JP6020027B2 - Intravesical urine volume estimation device, intravesical urine volume estimation method, and program - Google Patents

Description

  The present disclosure relates to an intravesical urine volume estimation device and an intravesical urine volume estimation method that estimate the intravesical urine volume.

  2. Description of the Related Art Conventionally, a food utensil provided with a food and beverage contact portion that comes into contact with food and drink, and a holding portion for a user to hold, motion detection means for detecting the movement of the meal utensil, and time information A technique for obtaining information serving as an index of how to eat using the movement of the eating utensil detected by the movement detecting means and the time information about the meal measured by the time measuring means. (For example, refer to Patent Document 1).

JP 2006-239272 A

  By the way, in order to estimate the urine volume in the user's bladder, a method using an abdominal ultrasonography or a skin resistance measurement method can be considered.

  Therefore, the disclosed technique aims to provide a bladder urine volume estimation device, a bladder urine volume estimation method, and the like that can estimate a user's bladder urine volume with a simple configuration.

According to one aspect of the present disclosure, an acceleration sensor worn on a user's hand;
Based on the output signal of the acceleration sensor, the moisture contained in the container by the user is grasped by hand, and the oral water intake when ingested from the mouth is estimated. Based on this, there is provided an intravesical urine volume estimation device comprising a processing device that estimates the urinary bladder volume of the user.

  According to the technique of the present disclosure, a bladder urine volume estimation device, a bladder urine volume estimation method, and the like that can estimate a user's bladder urine volume with a simple configuration can be obtained.

It is a figure which shows an example of the urinary bladder volume estimation apparatus. 1 is a diagram illustrating an example of a schematic configuration of a sensor device 10. FIG. It is a figure which shows an example of the definition of the axial direction of the acceleration sensor. 2 is a diagram illustrating an example of a hardware configuration of a processing apparatus 100. FIG. 3 is a functional block diagram illustrating an example of functions of the processing apparatus 100. FIG. 4 is a flowchart illustrating an example of a user profile generation process executed by a user profile generation unit 110. It is a figure which shows an example of the acceleration signal waveform from the acceleration sensor 12 at the time of drink action. It is the figure which extracted the waveform GX in FIG. It is the figure which extracted the waveform GY in FIG. It is a figure which shows another example of the acceleration signal waveform from the acceleration sensor 12 at the time of drink action. It is the figure which extracted the waveform GY in FIG. It is a figure which shows an example of the angular velocity signal waveform from the gyro sensor 14 at the time of drink action. It is a figure which shows an example of the acceleration signal waveform from the acceleration sensor 12 at the time of the drink action by the container containing a small quantity (50 ml) drink. It is a figure which shows an example of the acceleration signal waveform from the acceleration sensor 12 at the time of the drink action by the container in which a large quantity (1000 ml) drink entered. It is a figure which shows the vibration integrated value based on the triaxial synthetic | combination acceleration of the acceleration signal waveform shown to FIG. 13A. It is a figure which shows the vibration integrated value based on the triaxial synthetic | combination acceleration of the acceleration signal waveform shown to FIG. 13B. It is a figure which shows an example of the area S used as the parameter | index of the increase pattern of a vibration integrated value. It is a flowchart (the 1) which shows an example of the oral water intake estimation process performed by the oral water intake estimation part 112. It is a flowchart (the 2) which shows the continuation of the oral water intake estimation process shown in FIG. 7 is a flowchart illustrating an example of a urination amount estimation process executed by a urination amount estimation unit. 5 is a flowchart illustrating an example of an environmental temperature / humidity recording process executed by an environmental temperature / humidity recording unit. 7 is a flowchart illustrating an example of intravesical urine volume estimation processing executed by an intravesical urine volume estimation unit 118.

  Hereinafter, embodiments will be described in detail with reference to the accompanying drawings.

  FIG. 1 is a diagram illustrating an example of an intravesical urine volume estimation device 1.

  The intravesical urine volume estimation device 1 includes a processing device 100 and a sensor device 10.

  The processing apparatus 100 may be configured by an arbitrary form of computer. Various functions (including functions described below) of the processing device 100 may be realized by arbitrary hardware, software, firmware, or a combination thereof. For example, any or all of the functions of the processing apparatus 100 may be realized by an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or the like. Further, the processing device 100 may be realized by a plurality of processing devices. In the example illustrated in FIG. 1, the processing apparatus 100 is in the form of a server (host computer) located on the cloud 2.

  The sensor device 10 has any form that can be worn on the wrist of the user. In the illustrated example, the sensor device 10 has the form of a wristwatch and can be attached to the user's wrist by a belt. The sensor device 10 can communicate with the processing apparatus 100 via a wireless communication network. For example, the sensor device 10 may perform wireless communication with the processing apparatus 100 based on standards such as Bluetooth (registered trademark) and WiMAX (Worldwide Interoperability for Microwave Access).

  As will be described later, the sensor device 10 acquires user's daily behavior data and transmits the acquired daily behavior data to the processing device 100. As illustrated in FIG. 1, the sensor device 10 may directly transmit daily behavior data to the processing device 100 or may transmit the daily behavior data to the processing device 100 via another communication terminal 30 such as a smartphone.

  In addition, the intravesical urine volume estimation device 1 may include a management computer 20. The management computer 20 is a computer used by an administrator who should manage and monitor user behavior and the like. The management computer 20 may be configured by any form of computer. Note that the processing apparatus 100 described below may be realized by the management computer 20. That is, the management computer 20 can function as the processing device 100.

  Hereinafter, as an example, it is assumed that the user is an elderly person who lives in a nursing facility such as a nursing home. In this case, the management computer 20 is arranged in a care facility, and a doctor or a caregiver is assumed as a manager.

  FIG. 2 is a diagram illustrating an example of a schematic configuration of the sensor device 10.

  As shown in FIG. 2, the sensor device 10 includes an acceleration sensor 12, a gyro sensor 14, and a communication unit 16.

  The acceleration sensor 12 preferably detects triaxial acceleration, that is, triaxial acceleration perpendicular to each other. The three axes of the acceleration sensor 12 may be fixed with respect to the housing of the sensor device 10 or may be variable. The acceleration sensor 12 may be disposed inside the sensor device 10.

  The gyro sensor 14 may detect the angular velocity using a common coordinate system with the acceleration sensor 12. That is, the gyro sensor 14 may detect angular velocities around the three axes common to the acceleration sensor 12. The gyro sensor 14 may be disposed inside the sensor device 10.

  The communication unit 16 transmits output signals (daily activity data) from the acceleration sensor 12 and the gyro sensor 14 to the processing device 100. Each output signal from the acceleration sensor 12 and the gyro sensor 14 may be transmitted to the processing device 100 in real time. At this time, the output signals from the acceleration sensor 12 and the gyro sensor 14 may be transmitted to the processing apparatus 100 after undergoing a predetermined process (for example, a filter process).

  FIG. 3 is a diagram illustrating an example of the definition of the axial direction of the acceleration sensor 12. Here, as an example, as shown in FIG. 3, the X-axis corresponds to the longitudinal direction of the user's hand (the direction from the elbow to the wrist is the positive direction), and the Y-axis is the palm when the palm is opened. Corresponding to the vertical direction (the direction from the thumb to the little finger, that is, the downward direction is the positive direction) when the hand is straightened to the front, the Z direction is substantially perpendicular to the palm when the palm is opened. Corresponds to the direction. Here, the three axes of the acceleration sensor 12 are fixed to the user's wrist. However, the acceleration sensor 12 may include a mechanism such that the Y-axis is always directed in the direction of gravity regardless of the hand state. That is, the three axes of the acceleration sensor 12 may only allow the user to rotate around the Z axis (rotation in the XY plane) with respect to the wrist.

  FIG. 4 is a diagram illustrating an example of a hardware configuration of the processing apparatus 100.

  In the example illustrated in FIG. 4, the processing device 100 includes a control unit 101, a main storage unit 102, an auxiliary storage unit 103, a drive device 104, a network I / F unit 106, and an input unit 107.

  The control unit 101 is an arithmetic device that executes a program stored in the main storage unit 102 or the auxiliary storage unit 103, receives data from the input unit 107 or the storage device, calculates, processes, and outputs the data to the storage device or the like. To do.

  The main storage unit 102 is a ROM (Read Only Memory), a RAM (Random Access Memory), or the like, and a storage device that stores or temporarily stores programs and data such as an OS and application software that are basic software executed by the control unit 101. It is.

  The auxiliary storage unit 103 is an HDD (Hard Disk Drive) or the like, and is a storage device that stores data related to application software or the like.

  The drive device 104 reads the program from the recording medium 105, for example, a flexible disk, and installs it in the storage device.

  The recording medium 105 stores a predetermined program. The program stored in the recording medium 105 is installed in the processing device 100 via the drive device 104. The installed predetermined program can be executed by the processing apparatus 100.

  The network I / F unit 106 includes a peripheral device (for example, the sensor device 10 or the like) having a communication function connected via a network constructed by a data transmission path such as a wired and / or wireless line, and the processing apparatus 100. Interface.

