JP2015133608A - Wake-up notification system, wake-up notification program, wake-up notification method, and wake-up notification device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To reduce a burden on a nursing person by enabling the nursing person to grasp timing of a child waking up to prepare nursing action by using a period until the child wakes up.SOLUTION: A wake-up notification system (100) used in a space in which a child is sleeping includes a robot 10, a distance image sensor 12, a mic 14, a temperature sensor 16, a humidity sensor 18, and an illuminance sensor 20 which are provided around the child. The wake-up notification system (100) acquires wake-up factors for predicting a wake-up of the child by using these sensors; inputs the factors to a determination model created by a machine learning method for outputting, as a prediction result, a probability of a wakeup after a predetermined period; determines that the child is to wake up within the predetermined period when the possibility of the prediction result is higher than a threshold; and transmits a message for notifying that the child wakes up within the predetermined period to a portable terminal 22 of a nursing person.

Description

  The present invention relates to a wake-up notification system, a wake-up notification program, a wake-up notification method, and a wake-up notification device, and more particularly to, for example, a wake-up notification system, a wake-up notification program, a wake-up notification method, and a wake-up notification device that can be used for sleeping children. .

  An example of background art is disclosed in Patent Document 1. In the alarm system of this patent document 1, the time slot | zone when the user during sleep will be in a REM sleep state can be estimated based on a user's life form information. If the predicted time zone includes a predetermined scheduled wake-up time, the time zone is specified as the wake-up time zone. On the other hand, when the estimated wake-up time is not included in the predicted time zone, the closest time zone is specified as the wake-up time zone. Then, the time closest to the scheduled wake-up time in the wake-up time zone is specified as the wake-up time.

JP 2005-311534 [H04M 3/42, H04M 1/00, H04M 1/725, H04M 3/493]

  However, in the alarm system of Patent Document 1, the wake-up time cannot be specified unless the scheduled wake-up time is determined in advance. Therefore, this system cannot be used for children who do not use alarms.

  Therefore, a main object of the present invention is to provide a novel wakeup notification system, wakeup notification program, wakeup notification method, and wakeup notification device.

  Another object of the present invention is to provide a wake-up notification system, a wake-up notification program, a wake-up notification method, and a wake-up notification device that can reduce the burden on the childcare worker.

  The present invention employs the following configuration in order to solve the above problems. The reference numerals in parentheses, supplementary explanations, and the like indicate the corresponding relationship with the embodiments described in order to help understanding of the present invention, and do not limit the present invention.

  The first invention comprises an acquisition means for acquiring a wake-up factor, a prediction means for predicting whether a child wakes up by the wake-up factor, and a notification means for notifying a prediction result when the child is predicted to wake up. System.

  In the first invention, the wake-up notification system (100: reference numerals exemplifying corresponding parts in the embodiment, hereinafter the same) is used, for example, in a space where a child is sleeping on a bed. The acquisition means (80, S3-S13) includes, for example, a distance image sensor (12), a microphone (14), a temperature sensor (16), a humidity sensor (18), and an illuminance sensor (20) arranged around the bed. Use it to get a wake-up factor to predict the wake-up of a sleeping child. For example, a discrimination model is created by using the acquired wake-up factor as teacher data and learning the teacher data by a machine learning technique such as SVM. The predicting means (80, S35) predicts whether or not the child will wake up within a predetermined time by using, for example, the discrimination model created in this way. A notification means (80, S39) notifies a prediction result with respect to the portable terminal (22) etc. which a childcare person possesses, for example, when a child is predicted to get up within a predetermined time.

  According to the first invention, since the childcare person can grasp the timing when the child wakes up, the childcare person can prepare for childcare behavior using the time until the child wakes up. Therefore, the burden on the childcare worker is reduced.

  The second invention is dependent on the first invention, the wake-up factor includes a maximum value of a sound volume generated in a space where the child is present, and the predicting means uses the maximum value to determine whether the child wakes up. Predict.

  In the second invention, for example, when a loud sound is generated in the space, the possibility that the child will wake up becomes high. Therefore, the predicting means predicts whether the child will get up using the maximum value of the sound generated in the space.

  According to the second invention, the child's wake-up can be predicted using the maximum value of the sound generated in the space.

