- 238000013500 data storage Methods 0.000 description 14
- 230000005540 biological transmission Effects 0.000 description 11
- 230000016087 ovulation Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 10
- 238000007637 random forest analysis Methods 0.000 description 7
- 238000013523 data management Methods 0.000 description 6
- 230000027758 ovulation cycle Effects 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 4
- 125000002066 L-histidyl group Chemical group [H]N1C([H])=NC(C([H])([H])[C@](C(=O)[*])([H])N([H])[H])=C1[H] 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000017531 blood circulation Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000000968 intestinal effect Effects 0.000 description 1
- 210000000936 intestine Anatomy 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 238000004579 scanning voltage microscopy Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 210000002784 stomach Anatomy 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B10/00—Other methods or instruments for diagnosis, e.g. instruments for taking a cell sample, for biopsy, for vaccination diagnosis; Sex determination; Ovulation-period determination; Throat striking implements
- A61B10/0012—Ovulation-period determination
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4824—Touch or pain perception evaluation
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7271—Specific aspects of physiological measurement analysis
- A61B5/7275—Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B7/00—Instruments for auscultation
- A61B7/02—Stethoscopes
- A61B7/04—Electric stethoscopes
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B10/00—Other methods or instruments for diagnosis, e.g. instruments for taking a cell sample, for biopsy, for vaccination diagnosis; Sex determination; Ovulation-period determination; Throat striking implements
- A61B10/0012—Ovulation-period determination
- A61B2010/0029—Ovulation-period determination based on time measurement
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2562/00—Details of sensors; Constructional details of sensor housings or probes; Accessories for sensors
- A61B2562/02—Details of sensors specially adapted for in-vivo measurements
- A61B2562/0204—Acoustic sensors
Definitions
- the present invention relates to a physiology-related information output device or the like that acquires and outputs physiology-related information related to physiology.
- Patent Document 1 there has been a technique for the purpose of suppressing a decrease in prediction accuracy and making it possible to predict a menstrual day even when the variation in the menstrual cycle is large (see Patent Document 1).
- the physiology-related information output device of the first invention stores learning information configured by using two or more teacher data having sound information acquired from a user's abdominal sound and physiology-related information.
- Learning information storage unit sound information acquisition unit that acquires sound information from the user's abdominal sound
- prediction unit that applies learning information to the sound information acquired by the sound information acquisition unit and acquires physiology-related information.
- physiologically related information can be obtained using the abdominal sound from the abdomen or around the abdomen.
- the physiology-related information output device of the second invention is a physiology-related information output device in which the physiology-related information is the physiology-day-related information regarding the relationship with the day related to physiology with respect to the first invention.
- the physiology-related information output device of the third invention is a physiology-related information output device in which the physiology-related information is pain information related to physiology pain with respect to the first invention.
- physiology-related information output device of the fourth invention for any one of the first to third inventions, two or more teacher data are acquired from the abdomen of each day during the user's menstrual cycle. It is a physiology-related information output device composed of teacher data having sound information acquired from abdominal sounds and physiology-related information.
- the physiology-related information output device of the fifth invention performs learning processing on two or more teacher data for any one of the first to fourth inventions by a machine learning algorithm, and is a learning device. It is further equipped with a learning unit that acquires learning information, and the prediction unit performs prediction processing by a machine learning algorithm using the sound information and learning information acquired by the sound information acquisition unit, and acquires physiology-related information. It is a physiological information output device.
- the physiology-related information output device of the sixth aspect of the present invention outputs physiology-related information, wherein the sound information is two or more feature quantities of the user's abdominal sound for any one of the first to fifth inventions. It is a device.
- the learning device of the seventh invention obtains teacher data from a sound information acquisition unit that acquires sound information from the user's abdominal sound, a learning reception unit that receives physiology-related information, and sound information and physiology-related information.
- a learning device that can predict physiologically related information using abdominal sounds can be configured by machine learning algorithms.
- physiology-related information can be predicted using the abdominal sound.
- Block diagram of the information system A Block diagram of the same physiology-related information output device 2 A flowchart illustrating an operation example of the learning device 1. A flowchart illustrating the first example of the learning information configuration process. A flowchart illustrating a second example of the learning information configuration process. A flowchart illustrating an operation example of the same physiology-related information output device 2. A flowchart illustrating an example of the prediction process. A flowchart illustrating an operation example of the terminal device 3. Diagram showing the teacher data management table Figure showing the same output example Figure showing the same output example Figure showing the same output example Overview of the computer system Block diagram of the computer system
- the sound information related to the abdominal sound of one user is applied to the learning information configured by using two or more teacher data having the sound information related to the abdominal sound of the user and the physiologically related information, and the physiological related information is applied.
- a physiological information output device that acquires and outputs information will be described.
- the abdominal sound is a sound emitted from the user's abdomen.
- the abdominal sound may be considered to include a sound emitted from the periphery of the user's abdomen.
- the abdominal sound may include, for example, an intestinal sound emitted from the intestine.
- the abdominal sound may include a sound emitted by blood flow in the abdomen (for example, abdominal aortic sound) and a sound emitted from an organ such as the stomach.
- the menstruation-related information is information related to menstruation, and the details will be described later.
- the learning information is, for example, a learning device configured by the learning device, a correspondence table described later, and the like.
- the learning device may be called a classifier, a model, or the like.
- a learning device that performs learning processing by a machine learning algorithm from two or more teacher data having sound information related to the abdominal sound of the user and physiology-related information to form a learning device will be described. ..
- an information system including a learning device, a physiology-related information output device, and one or more terminal devices will be described.
- FIG. 1 is a conceptual diagram of the information system A in the present embodiment.
- the information system A includes a learning device 1, a physiology-related information output device 2, and one or more terminal devices 3.
- the learning device 1 is a device that constitutes a learning device by performing learning processing from two or more teacher data having sound information and physiology-related information by a machine learning algorithm.
- the physiology-related information output device 2 is a device that acquires and outputs physiology-related information using abdominal sounds.
- the learning device 1 and the physiology-related information output device 2 are so-called computers, for example, servers.
- the learning device 1 and the physiology-related information output device 2 are, for example, a so-called cloud server, an ASP server, or the like, but the type thereof does not matter.
- the learning device 1 and the physiology-related information output device 2 may be stand-alone devices.
- the terminal device 3 is a terminal used by the user.
- the user is a user who desires to acquire physiological-related information.
- the terminal device 3 is a terminal for acquiring learning information.
- the terminal device 3 is, for example, a so-called personal computer, a tablet terminal, a smartphone, or the like, and the type thereof does not matter.
- FIG. 2 is a block diagram of the information system A in the present embodiment.
- FIG. 3 is a block diagram of the physiology-related information output device 2. It was
- the learning device 1 includes a teacher data storage unit 11, a sound collection unit 12, a sound information acquisition unit 13, a learning reception unit 14, a teacher data composition unit 15, a learning unit 16, and a storage unit 17.
- the physiology-related information output device 2 includes a storage unit 21, a reception unit 22, a processing unit 23, and an output unit 24.
- the storage unit 21 includes a learning information storage unit 211.
- the processing unit 23 includes a sound information acquisition unit 231 and a prediction unit 232.
- the terminal device 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.
- the teacher data has sound information and physiology-related information.
- Sound information refers to information obtained based on abdominal sounds.
- the sound information may be the recorded abdominal sound data itself, or may be data obtained by processing or editing the data.
- the sound information is, for example, a spectrum image showing the result of analyzing the voice data (which may be processed) obtained by recording the abdominal sound by Fourier transform or fast Fourier transform in a predetermined mode. ..
- the sound information may be, for example, voice data (which may be processed) itself, or may be data converted into another format.