  The input unit 107 includes a keyboard having cursor keys, numeric input, various function keys, and the like, a mouse, a slice pad, and the like.

  In the example illustrated in FIG. 4, the intravesical urine volume estimation process and the like described below can be realized by causing the processing device 100 to execute a program. It is also possible to record the program in the recording medium 105 and cause the processing device 100 to read the recording medium 105 on which the program is recorded, thereby realizing the bladder urine volume estimation process and the like described below. The recording medium 105 is a recording medium that records information optically, electrically, or magnetically, such as a CD-ROM, a flexible disk, or a magneto-optical disk, and information is electrically stored such as a ROM or flash memory. Various types of recording media such as a semiconductor memory for recording can be used. Note that the recording medium 105 does not include a carrier wave.

  FIG. 5 is a functional block diagram illustrating an example of functions of the processing apparatus 100.

  As illustrated in FIG. 5, the processing device 100 includes a user profile generation unit 110, an oral water intake estimation unit 112, a urine output estimation unit 114, an environmental temperature / humidity recording unit 116, and an intravesical urine volume estimation unit 118. Including.

  Note that the program executed by the processing apparatus 100 may have a module configuration including these units 110, 112, 114, 116, and 118. In this case, as actual hardware, the control unit 101 reads out and executes a program from the auxiliary storage unit 103, so that one or more of the units 110, 112, 114, 116, and 118 are the main storage unit 102. One or a plurality of units may be generated on the main storage unit 102.

  The user profile generation unit 110 generates and registers a user profile. A user profile is generated and registered for each user. For example, the user profile may be stored in the auxiliary storage unit 103 of the processing apparatus 100 and may be databased. This user profile generation process may be executed only once when a new user is registered, and may be re-executed periodically for updating. In the case of a care facility such as a nursing home, the user profile does not change dynamically and is basically fixed.

  FIG. 6 is a flowchart illustrating an example of a user profile generation process executed by the user profile generation unit 110.

  In step 600, user attributes are registered as a user profile. The user attribute may be, for example, the user's height, weight, sex, date of birth, and the like.

  In step 602, the user's bladder capacity is calculated and registered as a user profile. The user's bladder capacity may be calculated by any method. For example, the average bladder capacity may be calculated based on the user attribute. In addition, referring to user attributes, the user's bladder capacity is estimated from the GSR (Galvanic Skin Resistance) sensor value of the lower abdomen (near the pubic bone) or ultrasound images using transabdominal ultrasonography. May be.

  In step 604, the user confirms a dominant hand holding a container (such as a cup or bottle) containing moisture and registers it as a user profile.

  In step 606, the attributes (for example, capacity, beverage type, mass) of the container used by the user for water intake are registered as a user profile.

  Other information may be registered as a user profile. For example, when there are predetermined meal menus, hydration places, and beverage types such as a specific facility such as a nursing home, information on the living environment may be registered as a user profile.

  The oral water intake estimation unit 112 estimates the user's oral water intake based on the acceleration signal from the acceleration sensor 12 of the sensor device 10 worn on the user's wrist. The oral water intake is the intake when the user takes water from the mouth. Here, in general, when drinking a beverage, the user's hand moves up to take a container containing the beverage, lifts the container gripped by the hand upwards to the mouth, and Maintain (however, tilt the container gradually) to drink. When you have finished drinking, lower the container down. Thus, in general, when performing a beverage action, a user pushes a hand forward to hold a container, a “lift action” that raises a hand holding the container, and a container. Perform a “lifting action” to lower the hand. Here, paying attention mainly to the fact that these three actions appear as characteristics in the acceleration signal (described later with reference to FIG. 7 and the like), the oral water intake estimation unit 112 receives the acceleration signal from the acceleration sensor 12. First, the beverage behavior is detected. Next, the oral water intake estimation unit 112 estimates the user's oral water intake based on the acceleration signal from the acceleration sensor 12 during the beverage action. Here, generally, a change occurs in the acceleration signal from the acceleration sensor 12 at the time of a beverage action according to the amount of the beverage contained in the container (described later with reference to FIG. 13 and the like). Focusing on this point, the oral water intake estimation unit 112 estimates the user's oral water intake based on the acceleration signal from the acceleration sensor 12 during the beverage action.

  FIG. 7 is a diagram illustrating an example of an acceleration signal waveform from the acceleration sensor 12 during a beverage action. In FIG. 7, the vertical axis represents the acceleration value, and the horizontal axis represents time. A waveform GX represents an acceleration waveform in the X-axis direction, a waveform GY represents an acceleration waveform in the Y-axis direction, and a waveform GZ represents an acceleration waveform in the Z-axis direction.

  As shown in FIG. 7, the acceleration signal from the acceleration sensor 12 during the beverage action has a characteristic waveform (corresponding to each of “protruding action”, “lifting action”, and “lifting action”). Acceleration change). That is, the “protruding action” corresponds to the waveform of the A1 part, the “lifting action” corresponds to the waveform of the A2 part, and the “lifting action” corresponds to the waveform of the A3 part. Note that the waveform at A4 corresponds to the action of the user pulling his hand away from the container. In addition, although the above three actions are mainly detected here, it is also possible to improve the detection accuracy of the drinking action by detecting this pulling action.

  FIG. 8 is a diagram in which the waveform GX in FIG. 7 is extracted. In FIG. 8, a picture schematically showing the state of the user's hand corresponding to the waveform portions of A11, A12, A2, and A3 is inserted. An arrow (solid line) attached to this schematic picture schematically shows an acceleration component in the X-axis direction.

  As shown in FIG. 8, at the time of “protruding action”, a positive acceleration is generated as indicated by A11. Further, since the “protruding action” is accompanied by an action of stopping the protruding hand (an action of decelerating), immediately after that, as shown by A12, a negative acceleration occurs. When the “lifting action” starts, the positive direction of the X axis of the acceleration sensor 12 changes from the horizontal direction to the upward direction in the vertical direction, as shown by a schematic picture in FIG. That is, the X axis rotates about 90 degrees in the absolute coordinate system. Therefore, at the time of “lifting action”, as shown in the schematic picture of FIG. 8, the acceleration sensor 12 generates acceleration in the positive direction due to hand movement in the X-axis direction and receives gravitational acceleration in the X-axis direction. Therefore, the acceleration of the X-axis component increases to a positive acceleration (1G) corresponding to the gravitational acceleration, as indicated by A2. The positive acceleration (1G) corresponding to the gravitational acceleration is maintained during the period from the “lifting action” to the “holding action” (that is, during oral water intake). The “lifting action” is the reverse of the “lifting action”, and the X axis of the acceleration sensor 12 changes in the direction (horizontal direction) before the start of the “lifting action”. Accordingly, when the “lifting action” is started, the acceleration sensor 12 generates a negative acceleration due to the movement of the hand in the X-axis direction and a gravitational acceleration in the X-axis direction as shown by a schematic picture in FIG. Therefore, as indicated by A3, the acceleration of the X-axis component decreases to the value before the start of the “lifting action”.

  As can be seen from FIG. 8, the X-axis component of the acceleration signal from the acceleration sensor 12 during the beverage action corresponds to “protruding action”, “lifting action”, and “holding action”, respectively. A characteristic waveform is generated. Therefore, by detecting this characteristic waveform, the beverage behavior can be detected with high accuracy.

  FIG. 9 is a diagram in which the waveform GY in FIG. 7 is extracted. In FIG. 8, a picture schematically showing the state of the user's hand corresponding to the waveform portions A1, A2, A3, and A4 is inserted. An arrow (solid line) attached to this schematic picture schematically shows an acceleration component in the Y-axis direction.

  As shown in FIG. 9, in a stationary state where the hand is straightened out in the front, an acceleration in the negative direction corresponding to the gravitational acceleration occurs. In the “protruding action”, as indicated by A1, the acceleration of the Y-axis component varies due to the act of holding the container. When the “lifting action” starts, the Y-axis of the acceleration sensor 12 changes from the vertical direction to the horizontal direction as shown by a schematic picture in FIG. That is, the Y axis rotates about 90 degrees in the absolute coordinate system. Therefore, at the time of “lifting action”, the acceleration sensor 12 is released from the gravitational acceleration in the Y-axis direction, as shown by a schematic picture in FIG. It increases from the acceleration (-1G) corresponding to the gravitational acceleration to near zero. The acceleration of the Y-axis component is maintained near zero during the period from the “lifting action” to the “holding action” (that is, during oral water intake). The “lifting action” is the reverse of the “lifting action”, and the Y axis of the acceleration sensor 12 changes in the direction (vertical direction) before the start of the “lifting action”. Accordingly, when the “lifting action” starts, the acceleration sensor 12 receives gravitational acceleration in the Y-axis direction, as shown by a schematic picture in FIG. 9, and therefore the acceleration of the Y-axis component is A2. As shown, it decreases to a value (-1G) corresponding to the gravitational acceleration. Note that the waveform at A4 corresponds to the action of the user pulling his hand away from the container. During this action, the acceleration of the Y-axis component varies due to the act of releasing the container.

