JP7398213B2 - Estimation device, estimation method, estimation program and system - Google Patents

Description

The present invention relates to an estimation device, an estimation method, an estimation program, and a system.

2. Description of the Related Art Conventionally, there has been known a technique for estimating the condition of an infant using biological information of the infant who has difficulty speaking. As an example of such a technique, a technique is known in which a sensor is installed in an absorbent article such as a diaper to detect whether or not an infant has excreted into the diaper.

JP 2019-37292 Publication

T Lindberg, Infantile Colic: aetiology and prognosis, Acta Paediatr, 89, 1-12, 2000 Nina F Steutel, Developing a core outcome set for infant colic for primary, secondary and tertiary care settings: a prospective study, BMJ Open, 2017 Sachiko Otawara and others, “Introduction of forward leaning sitting position and abdominal exercises for severely mentally and physically disabled patients with weak intestinal peristalsis and repeated ileus,” 48th Japanese Physical Therapy Congress, 2013 Bowel auscultation expert nurse 2017, vol33(4), 112p

However, the above-described conventional techniques may not be able to provide useful information regarding childcare.

For example, the above-mentioned technology merely detects whether or not the infant has excreted the toilet. For this reason, in addition to when an infant is crying due to excretion, for example, when the infant is in a bad mood or cries at night, it is not possible to show the parent why the infant is crying. It cannot be said that the physical and mental burden on parents has been alleviated.

This application was made in view of the above, and aims to provide useful information regarding childcare.

The estimation device according to the present application includes an acquisition unit that acquires the sound detected from the abdomen of the infant by a detection device attached to an article worn by the infant, and based on the characteristics of the sound acquired by the acquisition unit, The apparatus is characterized by comprising an estimating section that estimates the emotional state of the infant.

According to one aspect of the embodiment, it is possible to provide useful information regarding childcare.

FIG. 1 is a diagram illustrating an example of a providing system according to an embodiment. FIG. 2 is a first diagram showing an example of the survey results. FIG. 3 is a second diagram showing an example of the survey results. FIG. 4 is a front view showing an example of the shape of the wearable device WD according to the embodiment. FIG. 5 is a cross-sectional view showing an example of the shape of the wearable device WD according to the embodiment. FIG. 6 is a diagram showing an example of how the wearable device according to the embodiment is worn. FIG. 7 is a diagram illustrating an example of a functional configuration of a terminal device according to an embodiment. FIG. 8 is a diagram illustrating an example of information registered in the wearer database according to the embodiment. FIG. 9 is a diagram illustrating an example of information registered in the user database according to the embodiment. FIG. 10 is a flowchart illustrating an example of the flow of processing executed by the information providing apparatus according to the embodiment. FIG. 11 is a diagram illustrating an example of provided information provided by the information providing device according to the embodiment. FIG. 12 is a diagram showing an example of the hardware configuration.

From the description of this specification and the attached drawings, at least the following matters will become clear.

An acquisition unit that acquires sounds detected from the abdomen of the infant by a detection device attached to an article worn by the infant; and an estimation of the emotional state of the infant based on the characteristics of the sounds acquired by the acquisition unit. An estimating device having an estimating section.

In this way, the estimation device acquires the sound detected from the abdomen of the infant from the detection device attached to the article worn by the infant. Here, the sounds detected from the infant's abdomen may include, for example, sounds produced by the movement of the infant's intestines (ie, bowel sounds). As will be described later, an infant's intestinal movements are presumed to have a relationship with the infant's emotional state. Therefore, the estimation device estimates the emotional state of the infant based on the characteristics of the bowel sounds.

As a result of such processing, the estimation device can estimate the emotional state of the infant, so it can provide the user with a notification that the infant is likely to cry at night, or that the infant is in a bad mood, for example. can do. As a result, the estimation device can reduce the physical or mental burden of childcare on the user, and can provide useful information regarding childcare.

Further, the estimation device acquires the sound generated when the infant's intestines perform peristalsis, the sound generated when the infant's intestine makes a syllable movement, or the sound generated when the infant's intestine makes a pendulum movement detected from the infant's abdomen. As a result of such processing, the estimation device can estimate the emotional state of the infant based on the state of the infant's intestinal movements.

Here, the estimation device may estimate the emotional state of the infant based on the number of sounds having predetermined characteristics among the acquired sounds. Furthermore, the estimation device may estimate the emotional state of the infant based on the frequency of sounds having predetermined characteristics among the acquired sounds. Furthermore, the estimation device may estimate the emotional state of the infant based on the type of the acquired sound. As a result of such processing, the estimation device can appropriately estimate the emotional state of the infant.

Furthermore, the estimation device estimates the peristaltic state of the infant's intestines based on the characteristics of the acquired sound, and estimates the emotional state of the infant based on the estimated peristaltic state. For example, the estimation device estimates whether the peristalsis state is an enhanced state, a decreased state, or a normal state, and estimates the emotional state of the infant based on the estimation result. Therefore, the estimation device can accurately estimate the emotional state of the infant.

Furthermore, the estimation device estimates whether the infant is in an emotional state in which it is easy to fall asleep, as the emotional state of the infant. Furthermore, the estimation device estimates whether the infant is in an emotional state in which the infant is likely to cry at night, as the emotional state of the infant. In this way, the estimating device estimates whether the infant's emotional state is such that it is easy to fall asleep or cry at night, so it is possible to provide useful information regarding childcare.

Furthermore, the estimation device estimates, as the emotional state of the infant, an emotional state related to the quality of life of the infant or a user who has a predetermined relationship with the infant. Therefore, the estimation device can provide information that improves the quality of the user.

Further, the estimation device includes a providing unit that provides information according to the estimated emotional state. Therefore, the estimation device can provide information useful for childcare.

Furthermore, the estimation device provides information indicating recommended behavior to a user who has a predetermined relationship with the infant, depending on the emotional state. Therefore, the estimation device can provide the user with information on what action to take when the infant is crying, for example.

Further, the estimation device may further acquire body temperature information indicating the body temperature of the infant detected by the detection device, and further provide information according to the periodicity of the body temperature indicated by the body temperature information. Furthermore, the estimating device may further estimate the infant's excretion-related state based on the characteristics of the sound, and further provide information corresponding to the excretion-related state estimated by the estimator. For example, the estimation device provides information indicating the bedtime of the infant or the wake-up time of the infant specified based on the periodicity of body temperature indicated by the body temperature information. Therefore, the estimation device can provide more useful information to the user.