- the sound information may be, for example, a set of feature quantities acquired by performing A / D conversion of the abdominal sound and performing cepstrum analysis on the data after the A / D conversion. Further, the sound information may be, for example, a set of acquired features obtained by A / D converting the abdominal sound and performing LPC analysis on the data after the A / D conversion.
- the sound information is two or more feature quantities of the sound acquired from the user's abdominal sound.
- the sound collecting unit 12 collects abdominal sounds from one user's abdomen or around the abdomen.
- the sound collecting unit 12 is, for example, a microphone.
- the sound information acquisition unit 13 acquires sound information. Sound information is information obtained from the abdominal sound.
- the sound information acquisition unit 13 acquires sound information used for prediction processing for acquiring physiologically related information, which will be described later, from the abdominal sound.
- the sound information acquisition unit 13 may acquire sound information from the abdominal sound received from the terminal device 3, or may acquire sound information received from the terminal device 3. Further, the sound information acquisition unit 13 may acquire sound information from the abdominal sound acquired by the sound collection unit 12.
- the sound information acquisition unit 13 acquires sound information by A / D converting the abdominal sound, for example.
- the sound information acquisition unit 13 performs cepstrum analysis on the abdominal sound, for example, and acquires sound information which is a vector of multidimensional features.
- the sound information acquisition unit 13 performs LPC analysis on the abdominal sound and acquires sound information which is a vector of multidimensional feature quantities.
- the learning reception unit 14 receives menstruation-related information.
- the learning reception unit 14 usually receives physiological-related information input by the user.
- the learning reception unit 14 usually receives physiological-related information in association with the user identifier.
- the user identifier is information that identifies the user.
- the user identifier is, for example, an ID, an e-mail address, a telephone number, and a name.
- the learning reception unit 14 may receive abdominal sounds and physiology-related information. In such a case, the learning device 1 does not need the sound collecting unit 12.
- the learning reception unit 14 may receive teacher data having sound information and physiology-related information. In such a case, the learning device 1 does not need the sound collecting unit 12 and the sound information acquisition unit 13.
- the teacher data received by the learning reception unit 14 the abdominal sound, the physiology-related information, and the like are associated with the user identifier.
- Physiology-related information is information related to menstruation.
- the menstrual-related information is, for example, menstrual-day-related information or pain information.
- the menstrual day-related information is information related to the relationship with the day related to menstruation (for example, the start date of menstruation, the ovulation date, and the end date of menstruation).
- the menstrual day-related information includes, for example, information indicating whether or not the menstrual period start date is near, information indicating whether or not the period corresponds to the menstrual period, day number information indicating the number of days until the menstrual period start date, and the number of days until the ovulation date. It is the number of days information and the menstrual period information indicating the length of the menstrual period.
- the pain information is information about the next menstrual pain.
- the pain information is, for example, information indicating whether the pain is weak or strong, a pain level (for example, a value of any one of 5 steps from 1 to 5 and a value of any one of 10 steps of 1 to 10). Etc.).
- reception is usually reception from the terminal device 3, but reception from a microphone, reception of information input from an input device such as a keyboard, a mouse, or a touch panel, an optical disk, a magnetic disk, or a semiconductor memory. It may be a concept including acceptance of information read from a recording medium such as.
- Any means of inputting physiological information may be used, such as a touch panel, keyboard, mouse, or menu screen.
- the teacher data composition unit 15 configures teacher data from sound information and physiology-related information.
- the teacher data configuration unit 15 configures teacher data, which is a vector having sound information and physiology-related information, for example.
- the teacher data configuration unit 15 configures teacher data, which is a vector having one or more feature quantities, which are sound information, and physiology-related information as elements, for example. It is preferable that the teacher data corresponds to the user identifier.
- the teacher data configuration unit 15 may acquire other physiology-related information by using one or more received physiology-related information. That is, the received physiology-related information and the physiology-related information accumulated in association with the sound information do not have to be the same information.
- the teacher data configuration unit 15 acquires the menstruation-related information "menstruation period" by using, for example, the menstruation-related information indicating the "menstruation start date” and the menstruation-related information indicating the "menstruation end date”. That is, the teacher data configuration unit 15 acquires the day information indicating the day when the menstruation-related information indicating the "menstruation start date” is received. In addition, the teacher data configuration unit 15 acquires the day information indicating the day when the menstruation-related information indicating the "menstruation end date" is received. Then, the teacher data configuration unit 15 calculates the difference between the two day information and acquires the menstrual-related information "physiological period". The teacher data configuration unit 15 may acquire day information from a clock (not shown), or may acquire day information received from the terminal device 3. It doesn't matter how you get the day information.
- the teacher data configuration unit 15 uses, for example, physiology-related information indicating "during a non-physiological period” and physiology-related information indicating "menstruation start date", and physiology-related information "days information indicating the number of days until the menstruation start date”. To get. That is, the teacher data configuration unit 15 acquires the day information indicating the day when the menstrual-related information indicating "during the non-menstrual period" is received. In addition, the teacher data configuration unit 15 acquires the day information indicating the date when the menstruation-related information indicating the "menstruation start date” is received. Then, the teacher data configuration unit 15 calculates the difference between the two day information and acquires the menstruation-related information "days information indicating the number of days until the start date of menstruation”.
- the teacher data configuration unit 15 uses, for example, menstruation-related information indicating "menstruation start date” and menstruation-related information indicating “during a non-menstrual period”, and menstruation-related information "days information indicating the number of days until the ovulation day”. To get. That is, the teacher data configuration unit 15 acquires the day information indicating the day when the menstruation-related information indicating the "menstruation start date" is received. Further, the teacher data configuration unit 15 acquires information on the general number of days from the start date of menstruation to the day of ovulation from the storage unit 21.
- the teacher data configuration unit 15 calculates the day information indicating the ovulation date by using the day information corresponding to the menstrual period start date and the information on the number of days until the ovulation date.
- the teacher data configuration unit 15 acquires, for example, the day information of the day when the physiology-related information is received.
- the teacher data component 15 calculates the difference between the day information indicating the ovulation date and the day information on the day when the physiology-related information is received, and the physiology-related information “the number of days until the ovulation day” which is the number of days of the difference. Acquire "indicated number of days information".
- the teacher data configuration unit 15 stores the configured teacher data in the teacher data storage unit 11. It is preferable that the teacher data configuration unit 15 stores the configured teacher data in association with the user identifier. Further, it is preferable that the teacher data configuration unit 15 stores the configured teacher data in association with the day information.
- the learning unit 16 acquires learning information using one or more teacher data.
- the learning unit 16 acquires learning information for each user identifier, for example, using one or two or more teacher data paired with the user identifier.
- the learning unit 16 acquires learning information using, for example, one or two or more teacher data for each type of menstruation-related information (for example, the number of days until the start of menstruation, the level of pain).
- the learning unit 16 acquires learning information using, for example, one or two or more teacher data for each type of physiology-related information and user identifier.
- the learning unit 16 performs learning processing on two or more teacher data by a machine learning algorithm, and acquires learning information which is a learning device.
- the learning unit 16 performs machine learning learning processing on the teacher data configured by the teacher data configuration unit 15, and constitutes learning information which is a learning device.
- Machine learning algorithms may include deep learning, decision trees, random forests, SVMs, SVRs, etc., but they do not matter. Further, for machine learning, various machine learning functions such as TensorFlow library, fastText, tinySVM, R language random forest module, and various existing libraries can be used.
- the module may be referred to as a program, software, function, method or the like.
- the two or more teacher data are composed of teacher data having sound information acquired from the abdominal sound of each day during the menstrual cycle of one user and menstrual-related information.
- the learning unit 16 constitutes, for example, a correspondence table.
- the correspondence table has two or more correspondence information.
- Correspondence information may be said to be teacher data.
- Correspondence information is information indicating the correspondence between sound information and physiology-related information.
- the correspondence information is, for example, information indicating the correspondence between the sound information and one or more types of physiology-related information.