  As can be seen from FIG. 9, the X-axis component of the acceleration signal from the acceleration sensor 12 during the beverage action corresponds to “protruding action”, “lifting action”, and “holding action”, respectively. A characteristic waveform is generated. Therefore, by detecting this characteristic waveform, the beverage behavior can be detected with high accuracy.

  As shown in FIGS. 8 and 9, the characteristic waveforms corresponding to “protruding behavior”, “lifting behavior”, and “lifting behavior” are the X-axis of the acceleration signal from the acceleration sensor 12. It appears in both the component and the Y-axis component. Therefore, it is also possible to accurately detect the beverage behavior based on only one of the X-axis component and the Y-axis component of the acceleration signal from the acceleration sensor 12. However, when both the X-axis component and the Y-axis component of the acceleration signal from the acceleration sensor 12 are used (and the Z-axis component of the acceleration signal from the acceleration sensor 12), the beverage behavior can be detected with higher accuracy. It becomes possible.

  FIG. 10 is a diagram illustrating another example of an acceleration signal waveform from the acceleration sensor 12 during a beverage action. In FIG. 10, the vertical axis represents acceleration values, and the horizontal axis represents time. A waveform GX represents an acceleration waveform in the X-axis direction, a waveform GY represents an acceleration waveform in the Y-axis direction, and a waveform GZ represents an acceleration waveform in the Z-axis direction.

  The acceleration waveform shown in FIG. 10 is mainly different from the acceleration waveform shown in FIG. 7 in that it is a waveform when the beverage in the container is drunk. That is, the drink behavior shown in FIG. 7 is an action that does not drink all the beverage in the container, whereas the drink behavior shown in FIG. 10 is an action that drinks all the drink in the container.

  As shown in FIG. 10, the acceleration signal from the acceleration sensor 12 at the time of a beverage action in which all the beverage in the container is drunk is “drinking up” between “lifting action” and “holding action” (that is, during oral water intake). A characteristic waveform corresponding to “behavior” is generated. That is, “drinking behavior” corresponds to the waveform of the A5 part.

  FIG. 11 is a diagram in which the waveform GY in FIG. 10 is extracted. In FIG. 11, a picture schematically showing the state of the user's hand corresponding to the waveform portion of A5 is inserted. An arrow (solid line) attached to this schematic picture schematically shows an acceleration component in the Y-axis direction.

  During oral fluid intake, acceleration near zero is maintained as described above. However, in the “drinking and drinking action”, the user performs an action of tilting the container by hand (the action of returning the wrist accordingly). During this time, therefore, during the “drinking behavior”, the acceleration sensor 12 receives the gravitational acceleration in the Y-axis direction as shown in the schematic picture in FIG. 11 (in the figure, the component of the gravitational acceleration in the Y-axis direction). Gy), the acceleration of the Y-axis component is greater than zero, as indicated by A5.

  Thus, as shown in FIGS. 10 and 11, in the acceleration waveform in the Y-axis direction, by determining the presence or absence of the feature of “drinking behavior” between “lifting behavior” and “lifting behavior”, the beverage behavior The presence / absence of drinking / drying can be accurately determined.

  FIG. 12 is a diagram illustrating an example of an angular velocity signal waveform from the gyro sensor 14 during a beverage action. In FIG. 12, the vertical axis represents angular velocity values, and the horizontal axis represents time. A waveform GYX represents an angular velocity waveform around the X axis, a waveform GYY represents an angular velocity waveform around the Y axis, and a waveform GYZ represents an angular velocity waveform around the Z axis.

  As shown in FIG. 12, the angular velocity signal from the gyro sensor 14 at the time of a beverage action has a characteristic waveform corresponding to each of “protruding action”, “lifting action”, and “lifting action”. Occur. That is, the “protruding action” corresponds to the waveform of the A1 part, the “lifting action” corresponds to the waveform of the A2 part, the “lifting action” corresponds to the waveform of the A3 part, and the “drinking action” is , Corresponding to the waveform of part A5. By detecting this characteristic waveform, the beverage behavior can be detected with high accuracy. However, the angular velocity signal waveform from the gyro sensor 14 does not appear as distinctive as the acceleration signal waveform from the acceleration sensor 12 described above. Accordingly, the angular velocity signal from the gyro sensor 14 may preferably be used with the acceleration signal from the acceleration sensor 12 rather than alone.

  FIG. 13A shows an example of an acceleration signal waveform from the acceleration sensor 12 during a beverage action by a container containing a small amount (50 ml) of beverage, and FIG. 13B shows a beverage by a container containing a large amount (1000 ml) of beverage. An example of the acceleration signal waveform from the acceleration sensor 12 at the time of action is shown. 13A and 13B, similarly, the vertical axis represents the acceleration value, and the horizontal axis represents time. A waveform GX represents an acceleration waveform in the X-axis direction, a waveform GY represents an acceleration waveform in the Y-axis direction, and a waveform GZ represents an acceleration waveform in the Z-axis direction.

  13A and 13B, the acceleration from the acceleration sensor 12 in the case of a container containing a small amount (50 ml) of beverage and the case of a container containing a large amount (1000 ml) of beverage. Signal waveforms are very different. In particular, in the case of a container containing a small amount (50 ml) of beverage, the vibration component is small, whereas in the case of a container containing a large amount (1000 ml) of beverage, the vibration component is large. This is because a force is required when holding a heavy object in the hand, and the hand shakes. Such a difference in vibration components is particularly noticeable in “lifting behavior” and “lifting behavior”. Therefore, it is possible to estimate the oral water intake of the user by paying attention to such a difference.

Figure 14A is a diagram showing a vibration accumulated value V _g based on the three-axis composite acceleration of the acceleration signal waveform shown in FIG. 13A, FIG. 14B, the vibration accumulated value based on three-axis composite acceleration of the acceleration signal waveform shown in FIG. 13B It is a figure which shows _Vg . 14A and 14B, the vertical axis represents the vibration integrated value _Vg , and the horizontal axis represents time.

The triaxial composite acceleration _Vg is calculated by the following equation.
V _g = √ (Gx ² + Gy ² + Gz ² )
Gx, Gy, and Gz respectively represent X-axis component acceleration, Y-axis component acceleration, and Z-axis component acceleration.

Vibration accumulated value, calculates a difference (absolute value) of the three-axis composite acceleration V _g, is obtained by integrating the respective differences. Difference 3-axis composite acceleration V _g is as follows, for example.
3-axis composite acceleration _{V g} of the difference = 3-axis composite acceleration _V g (t) -3-axis composite acceleration _V g _(t-Δt)
Here, t is a certain time, and Δt is a minute time. Difference 3-axis composite acceleration V _g is, for example, calculated for each Delta] t, it will be accumulated. Therefore, the vibration accumulated value becomes a value obtained by integrating the difference between the three-axis composite acceleration V _g for a predetermined time.

  14A and 14B, as is clear from the comparison between FIG. 14A and FIG. 14B, in the case of a container containing a small amount (50 ml) of beverage and in the case of a container containing a large amount (1000 ml) of beverage, the mode of increase in vibration integrated value Are very different. For example, in the case of a container containing a small amount (50 ml) of beverage, since the vibration component is small, the increase mode of the vibration integrated value is relatively slow, whereas a large amount (1000 ml) of beverage is contained. In the case of a container, since there are many vibration components, the increase mode of the vibration integrated value is relatively steep. Such a difference in vibration components is particularly noticeable in “lifting action” and “lifting action”, as shown by A1 and A2 parts in FIGS. 14A and 14B. Therefore, the user's oral water intake can be estimated by paying attention to the increase mode (pattern) of the vibration integrated value.

Specifically, the amount of beverage in the container (moisture capacity) is changed, and an increase mode (increase pattern) of the vibration integrated value is derived for the water capacity in a plurality of containers by testing, and vibration is performed for each water capacity. The increase pattern of the integrated value is stored (in association with each moisture capacity). The increase pattern of the vibration integrated value may be evaluated by an area S obtained by integrating the waveform of the vibration integrated value as shown in FIG. In this case, the area S may be calculated separately for the section corresponding to the “lifting action” and the section corresponding to the “lifting action”. That is, the difference of three-axis composite acceleration V _g is a section corresponding to the "lifting action", in a section corresponding to "Have lowering action", it may be integrated independently. This is because the water capacity in the container may change between the “lifting action” and the “holding action” due to oral water intake.

  In addition, since the increase pattern of the vibration integrated value for each water capacity may be different for each user, it may be derived by a test for each user. In this case, the increase pattern of the vibration integrated value for each moisture capacity may be registered as a user profile in a manner associated with each user. For the moisture capacity not derived from the test, an increase pattern of the vibration integrated value may be estimated and registered by interpolation or the like.

As described above, according to the method described with reference to FIGS. 14A and 14B, the user's oral water intake is accurately estimated by considering the vibration integrated value V _g based on the triaxial synthetic acceleration of the acceleration signal waveform. Is possible.