Moreover, the estimation device acquires the sound detected by the detection device attached to sandwich the end of the waist of the absorbent article worn by the infant. As a result, the estimation device can acquire abdominal sounds with less noise, and therefore can improve the accuracy of estimating the emotional state of the infant.

Below, an example of an estimation device, an estimation method, an estimation program, and a mode for implementing the system (hereinafter referred to as "embodiment") will be described in detail with reference to the drawings. Note that the estimation device, estimation method, estimation program, and system are not limited to this embodiment. In addition, in the following embodiments, the same parts are given the same reference numerals, and redundant explanations will be omitted.

[Embodiment]
[1. About an example of the provision system]
First, an example of a providing system according to an embodiment will be described using FIG. 1. FIG. 1 is a diagram illustrating an example of a providing system according to an embodiment. As shown in FIG. 1, the providing system includes an information providing device 10, which is an example of an estimation device, and a terminal device 100 used by a user U. Note that the providing system may include any number of information providing devices 10 and terminal devices 100. Further, the information providing device 10 may perform processing described below with an arbitrary number of terminal devices 100.

The information providing device 10 is an information processing device that performs information processing to be described later, and is realized by, for example, a server device, a cloud system, or the like. For example, the information providing device 10 supports various mobile communication systems such as LTE (Long Term Evolution), 4G (Generation) including LET-Advanced, which is a type of LET, and 5G, which will be standardized in the future; Communication is performed with the terminal device 100 via a network N (for example, see FIG. 5), such as various wireless communication networks such as (registered trademark) or wireless LAN (Local Area Network), or various wired communication networks.

The terminal device 100 is a terminal device used by a user U, and is realized by a smart device such as a PC (Personal Computer), a server device, a smart television, a smartphone or a tablet, and is connected to an information providing device via a network N. This is a mobile terminal device that can communicate with 10. In addition, the terminal device 100 has a screen such as a liquid crystal display, which has a touch panel function, and the information providing device 10 allows the user to perform tap operations, slide operations, scroll operations, etc. using a finger or a stylus, etc. It may have a function that can accept various operations on the content that is displayed.

[1-1. About bowel sounds in infants]
Here, in childcare, the emotional state of infants and young children is important. For example, if an infant is in a bad mood, he or she may cry at night. However, infants cannot speak well. For this reason, when night crying occurs, users who are caring for children become anxious and their mental burden increases. In addition, night crying may wake up a sleeping user, resulting in a physical burden.

In addition to the above-mentioned night crying, depending on the mood of the infant, such as when the infant is excited, it may be impossible to put the infant to sleep. Furthermore, when an infant cries, it is difficult to take appropriate measures unless the infant's mood is known, such as whether the infant is simply in a bad mood or whether he or she wants to excrete. In this way, an infant's mood, or emotional state, can be an important factor in childcare. In particular, it is estimated that for users who are raising children for the first time, it is difficult to estimate the mood of the infant based on the condition of the infant, and the burden becomes heavy.

On the other hand, it is known that the human intestines make various movements and emit various sounds (i.e., "intestinal peristaltic sounds", hereinafter sometimes referred to collectively as "intestinal sounds") depending on the movements. ing. For example, the human intestine moves its contents through peristaltic movements, segmental movements that expand its contents by changing the positions of its constrictions and bulges, and its repeated contraction and relaxation in the longitudinal direction. It is known to perform a pendulum movement to increase sales (for example, see Non-Patent Document 4). Due to these various movements, the human intestines produce characteristic intestinal sounds such as "gurgling" and "gurgling."

Here, it is thought that the emotional state of a person changes due to the movement of the human intestine. Therefore, the applicant investigated the relationship between the infant's bowel sounds and the infant's emotional state and found that there is a possibility that there is a certain relationship.

For example, in such a survey, users were asked about the number of times they cried at night, and the number of times bowel sounds such as "poko" or "guru" occurred in the sounds detected from the infant's abdomen within one minute was counted. . If the number of times the sound "poko" occurs is 5 or less, then the state of peristalsis, which is the state of intestinal movement, is in a "decreased" state, and if the number of times the sound "poko" is heard is 6 or more times, In some cases, the peristaltic state was "normal", and if the number of times a sound such as "poko" or "guru" occurred was 10 or more times, the peristaltic state was considered to be "enhanced". We then investigated the relationship between peristaltic status and the number of night cries.

For example, FIG. 2 is a first diagram showing an example of the survey results. In the example shown in FIG. 2, the horizontal axis represents the peristaltic state estimated from bowel sounds, and the vertical axis represents the number of night cries, and the relationship between the number of night cries and the peristaltic state of each infant is plotted. As shown in FIG. 2, it was found that the number of night cries tends to increase when the peristalsis is in an "enhanced" state than when the peristaltic state is "normal" or "decreased."

In addition, the user was similarly asked whether the patient was put to sleep smoothly, and the state of peristalsis was also examined. For example, FIG. 3 is a second diagram showing an example of the survey results. In the example shown in Figure 3, the horizontal axis represents the peristaltic state estimated from bowel sounds, and the vertical axis represents the evaluation value indicating whether putting the infant to sleep went smoothly or was difficult. The relationship between the two was plotted. As shown in FIG. 3, it was found that it was more difficult to put the patient to sleep when the peristalsis was in an "enhanced" state than when the peristaltic state was "normal" or "decreased."

In this way, it can be seen that the number of times a patient cries at night and the difficulty of putting her to sleep can be related to the state of peristalsis estimated from bowel sounds. Based on the results of such research, the applicant came up with the idea of detecting sounds from the abdomen of an infant and estimating the emotional state of the infant based on the characteristics of bowel sounds included in the detected sounds.

[1-2. About the estimation process]
Therefore, the information providing device 10 executes the following estimation process. First, the information providing device 10 acquires a sound detected from the abdomen of an infant, which is detected by a detection device attached to an article worn by the infant. The information providing device 10 then estimates the infant's emotional state based on the characteristics of the acquired sound.