  A third invention is dependent on the first invention or the second invention, the wake-up factor includes the sleep time of the child, and the predicting means predicts whether the child wakes up using the sleep time.

  In the third invention, for example, when the sleeping time of the child is longer than the average sleeping time, the possibility that the child wakes up increases. Therefore, the predicting means predicts whether or not the child will wake up using the sleeping time of the child.

  According to the third aspect, the child's sleep time can be used to predict the child's wake-up.

  A fourth invention is according to any one of the first to third inventions, further comprising a robot that outputs content, and when the child is predicted to wake up, the robot outputs the content.

  In the fourth invention, the robot (10) is arranged, for example, on a handrail of a bed where a child is sleeping, and outputs content such as a greeting. For example, when it is predicted that a child will wake up, the robot changes from a standby state to an active state, and the robot outputs content.

  According to the fourth aspect of the invention, since the childcare action that is performed after the child gets up is assisted, the burden on the childcare worker is reduced.

  The fifth invention is dependent on the fourth invention and further comprises a judging means for judging whether the child has woken up, and when it is judged that the child has woken up, the robot outputs the content.

  In the fifth invention, the determination means (36, S63, S65), for example, captures the child's face and applies image recognition processing to the captured image to determine whether the child has woken up. When it is determined that the child has woken up, the robot outputs the content.

  According to the fifth aspect, the content is output to the child at an appropriate timing.

  The sixth invention provides a processor (80) of the wake-up notification system for obtaining means (S3-S13) for obtaining a wake-up factor, predicting means (S35) for predicting whether the child wakes up by the wake-up factor, and Then, when predicted, this is a wake-up prediction program that functions as notifying means (S39) for notifying the prediction result.

  In the sixth invention as well, as in the first invention, the childcare worker can grasp the timing when the child wakes up, and can use the time until the child wakes up to prepare for childcare behavior. .

  In the seventh invention, the processor (80) of the wake-up notification system acquires the wake-up factor (S3-S13), the prediction step (S35) for predicting whether the child wakes up by the wake-up factor, and the child wakes up Then, when predicted, this is a wake-up prediction method that executes a notification step (S39) of notifying the prediction result.

  In the seventh invention as well, as in the first invention, the childcare worker can grasp the timing when the child wakes up, and can use the time until the child wakes up to prepare for childcare behavior. .

  The eighth aspect of the invention relates to an acquisition means (80, S3-S13) for acquiring a wake-up factor, a prediction means (80, S35) for predicting whether a child wakes up by the wake-up factor, and when the child is predicted to wake up, This is a wake-up notification device including notification means (80, S39) for notifying the prediction result.

  In the eighth invention as well, as in the first invention, the childcare person can grasp the timing when the child wakes up, and can use the time until the child wakes up to prepare for childcare behavior. .

  According to this invention, the burden on the childcare worker can be reduced.

  The above object, other objects, features, and advantages of the present invention will become more apparent from the following detailed description of embodiments with reference to the drawings.

FIG. 1 is an illustrative view showing an outline of a wake-up notification system according to an embodiment of the present invention. FIG. 2 is an illustrative view showing one example of a configuration of the wake-up notification system shown in FIG. 3 is an illustrative view showing an example of the appearance of the robot shown in FIG. 1, FIG. 3 (A) shows the front of the robot, and FIG. 3 (B) shows the side of the robot. FIG. 4 is a block diagram showing an example of the electrical configuration of the robot shown in FIG. FIG. 5 is a block diagram showing an example of the electrical configuration of the distance image sensor shown in FIG. FIG. 6 is a block diagram showing an example of an electrical configuration of the central controller shown in FIG. FIG. 7 is an illustrative view showing one example of a configuration of an environmental data table stored in the memory of the central control unit shown in FIG. FIG. 8 is an illustrative view showing one example of a message notified from the central control apparatus shown in FIG. FIG. 9 is an illustrative view showing one example of a memory map of a memory of the central control unit shown in FIG. 10 is an illustrative view showing one example of a memory map of a memory of the robot shown in FIG. FIG. 11 is a flowchart showing an example of acquisition processing of the processor of the central controller shown in FIG. FIG. 12 is a flowchart showing an example of the wake-up notification process of the processor of the central controller shown in FIG. FIG. 13 is a flowchart showing an example of the wake-up correspondence process of the processor of the robot shown in FIG.