In the method described with reference to FIGS. 14A and 14B, the three-axis composite acceleration _Vg is used. However, any of the acceleration of the X-axis component, the acceleration of the Y-axis component, and the acceleration of the Z-axis component is used. A combination of the two accelerations may be used, or any one of the accelerations may be used. For example, instead of the three-axis composite acceleration _{V g,} for example, synthetic acceleration between the acceleration of the acceleration and the Y-axis component of the X-axis component ^{(= √ (Gx 2 + Gy} 2)) may be used. Further, instead of the three-axis composite acceleration V _g, when the acceleration of the Y-axis component is used, the difference of the acceleration in the Y-axis component may be a difference between the absolute value of the acceleration in the Y-axis component.

  FIG. 16 is a flowchart (part 1) illustrating an example of an oral water intake estimation process executed by the oral water intake estimation unit 112. FIG. 17 is a flowchart (No. 2) showing a continuation of the oral water intake estimation process shown in FIG. 16 and 17, it is assumed that an acceleration signal from the acceleration sensor 12 of the sensor device 10 attached to the user's wrist is supplied to the processing apparatus 100 in real time.

  In step 1600, the axis in the direction of gravity is determined based on the acceleration signal (acceleration sensor value) from the acceleration sensor 12 of the sensor device 10. The direction of gravity is an axis where acceleration of approximately 1G is generated. Here, for convenience, it is assumed that the Y-axis direction corresponds to the gravity direction.

  In step 1602, dominant hand information is extracted from the user profile. The user profile may be generated and registered by the method described above with reference to FIG.

  In step 1604, the mounting direction of the sensor device 10 is determined based on the gravity direction axis and dominant hand information. The sensor device 10 is mounted on the inside or the outside of the wrist. For example, in the example shown in FIG. 3, the sensor device 10 is attached to the outside of the wrist of the left hand. In this case, the gravity direction is the positive direction of the Y-axis direction. On the other hand, when the sensor device 10 is mounted on the inner side of the wrist of the left hand, the sensor device 10 is turned from the example shown in FIG. 3, so the gravity direction is the negative direction of the Y-axis direction. Hereinafter, for convenience, it is assumed that the mounting direction of the sensor device 10 is a direction in which the direction of gravity corresponds to the positive direction of the Y-axis direction.

In step 1606, it is determined whether or not the combined acceleration V (= √ (Gy ² + Gz ² )) of the X axis and the Z axis is greater than 0 and less than 0.5G. When the combined acceleration V is larger than 0 and smaller than 0.5G, it can be estimated that the user's hand is not moving greatly in the horizontal plane (rest state). For example, this corresponds to a state where the user puts his hand on the table and is not moving. In this case, a waiting state is entered. On the other hand, when the combined acceleration V is greater than 0 and greater than 0.5G, it can be estimated that the user's hand has moved in the horizontal plane. For example, it corresponds to the above-described “protruding action”. Accordingly, in this case, the process proceeds to step 1608, and it is determined whether or not the “protruding action” is performed.

  In step 1608, it is determined whether the combined acceleration V of the X axis and the Z axis is greater than 0.5G. This is because in the case of the “protruding action”, the composite acceleration V becomes larger than 0.5 G as shown in FIG. Instead of the combined acceleration V, it may be determined whether or not the acceleration of the X-axis component is greater than 0.5G. If the combined acceleration V of the X axis and the Z axis is greater than 0.5G, it is determined that there is a “protruding action” and the process proceeds to step 1610. When the combined acceleration V of the X axis and the Z axis is 0.5 G or less, a standby state is entered.

  In step 1610, it is determined whether or not the change amount ΔX of the X-axis component acceleration is negative and the acceleration change amount ΔY of the Y-axis component is negative. This is an example of a determination condition for detecting a motion at the start of the “lifting action”. That is, as indicated by A2 in FIG. 7 and the like, when the “lifting action” starts, the acceleration of the X-axis component and the acceleration of the Y-axis component instantaneously decrease due to the motion at that time. Therefore, it is possible to detect the “lifting action” with high accuracy by using such a feature of acceleration change. If the X-axis component acceleration change ΔX is negative and the Y-axis component acceleration change ΔY is negative, it is determined that the “lifting action” has started, and the process proceeds to Step 1612. In the case of, it becomes a waiting state. In this waiting state, if the change amount ΔX of the X-axis component acceleration is negative and the acceleration change amount ΔY of the Y-axis component does not become negative for a certain period of time, the process may return to step 1606. .

In step 1612, to record the current time _{T 0.} Time T ₀ is a time corresponding to the start of the “lifting action”.

  In step 1614, it is determined whether or not the state where the acceleration of the Y-axis component is larger than -1G and smaller than 0G and the change amount ΔY of the acceleration of the Y-axis component is positive continues for a predetermined threshold time H1 or longer. To do. This is an example of a determination condition for detecting a motion after the start of “lifting action” (an action of lifting a hand). This is because the acceleration of the Y-axis component increases and the acceleration of the Y-axis component becomes significantly larger than −1G during the “lifting action” as shown in FIG. The predetermined threshold time H1 may correspond to a minimum time within a possible range of time required for the “lifting action”. The predetermined threshold time H1 may be a predetermined fixed value, or may be set for each user based on the test result. If the acceleration of the Y-axis component is greater than -1G and less than 0G and the change amount ΔY of the acceleration of the Y-axis component is positive for a predetermined threshold time H1 or longer, there is a “lifting action”. If not, the process proceeds to step 1616. Otherwise, the process returns to step 1608.

  In step 1616, it is determined whether or not the acceleration of the Y-axis component is larger than −0.4G and the acceleration of the X-axis component is larger than 0.8G. This is an example of a determination condition for detecting the end state of the “lifting action”, that is, the completion state of the movement of the container to the mouth. As shown in A2 in FIG. 7 and the like, in the final state of the “lifting action”, the X axis and the Y axis rotate about 90 degrees in the absolute coordinate system (the gravity direction changes from the Y axis direction to the X axis direction). To change). For this reason, the acceleration of the Y-axis component is larger than −0.4G and the acceleration of the X-axis component is larger than 0.8G. Therefore, the end state of the “lifting action” can be detected with high accuracy using such a feature of acceleration change. If the acceleration of the Y-axis component is greater than −0.4G and the acceleration of the X-axis component is greater than 0.8G, it is determined that the “lifting action” has ended, and the process proceeds to step 1618; Enters a wait state. In this waiting state, if the acceleration of the Y-axis component is larger than −0.4G and the acceleration of the X-axis component is not larger than 0.8G for a certain time, the process returns to step 1606. As good as

In step 1618, it records the current time _{T 1.} Time T ₁ becomes a time corresponding to the time of "lifting action" end.

In step 1620, based on an acceleration signal of three axes in the section from time T ₀ to time T ₁ (i.e. the section of "lifting action"), 3 differential integrated value of the axis composite acceleration V _g (vibration cumulative value) S ₀₁ is calculated. When the process of step 1620 ends, the process proceeds to step 1700.

In step 1700, the acceleration of the Y-axis component is larger than −0.25G and smaller than 0G for a predetermined threshold time H2 or more, and the combined acceleration V (= √ (Gy ² + Gz ² )) of the X-axis and the Z-axis. It is determined whether the state larger than 0.8G and smaller than 1.2G has continued. This is an example of a determination condition for detecting a drinking operation (oral water intake operation) after the end of the “lifting behavior”. As shown in FIG. 7 and the like, during oral water intake, the acceleration of the Y-axis component is larger than −0.25 G and smaller than 0 G, and the combined acceleration V is larger than 0.8 G and smaller than 1.2 G. Is formed. The predetermined threshold time H2 may correspond to a minimum time within a possible range of time required for oral water intake. The predetermined threshold time H2 may be a predetermined fixed value, or may be set for each user based on the test result. When the acceleration of the Y-axis component is larger than −0.25 G and smaller than 0 G and the combined acceleration V is larger than 0.8 G and smaller than 1.2 G, the oral water content is maintained. It is determined that it is ingestion, and the process proceeds to step 1702, otherwise it is determined that oral water intake has not been performed (for example, when the container is simply put on the mouth and returned to its original state). Return to step 1600. Instead of returning to step 1600, the process may return to step 1606.

  In step 1702, it is determined whether or not the acceleration of the Y-axis component has become larger than 0G. This is an example of a determination condition for detecting “drinking behavior”. This is because the acceleration of the Y-axis component becomes larger than zero as shown in FIG. If the acceleration of the Y-axis component is greater than 0G, it is determined that “drinking behavior” has occurred, and the process proceeds to step 1704. On the other hand, if the acceleration of the Y-axis component does not become greater than 0G, the process proceeds to step 1706.

In step 1704, assuming that the current water capacity (amount of beverage) in the container is 0, the oral water intake during the current beverage behavior is calculated (estimated). That is, since “drinking behavior” is detected, it is estimated that there is no beverage in the current container (that is, it is estimated that the second moisture capacity W ₁ described later is 0), and based on this estimation Calculate the oral water intake during the current beverage behavior. At this time, the oral water intake during the current beverage action is the water capacity (first water capacity) in the container before the current beverage action. The first water capacity may be calculated by a method described later (see step 1716), or may be calculated by subtracting the total oral water intake from the previous time from the initial water capacity in the container. The initial moisture capacity may be a fixed value according to the capacity of the container, or may be set for each user. Note that the method of subtracting the total oral water intake from the initial water volume in the container to the previous time is based on the premise that there is no supplementation of the beverage until the “drinking behavior” occurs. When the process of step 1704 ends, the process proceeds to step 1722.