Here, the infant's emotional state does not need to be clearly distinguishable, such as being in a "bad mood" or "being hungry." More specifically, the information providing device 10 determines whether certain events in child-rearing are likely to occur, such as whether or not it is easy to cry at night, or whether it is difficult to put the child to bed. , it is sufficient to estimate whether the person is in a state such as whether or not the person is in a state of feeling that makes it easy to carry out an event. In other words, the information providing device 10 may estimate whether the emotional state of the infant is related to the presence or absence of various events in childcare and the progress of events.

To give a more specific example, the information providing device 10 can determine whether the infant's emotional state, such as whether the infant is easily excreted or not, or whether the infant's emotional state is easy to show happy behavior, can be detected by any event. It may be estimated whether the condition is related to the presence or absence and progression of the condition.

As a result of such processing, the information providing device 10 can, for example, notify the user in advance that the infant is likely to cry at night or that it is difficult to put the infant to sleep. Therefore, the information providing device 10 can provide information useful for childcare that reduces the physical and mental burden on the user.

[1-3. Regarding an example of estimation processing]
An example of the estimation process will be described below with reference to FIG. For example, in the example shown in FIG. 1, an infant B1 is wearing an absorbent article D. Here, the absorbent article D may be any absorbent article that is used by infants, such as a tape-type diaper or a pant-type diaper that is worn using tape.

Here, a wearable device WD is attached to the absorbent article D as a detection device for detecting abdominal sounds of the infant B1. For example, the wearable device WD is an article that can be attached to or detached from any absorbent article D, and is attached to the absorbent article D so as to sandwich the ends of the waist.

An example of the wearable device WD will be described below with reference to FIGS. 4 to 6. FIG. 4 is a front view showing an example of the shape of the wearable device WD according to the embodiment. For example, in the wearable device WD, as shown in FIG. 4, a head part P1, a connecting part P2, and a rear part P3 are integrally formed of a soft and flexible material such as silicone resin.

The head part P1 has an opening H1 smaller than a sensor S, which will be described later, and is configured to be able to hold a sensor S, which will be described later, through the opening H1. Furthermore, magnets M1 and M2 are enclosed in the head part P1 and the rear part P3, which are arranged so that their magnetic poles with respect to the front are reversed. Therefore, the wearable device WD can be fixed to an object by bending the connection part P2 and sandwiching a part of the object between the head part P1 and the rear part P3.

FIG. 5 is a cross-sectional view showing an example of the shape of the wearable device WD according to the embodiment. Note that FIG. 5 shows an example of a cross-sectional view when the wearable device WD is cut along the line AA shown in FIG. 4.

As shown in FIG. 5, a sensor S for measuring abdominal sounds of an infant is enclosed in the head part P1 of the wearable device WD via an opening H1. For example, the sensor S has a main body made of various resins or metals, and is equipped with various microphones and various circuits for performing short-range wireless communication such as NFC (Near Field Communication). Note that the sensor S may be waterproof, and may be provided with a circuit for wireless power supply or a circuit or terminal for wired power supply. Such a sensor S is enclosed in the head part P1 of the wearable device WD via the opening H1.

Here, the opening H1 is provided so as to face the body side of the infant B1 when the connecting part P2 of the wearable device WD is bent. For example, FIG. 6 is a diagram showing an example of how the wearable device according to the embodiment is worn. For example, as shown in FIG. 6, by bending the wearable device WD so that the ends of the absorbent article D are sandwiched between the magnets M1 and M2, the electromagnetic EM generated by the magnets M1 and M2 moves the wearable device WD into the absorbent article. It is possible to fix it at D. At this time, the head part P1 in which the sensor S is enclosed is placed so as to be in contact with the body (for example, around the abdomen or side) of the infant B1 wearing the absorbent article D. As a result of this arrangement, the wearable device WD can appropriately measure the abdominal sounds of the infant B1. Note that the main body portion of the wearable device WD may be hollow or may be omitted.

Note that the configurations of the wearable device WD shown in FIGS. 4 to 6 are merely examples. For example, the wearable device WD may have a clip-shaped shape made of plastic. For example, the wearable device WD is equipped with a microphone in a range that comes into contact with the infant B1 when worn (e.g., the head part P1), and a microphone, such as NFC, is mounted in an area that does not come into contact with the infant B1 (e.g., the rear part P3). It may also be equipped with other functions. Further, the wearable device WD (or a sound collecting device such as a microphone) may be embedded in a portion of the absorbent article D such as a diaper that comes into contact with the abdomen of the infant.

Returning to FIG. 1, the explanation will be continued. Such a wearable device WD acquires the sound of the abdomen of the infant B1 (step S1). For example, the wearable device WD acquires the abdominal sounds of the infant B1 for a predetermined period of time (for example, one minute) at predetermined time intervals (for example, in units of several hours). Wearable device WD then retains audio information indicating the acquired audio in its own storage device.

Wearable device WD then provides audio information to terminal device 101 used by user U (step S2). For example, the wearable device WD transmits the voice information and body temperature information it holds to the terminal device 100 via short-range wireless communication or the like.

In such a case, the terminal device 100 transmits the audio information to the information providing device 10 (step S3). In such a case, the information providing device 10 acquires bowel sounds included in the audio information (step S4). The information providing device 10 then estimates the emotional state of the infant B1 from the characteristics of the bowel sounds (step S5). For example, the information providing device 10 estimates whether the emotional state of the infant B1 is such that it is easy to fall asleep. The information providing device 10 then provides information indicating the estimated state to the terminal device 100 (step S6).

In this way, the information providing device 10 estimates the emotional state of the infant B1 from the sound detected by the detection device attached to the absorbent article worn by the infant B1. As a result of such processing, the information providing device 10 can reduce the physical or mental burden of childcare on the user U, and can improve the quality of life.

[1-4. About wearable device WD]
Note that the information providing apparatus 10 acquires not only audio information indicating the sound detected by the wearable device WD, but also body temperature information indicating the infant's body temperature detected by the wearable device WD. For example, the wearable device WD has a sensor S equipped with a body temperature sensor that acquires sound and measures the body temperature of an infant, and transmits audio information indicating the detected sound and body temperature information indicating the detected body temperature to the terminal. It may also be transmitted to the information providing device 10 via the device 100.