- the correspondence information is, for example, information indicating the correspondence between the sound information and one or more physiology-related information and the other one or more physiology-related information.
- the correspondence table may exist for each user identifier.
- Correspondence tables may exist for each type of physiology-related information.
- Correspondence tables may exist for each user identifier and for each type of physiology-related information.
- the storage unit 17 stores the learning information acquired by the learning unit 16.
- the storage unit 17 stores, for example, the learning device acquired by the learning unit 16.
- the learning information of the storage unit 17 may be stored in a local recording medium or another device such as the physiology-related information output device 2.
- the storage unit 17 stores the learning information acquired by the learning unit 16 in association with each user identifier for each user identifier, for example.
- the storage unit 17 stores the learning information acquired by the learning unit 16 in association with the identifier of each type of physiology-related information for each type of physiology-related information.
- the storage unit 17 stores the learning information acquired by the learning unit 16 in association with each user identifier and type identifier for each user identifier and each type of physiology-related information, for example.
- the type identifiers are, for example, "whether or not the start date of menstruation is near”, “whether or not it corresponds to the menstrual period", “the number of days until the start date of menstruation”, “the number of days until the day of ovulation”, and "physiology”. The length of the period. "
- the various types of information are stored in the storage unit 21 that constitutes the physiology-related information output device 2.
- the various information is, for example, learning information.
- the learning information storage unit 211 stores one or more learning information.
- the learning information is, for example, the above-mentioned learning device or a correspondence table. It is preferable that the learning information is the information acquired by the learning device 1. It is preferable that the learning information of the learning information storage unit 211 corresponds to the user identifier. That is, it is preferable that different learning information is used for each user. However, learning information common to two or more users may be used.
- the learning information corresponds to, for example, a user identifier and an identifier of a type of physiology-related information.
- the reception unit 22 receives, for example, the abdominal sound of one user.
- the reception unit 22 receives, for example, sound information acquired from the abdominal sound of one user.
- the reception unit 22 receives, for example, abdominal sound or sound information in association with a user identifier.
- the reception unit 22 receives, for example, an output instruction.
- the output instruction is an instruction to output physiologically related information.
- the output instruction has, for example, abdominal sound data.
- the output instruction has, for example, sound information. It is preferable that the output instruction includes a user identifier.
- the reception unit 22 receives, for example, abdominal sound or sound information or an output instruction from the terminal device 3.
- the reception of information in the reception unit 22 is usually reception from the terminal device 3, but reception from a microphone, reception of information input from an input device such as a keyboard, mouse, or touch panel, optical disk or magnetic disk.
- the concept may include acceptance of information read from a recording medium such as a semiconductor memory.
- the processing unit 23 performs various processes.
- the various processes are, for example, processes performed by the sound information acquisition unit 231 and the prediction unit 232.
- the sound information acquisition unit 231 acquires sound information.
- the sound information acquisition unit 231 may acquire sound information from the abdominal sound received by the reception unit 22, and the sound information acquisition unit 231 may acquire the sound information received by the reception unit 22.
- the sound information acquisition unit 231 performs the same function as the sound information acquisition unit 13.
- the sound information acquisition unit 231 may acquire the sound information received by the reception unit 22.
- the prediction unit 232 applies learning information to the sound information acquired by the sound information acquisition unit 231 and acquires physiology-related information.
- the prediction unit 232 acquires physiology-related information using the sound information acquired by the sound information acquisition unit 231 and the learning information of the learning information storage unit 211.
- the prediction unit 232 gives the sound information acquired by the sound information acquisition unit 231 and the learning information of the learning information storage unit 211 to the machine learning prediction module, executes the module, and acquires physiology-related information.
- the machine learning algorithm may include deep learning, decision tree, random forest, SVM, SVR, etc., but it does not matter whether the learning process or the prediction process is the same.
- the prediction unit 232 acquires the learning information corresponding to the user identifier corresponding to the sound information acquired by the sound information acquisition unit 231 from the learning information storage unit 211, and uses the sound information acquired by the sound information acquisition unit 231 as the sound information. , Apply the learning information and acquire physiology-related information. That is, it is preferable that the prediction unit 232 acquires the physiology-related information by using different learning information depending on the user. However, the prediction unit 232 may acquire physiology-related information by using learning information common to two or more users or all users.
- the prediction unit 232 acquires learning information corresponding to an identifier of the type of physiologically related information to be acquired from the learning information storage unit 211, and applies the learning information to the sound information acquired by the sound information acquisition unit 231. And acquire the relevant type of physiology-related information.
- the prediction unit 232 acquires the identifier of the type of physiologically related information to be acquired and the learning information corresponding to the user identifier from the learning information storage unit 211, and adds the sound information acquired by the sound information acquisition unit 231 to the sound information.
- the learning information is applied to acquire physiology-related information.
- the prediction unit 232 performs prediction processing by a machine learning algorithm using, for example, sound information and a learning device, and acquires physiology-related information.
- the prediction unit 232 selects the sound information that most closely resembles the sound information from the correspondence table, and acquires the physiologically related information that is paired with the selected sound information from the correspondence table.
- the prediction unit 232 selects from the correspondence table two or more sound information that is close to the sound information acquired by the sound information acquisition unit 231 so as to satisfy a predetermined condition (for example, the similarity is equal to or higher than the threshold value).
- a predetermined condition for example, the similarity is equal to or higher than the threshold value.
- Two or more physiology-related information corresponding to each of the two or more selected sound information is acquired from the correspondence table, and one physiology-related information is acquired from the two or more physiology-related information.
- the prediction unit 232 acquires, for example, representative values (for example, an average value, a median value, and a value selected by majority vote) of the two or more physiologically related information.
- the output unit 24 outputs the physiology-related information acquired by the prediction unit 232.
- the output is usually transmission to the terminal device 3, but display on a display, projection using a projector, printing by a printer, sound output, storage in an external recording medium, other processing devices, and the like.
- the concept may include passing the processing result to another program or the like.
- the various information is, for example, a user identifier.
- the user identifier may be the ID of the terminal device 3 or the like.
- the terminal reception unit 32 receives various information and instructions.
- the various information and instructions are, for example, abdominal sounds, physiology-related information, and output instructions.
- the input means for various information and instructions may be any, such as a microphone, a touch panel, a keyboard, a mouse, or a menu screen.
- the terminal processing unit 33 performs various processes.
- the various processes are, for example, A / D conversion of the abdominal sound received by the terminal reception unit 32 into data of the abdominal sound to be sent.
- the various processes are, for example, a process of forming a data structure for transmitting instructions and information received by the terminal reception unit 32. Further, the various processes are, for example, a process of forming a data structure for outputting the information received by the terminal receiving unit 35.
- the terminal transmission unit 34 transmits various information and instructions to the learning device 1 or the physiology-related information output device 2.
- the various information and instructions are, for example, abdominal sounds, physiology-related information, and output instructions.
- the terminal receiving unit 35 receives various information from the physiology-related information output device 2.
- Various types of information are, for example, physiologically related information.
- the terminal output unit 36 outputs various information. Various types of information are, for example, physiologically related information. It is preferable that the terminal output unit 36 outputs the physiology-related information for each type of physiology-related information.
- the teacher data storage unit 11, the storage unit 21, the learning information storage unit 211, and the terminal storage unit 31 are preferably non-volatile recording media, but can also be realized by volatile recording media.
- the process of storing information in the teacher data storage unit 11 or the like does not matter.
- the information may be stored in the teacher data storage unit 11 or the like via the recording medium, and the information transmitted via the communication line or the like may be stored in the teacher data storage unit 11 or the like.
- the information input via the input device may be stored in the teacher data storage unit 11 or the like.