  In step 1706, it is determined whether or not the state where the acceleration of the Y-axis component is larger than −1G and smaller than 0G and the change amount ΔY of the acceleration of the Y-axis component is negative continues for a predetermined threshold time H3 or more. To do. This is an example of a determination condition for detecting the start time of “holding action”. This is because the acceleration of the Y-axis component decreases from around 0G to -1G at the start of the "lifting action" as shown by A3 in FIG. The predetermined threshold time H3 may correspond to a minimum time at which it can be determined that the “holding action” starts. If the state where the acceleration of the Y-axis component is larger than −1G and smaller than 0G and the change amount ΔY of the acceleration of the Y-axis component is negative continues for a predetermined threshold time H3 or more, the process proceeds to Step 1708. Otherwise, it is in a waiting state. In this waiting state, if the condition of step 1702 is satisfied, the process may proceed to step 1704.

In step 1708, it records the current time _{T 2.} Time T ₂ is a time corresponding to the start of the "have lowering action".

In step 1710, the time from time _{T 1} to time _{T 2,} the _(T 2 -T ₁₎ is stored as fluid intake time.

  In step 1712, the absolute value of the Y axis component acceleration change ΔY after the Y axis component acceleration change amount ΔY becomes negative is 1G, and the X axis component acceleration change amount ΔX is the absolute value. Is 1G, and whether or not the acceleration of the Y-axis component <the acceleration of the X-axis component <the acceleration of the Z-axis component is established. This is an example of a determination condition for detecting the end of the “lifting action”. As shown in A3 in FIG. 7 and the like, when the “lifting action” ends, the X axis and the Y axis rotate about 90 degrees in the absolute coordinate system compared to before the “holding action” starts ( This is because the gravity direction changes from the Y-axis direction to the X-axis direction), and changes corresponding to the gravitational acceleration occur in the acceleration of the Y-axis component and the acceleration of the X-axis component. Further, as indicated by A3 in FIG. 7 and the like, in the end state of the “lifting action”, the acceleration of the Y-axis component <the acceleration of the X-axis component <the acceleration of the Z-axis component. The absolute value of the acceleration change amount ΔY of the Y axis component after the Y axis component acceleration change amount ΔY becomes negative is 1 G, and the absolute value of the acceleration change amount ΔX of the X axis component is 1 G. If the acceleration of the Y-axis component <the acceleration of the X-axis component <the acceleration of the Z-axis component is established, the process proceeds to step 1713. Otherwise, the process enters a waiting state.

In step 1713, it records the current time _{T 3.} Time T ₃ is a time corresponding to the at the end of the "have lowering action".

In step 1714, based on the 3-axis acceleration signals in the interval from time T _2, to the time T ₃ (i.e. section for "Have lowering action"), the differential integrated value of the three-axis composite acceleration V _g (vibration cumulative value) to calculate the S _23.

In step 1716, it compares previously and set the registered plurality of registered vibration accumulated value S _01, the current oscillating integrated value S ₀₁ and _(vibration accumulated value S ₀₁ calculated in step _1620), this beverage action The amount of the beverage in the previous container (first water capacity), that is, the water capacity W ₀ in the container before drinking is estimated. This is because, as described above with reference to FIGS. 14A and 14B, the vibration integrated value S ₀₁ changes according to the amount of beverage (moisture capacity) in the container. A set of a plurality of registered vibration accumulated value S ₀₁ is a set of vibration accumulated value S ₀₁ obtained for each predetermined water volume may be generated from past measured data. If the registration vibration accumulated value S ₀₁ that matches the current vibration accumulated value S ₀₁ is present, the first moisture capacity W ₀ is the moisture capacity when the registration vibration accumulated value S ₀₁ were obtained. Also, if a registered vibration accumulated value S ₀₁ that matches the current vibration accumulated value S ₀₁ is not present, for example by interpolation using two reference vibration accumulated value S ₀₁ in proximity to the current vibration accumulated value S ₀₁ first The moisture capacity W ₀ may be estimated. The first water volume W ₀ is obtained by subtracting the total oral water intake from the initial water volume in the container to the previous time instead of the method using the vibration integrated value S ₀₁ (method estimated from the acceleration signal). It may be calculated by The initial moisture capacity may be a fixed value according to the capacity of the container, or may be set for each user. Note that the method of subtracting the total oral water intake from the initial water volume in the container to the previous time is based on the premise that there is no supplementation of the beverage until the “drinking behavior” occurs.

In step 1718, as in step 1716, compares previously a set of a plurality of registered vibration accumulated value _{S 23} registered, this vibration accumulated value _{S 23} and (vibration accumulated value _{S 23} calculated in step 1714) , the amount (the second moisture capacity) of the beverage in the container after this drink behavior, to estimate the moisture capacity W ₁ after drinking that is. This, as described above with reference to FIGS. 14A and 14B, the vibration accumulated value S ₂₃ is to vary depending on the amount of the beverage in the container (water volume). A set of a plurality of registered vibration accumulated value S ₂₃ is a set of vibration accumulated value S ₂₃ obtained for each predetermined water volume may be generated from past measured data. If the registration vibration accumulated value S ₂₃ that matches the current vibration accumulated value S ₂₃ is present, a second water capacity W ₁ is a moisture capacity when the registration vibration accumulated value S ₂₃ were obtained. Further, when there is no registered vibration integrated value S ₂₃ that coincides with the current vibration integrated value S ₂₃ , for example, the second registered vibration integrated value S ₂₃ adjacent to the current vibration integrated value S ₂₃ is interpolated by the second interpolation. water capacity W ₁ may be estimated.

In step 1720, the first moisture capacity _{W 0} obtained in Step 1716 and Step 1718 and based on a second water capacity _{W 1,} it calculates the oral fluid intake during this beverage action (estimated). Specifically, the oral water intake during the current drinking behavior may be calculated by subtracting the second water capacity W ₁ from the first water capacity W ₀ .

In step 1722, the water intake time T ₁ (step 1618), the water intake time (step 1710) and the estimated water intake (step 1704 or step 1720) related to the beverage behavior detected this time are stored. At this time, when the type of the ingested beverage can be determined, the type of the ingested beverage may be stored. The beverage type information representing the type of beverage may be registered as a user profile.

  As described above, according to the processing shown in FIGS. 16 and 17, it is possible to accurately detect the beverage behavior of the user in real time based on the triaxial acceleration data. That is, the user's beverage behavior can be accurately detected with a simple configuration using only the sensor device 10 as a sensor. In particular, since the user's beverage behavior is detected only when “protruding behavior”, “lifting behavior”, and “lifting behavior” are detected, other behavior that does not involve such behavior (behavior similar to beverage behavior) It is possible to eliminate it, and it is possible to detect the beverage behavior with high accuracy.

Moreover, according to the process shown in FIG.16 and FIG.17, the oral water intake at the time of a user's drink action can be detected with a simple structure only by using the sensor device 10 as a sensor. That is, by focusing on the point where the vibration accumulated value (such as a vibration accumulated value S ₂₃₎ is varied depending on the water capacity of the container (by weight), water volume in the container based on the vibration integrated value (second water capacity W ₁ ) and the oral water intake can be accurately estimated. Further, to detect the presence or absence of a "drank behavior", according to the detection result, changes the method of estimating the oral fluid intake during drinking behavior (second method of estimating the water volume W _1), "drank behavior" The oral water intake can be accurately estimated according to the presence or absence of.

  Note that the processes shown in FIGS. 16 and 17 are merely examples, and other determination conditions may be added, some of the determination conditions may be omitted, and some of the determination conditions may be corrected / It may be changed. For example, in order to eliminate gargle behavior, immediately after ingestion of oral water, for example, based on an acceleration sensor attached to the body, if "the action of lowering the head (to expel liquid)" is detected, It may be determined that there is not. Further, at the time of “lifting action” or “lifting action”, it may be considered that the user's wrist moves in the vicinity of the mouth while drawing an arc trajectory with the elbow as an axis. Further, the wrist returning operation during the “drinking and drinking action” may be detected based on an angular velocity signal (angular velocity around the Z axis) from the gyro sensor 14. Also, for example, with respect to step 1712, the absolute value of the Y axis component acceleration change ΔY after the Y axis component acceleration change ΔY becomes negative is 1 G, and the acceleration change amount of the X axis component is 1G. Instead of determining whether the absolute value of ΔX is 1G and the acceleration of the Y-axis component <the acceleration of the X-axis component <the acceleration of the Z-axis component is satisfied, the acceleration of the Y-axis component is −1G And the end of the “lifting action” is determined (detected) by determining whether or not the acceleration of the X-axis component has decreased to around 0G (or near the value at the start of the “lifting action”). )

  In the processing shown in FIGS. 16 and 17, for convenience, the mounting direction of the sensor device 10 is assumed to be a direction in which the gravity direction corresponds to the positive direction of the Y-axis direction. However, the above various determination conditions may be changed according to the difference in dominant hand or the mounting direction. For example, when the mounting direction of the sensor device 10 is different from the above assumption and the gravity direction is a direction corresponding to the negative direction of the Y-axis direction, the acceleration of the Y-axis component shown in FIG. Therefore, for example, in step 1614, whether or not the state where the acceleration of the Y-axis component is smaller than 1G and larger than 0G and the change amount ΔY of the acceleration of the Y-axis component is negative for a predetermined threshold time H1 or longer is continued. This may be determined. For example, in step 1702, it may be determined whether or not the acceleration of the Y-axis component has become smaller than 0G.