In addition, the wearable device WD may include an acceleration sensor capable of detecting acceleration in each axial direction, and may output body movement information indicating the body movement of the infant. Such body movement information can be used to estimate various events related to infants, such as whether the infant is moving or not, and whether or not the infant is sleeping.

[2. Regarding an example of functional configuration]
An example of a functional configuration for realizing the above-described selection process will be described below. In the following description, an overview of the functional configuration of the information providing apparatus 10 will be described, and then an example of a process performed by the functional configuration of the information providing apparatus 10 will be described. In addition, in the following description, an example of the process when voice information and body temperature information are acquired from wearable device WD will be described.

[2-1. About the overview of the functional configuration of the terminal device 100]
FIG. 7 is a diagram illustrating an example of a functional configuration of a terminal device according to an embodiment. As shown in FIG. 7, the information providing device 10 includes a communication section 20, a storage section 30, and a control section 40.

The communication unit 20 is connected to the network N by wire or wirelessly, and transmits and receives information to and from the terminal device 100. For example, the communication unit 20 is realized by a communication circuit or the like.

The storage unit 30 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk, and various data for executing output processing is registered. be done. For example, in the example shown in FIG. 2, a wearer database 31, a user database 32, and a model database 33 are registered in the storage unit 30.

In the wearer database 31, information regarding a wearer (that is, an infant) who wears the absorbent article D is registered. That is, information on users whose emotional states are to be estimated is registered in the wearer database 31. For example, FIG. 8 is a diagram showing an example of information registered in the wearer database according to the embodiment. As shown in FIG. 8, in the wearer database 31, a wearer ID (Identifier), a responder ID, characteristic information, estimation results, and sensor information are registered in association with each other. Here, information having items such as date and time, body temperature information (temperature), and voice information is registered in the wearer database 31 as sensor information. In addition to the information shown in FIG. 8, the wearer database 31 may also register various sensor data acquired from the wearer and information regarding the wearer.

Here, the "wearer ID" is an identifier for identifying the wearer. Further, the "responder ID" is an identifier for identifying a user who performs various actions toward the wearer, such as exchanging absorbent articles, and is, for example, a user ID described later. Further, "characteristic information" is information indicating the characteristics of the intestinal sounds included in the audio information, and is, for example, information indicating the peristaltic state of the intestines indicated by the intestinal sounds. Further, the "estimation result" is information indicating the emotional state of the infant estimated from the intestinal sounds through the estimation process.

Further, the "date and time" is information indicating the date and time when the body temperature indicated by the body temperature information and the voice indicated by the voice information were detected, and is, for example, information indicating the date and time of detection. Moreover, "body temperature information" is information indicating the wearer's body temperature (for example, degrees Celsius) detected by the sensor S. Further, "audio information" is information indicating the sounds of the infant's abdomen detected by the sensor S.

For example, in the example shown in FIG. 8, the wearer database 31 corresponds to the wearer ID "UID#1", the responder ID "U#1", the characteristic information "enhancement", and the estimation result "night crying: a lot". It is registered with. Such information indicates that the user who performs various actions toward the wearer indicated by the wearer ID "UID#1" is the user indicated by the responder ID "U#1" and is detected from the wearer's abdomen. For example, the intestinal state that can be inferred from the characteristics of the bowel sounds is "active," and the estimated emotional state is an emotional state where "night crying" is "profuse." Indicate that something is true.

In the example shown in FIG. 8, the wearer database 31 includes, for the wearer ID "UID#1", the date and time "2019/05/01/10:15:25", body temperature information "37.2", Audio information "Voice #1-1" is registered in association. Such information indicates that the body temperature of the wearer indicated by the wearer ID "UID #1" measured at 10:15:25 on May 1, 2019 was "37.2" degrees, and the acquired abdominal temperature was "37.2" degrees. Indicates that the sound is "Voice #1-1".

In the example shown in FIG. 8, conceptual information such as "audio #1-1" is shown, but in reality, various PCM (Pulse Code Modulation) modulated sound data and irreversibly compressed audio Various audio data obtained by converting the sound detected by the sensor S in a reversible compressed audio format or a reversible compressed audio format will be registered.

Information regarding users who perform various actions toward the wearer is registered in the user database 32. For example, FIG. 9 is a diagram showing an example of information registered in the user database according to the embodiment. As shown in FIG. 9, information such as a user ID, terminal information, and related information is registered in the user database 32. In addition to the information shown in FIG. 9, the user database 32 may also register any information regarding users who perform various actions toward the wearer.

Here, the "user ID" is an identifier for identifying a user. Moreover, "terminal information" is information for identifying the terminal device 100 used by the user indicated by the associated user ID. Moreover, "relationship information" is information which shows the relationship between the user indicated by the matched user ID, and the wearer indicated by the wearer ID linked with the user ID.

For example, in the example shown in FIG. 9, information such as user ID "U#1", terminal information "T#1", and related information "mother" are registered in the user database 32 in association with each other. Such information indicates that the user indicated by the user ID "U#1" is using the terminal device 100 indicated by the terminal information "T#1". In addition, such information is provided by the user indicated by the user ID "U#1" and the wearer ID "UID#1" associated with the user ID "U#1" in the wearer database 31. Indicates that she is the wearer's "mother."

A model for estimating the emotional state of an infant based on sounds detected from the abdomen of the infant is registered in the model database 33. For example, when audio data of sounds detected from the abdomen of an infant who cries frequently at night is input to the model database 33, a model trained to output information indicating that the infant cries frequently at night is registered. . Note that the model database 33 is assumed to have registered various parameters constituting the model, and illustration thereof will be omitted.

Note that any type of model can be adopted as such a model. For example, the information providing device 10 may employ SVM (Support Vector Machine) or DNN (Deep Neural Network) as a model. Here, the DNN may be a CNN (Convolutional Neural Network) or an RNN (Recurrent Neural Network). Further, the RNN may be LSTM (Long short-term memory) or the like. Further, the model may be realized by combining a plurality of models, such as a model combining CNN and RNN. Further, an example of such a model learning method will be described later. Note that when using such a learning model to estimate or predict an infant's emotions, such as those who cry frequently at night, it is preferable to accept input from the user as to whether the estimation or prediction is correct or incorrect. Thereby, the learning model can be updated using the input correctness or incorrectness.