- the sound information acquisition unit 13, the teacher data configuration unit 15, the learning unit 16, the storage unit 17, the processing unit 23, the sound information acquisition unit 231 and the prediction unit 232, and the terminal processing unit 33 are usually realized from a processor, a memory, or the like. obtain.
- the processing procedure of the sound information acquisition unit 13 and the like is usually realized by software, and the software is recorded in a recording medium such as ROM. However, it may be realized by hardware (dedicated circuit).
- the processor is, for example, a CPU, an MPU, a GPU, or the like, and the type thereof does not matter.
- the learning reception unit 14, the reception unit 22, and the terminal reception unit 35 are realized by, for example, wireless or wired communication means.
- the output unit 24 and the terminal transmission unit 34 are realized by, for example, wireless or wired communication means.
- the terminal reception unit 32 can be realized by a device driver for input means such as a microphone, a touch panel, or a keyboard, a menu screen control software, or the like.
- the terminal output unit 36 may or may not include an output device such as a display or a speaker.
- the terminal output unit 36 can be realized by the driver software of the output device, the driver software of the output device, the output device, or the like.
- Step S401 The learning reception unit 14 determines whether or not the abdominal sound or the like has been received from the terminal device 3. If the abdominal sound or the like is received, the process goes to step S402, and if the abdominal sound or the like is not received, the process goes to step S403.
- the abdominal sound and the like are, for example, abdominal sound and physiologically related information.
- the abdominal sound and the like are, for example, an abdominal sound, physiology-related information, and a user identifier.
- the learning reception unit 14 does not need to receive the abdominal sound and the physiology-related information together. It suffices if the abdominal sound and the physiology-related information are associated with each other.
- the learning reception unit 14 may receive the teacher data.
- the teacher data configuration unit 15 stores the received teacher data in the teacher data storage unit 11.
- the learning reception unit 14 may receive the teacher data in association with the user identifier.
- Step S402 The sound information acquisition unit 13 acquires sound information from the abdominal sound received in step S401. Then, the teacher data component unit 15 configures teacher data having the sound information and the received physiology-related information. Then, the teacher data configuration unit 15 stores the teacher data in the teacher data storage unit 11 in association with the user identifier. Return to step S401.
- Step S403 The learning unit 16 determines whether or not it is the timing to configure the learning information. If it is the timing to configure the learning information, the process goes to step S404, and if it is not the timing to configure the learning information, the process returns to step S401.
- the learning unit 16 may determine that it is the timing to configure the learning information according to the instruction from the terminal device 3. Further, the learning unit 16 may determine that it is the timing to configure the learning information when the teacher data equal to or larger than the threshold value exists in the teacher data storage unit 11. Further, the learning unit 16 may determine that it is the timing to configure the learning information corresponding to the one user identifier when the teacher data corresponding to the one user identifier exists in the threshold value or more. Further, the learning unit 16 determines that it is the timing to configure the learning information when the teacher data of the predetermined variation day exists in the teacher data storage unit 11 during the period of the menstrual cycle. Is also good.
- the learning unit 16 when the day (any day in the cycle) of the plurality of teacher data corresponding to one user identifier satisfies the condition regarding the predetermined variation in the period of the menstrual cycle. In addition, it may be determined that it is the timing to configure the learning information.
- the "predetermined variation" is a variation of days in the menstrual cycle. For example, the teacher data on different days from the start date of menstruation to the start date of the next menstruation is equal to or more than the threshold value (for example, 15 days or more). ) Or more than the threshold (eg, more than 18 days).
- Step S404 The learning unit 16 substitutes 1 for the counter i.
- Step S405 The learning unit 16 determines whether or not the i-th user identifier of the target constituting the learning information exists. If the i-th user identifier exists, the process goes to step S406, and if the i-th user identifier does not exist, the process returns to step S401.
- Step S406 The learning unit 16 substitutes 1 for the counter j.
- Step S407 The learning unit 16 determines whether or not the jth type of physiology-related information that constitutes the learning information exists. If the jth type of physiology-related information exists, the process goes to step S408, and if the jth type of physiology-related information does not exist, the process goes to step S412.
- the learning unit 16 acquires one or more teacher data that is paired with the i-th user identifier and includes the j-th type of physiology-related information from the teacher data storage unit 11. do.
- Step S409 The learning unit 16 configures learning information using one or more teacher data acquired in step S408. An example of such learning information configuration processing will be described with reference to the flowcharts of FIGS. 5 and 6.
- Step S410 The storage unit 17 stores the learning information acquired in step S407 in association with the i-th user identifier and the j-th type type identifier.
- the learning information may be stored in the learning device 1 or the learning information storage unit 211 of the physiology-related information output device 2.
- Step S411 The learning unit 16 increments the counter j by 1. Return to step S407.
- Step S412 The learning unit 16 increments the counter i by 1. Return to step S405.
- learning information is configured for each user identifier. However, learning information common to two or more users may be configured.
- the learning information when there is only one type of physiology-related information, the learning information does not correspond to the type identifier of the type of physiology-related information.
- the processing is terminated by the power off or the interrupt of the processing termination.
- the first example is a case where learning information, which is a learning device, is acquired by a learning process of machine learning.
- Step S501 The learning unit 16 determines whether or not to configure learning information, which is a learning device that performs multi-value classification.
- learning information which is a learning device that performs multi-value classification.
- step S502 To configure a learner for multi-value classification, go to step S502, and to configure a learner for binary classification, go to step S504.
- the multi-value classification or the binary classification may be determined in advance, or may be determined by the learning unit 16 according to the number of target teacher data. For example, the learning unit 16 determines "binary classification" when the number of teacher data to be learned is equal to or more than the threshold value or more than the threshold value, and "many" when the number of teacher data is less than or equal to the threshold value or less than the threshold value. Value classification "is determined.
- Step S502 The learning unit 16 gives one or more teacher data acquired in step S408 to the learning module of machine learning, and executes the learning module.
- Step S503 The learning unit 16 acquires a learning device that is the execution result of the module in step S502. Return to higher-level processing.
- Step S504 The learning unit 16 substitutes 1 for the counter i.
- Step S505 The learning unit 16 determines whether or not the i-th class exists. If the i-th class exists, the process goes to step S506, and if the i-th class does not exist, the process returns to higher processing.
- the class is data of candidates for physiology-related information. The classes are, for example, "near the start date of menstruation" and "far from the start date of menstruation".
- Step S506 The learning unit 16 acquires one or more teacher data (normal example) corresponding to the i-th class from the one or more teacher data acquired in step S408. Further, the learning unit 16 acquires one or more teacher data (negative example) that does not correspond to the i-th class from the one or more teacher data acquired in step S406.
- Step S507 The learning unit 16 gives the teacher data of the positive example and the negative example acquired in step S506 to the learning module of machine learning, and executes the learning module.
- Step S508 The learning unit 16 acquires a learning device that is the execution result of the module in step S507 in association with the class identifier of the i-th class.
- Step S509 The learning unit 16 increments the counter i by 1. Return to step S505.
- step S409 a second example of the learning information configuration process in step S409 will be described with reference to the flowchart of FIG.
- the second example is the case of acquiring learning information which is a correspondence table.
- Step S601 The learning unit 16 substitutes 1 for the counter i.
- Step S602 The learning unit 16 determines whether or not the i-th class exists. If the i-th class exists, the process goes to step S603, and if the i-th class does not exist, the process goes to step S606.
- the learning unit 16 acquires one or more teacher data corresponding to the i-th class. That is, the learning unit 16 acquires, for example, one or two or more sound information corresponding to the i-th class, and the representative value of the one or more sound information (for example, the average value, the median value, and the majority decision of each feature amount). Get the vector) whose elements are the result of. Next, the learning unit 16 acquires teacher data having the acquired representative value and the i-th class.
- the learning unit 16 configures the i-th correspondence information by using one or more teacher data acquired in step S603.