In the processing shown in FIG. 16 and FIG. 17, the water capacity (second water capacity W _{1 and the} like) in the container and the oral water intake are estimated based on the vibration integrated value (vibration integrated value S _{23 and the} like). However, it is also possible to estimate the oral water intake during the current beverage behavior based on the water intake time during the current beverage behavior (step 1710). In this case, the relationship between the water intake time and the oral water intake may be derived in advance by a test or the like for each user, or a predetermined average relationship may be used. Or it is good also as estimating a water intake using the difference of the track | orbit of a wrist before and behind a drink action.

  The urination amount estimation unit 114 estimates the urination amount of the user. The estimation method of the user's urination amount may be any method. For example, the user's stay time in the toilet may be calculated by a sensor (for example, a camera or an RF sensor (RF tag)) provided at the entrance of the toilet, and the user's urine output may be estimated based on the stay time. Alternatively, in the case of a healthy adult man in his 30s, the amount of urination may be estimated as a fixed value (for example, 270 ml) based on statistical data that 52% of all urination is 270 ml or less. Alternatively, for each user, an average value of past urination amount may be derived and the average value may be estimated as the urination amount. In these cases, additional sensors (such as an acceleration sensor 202 and a temperature / humidity sensor 204 described later) are unnecessary. Alternatively, the excretion time may be estimated from a change in the deep temperature of the user, and the amount of urination may be calculated in the case of urination.

  FIG. 18 is a flowchart illustrating an example of the urination amount estimation process executed by the urination amount estimation unit 114. Note that the processing shown in FIG. 18 requires an acceleration sensor 202 that is worn on the user's clothes and a temperature and humidity sensor 204 that is carried by the user (see FIG. 1). The temperature / humidity sensor 204 may be integrated with the acceleration sensor 202 to be configured as the second sensor device 200, or may be incorporated in the sensor device 10. In addition, the 2nd sensor device 200 may be a clip-shaped form, and may be mounted | worn with being pinched | interposed into a user's clothes (trousers etc.). Each output signal from the acceleration sensor 202 and the temperature / humidity sensor 204 may be transmitted to the processing apparatus 100 in real time, like the output signal from the sensor device 10.

  In step 1800, based on the acceleration signal (acceleration sensor value) from the acceleration sensor 202, it is determined whether or not an attachment / detachment action (here, an undressing action) has been detected. Since the acceleration sensor 202 is attached to the user's clothes, when the user performs an action of taking off the clothes, a corresponding waveform characteristic (for example, a change in the positive direction of the gravity direction) is generated. The attachment / detachment behavior (here, the undressing behavior) can be easily detected based on the waveform characteristics. If the clothes attaching / detaching behavior is detected, the process proceeds to step 1806, and if the clothes attaching / detaching behavior is not detected, the process proceeds to step 1802.

  In step 1802, based on the acceleration signal from the acceleration sensor 202, it is determined whether or not the user has left the seat and walked for a short time (or the standing action associated with leaving the seat and the stationary state after walking for a short distance). judge. Since the acceleration sensor 202 is attached to the user's clothes, when the user walks away from the desk and walks for a short time, a corresponding waveform feature is generated. A user's absence and a short walk can be easily detected based on such waveform characteristics. In addition, the detection of leaving and walking from the acceleration sensor 202 uses existing technology (Okubo et al., “Proposal of concentration degree estimation system using acceleration sensor, WISS2008,” “Iketani et al. It may be realized by using a moving situation estimation method, 2008-UBI-19 (14), pp.75-80 "). Further, the short time may be a parameter to be determined according to the facility where the user stays, and may correspond to, for example, the time to walk from the dining room to the toilet, for example, 4 minutes. In some environments, there is statistical data that 96% of all urination is less than 4 minutes away. Therefore, it is desirable to set the time according to the environment to be used. If the user's absence and a short walk are detected, it is determined that there is a high possibility of going to the toilet to urinate, and the process proceeds to step 1804.

  In step 1804, based on the output signal (temperature / humidity sensor value) from the temperature / humidity sensor 204, it is determined whether or not it has been detected that the user has entered the surrounding water environment (for example, a toilet). For example, based on the temperature / humidity sensor value, it may be determined that the user has entered the water environment when the ambient temperature of the user falls below the threshold and the humidity rises above the threshold. If it is detected that the user has entered the water environment, the process proceeds to step 1806; otherwise, the process returns to step 1802. If the walking state is not detected without detecting that the user has entered the water environment, the process may return to step 1800. Note that the entrance to the water environment (for example, a toilet) may be detected by a sensor (for example, a camera, an RF sensor, or the like) that may be provided at the entrance and exit of the water environment.

In step 1806, it records the current time _{T 4.} Time T ₄ is a time corresponding to at the start of urination.

  In step 1808, based on the acceleration signal from the acceleration sensor 202, it is determined whether or not a clothing attachment / detachment behavior (here, clothing behavior) has been detected. Similarly, since the acceleration sensor 202 is worn on the user's clothes, when the user performs an action of wearing the clothes, a corresponding waveform characteristic (for example, a change in the negative direction of the gravity direction) is generated. The clothes attaching / detaching behavior (here, the clothing behavior) can be easily detected based on the waveform characteristics. If a clothing attachment / detachment behavior is detected, the process proceeds to step 1814. If a clothing attachment / detachment behavior is not detected, the process proceeds to step 1810.

  In Step 1810, it is determined whether or not the user has detected that he / she has left the surrounding water environment (for example, a toilet) based on the output signal (temperature / humidity sensor value) from the temperature / humidity sensor 204. For example, based on the temperature / humidity sensor value, when the ambient temperature and humidity of the user return to the same level as before the movement to the water environment, it may be detected that the user has left the water environment. If it is detected that the user has left the water environment, the process proceeds to Step 1812. Otherwise, the process returns to Step 1808. Note that the exit from the water environment (for example, a toilet) may be detected by a sensor (for example, a camera or an RF sensor) that may be provided at the entrance and exit of the water environment.

  In step 1812, as in step 1802 described above, based on the acceleration signal from the acceleration sensor 202, it is determined whether or not a short walk and seating of the user has been detected. If the user's short walk and seating are detected, the process proceeds to step 1814. Otherwise, the process returns to step 1810.

In step 1814, to record the current time _{T 5.} Time T ₅ is a time corresponding to the time of urination end.

In step 1816, a time difference (difference time = T ₅ −T ₄ ) between the urination start time T ₄ and the urination end time T ₅ is calculated.

  In step 1818, it is determined whether or not the difference time calculated in step 1816 is less than 5 minutes. If the difference time is less than 5 minutes, the process proceeds to step 1820. Otherwise, it is determined that urination has not been performed, and the process ends.

  In step 1820, it is determined that the excretion type is urination.

In step 1822, the amount of urination during the current urination is calculated (estimated). The amount of urination may be calculated by the following formula, for example.
Urination volume (ml) = Difference time (minutes) x 90
The environmental temperature / humidity recording unit 116 detects and records changes in the ambient temperature and humidity of the user based on an output signal (temperature / humidity sensor value) from the temperature / humidity sensor 204. For example, the environmental temperature / humidity recording unit 116 is configured such that when the environmental temperature and / or environmental humidity around the user changes beyond a predetermined threshold, the current time and the changed value at that time Record.

  FIG. 19 is a flowchart showing an example of the environmental temperature / humidity recording process executed by the environmental temperature / humidity recording unit 116.

  In step 1900, threshold values (Tt, Th) for detecting changes in environmental temperature and environmental humidity are set. The threshold values (Tt, Th) may be set for each user.

  In step 1902, it is determined based on the output signal (temperature / humidity sensor value) from the temperature / humidity sensor 204 whether or not the change amount of the environmental temperature exceeds the threshold value Tt. If the change amount of the environmental temperature exceeds the threshold value Tt, the process proceeds to step 1906; otherwise, the process proceeds to step 1904.

  In step 1904, based on the output signal (temperature / humidity sensor value) from the temperature / humidity sensor 204, it is determined whether or not the amount of change in environmental humidity exceeds the threshold Th. If the amount of change in the environmental humidity exceeds the threshold value Th, the process proceeds to step 1906; otherwise, the process returns to step 1902. That is, the process waits until the change amount of the environmental temperature exceeds the threshold value Tt or the change amount of the environmental humidity exceeds the threshold value Th.

  In step 1906, the current time and the changed value (environment temperature or environment humidity) are recorded.

  In the process shown in FIG. 19, changes in both environmental temperature and environmental humidity are recorded, but only changes in environmental temperature may be recorded.