Returning to FIG. 7, the explanation will be continued. The control unit 40 is, for example, an arithmetic processing device for executing various types of processing, and is, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), etc., and a predetermined storage device (for example, the storage unit 30). This is realized by executing various programs (corresponding to an example of an output program) stored in the RAM using the RAM as a work area. Further, the control unit 80 may be realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

In the example shown in FIG. 7, the control unit 40 includes an acquisition unit 41, an estimation unit 42, a specification unit 43, a provision unit 44, and a learning unit 45, and executes information processing described below.

[2-2. About information processing]
An example of information processing executed by the control unit 40 will be described below with reference to FIG. 10. FIG. 10 is a flowchart illustrating an example of the flow of processing executed by the information providing apparatus according to the embodiment.

For example, the acquisition unit 41 determines whether it is a predetermined processing timing (step S101). For example, when receiving various sensor information such as voice information and body temperature information from the terminal device 100, the acquisition unit 41 determines that it is processing timing. Then, if it is not the predetermined processing timing (step S101: No), the acquisition unit 41 waits until the predetermined processing timing. Then, if it is the predetermined processing timing (step S101: Yes), the acquisition unit 41 acquires the voice information and body temperature information from the terminal device 100 (step S102).

Here, the acquisition unit 41 acquires audio information indicating the sound of the infant's abdomen detected by a detection device attached to an article worn by the infant, and body temperature information indicating the body temperature of the infant. For example, the acquisition unit 41 acquires audio information and body temperature information from a wearable device WD attached to sandwich the end of the waist circumference of the absorbent article D. As a result, the acquisition unit 41 acquires various intestinal sounds such as the sounds produced when the infant's intestines undergo peristaltic movement, the sounds produced when the intestines make syllable movements, or the sounds produced when the infant's intestines make pendulum movements. The acquisition unit 41 then registers the acquired sensor information in the wearer database 31.

The estimation unit 42 identifies the characteristics of the intestinal sounds included in the audio information (step S103). Then, the estimation unit 42 estimates the emotional state of the infant based on the characteristics of the intestinal sounds (step S104). For example, the estimation unit 42 estimates the peristaltic state of the infant's intestines based on the characteristics of the acquired sound, and estimates the emotional state of the infant based on the estimated peristaltic state. More specifically, the estimating unit 42 estimates whether the peristalsis state is an increased state, a decreased state, or a normal state based on the bowel sounds, and based on the estimation result, determines whether it is easy to fall asleep or not. Estimating the emotional state of infants, such as whether they are easy to act or not.

For example, the estimation unit 42 estimates the emotional state of the infant based on the number of sounds having predetermined characteristics. To give a more specific example, the estimation unit 42 uses various voice recognition techniques to extract voices such as "poco" and "guru" from the voices indicated by each voice information registered in the wearer database 31. , and the number of extracted voices, that is, voices having predetermined characteristics, is counted. Next, the estimation unit 42 specifies whether the infant's intestinal condition is "promoted", "normal", or "decreased" based on the number of times each voice is heard. Then, the estimating unit 42 estimates whether the infant's emotional state is such that the baby cries less at night or cries more at night, based on the identified intestinal state. Thereafter, the estimation unit 42 registers the information indicating the state of the intestine as characteristic information in the wearer database 31 together with the estimation result.

Note that the estimation unit 42 may estimate the emotional state of the infant based on any conditions other than the estimation method described above. For example, the estimation unit 42 may estimate the emotional state of the infant based on the frequency of sounds having predetermined characteristics. For example, the estimation unit 42 identifies sounds having predetermined characteristics among the intestinal sounds, and calculates the number of times the identified sounds occur within a predetermined period (for example, 1 minute) as the frequency. Depending on the calculated frequency, it may be estimated whether the infant is in a state where the infant cries frequently at night.

Furthermore, the estimation unit 42 may estimate the emotional state of the infant based on the type of the acquired sound. For example, the estimation unit 42 separately counts the number of times a sound such as "poko" occurs and the number of times a sound such as "guru" occurs, and determines the emotional level of the infant according to the number of times each counted sound occurs. The state may be estimated. For example, the estimating unit 42 estimates that if there are many sounds such as "poko", it means that the person has a lot of night crying, etc., and if there are many sounds such as "guru", it means that the person is having trouble falling asleep, etc. Different states may be estimated depending on the type.

Note that bowel sounds are estimated to indicate not only the emotional state of the infant but also the infant's state regarding excretion. For example, similar to the emotional state mentioned above, we investigated the relationship between the state of intestinal peristalsis (i.e., normal, decreased, or increased) estimated from bowel sounds and the frequency of bowel movements. It was found that the amount of excrement tends to be larger when peristalsis is enhanced than when peristalsis is normal or decreased. Therefore, the estimating unit 42 may further estimate the state regarding excretion, such as whether there is a lot of excrement, from the characteristics of the bowel sounds.

Note that the estimating unit 42 estimates not only the amount of excrement but also the condition of the excrement (for example, whether it is hard or soft stool) and the time of day when excretion is to be performed. Good too. For example, if the estimation unit 42 detects a bowel sound having predetermined characteristics based on the relationship between the characteristics of each infant's bowel sounds identified in advance and the time period in which the infant defecated, may estimate the time period corresponding to the detected bowel sounds as the time period for defecation.

Note that the various estimations described above may be realized on a rule basis or by processing using various models. For example, the information providing device 10 collects abdominal sounds detected from each infant, information indicating each infant's amount of night crying, ease of falling asleep, time of defecation, mode of defecation, and the like. Then, the information providing device 10 uses various pattern recognition techniques to identify patterns between bowel sounds and the infant's emotional state or excretion-related state, and based on the identified pattern, the information providing device 10 uses a variety of pattern recognition techniques to Then, the estimation described above may be performed.

For example, the information providing device 10 reads out from the model database 33 a model that has been trained to output information indicating emotional states and excretion-related states based on abdominal sounds through a learning process to be described later. Then, the estimating unit 42 may input the detected intestinal sounds to the model and use the information outputted by the model as various estimation results. After that, the estimation unit 42 registers the estimation result in the wearer database 31.