- the correspondence information is information in which sound information and physiology-related information (class data) are associated with each other.
- Step S605 The learning unit 16 increments the counter i by 1. Return to step S602.
- Step S606 The learning unit 16 constitutes a correspondence table having two or more correspondence information configured in step S604. Return to higher-level processing.
- Step S701 The reception unit 22 determines whether or not an output instruction has been received from the terminal device 3. If the output instruction is received, the process goes to step S702, and if the output instruction is not received, the process returns to step S701.
- the output instruction includes, for example, an abdominal sound and a user identifier.
- the output instruction may include sound information and a user identifier.
- Step S702 The sound information acquisition unit 231 acquires sound information from the abdominal sound of the output instruction received in step S701.
- Step S703 The prediction unit 232 performs a prediction process of acquiring physiologically related information using the sound information acquired in step S702. An example of the prediction process will be described with reference to the flowchart of FIG.
- Step S704 The output unit 24 transmits the physiology-related information acquired in step S703 to the terminal device 3. Return to step S701.
- step S703 the first example of the prediction process in step S703 will be described with reference to the flowchart of FIG.
- Step S801 The prediction unit 232 acquires the user identifier corresponding to the received abdominal sound.
- Step S802 The prediction unit 232 substitutes 1 for the counter i.
- Step S803 The prediction unit 232 determines whether or not the i-th class exists. If the i-th class exists, the process goes to step S804, and if the i-th class does not exist, the process goes to step S808.
- Step S804 The prediction unit 232 acquires the user identifier acquired in step S801 and the learning device corresponding to the i-th class from the learning information storage unit 211.
- Step S805 The prediction unit 232 gives the learning device acquired in step S805 and the sound information acquired in step S702 to the module that performs the prediction processing of machine learning, and executes the module.
- Step S806 The prediction unit 232 acquires the prediction result and the score, which are the execution results of the module in step S805.
- the prediction result here is information indicating whether or not it belongs to the i-th class.
- Step S807 The prediction unit 232 increments the counter i by 1. Return to step S803.
- Step S808 The prediction unit 232 acquires physiology-related information using the prediction result and the score acquired in step S806. Return to higher-level processing.
- the prediction unit 232 is the result that the prediction result acquired in step S806 "belongs to the i-th class", and acquires the class identifier of the class having the highest score as physiology-related information.
- menstruation-related information include, for example, information indicating whether or not the start date of menstruation is near, information indicating whether or not the period corresponds to the menstrual period, information on the number of days until the start date of menstruation, and the number of days until the day of ovulation.
- Information indicating the number of days information indicating the length of the menstrual period, information indicating whether the next menstrual period is weak or strong, and information indicating the level of pain.
- the second prediction process may be used. That is, the prediction unit 232 is a learning device corresponding to the user identifier corresponding to the received abdominal sound, and acquires a learning device capable of multi-value classification from the learning information storage unit 211. Next, the prediction unit 232 gives the learning device and the sound information acquired in step S702 to the module that performs the prediction processing of machine learning, executes the module, and acquires physiology-related information.
- the third prediction process may be used. That is, the prediction unit 232 acquires the correspondence table corresponding to the user identifier corresponding to the received abdominal sound from the learning information storage unit 211. Next, the prediction unit 232 determines the sound information (for example, a vector) that most closely resembles the sound information (for example, a vector) acquired in step S702 from the correspondence table. Next, the prediction unit 232 acquires the physiologically related information paired with the most similar sound information from the correspondence table.
- the sound information for example, a vector
- the prediction unit 232 acquires the physiologically related information paired with the most similar sound information from the correspondence table.
- the prediction unit 232 uses learning information common to two or more users (a learning device capable of multi-value classification, a learning device capable of binary classification for each class, or a correspondence table) for prediction processing. But it's okay.
- Step S901 The terminal reception unit 32 determines whether or not the abdominal sound or the like has been received. If the abdominal sound or the like is received, the process goes to step S902, and if the abdominal sound or the like received in step S901 is not received, the process goes to step S904.
- the abdominal sound and the like are, for example, abdominal sound and physiologically related information.
- the terminal processing unit 33 configures information to be transmitted to the learning device 1 by using an abdominal sound or the like. That is, the terminal processing unit 33 acquires the user identifier from the terminal storage unit 31, for example.
- the terminal processing unit 33 A / D-converts the abdominal sound collected by the microphone.
- the terminal processing unit 33 is information having A / D converted abdominal sound data, physiology-related information, and a user identifier, and constitutes information to be transmitted.
- Step S903 The terminal transmission unit 34 transmits the information configured in step S902 to the learning device 1.
- Step S904 The terminal reception unit 32 determines whether or not an output instruction including an abdominal sound has been received. If the output instruction is accepted, the process goes to step S905, and if the output instruction is not accepted, the process returns to step S901.
- the terminal processing unit 33 configures an output instruction to be transmitted. That is, the terminal processing unit 33 acquires the user identifier from the terminal storage unit 31, for example.
- the terminal processing unit 33 A / D-converts the abdominal sound.
- the terminal processing unit 33 constitutes an output instruction having A / D-converted abdominal sound data and a user identifier.
- the terminal processing unit 33 may acquire sound information from the abdominal sound and configure an output instruction having the sound information and the user identifier.
- Step S906 The terminal transmission unit 34 transmits the output instruction configured in step S905 to the physiology-related information output device 2.
- Step S907 The terminal receiving unit 35 determines whether or not one or two or more types of physiologically related information have been received in response to the transmission of the output instruction in step S906. If the menstruation-related information is received, the process goes to step S908, and if the menstruation-related information is not received, the process returns to step S907.
- Step S908 The terminal processing unit 33 configures the physiology-related information to be output by using the physiology-related information received in step S907.
- the terminal output unit 36 outputs the physiologically related information. Return to step S901.
- FIG. 1 The conceptual diagram of the information system A is FIG.
- the teacher data storage unit 11 of the learning device 1 stores a teacher data management table having the structure shown in FIG.
- the teacher data management table is a table that manages one or more records having "ID”, “user identifier”, “sound information”, “date and time information”, and "physiological information”.
- the "physiological information” has a “physiological flag”, “days information”, “period information”, and "level”.
- the "sound information” is a feature vector which is a set of two or more features acquired from the abdominal sound.
- “Date and time information” is information on the date and time corresponding to the sound information.
- the “date and time information” may be the date and time when the abdominal sound was acquired, the date and time when the learning device 1 received the abdominal sound or sound information, or the date and time when the terminal device 3 transmitted the abdominal sound or sound information. ..
- “Date and time information” includes day information that identifies the day.
- the "date and time information” may be day information.
- the "menstrual flag” is information indicating whether or not it is during the menstrual period. Here, a value of “1” is taken if it is during the menstrual period, and a value of "0” is taken if it is not during the menstrual period.
- Days information is information indicating the number of days until the next menstrual period start date.
- Period information is information indicating the number of days of the menstrual period.
- Days information is information indicating the period from the start to the end of the menstrual period if it is during the menstrual period, and is information indicating the period of the next menstruation if it is not during the menstrual period.
- the "level” is information indicating the level of menstrual pain, and is a value input by the user.
- the teacher data configuration unit 15 acquires "days information" as follows, for example. That is, the teacher data configuration unit 15 acquires the user identifier corresponding to the sound information acquired by the sound information acquisition unit 13.
- the teacher data configuration unit 15 is teacher data paired with the user identifier, and has date and time information paired with teacher data (teacher data on the start date of physiology) including the physiology flag “1” and the number of days information “28”. Get the first day information. Further, the teacher data configuration unit 15 acquires the second day information (second day information ⁇ first day information) possessed by the date and time information corresponding to the sound information acquired by the sound information acquisition unit 13. Next, the teacher data configuration unit 15 acquires the difference between the first day information and the second day information as "days information". Here, the cycle of menstruation is 28 days.