  The intravesical urine volume estimation unit 118 is configured such that the oral water intake estimated by the oral water intake estimation unit 112, the urine output estimated by the urine volume estimation unit 114, and the environment recorded by the environment temperature / humidity recording unit 116. Based on the temperature, the amount of urine in the bladder of the user is estimated. The method for estimating the intravesical urine volume may be arbitrary. For example, when the “beverage behavior” is detected by the oral water intake estimation unit 112, the intravesical urine volume estimation unit 118 extracts the water intake time, the beverage type at that time, and the environmental temperature for each beverage behavior. Next, the elapsed time for each temperature is calculated using the water intake time and the current time. Next, the total intravesical urine volume is calculated and added for all beverage behaviors. However, if there is urination behavior in the middle, the urination amount estimated by the urination amount estimation unit 114 at that time is subtracted. The intravesical urine volume estimation unit 118 performs such addition / subtraction processing, and outputs the remaining accumulated intravesical urine volume as the current intravesical urine volume.

  FIG. 20 is a flowchart illustrating an example of an intravesical urine volume estimation process executed by the intravesical urine volume estimation unit 118. The process shown in FIG. 20 may be called and executed periodically (for example, every 1 minute or every 5 minutes).

In step 2000, the moisture intake time T ₁ (see step 1722), beverage type (see step 1722), and environmental temperature (see FIG. 20) recorded as described above are extracted.

In step 2002, it calculates the elapsed time for each temperature (predetermined temperature Temperature range) by using the fluid intake time T ₁ and the current time. The predetermined temperature range may be a range having a width corresponding to the threshold value Tt of the process shown in FIG. For example, if the threshold Tt is 5 degrees, 0-5 degrees, 5-10 degrees, 10-15 degrees, 15-20 degrees, 20-25 degrees, 25-30 degrees, 30-35 degrees, 35-40 degrees, A plurality of predetermined temperature ranges are defined such as 40-45 degrees. The time from the water intake time T ₁ to the current time, to calculate how much of or not in time staying in any temperature range. For example, when the time from the fluid intake time _{T 1} to the current time is 1 hour, the temperature range of 20-25 degrees, 20 minutes, at a temperature range of 25-30 degrees, and so on for 40 minutes.

  In step 2004, it is determined whether or not there is a beverage behavior (oral water intake at that time) that has not yet been added to the accumulated intravesical urine volume. If there is a beverage action that has not yet been added to the integrated bladder urine volume, the process proceeds to step 2006; otherwise, the process proceeds to step 2008.

In step 2006, an increment resulting from a beverage action that has not yet been added is added to the current accumulated intravesical urine volume. The increment ΔV resulting from the beverage behavior may be calculated by, for example, the following equation.
ΔV (ml) = (1 + 1 / (− T × α × e (Δt))) × L Formula (1)
Here, T is a weight due to environmental temperature, α is a diuretic rate, and L is an oral water intake. The oral water intake L may be a value calculated (estimated) by the oral water intake estimation unit 112 as described above. The diuretic rate α may be determined according to the beverage type. Δt is the elapsed time calculated in step 2002. ΔV (ml) may be calculated for each environmental temperature (that is, for each predetermined temperature range obtained in step 2002), and these may be summed. Note that e represents an exponential (exp).

  As can be seen from the equation (1), the increase ΔV in the urinary bladder due to the beverage behavior changes according to the elapsed time. Accordingly, for the past beverage behavior that has already been added to the accumulated intravesical urine volume, the increment ΔV of the intravesical urine volume may be calculated (updated) again and reflected in the current accumulated intravesical urine volume. That is, regarding the increase ΔV in the bladder urine volume caused by the past drinking behavior, the time until the increase ΔV in the bladder urine volume becomes approximately L (oral water intake estimated during the drinking behavior). It may be updated as time passes.

  In step 2008, it is determined whether or not urination has occurred since the previous estimation of the amount of urine in the bladder. Whether or not urination has occurred may be determined based on information from the urine output estimation unit 114. If urination has occurred since the previous estimation of the urine volume in the bladder, the process proceeds to step 2010. On the other hand, if there is no urination since the previous estimation of the amount of urine in the bladder, the process is terminated as it is. In this case, the current cumulative bladder urine volume is estimated as the current user's bladder urine volume.

  In step 2010, the urination volume estimated by the urination volume estimation unit 114 is subtracted from the current accumulated intravesical urine volume.

  In step 2012, the current cumulative bladder urine volume (the cumulative bladder urine volume after subtracting the urination volume) is estimated as the current user's bladder urine volume.

  When the current accumulated intravesical urine volume estimated by the processing shown in FIG. 20 (current user's intravesical urine volume) reaches a predetermined threshold urine volume, the management computer 20 is notified of this. May be. The predetermined threshold urine volume may be set for each user, for example, based on the bladder capacity of each user. A caregiver or the like who has been contacted via the management computer 20 can take measures such as prompting the user who has reached the predetermined threshold urine volume of the current cumulative urine volume to urinate.

  In the process shown in FIG. 20, the only decrease factor with respect to the accumulated amount of urine in the bladder is the amount of urination, but other decrease factors such as insensitive steaming and sensitive steaming may be considered. Insensitive digestion is the water lost by exhalation from the lungs, about 1 liter per day. Insensitive digestion may be calculated from the relationship between temperature, weight and fever. Sensitive excretion is sweating. Sensitive digestion may be estimated by a comfort index PWV (Predicted Mean Vote) or skin resistance. PMV may be calculated using six elements related to the temperature environment (air temperature, average radiation temperature, wind speed, relative humidity, clothing amount, metabolic rate). In addition, defecation may be considered as another reduction factor. The average amount of water excreted per day for general adults is 1300 ml from urine and 100 ml from stool. Therefore, for example, when the difference time is larger than 5 minutes in step 1818 in FIG. 18, it is determined that the stool is defecation, and the drainage amount (handled as urination amount) at that time may be a fixed value of 100 ml.

  Further, in the process shown in FIG. 20, the only increasing factor for the accumulated intravesical urine volume is the oral water intake, but other increasing factors such as metabolic water may be considered. Metabolic water is water generated by substance metabolism in the body. In the case of general adults, the metabolic water is about 300 ml / day. Oral water intake taken with meals may also be considered. In general, in the case of general adults, 2000 ml is the amount of water taken orally, of which about 500 to 700 ml is taken with meals. Therefore, the water intake by drinking water is 1300-1500 ml.

  Although each embodiment has been described in detail above, it is not limited to a specific embodiment, and various modifications and changes can be made within the scope described in the claims. It is also possible to combine all or a plurality of the components of the above-described embodiments.

  For example, in the embodiment described above, the sensor device 10 includes the gyro sensor 14, but the gyro sensor 14 is not necessarily essential and may be omitted. Further, the acceleration sensor 12 of the sensor device 10 has three axes, but may have two axes or one axis. For example, in the case of two axes, detection (estimation) with relatively high accuracy can be maintained if the two axes are the Y axis and the X axis. In addition, although the accuracy is lowered, it is possible to use the Y axis or the X axis as one axis.

  Moreover, in the Example mentioned above, the simple structure is implement | achieved by using only the sensor device 10 (ultimately only the acceleration sensor 12 of the sensor device 10) especially for detection of a drink action. However, other sensors can be used as an auxiliary. For example, an RF tag may be embedded in the container, and the sensor device 10 may detect the RF tag, thereby detecting that the user has held the container in the hand (that is, the “protruding behavior” described above). Also, considering that the person uses muscles near the wrist when lifting heavy objects, when the user's myoelectric value (for example, a value measured by an electromyograph) changes by more than a threshold, “lifting behavior” May be detected.

  In the above-described embodiment, the sensor device 10 is mounted on the user's wrist, but is mounted on a hand portion other than the user's wrist, for example, the back of the hand, a portion between the wrist and the elbow, a finger, or the like. Also good.

  In the embodiment described above, some or all of the functions of the processing apparatus 100 described above may be incorporated in the sensor device 10. Of course, when all of the functions of the processing apparatus 100 are built in the sensor device 10, wireless communication between the sensor device 10 and the processing apparatus 100 is unnecessary.

  In the above-described embodiments, the beverage may be a liquid or a fluid having viscosity such as a jelly shape.