Here, in order to promote the growth of infants, it is considered effective to maintain the sleep rhythm of infants. Therefore, it is believed that if the appropriate time for infants to fall asleep is detected and the detected information is provided to users, it will be possible to encourage infants to sleep in an appropriate rhythm and promote their development. It will be done. Therefore, the specifying unit 43 specifies an appropriate time for falling asleep, which is a time period suitable for falling asleep, based on the periodicity of body temperature (step S105).

For example, when an infant falls asleep, it is estimated that the infant's body movements decrease, and the infant's body temperature gradually increases toward the time of falling asleep, and after falling asleep, the infant's body temperature gradually decreases. Additionally, infants are generally considered to sleep at night. Therefore, the specifying unit 43 specifies the infant's sleep pattern and appropriate sleep onset time based on the periodicity of body temperature indicated by the body temperature information and the maximum value of body temperature.

For example, the specifying unit 43 specifies the cycle of body temperature fluctuation indicated by the body temperature information every 24 hours. Then, the identifying unit 43 determines that the infant has fallen asleep at the timing when the maximum value of body temperature during the night is measured. Further, the identification unit 43 may determine that the infant has woken up at a timing when the rate of increase in body temperature in the morning exceeds a predetermined threshold. Then, the specifying unit 43 specifies the infant's sleeping pattern from the average bedtime and wake-up time.

Further, the specifying unit 43 specifies a pattern of time periods in which the infant falls asleep as an appropriate time for falling asleep. For example, the specifying unit 43 may determine, based on the periodicity and maximum value of body temperature, that a predetermined time before the maximum value is the appropriate time to fall asleep. That is, the specifying unit 43 may specify an appropriate time period for putting an infant to sleep based on the periodicity or maximum value of body temperature.

Further, the identifying unit 43 may determine the infant's sleep by considering the infant's body movements. For example, the identifying unit 43 determines that the infant has fallen asleep at the timing when the maximum value of the body temperature is measured in the periodicity of the body temperature indicated by the body temperature information and the body movement indicated by the body movement information becomes equal to or less than a predetermined threshold. You may. Furthermore, if the body movement exceeds a predetermined threshold at the time determined to be the appropriate time to fall asleep, it may be determined that a notification or information to encourage falling asleep is to be provided. That is, when the body movement indicated by the body movement information satisfies a predetermined condition at the appropriate time for falling asleep determined from the periodicity and maximum value of body temperature, the identifying unit 43 determines that appropriate sleep onset is not performed. Good too. Further, similar to the appropriate time for falling asleep, the specifying unit 43 may specify a pattern of time slots in which infants wake up (wake-up pattern) and an appropriate wake-up time that is an appropriate time slot for waking up.

The providing unit 44 provides information corresponding to the estimated emotional state and appropriate time for falling asleep (step S106). For example, the providing unit 44 may provide information indicating recommended behavior to a user who has a predetermined relationship with an infant, depending on the emotional state. For example, the providing unit 44 may notify the user to refrain from providing breast milk when the estimated cause of the emotional state is estimated to be overfeeding of breast milk. Furthermore, when it is estimated that it is difficult to go to bed, the providing unit 44 may provide web content that shows music, lighting conditions, etc. that are easy to induce sleep.

Further, the providing unit 44 may provide information that visually indicates a sleeping pattern, an appropriate time to fall asleep, an appropriate time to wake up, etc., or may provide information corresponding to an estimated state regarding excretion. For example, FIG. 11 is a diagram illustrating an example of provided information provided by the information providing device according to the embodiment. For example, as shown in FIG. 11, the providing unit 44 determines the appropriate time for the infant to wake up and the appropriate time for the infant to wake up based on the sleeping pattern, appropriate time for falling asleep, appropriate time for waking up, etc. specified by the specifying unit 43. Providing information C10 is generated that indicates a time period in which infants are likely to fall asleep (i.e., wake-up timing), a time period suitable for infants to fall asleep, and a time period in which infants are likely to go to bed (i.e., bedtime timing). For example, when the estimation unit 42 estimates that the infant's emotional state is “likely to cry at night,” the providing unit 44 may provide an icon indicating that the infant is “likely to cry at night” as a night crying forecast. Provided information C10 indicating text is generated. In addition, if the estimation unit 42 estimates that the infant's emotional state is that it will be difficult to get the infant to sleep, an icon or text indicating that it will take a long time to sleep is used as a night crying forecast. Providing information C10 indicating the information is generated.

Furthermore, when the excretion time slot estimated by the estimating unit 42 is "morning", the providing unit 44 generates provision information C10 indicating that there is a possibility of defecating in the "morning". In addition to the information shown in FIG. 11, the providing unit 44 may also provide information indicating various excretion-related states, such as whether the stool is soft or hard, the amount of excretion, and the like. Further, the providing unit 44 may provide information on absorbent articles corresponding to such excretion-related conditions. For example, when there is a high possibility that the infant's excrement will be loose stool, the providing unit 44 may provide information C10 that encourages the use of an absorbent article that has a function of preventing leakage of loose stool.

Next, the learning process executed by the learning unit 45 will be explained. For example, the learning unit 45 acquires the abdominal sounds of each infant and transmits a questionnaire requesting input of the state to be estimated through a terminal device used by the parent of each infant. The learning unit 45 then receives inputs such as whether or not the person cries a lot at night, whether or not it is difficult to go to bed, the time of defecation, various states related to defecation, and the like. In addition to these, the learning unit 45 may also receive input of information indicating the emotional state of the infant to be estimated. For example, the learning unit 45 accepts inputs such as whether the infant performed predetermined actions, such as whether the infant disliked food, whether the infant disliked being held, whether the infant threw something, and whether the infant disliked the infant.

The learning unit 45 then learns the model so that when inputting the abdominal sounds of a certain infant, it outputs information indicating the behavior that has been input from the parent. A model is learned that estimates whether the user is in the mood to perform a certain action or not, and whether the user is in the mood to dislike a certain action. Note that various arbitrary learning methods such as back propagation can be used for learning such a model.