- the teacher data component unit 15 acquires "period information" as follows, for example. That is, the teacher data configuration unit 15 acquires the user identifier corresponding to the sound information acquired by the sound information acquisition unit 13. The teacher data configuration unit 15 acquires the first day information of the date and time information paired with the sound information of the physiological start date, which is the sound information paired with the user identifier. The teacher data configuration unit 15 is date and time information paired with the user identifier, date and time information indicating a day after the first day information, and date and time information indicating the day closest to the first day information. , Acquires the second day information possessed by the date and time information paired with the physiological flag "0".
- Specific example 1 is an example for explaining the learning process by the learning device 1.
- Specific Example 2 is an example for explaining the prediction processing of the physiology-related information by the physiology-related information output device 2.
- the learning reception unit 14 receives the physiology-related information.
- the terminal reception unit 32 of the terminal device 3 receives the abdominal sound.
- the terminal processing unit 33 reads out the user identifier "U02" of the terminal storage unit 31.
- the terminal processing unit 33 acquires the menstruation-related information " ⁇ menstruation day-related information> menstruation start date ⁇ pain information> 3".
- the terminal processing unit 33 digitizes the abdominal sound.
- the terminal processing unit 33 constitutes information having the physiologically related information, the abdominal sound, and the user identifier “U02”.
- the terminal transmission unit 34 transmits the configured information to the learning device 1.
- the learning reception unit 14 of the learning device 1 receives the physiology-related information, the abdominal sound, and the user identifier from the learning device 1.
- the teacher data component unit 15 receives the received menstruation-related information " ⁇ menstruation day-related information> menstruation start date ⁇ pain information>3", the menstruation flag "1", the number of days information "28", and the level "3". To get.
- the teacher data configuration unit 15 acquires the date and time information “9/10 8:15” from a clock (not shown). Further, the teacher data component unit 15 acquires various feature quantities from the abdominal sound and configures sound information (x 981 , x 982 , ..., X 98n ).
- the teacher data composition unit 15 constitutes a record to be accumulated in the teacher data management table.
- the learning unit 16 configures a learning device for each user and each physiology-related information as follows.
- the learning unit 16 may or may not use other physiology-related information.
- the learning unit 16 configures a learning device for outputting the physiology-related information "level”, among other physiology-related information (here, "physiological flag", "days information", "period information").
- the learning process may be performed using the teacher data including one or more physiology-related information, or the learning process may be performed using the teacher data not including other physiology-related information.
- the learning unit 16 acquires all teacher data consisting of sound information paired with the user identifier of the user and one physiology-related information (for example, "level”) from the teacher data management table for each user. do.
- the learning unit 16 configures a learning device that performs learning processing by a machine learning algorithm (for example, random forest), inputs sound information, and outputs one physiologically related information (for example, "level”).
- the storage unit 17 stores the learning device acquired by the learning unit 16 as a pair with the user identifier.
- the learning unit 16 performs the same processing as above for each physiology-related information of other physiology-related information (“physiology flag”, “days information”, “period information”) for each user, and for each user, physiology-related information. Configure a learner for each piece of information.
- the storage unit 17 stores the learning device acquired by the learning unit 16 as a pair with the user identifier.
- the terminal reception unit 32 of the terminal device 3 receives the abdominal sound.
- the terminal processing unit 33 reads out the user identifier "U02" of the terminal storage unit 31.
- the terminal processing unit 33 digitizes the abdominal sound.
- the terminal processing unit 33 constitutes an output instruction having the abdominal sound and the user identifier “U02”.
- the terminal transmission unit 34 transmits the output instruction to the physiology-related information output device 2.
- the reception unit 22 of the physiology-related information output device 2 receives the output instruction. Then, the sound information acquisition unit 231 acquires a feature amount vector which is sound information from the abdominal sound of the received output instruction.
- the prediction unit 232 uses the acquired sound information to perform a prediction process for acquiring physiologically related information as follows.
- the prediction unit 232 acquires the user identifier "U02" possessed by the output instruction. Next, the prediction unit 232 acquires the learning device corresponding to the user identifier "U02" and the "physiological flag” from the learning information storage unit 211. Next, the prediction unit 232 gives the learner and the feature quantity vector which is sound information to the machine learning module (for example, the module of the random forest), executes the module, and acquires the physiological flag "0". Yes.
- the machine learning module for example, the module of the random forest
- the prediction unit 232 acquires the learning device corresponding to the user identifier "U02" and the "days information" from the learning information storage unit 211. Next, the prediction unit 232 gives the learning device and the feature quantity vector which is sound information to the machine learning module (for example, the deep learning module), executes the module, and acquires the number of days information "3". Yes.
- the machine learning module for example, the deep learning module
- the prediction unit 232 acquires the learning device corresponding to the user identifier "U02" and the "period information" from the learning information storage unit 211. Next, the prediction unit 232 gives the learning device and the feature quantity vector which is sound information to the machine learning module (for example, the SVM module), executes the module, and outputs the period information "4.5". It is assumed that it was acquired.
- the machine learning module for example, the SVM module
- the prediction unit 232 acquires the learning device corresponding to the user identifiers "U02" and the "level” from the learning information storage unit 211. Next, the prediction unit 232 gave the learner and the feature quantity vector which is sound information to a machine learning module (for example, a module of a random forest), executed the module, and acquired level "3". , And.
- a machine learning module for example, a module of a random forest
- the prediction unit 232 configures the menstruation-related information to be transmitted by using the menstruation flag "0", the number of days information "3", the period information "4.5", and the level "3".
- the output unit 24 transmits the configured physiology-related information to the terminal device 3.
- the terminal receiving unit 35 of the terminal device 3 receives the physiology-related information in response to the transmission of the output instruction.
- the terminal processing unit 33 configures the output physiological-related information using the received physiological-related information.
- the terminal output unit 36 outputs the physiologically related information. An example of such an output is shown in FIG.
- physiologically related information can be acquired using the abdominal sound.
- the learning device 1 may use different machine learning algorithms depending on the type of physiology-related information when creating the learning device.
- the learning device 1 uses, for example, a random forest module when configuring a learning device for outputting "physiological flags", and deep learning when configuring a learning device for outputting "days information”.
- the SVR module may be used when the learning device for outputting the "period information" is configured by using the module.
- the learning device 1 may be a stand-alone device.
- the learning device 1 has a sound collecting unit that collects abdominal sounds from one user's abdomen or around the abdomen, a sound information acquiring unit that acquires sound information from the abdominal sounds, and a learning reception unit that receives physiological information.
- a learning process of machine learning is performed on the teacher data component unit that constitutes teacher data from the sound information and the physiology-related information, and the teacher data configured by the teacher data component unit, and the learning device is used.
- the physiology-related information output device 2 may be a stand-alone device.
- the physiology-related information output device 2 in such a case is configured by using two or more teacher data having sound information acquired from the abdominal sound from one user's abdomen or the abdomen and physiology-related information. Sound information acquisition to acquire sound information used for prediction processing to acquire physiology-related information from the learning information storage unit in which the learning information is stored and the sound acquired from the abdomen or the abdomen of the one user.
- a unit, a prediction unit that applies the learning information to the sound information acquired by the sound information acquisition unit to acquire the physiology-related information, and an output unit that outputs the physiology-related information acquired by the prediction unit are provided. It is a physiology-related information output device 2.
- the physiology-related information output device 2 may be configured to include the learning device 1.
- the processing in this embodiment may be realized by software. Then, this software may be distributed by software download or the like. Further, this software may be recorded on a recording medium such as a CD-ROM and disseminated. It should be noted that this also applies to other embodiments herein.
- the software that realizes the learning device 1 in this embodiment is the following program. That is, this program configures the computer as teacher data from a sound information acquisition unit that acquires sound information from the user's abdominal sound, a learning reception unit that accepts physiology-related information, and the sound information and the physiology-related information.