In addition, the following additional remarks are disclosed regarding the above Example.
(Appendix 1)
An acceleration sensor worn on the user's hand;
Based on the output signal of the acceleration sensor, the oral water intake when the user takes in the water contained in the container from the mouth is estimated, and based on the estimated oral water intake, the urine in the bladder of the user An intravesical urine volume estimation device including a processing device for estimating the volume.
(Appendix 2)
The intravesical urine volume estimation device according to appendix 1, wherein the processing device acquires an output signal of the acceleration sensor via wireless communication with the acceleration sensor.
(Appendix 3)
The intravesical urine volume estimation device according to appendix 2, wherein the processing device estimates the oral water intake of the user during the beverage behavior based on the output signal of the acceleration sensor during the detected beverage behavior. .
(Appendix 4)
The processing device estimates a first moisture capacity in the container based on an output signal of the acceleration sensor when the user lifts the container by hand, and the user holds the container by hand. Based on the output signal of the acceleration sensor during the lowering action, the second moisture capacity in the container is estimated, and based on the difference in the second moisture capacity from the first moisture capacity, The intravesical urine volume estimation apparatus according to appendix 2 or 3, wherein the oral water intake of the user is estimated.
(Appendix 5)
The processing device estimates a first moisture capacity in the container based on an integrated value of vibration components of an output signal of the acceleration sensor when the user lifts the container by hand, and the user The intravesical urine volume estimation device according to appendix 4, wherein a second water volume in the container is estimated based on an integrated value of vibration components of an output signal of the acceleration sensor when the container is held down by hand. .
(Appendix 6)
The processing device determines whether or not there is an action of drinking water in the container during the beverage action of the user based on an output signal of the acceleration sensor, and the user at the time of the drink action based on the determination result The intravesical urine volume estimation device according to appendix 2, which estimates the oral water intake of
(Appendix 7)
When it is determined that there has been an action of drinking the water in the container during the user's beverage action, the processing device determines the water capacity in the container before the user's drink action, The intravesical urine volume estimation device according to appendix 6, which is estimated as a user's oral water intake.
(Appendix 8)
The processing apparatus estimates the urinary volume in the bladder of the user based on the elapsed time from the detected beverage behavior and the estimated oral water intake for the detected beverage behavior, The intravesical urine volume estimation apparatus as described.
(Appendix 9)
The intravesical urine volume according to appendix 2, wherein the processing device estimates a urinary volume and estimates the bladder urine volume of the user based on the estimated oral water intake and the estimated urinary volume. Estimating device.
(Appendix 10)
The processor is an acceleration detected by the acceleration sensor, and the acceleration (X-axis component) in the longitudinal direction of the user's hand (direction from the elbow to the wrist) changes by a predetermined threshold value or more. The intravesical urine volume estimation device according to any one of appendices 2 to 9, wherein an action of the user pushing a hand forward is detected.
(Appendix 11)
The processing device is an acceleration detected by the acceleration sensor, the acceleration (X-axis component) in the longitudinal direction of the user's hand (direction from the elbow to the wrist), and when the user opens the palm When the combined acceleration (= √ (Gy ² + Gz ² )) with acceleration (Z-axis component) in a direction substantially perpendicular to the palm changes by a predetermined threshold value (for example, 0.5 G), the user moves the hand forward. The intravesical urine volume estimation apparatus according to any one of appendices 2 to 9, which detects an action protruding into the urine.
(Appendix 12)
The processor is an acceleration detected by the acceleration sensor, and the acceleration (X-axis component) in the longitudinal direction (direction from the elbow to the wrist) of the user's hand increases toward 1G. Furthermore, the intravesical urine volume estimation apparatus according to any one of appendices 2 to 11, wherein the user detects an action of lifting the container by hand.
(Appendix 13)
The processing device is an acceleration detected by the acceleration sensor, and is an acceleration in the vertical direction (Y-axis component) when the user opens the palm substantially parallel to the palm and extends the hand straight to the front. The intravesical urine volume estimation device according to any one of appendices 2 to 12, wherein the user detects an action of lifting the container by hand when the size of the urine decreases toward 0G.
(Appendix 14)
When the acceleration detected by the acceleration sensor and the acceleration (X-axis component) in the longitudinal direction of the user's hand (direction from the elbow to the wrist) decreases toward 0G In addition, the intravesical urine volume estimation device according to any one of appendices 2 to 13, wherein the user detects an action of manually lifting the container.
(Appendix 15)
The processing device is an acceleration detected by the acceleration sensor, and is an acceleration in the vertical direction (Y-axis component) when the user opens the palm substantially parallel to the palm and extends the hand straight to the front. The intravesical urine volume estimation apparatus according to any one of appendices 2 to 14, wherein the user detects an action of lifting the container by hand when the size increases toward 1G.
(Appendix 16)
The processing device is an acceleration detected by the acceleration sensor, and is an acceleration in the vertical direction (Y-axis component) when the user opens the palm substantially parallel to the palm and extends the hand straight to the front. And the acceleration (Y-axis component) remains in the vicinity of 1G, and the sign of the acceleration (Y-axis component) is reversed. The intravesical urine volume estimation device according to appendix 6 or 7, which detects an action of drinking water in the container.
(Appendix 17)
The processing device is configured based on a relationship between the user's past actual measurement data regarding the integrated value of the vibration component of the output signal of the acceleration sensor and the integrated value of the vibration component during the beverage action detected this time. The intravesical urine volume estimation device according to appendix 5, which estimates a water volume and the second water volume.
(Appendix 18)
Obtain the output signal of the acceleration sensor worn on the user's hand,
Based on the acquired output signal of the acceleration sensor, estimate the oral water intake when the user takes the water that has entered the container from the mouth,
A method for estimating intravesical urine volume, wherein the urinary bladder volume of the user is estimated based on the estimated oral water intake.
(Appendix 19)
Based on the output signal of the acceleration sensor that is worn on the user's hand, estimating the oral water intake when the user ingests the water contained in the container from the mouth,
Based on the estimated oral water intake, the user's bladder urine volume is estimated,
A program that causes a computer to execute processing.
(Appendix 20)
Based on the output signal of the acceleration sensor that is worn on the user's hand, estimating the oral water intake when the user ingests the water contained in the container from the mouth,
Based on the estimated oral water intake, the user's bladder urine volume is estimated,
A storage medium storing a program that causes a computer to execute processing.
(Appendix 21)
Based on the output signal of the acceleration sensor that is worn on the user's hand, the oral water intake when the user ingests the water contained in the container from the mouth is estimated, based on the estimated oral water intake, A processing apparatus for estimating a urine volume in the bladder of the user.
(Appendix 22)
An acceleration sensor worn on the user's hand;
Based on the output signal of the acceleration sensor, the oral water intake when the user takes in the water contained in the container from the mouth is estimated, and based on the estimated oral water intake, the urine in the bladder of the user An intravesical urine volume estimation device including a processing device for estimating the volume;
A wireless communication network for transmitting the output signal of the acceleration sensor to the processing device by wireless communication.
(Appendix 23)
In any one of Supplementary notes 1 to 22, the acceleration sensor is attached to a user's wrist.

DESCRIPTION OF SYMBOLS 1 Intravesical urine volume estimation apparatus 10 Sensor device 12 Acceleration sensor 14 Gyro sensor 20 Management computer 100 Processing apparatus 110 User profile production | generation part 112 Oral water intake estimation part 114 Urination volume estimation part 116 Environment temperature / humidity recording part 118 Bladder urine volume Estimator 200 Second sensor device 202 Acceleration sensor 204 Temperature / humidity sensor

Claims (8)

An acceleration sensor worn on the user's hand;
Based on the output signal of the acceleration sensor, the moisture contained in the container by the user is grasped by hand, and the oral water intake when ingested from the mouth is estimated. An intravesical urine volume estimation device comprising: a processing device that estimates the urinary bladder volume of the user based on the above.   The processing device includes an action in which the user pushes his hand forward based on an output signal of the acceleration sensor, an action in which the user lifts the container with his hand, and an action in which the user lifts the container with his hand. And detecting the user's beverage behavior and estimating the user's oral water intake during the beverage behavior based on an output signal of the acceleration sensor during the detected beverage behavior. Item 2. The intravesical urine volume estimation device according to Item 1.   The processing device estimates a first moisture capacity in the container based on an output signal of the acceleration sensor when the user lifts the container by hand, and the user holds the container by hand. Based on the output signal of the acceleration sensor during the lowering action, the second moisture capacity in the container is estimated, and based on the difference in the second moisture capacity from the first moisture capacity, The intravesical urine volume estimation apparatus according to claim 2, wherein the oral water intake of the user is estimated.   The processing device estimates a first moisture capacity in the container based on an integrated value of vibration components of an output signal of the acceleration sensor when the user lifts the container by hand, and the user The intravesical urine volume estimation according to claim 3, wherein a second water volume in the container is estimated based on an integrated value of vibration components of an output signal of the acceleration sensor during an action of manually lifting the container. apparatus.   The processing device determines whether or not there is an action of drinking water in the container during the beverage action of the user based on an output signal of the acceleration sensor, and the user at the time of the drink action based on the determination result The intravesical urine volume estimation apparatus according to claim 2, wherein the oral water intake is estimated.   When it is determined that there has been an action of drinking the water in the container during the user's beverage action, the processing device determines the water capacity in the container before the user's drink action, The intravesical urine volume estimation apparatus according to claim 5, wherein the apparatus is estimated as a user's oral water intake. Obtain the output signal of the acceleration sensor worn on the user's hand,
Based on the acquired output signal of the acceleration sensor, the moisture contained in the container by the user , holding the container by hand, estimating the oral water intake when ingesting from the mouth,
A computer-implemented bladder urine volume estimation method comprising estimating the bladder urine volume of the user based on the estimated oral water intake. Based on the output signal of the acceleration sensor attached to the user's hand, the moisture contained in the container by the user , holding the container by hand, estimating the oral water intake when ingesting from the mouth,
Based on the estimated oral water intake, the user's bladder urine volume is estimated,
A program that causes a computer to execute processing.