Note that the learning unit 45 may input any information corresponding to the sound of the abdomen of the infant. For example, the learning unit 45 may input intestinal sounds extracted from the abdomen of an infant, or may input only sounds having predetermined characteristics among the intestinal sounds. Further, the learning unit 45 may input the number, frequency, type, etc. of sounds having predetermined characteristics, or may input information indicating the peristaltic state of the intestine estimated from these. By receiving such information as input, the learning unit 45 estimates whether or not the infant has the emotion to perform a predetermined action, the state of excretion, etc. from the various sounds and information based on the sounds described above. The model can be trained. The learning unit 45 then registers the learned model in the model database 33.

[3. Regarding processing variations]
Hereinafter, variations of the above-mentioned processing will be explained. Note that the output processing described below may be performed individually or in any combination.

[3-1. Regarding processing that takes into account the QOL of parents]
As described above, the sounds of the infant's abdomen can be said to be useful information for estimating the infant's emotional state and state regarding excretion. Here, if the infant's emotional state and excretion-related state are estimated, it is possible to appropriately respond to the infant's behavior and improve the infant's quality of life. Furthermore, such estimation results can reduce the burden required to care for infants and children, and are therefore considered to be able to improve the quality of life of parents who take care of infants.

Therefore, the information providing device 10 may estimate the emotional state regarding the quality of life of the infant or the user who has a predetermined relationship with the infant. For example, when the information providing device 10 inputs the abdominal sounds of an infant, the information providing device 10 performs model learning so as to output a score indicating the quality of life of the infant and the parent thereafter. Various emotional states of an infant related to quality of life may be estimated based on fluctuations in scores output when the abdominal sounds of a certain infant are input. For example, if the score indicating the quality of life is continuously decreasing, the information providing device 10 may provide a message such as "Let's reconsider how you deal with babies" so that the score continues to decrease. Users may be guided to reconsider their handling of infants and young children in order to improve their performance.

[3-2. About the executing body]
In the above description, the terminal device 100 acquires the sensor information detected by the wearable device WD, the information providing device 10 acquires the sensor information from the terminal device 100, and the information providing device 10 performs various processes. The estimation process described above was realized. However, embodiments are not limited thereto.

For example, all or part of the various processes executed by the information providing apparatus 10 described above may be executed on the terminal device 100 side. For example, the terminal device 100 includes an acquisition unit 41, an estimation unit 42, a specification unit 43, and a provision unit 44 shown in FIG. Emotional state estimation may also be made. Further, the terminal device 100 may register various types of information in a storage device within the terminal device 100, or may register it in a storage area on various networks such as a cloud server, for example.

[3-3. About applicable targets]
In the example described above, the information providing device 10 estimates the emotional state of the infant from the sensor information detected by the wearable device WD attached to the absorbent article worn by the infant. However, the embodiment is limited to this. It is not something that will be done. For example, the information providing device 10 uses sensor information detected by a wearable device WD attached to an absorbent article or clothing worn by a cared person who needs care to estimate the emotional state of the cared person. You may go.

[3-4. others〕
Note that among the above-described processes, all or part of the processes described as being performed automatically may be performed manually. Further, all or part of the processing described as being performed manually may be performed automatically by a known method. In addition, information including the processing procedures, specific names, and various data and parameters shown in the above documents and drawings may be changed arbitrarily, unless otherwise specified. For example, the various information shown in each figure is not limited to the illustrated information.

Furthermore, each component of each device shown in the drawings is functionally conceptual, and does not necessarily have to be physically configured as shown in the drawings. That is, the specific form of distributing and integrating each device is not limited to what is illustrated. In addition, all or part of each component may be functionally or physically distributed and integrated in arbitrary units depending on various loads and usage conditions. Furthermore, the above-described processes may be executed in combination as appropriate to the extent that they do not contradict each other.

[4. Hardware configuration]
Further, the information providing apparatus 10 according to the embodiment described above is realized by, for example, a computer 1000 having a configuration as shown in FIG. 12. FIG. 12 is a diagram showing an example of the hardware configuration. The computer 1000 is connected to an output device 1010 and an input device 1020, and has an arithmetic device 1030, a cache (primary storage device) 1040, a memory (secondary storage device) 1050, an output IF (Interface) 1060, an input IF 1070, and a network IF 1080 connected to a bus. 1090.

The arithmetic unit 1030 operates based on programs stored in the cache 1040 and memory 1050, programs read from the input device 1020, and performs various processes. The cache 1040 is a cache, such as a RAM, that temporarily stores data used by the arithmetic unit 1030 for various calculations. Further, the memory 1050 is a storage device in which data used by the arithmetic unit 1030 for various calculations and various databases are registered, and is realized by ROM (Read Only Memory), HDD (Hard Disk Drive), flash memory, etc. It is a memory that

The output IF 1060 is an interface for transmitting information to be output to an output device 1010 that outputs various information such as a monitor or a printer, and is, for example, a USB (Universal Serial Bus), a DVI (Digital Visual Interface), It may be realized by a connector of a standard such as HDMI (registered trademark) (High Definition Multimedia Interface). On the other hand, the input IF 1070 is an interface for receiving information from various input devices 1020 such as a mouse, a keyboard, and a scanner, and is realized by, for example, a USB or the like.

For example, the input device 1020 may be an optical recording medium such as a CD (Compact Disc), a DVD (Digital Versatile Disc), or a PD (Phase change rewritable disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, It may be realized by a device that reads information from a magnetic recording medium, a semiconductor memory, or the like. Further, the input device 1020 may be realized by an external storage medium such as a USB memory.

The network IF 1080 has a function of receiving data from other devices via the network N and sending it to the computing device 1030, and also transmitting data generated by the computing device 1030 to the other devices via the network N.

Here, the arithmetic device 1030 controls the output device 1010 and the input device 1020 via the output IF 1060 and the input IF 1070. For example, the arithmetic device 1030 loads a program from the input device 1020 or the memory 1050 onto the cache 1040, and executes the loaded program. For example, when the computer 1000 functions as the information providing device 10, the arithmetic unit 1030 of the computer 1000 realizes the functions of the control unit 140 by executing a program loaded onto the cache 1040. Further, when the computer 1000 functions as the terminal device 100, the arithmetic unit 1030 of the computer 1000 acquires various sensor information from the wearable device WD by executing a program (application) loaded on the cache 1040, A function that realizes a function of transmitting sensor information to a computer functioning as an information providing device 10, and a function of displaying various types of provided information such as an estimation result of an infant's emotional state provided by the information providing device 10 on a screen. This will be realized.