- a learning unit that performs machine learning learning processing on the teacher data configuration unit configured by the teacher data configuration unit and the teacher data configuration unit to configure learning information that is a learning device, and a storage unit that accumulates the learning device. It is a program to function as a department.
- the software that realizes the physiology-related information output device 2 is the following program. That is, this program accesses a learning information storage unit that stores learning information configured by using two or more teacher data having sound information acquired from the user's abdominal sound and physiology-related information.
- Possible computers include a sound information acquisition unit that acquires sound information from the user's abdominal sound, and a prediction unit that applies the learning information to the sound information acquired by the sound information acquisition unit and acquires physiology-related information.
- This is a program for functioning as an output unit for outputting the physiologically related information acquired by the prediction unit.
- FIG. 14 shows the appearance of a computer that executes the program described in the present specification to realize the learning device 1, the physiology-related information output device 2, or the terminal device 3 of the various embodiments described above.
- the above-described embodiment can be realized by computer hardware and a computer program executed on the computer hardware.
- FIG. 14 is an overview view of the computer system 300
- FIG. 15 is a block diagram of the system 300.
- the computer system 300 includes a computer 301 including a CD-ROM drive, a keyboard 302, a mouse 303, a monitor 304, and a microphone 305.
- the computer 301 in addition to the CD-ROM drive 3012, the computer 301 includes an MPU 3013, a bus 3014 connected to the CD-ROM drive 3012, the ROM 3015 for storing a program such as a boot-up program, and the MPU 3013. It includes a RAM 3016 that is connected and for temporarily storing instructions of an application program and providing a temporary storage space, and a hard disk 3017 for storing an application program, a system program, and data.
- the computer 301 may further include a network card that provides a connection to the LAN.
- the program for causing the computer system 300 to execute the functions of the learning device 1 and the like according to the above-described embodiment may be stored in the CD-ROM 3101, inserted into the CD-ROM drive 3012, and further transferred to the hard disk 3017.
- the program may be transmitted to the computer 301 via a network (not shown) and stored in the hard disk 3017.
- the program is loaded into RAM 3016 at run time.
- the program may be loaded directly from the CD-ROM3101 or the network.
- the program does not necessarily have to include an operating system (OS) or a third-party program that causes the computer 301 to execute the functions of the learning device 1 and the like according to the above-described embodiment.
- the program need only include a part of the instruction that calls the appropriate function (module) in a controlled manner and obtains the desired result. It is well known how the computer system 300 works, and detailed description thereof will be omitted.
- the processing performed by the hardware for example, the processing performed by the modem or the interface card in the transmission step (only performed by the hardware). Processing) is not included.
- the number of computers that execute the above program may be singular or plural. That is, centralized processing may be performed, or distributed processing may be performed. That is, the information processing device 5 may be a stand-alone device or may be composed of two or more devices.
- the two or more communication means existing in one device may be physically realized by one medium.
- each process may be realized by centralized processing by a single device, or may be realized by distributed processing by a plurality of devices.
- the physiology-related information output device has the effect of being able to predict physiology-related information by using the abdominal sound from the abdomen or the abdomen, and is useful as a device for outputting physiology-related information. Is.
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Pathology (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Biophysics (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Acoustics & Sound (AREA)
- Pain & Pain Management (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Hospice & Palliative Care (AREA)
- Electrically Operated Instructional Devices (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Description
本実施の形態において、ユーザの腹部音に関する音情報と生理関連情報とを有する2以上の教師データを用いて構成された学習情報に、一のユーザの腹部音に関する音情報を適用し、生理関連情報を取得し、出力する生理関連情報出力装置について説明する。
また、音情報取得部13は、音収集部12が取得した腹部音から音情報を取得しても良い。
今、「U02」で識別されるユーザが、生理関連情報を学習させるために、端末装置3のアプリケーション(以下、適宜、「アプリ」という)を起動させた、とする。かかるアプリの出力例は、図11である。
次に、「U02」で識別されるユーザが、次回の生理日までの日数、次回の生理期間、および次回の生理の疼痛のレベルを予測するために、以下のように、アプリを使用する、とする。
Claims (10)
- ユーザの腹部音から取得された音情報と生理に関連する生理関連情報とを有する2以上の教師データを用いて構成された学習情報が格納される学習情報格納部と、
ユーザの腹部音からの音情報を取得する音情報取得部と、
前記音情報取得部が取得した音情報に、前記学習情報を適用し、生理関連情報を取得する予測部と、
前記予測部が取得した生理関連情報を出力する出力部とを具備する生理関連情報出力装置。 - 前記生理関連情報は、生理に関する日との関係に関する生理日関係情報である、請求項1記載の生理関連情報出力装置。
- 前記生理関連情報は、生理の疼痛に関する疼痛情報である、請求項1記載の生理関連情報出力装置。
- 前記2以上の教師データは、
前記ユーザの生理周期の間の各日の腹部から取得された腹部音から取得された前記音情報と前記生理関連情報とを有する教師データから構成される、請求項1記載の生理関連情報出力装置。 - 前記2以上の教師データに対して、機械学習のアルゴリズムにより学習処理を行い、学習器である学習情報を取得する学習部をさらに具備し、
前記予測部は、
前記音情報取得部が取得した音情報と前記学習情報とを用いて、機械学習のアルゴリズムにより予測処理を行い、生理関連情報を取得する、請求項1記載の生理関連情報出力装置。 - 前記音情報は、
前記ユーザの腹部音の2以上の特徴量である、請求項1記載の生理関連情報出力装置。 - ユーザの腹部音からの音情報を取得する音情報取得部と、
生理関連情報を受け付ける学習受付部と、
前記音情報と前記生理関連情報とから教師データを構成する教師データ構成部と、
前記教師データ構成部が構成した前記教師データに対して、機械学習の学習処理を行い、学習器である学習情報を構成する学習部と、
前記学習器を蓄積する蓄積部とを具備する学習装置。 - 音情報取得部と、学習受付部と、教師データ構成部と、学習部と、蓄積部とにより実現される学習情報の生産方法であって、
前記音情報取得部が、ユーザの腹部音からの音情報を取得する音情報取得ステップと、
前記学習受付部が、生理関連情報を受け付ける学習受付ステップと、
前記教師データ構成部が、前記音情報と前記生理関連情報とから教師データを構成する教師データ構成ステップと、
前記学習部が、前記教師データ構成ステップで構成された前記教師データに対して、機械学習の学習処理を行い、学習器である学習情報を構成する学習ステップと、
前記蓄積部が、前記学習器を蓄積する蓄積ステップとを具備する学習情報の生産方法。 - ユーザの腹部音から取得された音情報と生理に関連する生理関連情報とを有する2以上の教師データを用いて構成された学習情報が格納される学習情報格納部にアクセス可能なコンピュータを、
ユーザの腹部音からの音情報を取得する音情報取得部と、
前記音情報取得部が取得した音情報に、前記学習情報を適用し、生理関連情報を取得する予測部と、
前記予測部が取得した生理関連情報を出力する出力部として機能させるためのプログラムを記録した記録媒体。 - コンピュータを、
ユーザの腹部音からの音情報を取得する音情報取得部と、
生理関連情報を受け付ける学習受付部と、
前記音情報と前記生理関連情報とから教師データを構成する教師データ構成部と、
前記教師データ構成部が構成した前記教師データに対して、機械学習の学習処理を行い、学習器である学習情報を構成する学習部と、
前記学習器を蓄積する蓄積部として機能させるためのプログラムを記録した記録媒体。
Priority Applications (5)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020237011491A KR20230116770A (ko) | 2020-12-07 | 2021-12-02 | 생리 관련 정보 출력 장치, 학습 장치, 학습 정보의 생산 방법, 및 기록 매체 |
JP2022568232A JPWO2022124189A1 (ja) | 2020-12-07 | 2021-12-02 | |
CN202180082367.0A CN116568224A (zh) | 2020-12-07 | 2021-12-02 | 月经关联信息输出装置、学习装置、学习信息的生成方法及存储介质 |
EP21903293.5A EP4257059A1 (en) | 2020-12-07 | 2021-12-02 | Menstruation-related information output device, learning device, method for producing learning information, and recording medium |
US18/265,551 US20240023942A1 (en) | 2020-12-07 | 2021-12-02 | Menstruation-related information output apparatus, learning apparatus, learning information producing method, and recording medium |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2020-202489 | 2020-12-07 | ||
JP2020202489 | 2020-12-07 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022124189A1 true WO2022124189A1 (ja) | 2022-06-16 |
Family
ID=81974423
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2021/044233 WO2022124189A1 (ja) | 2020-12-07 | 2021-12-02 | 生理関連情報出力装置、学習装置、学習情報の生産方法、および記録媒体 |
Country Status (7)
Country | Link |
---|---|
US (1) | US20240023942A1 (ja) |
EP (1) | EP4257059A1 (ja) |
JP (1) | JPWO2022124189A1 (ja) |
KR (1) | KR20230116770A (ja) |
CN (1) | CN116568224A (ja) |
TW (1) | TW202222261A (ja) |
WO (1) | WO2022124189A1 (ja) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2014064706A (ja) | 2012-09-25 | 2014-04-17 | Terumo Corp | 情報処理装置及び情報処理方法 |
JP2015523319A (ja) | 2012-05-02 | 2015-08-13 | ベドウキアン リサーチ, インコーポレイテッド | 蚊の防除及び忌避 |
WO2019073900A1 (ja) * | 2017-10-10 | 2019-04-18 | 国立大学法人徳島大学 | 機械学習装置、判定装置、機械学習方法、判定方法、学習用プログラム、判定用プログラムおよび記録媒体 |
WO2020105229A1 (ja) * | 2018-11-19 | 2020-05-28 | テルモ株式会社 | 診断支援システム |
-
2021
- 2021-11-04 TW TW110141141A patent/TW202222261A/zh unknown
- 2021-12-02 WO PCT/JP2021/044233 patent/WO2022124189A1/ja active Application Filing
- 2021-12-02 US US18/265,551 patent/US20240023942A1/en active Pending
- 2021-12-02 KR KR1020237011491A patent/KR20230116770A/ko unknown
- 2021-12-02 CN CN202180082367.0A patent/CN116568224A/zh active Pending
- 2021-12-02 JP JP2022568232A patent/JPWO2022124189A1/ja active Pending
- 2021-12-02 EP EP21903293.5A patent/EP4257059A1/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2015523319A (ja) | 2012-05-02 | 2015-08-13 | ベドウキアン リサーチ, インコーポレイテッド | 蚊の防除及び忌避 |
JP2014064706A (ja) | 2012-09-25 | 2014-04-17 | Terumo Corp | 情報処理装置及び情報処理方法 |
WO2019073900A1 (ja) * | 2017-10-10 | 2019-04-18 | 国立大学法人徳島大学 | 機械学習装置、判定装置、機械学習方法、判定方法、学習用プログラム、判定用プログラムおよび記録媒体 |
WO2020105229A1 (ja) * | 2018-11-19 | 2020-05-28 | テルモ株式会社 | 診断支援システム |
Non-Patent Citations (3)
Title |
---|
ANONYMOUS: "[Verification of too detailed menstrual application 7] Roughly manage the menstrual cycle with the ring display! I tried using the minimal design "Clue" with zero cuteness", IPHONEJOSHIBU, 2 October 2018 (2018-10-02), pages 1 - 19, XP055941439, Retrieved from the Internet <URL:https://www.iphonejoshibu.com/8906> [retrieved on 20220712] * |
ANONYMOUS: "why? A whirling sound from the stomach | How to eliminate diarrhea, abdominal pain, and gas. What is the possibility of illness?", 10 March 2020 (2020-03-10), pages 1 - 7, XP055940669, Retrieved from the Internet <URL:https://web.archive.org/web/20200506051908/https://epark.jp/medicalook/stomach-growling/> [retrieved on 20220711] * |
BUHR, SARAH: "Menstrual cycle predictor Clue raises $20M from Nokia Growth Partners and others", 5 December 2016 (2016-12-05), Japan, pages 1 - 4, XP009538180, Retrieved from the Internet <URL:https://web.archive.org/web/20161205002344/https://jp.techcrunch.com/2016/12/02/20161130period-tracking-app-clue-pulls-in-20-million-series-b-from-nokia-growth-partners/> [retrieved on 20220811] * |
Also Published As
Publication number | Publication date |
---|---|
KR20230116770A (ko) | 2023-08-04 |
TW202222261A (zh) | 2022-06-16 |
JPWO2022124189A1 (ja) | 2022-06-16 |
US20240023942A1 (en) | 2024-01-25 |
EP4257059A1 (en) | 2023-10-11 |
CN116568224A (zh) | 2023-08-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6355800B1 (ja) | 学習装置、生成装置、学習方法、生成方法、学習プログラム、および生成プログラム | |
CN107097234A (zh) | 机器人控制系统 | |
Cortés et al. | Ambulatory assessment of phonotraumatic vocal hyperfunction using glottal airflow measures estimated from neck-surface acceleration | |
KR102424085B1 (ko) | 기계-보조 대화 시스템 및 의학적 상태 문의 장치 및 방법 | |
KR102298330B1 (ko) | 음성인식과 자연어 처리 알고리즘을 통해 의료 상담 요약문과 전자 의무 기록을 생성하는 시스템 | |
WO2022121180A1 (zh) | 模型的训练方法、装置、语音转换方法、设备及存储介质 | |
Emerich et al. | Emotions recognition by speechand facial expressions analysis | |
Ntalampiras | A transfer learning framework for predicting the emotional content of generalized sound events | |
CN111387936B (zh) | 一种睡眠阶段识别方法、装置及设备 | |
JP2021117967A (ja) | センサからの自動学習方法及びプログラム | |
Anders et al. | Automatic classification of infant vocalization sequences with convolutional neural networks | |
CN113255763A (zh) | 基于知识蒸馏的模型训练方法、装置、终端及存储介质 | |
WO2008054162A1 (en) | Method, apparatus, and system for diagnosing health status of mobile terminal users | |
WO2022124189A1 (ja) | 生理関連情報出力装置、学習装置、学習情報の生産方法、および記録媒体 | |
CN108415995B (zh) | 搜索方法和装置 | |
CN113051425A (zh) | 音频表征提取模型的获取方法和音频推荐的方法 | |
CN114341867A (zh) | 翻译方法、装置、客户端、服务器和存储介质 | |
JP2021111241A (ja) | 情報処理装置、発症確率判定方法および発症確率判定プログラム | |
JP2020149072A (ja) | 会話記録システム、会話記録方法、サーバ装置、及びプログラム | |
EP4339848A1 (en) | Information processing device, information processing server, information processing method, and non-transitory computer readable storage medium | |
CN110827989B (zh) | 一种基于关键因子对医学数据进行处理的控制方法 | |
JP7495767B1 (ja) | プログラム、特許情報処理装置、および特許情報処理方法 | |
CN117238532B (zh) | 智能随访方法及装置 | |
US20240232721A1 (en) | Information processing apparatus, information processing server, information processing method, and non-transitory computer-readable storage medium | |
EP4145386A1 (en) | Information processing device and program |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21903293 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2022568232 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 18265551 Country of ref document: US |
|
WWE | Wipo information: entry into national phase |
Ref document number: 202180082367.0 Country of ref document: CN |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 2021903293 Country of ref document: EP Effective date: 20230707 |