That is, the applied system includes programs installed in various information processing devices such as the information providing device 10 and applications installed in the terminal device 100. The application installed in such a terminal device 100 includes an acquisition procedure for acquiring sounds detected from the abdomen of an infant by a detection device (for example, a wearable device WD) attached to an article worn by the infant, and an information processing device. This causes the terminal device 100 to perform an output procedure for outputting the estimation result of the infant's emotional state transmitted from the terminal device 100. Further, the program installed in such an information processing device causes the information processing device to execute an estimation procedure for estimating the emotional state of the infant based on the characteristics of the sound acquired by the terminal device 100. Become.

[5. effect〕
As described above, the information providing device 10 estimates the emotional state of the infant based on the sounds of the infant's abdomen detected by the detection device attached to the article worn by the infant. For example, the information providing device 10 determines the emotional state of the infant, such as whether the infant is prone to crying at night or falling asleep easily, based on the characteristics of bowel sounds and the type, number, frequency, etc. of characteristic sounds. Estimate whether the person is in a state where it is easy to take various actions.

When the results of such estimation processing are provided to a user who takes care of an infant, the user can prepare and provide various responses in advance based on the infant's emotional state. It can reduce physical and mental burden and improve quality of life. Therefore, the information providing device 10 can provide useful information regarding childcare.

The embodiments of the present application have been described above in detail based on the drawings. However, these are merely examples, and the embodiments of the present application may be implemented in other forms with various modifications and improvements based on the knowledge of those skilled in the art, including the embodiments described in the disclosure section of the invention. is possible. Further, the above-mentioned "section, module, unit" can be read as "means", "circuit", etc.

10 information providing device 20 communication unit 30 storage unit 31 wearer database 32 user database 33 model database 40 control unit 41 acquisition unit 42 estimation unit 43 identification unit 44 provision unit 45 learning unit 100 terminal device WD wearable device

Claims (20)

an acquisition unit that acquires abdominal sounds inside the infant's body detected by a detection device attached to an article worn by the infant;
An estimating device comprising: an estimating section that estimates the emotional state of the infant based on the characteristics of the sound acquired by the acquiring section. The acquisition unit acquires abdominal sounds inside the infant's body , such as sounds generated when the infant's intestines make peristaltic movements, sounds generated when the infant's intestines make syllable movements, or sounds generated when the infant's intestines make pendulum movements. The estimation device according to claim 1, characterized in that: 3. The estimation unit estimates the emotional state of the infant based on the number of sounds having a predetermined characteristic among the sounds acquired by the acquisition unit. estimation device. The estimating unit estimates the emotional state of the infant based on the frequency of sounds having predetermined characteristics among the sounds acquired by the acquiring unit. The estimation device according to any one of the above. The estimation device according to any one of claims 1 to 4, wherein the estimation unit estimates the emotional state of the infant based on the type of sound acquired by the acquisition unit. . The estimation unit estimates the peristaltic state of the infant's intestines based on the characteristics of the sound acquired by the acquisition unit, and estimates the emotional state of the infant based on the estimated peristaltic state. The estimation device according to any one of claims 1 to 5, characterized in that: The estimation unit estimates whether the peristalsis state is an enhanced state, a decreased state, or a normal state, and estimates the emotional state of the infant based on the estimation result. 6. The estimation device according to 6. The estimation according to any one of claims 1 to 7, wherein the estimation unit estimates whether or not the infant is in an emotional state in which it is easy to fall asleep, as the emotional state of the infant. Device. 9. The estimation unit estimates, as the emotional state of the infant, whether or not the infant is in an emotional state where the infant is likely to cry at night. Estimation device. The estimation unit estimates, as the emotional state of the infant, an emotional state related to the quality of life of the infant or a user who has a predetermined relationship with the infant. The estimation device according to any one of them. The estimating device according to any one of claims 1 to 10, further comprising a providing section that provides information according to the emotional state estimated by the estimating section. The estimation according to claim 11, wherein the providing unit provides information indicating recommended behavior to a user who has a predetermined relationship with the infant according to the emotional state. Device. The acquisition unit further acquires body temperature information indicating the body temperature of the infant detected by the detection device,
The estimation device according to claim 11 or 12, wherein the providing unit further provides information according to periodicity of body temperature indicated by the body temperature information. 14. The providing unit provides information indicating the bedtime of the infant or the wake-up time of the infant specified based on the periodicity of body temperature indicated by the body temperature information. Estimation device. The estimating unit further estimates a state regarding excretion of the infant based on the characteristics of the sound,
The estimating device according to any one of claims 11 to 14, wherein the providing unit further provides information according to the state regarding excretion estimated by the estimating unit. The estimating unit estimates a time period in which the infant excretes based on the infant's excretion-related condition,
The estimating device according to claim 15, wherein the providing unit provides information indicating the time zone estimated by the estimating unit. Any one of claims 1 to 16, wherein the acquisition unit acquires the sound detected by a detection device attached to sandwich an end of the waist of the absorbent article worn by the infant. 1. Estimation device according to item 1. An estimation method executed by an estimation device,
an acquisition step of acquiring abdominal sounds inside the infant's body detected by a detection device attached to an article worn by the infant;
and an estimation step of estimating the emotional state of the infant based on the characteristics of the sound acquired in the acquisition step. an acquisition procedure for acquiring abdominal sounds inside the infant's body detected by a detection device attached to an article worn by the infant;
an estimation procedure for estimating the emotional state of the infant based on the characteristics of the sound acquired by the acquisition procedure; and an estimation program for causing a computer to execute the following. A system including a program installed in an information processing device and an application installed in a terminal device,
The application is
an acquisition procedure for acquiring abdominal sounds inside the infant's body detected by a detection device attached to an article worn by the infant;
an output procedure for outputting an estimation result of the emotional state of the infant transmitted from the information processing device;
cause the terminal device to execute
The system is characterized in that the program causes the information processing device to execute an estimation procedure for estimating the emotional state of the infant based on the characteristics of the sound acquired by the terminal device.

Images