  With reference to FIG. 1, the wake-up notification system 100 of this embodiment is used in a space (environment) such as a room where a child is sleeping. For example, a bed is placed in the space, and the child sleeps on the bed. Parents such as parents and childcare workers are in or around the space, raising children or doing housework. A robot 10, a distance image sensor 12, a microphone 14, a temperature sensor 16, a humidity sensor 18, and an illuminance sensor 20 are provided around the child. The childcare person possesses the portable terminal 22.

  The robot 10 is provided so as to enter the field of view of the child. In the embodiment, the robot 10 is disposed on the handrail of the bed as a position that enters the child's field of view. The robot 10 can attract children's attention by outputting contents such as greetings and music.

  The distance image sensor 12 is provided on the bed for the purpose of detecting the movement of the child. The microphone 14 is provided on a handrail of the bed in order to collect sound (noise) generated in the space. The temperature sensor 16 is provided on the handrail of the bed in order to measure the temperature around the child. The humidity sensor 18 is provided on the handrail of the bed in order to measure the humidity around the child. The illuminance sensor 20 is provided on the handrail of the bed in order to measure the illuminance in the space where the child is present.

  The mobile terminal 22 is a mobile phone possessed by a childcare worker. The wake-up notification system 100 transmits (notifies) a message to the portable terminal 22, and when the portable terminal 22 receives the message, the childcare person is notified of reception of the message by voice or vibration. The childcare person can check the message from the wake-up notification system 100 using the portable terminal 22. In another embodiment, a data terminal such as ipod touch (registered trademark) or PDA may be employed as the mobile terminal 22.

  The wake-up notification system 100 predicts the child's wake-up using the distance image sensor 12, the microphone 14, the temperature sensor 16, the humidity sensor 18, and the illuminance sensor 20. Then, the prediction result is notified to the mobile terminal 22.

  In addition, although the space of an Example is a room where the child is sleeping, not only this but the wake-up notification system 100 will be used if the child can sleep in a nursery school, a kindergarten, a school nursery school, a hospital, etc. Is possible.

  A plurality of distance image sensors 12, microphones 14, temperature sensors 16, humidity sensors 18, and illuminance sensors 20 may be placed in the space. Further, the microphone 14, the temperature sensor 16, the humidity sensor 18, and the illuminance sensor 20 may be provided at a place other than the handrail of the bed.

  Referring to FIG. 2, central control device 24 of wake-up notification system 100 is also called a wake-up notification device, and is connected to distance image sensor 12, microphone 14, temperature sensor 16, humidity sensor 18, illuminance sensor 20, and the like. The central control device 24 performs wireless communication with the robot 10 and the portable terminal 22 via the network 1000. The central control device 24 acquires sensor information output by the distance image sensor 12, the microphone 14, the temperature sensor 16, the humidity sensor 18, and the illuminance sensor 20 every first time (for example, 0.05 seconds). Then, the central control device 24 stores environmental data (see FIG. 7) including child movement, sound information of sounds generated in the space, and the like from the acquired information of each sensor in a table.

  FIG. 3A shows the appearance of the front of the robot 10, and FIG. 3B shows the appearance of the side of the robot 10. Referring to FIGS. 3A and 3B, the robot 10 is large enough to be held by a child and is like a doll having a head, a torso, two arms, and two legs. It has a nice shape. In the head of the robot 10, a speaker 30 is provided at the mouth portion, and a camera 32 is provided at the left eye portion. Further, the connecting portion between the body and the foot, that is, the buttocks is called an arrangement portion 34.

  The speaker 30 is used to output speech content and music content. The camera 32 is used for photographing a child. The placement unit 34 is in a substantially horizontal state so that the robot 10 can be stably placed on a handrail of the bed. When placing the robot 10 on the bed, Magic Tape (registered trademark), a rubber band, an adhesive tape, or the like may be used.

  FIG. 4 is an illustrative view showing an electrical configuration of the robot 10. Referring to FIG. 4, the robot 10 includes a processor 36, which may be called a microcomputer or a CPU. To the processor 36, a camera 32, a memory 38, a D / A converter 40, a wireless LAN module 42, and the like are connected.

  The processor 36 controls the entire robot 10. Further, the processor 36 can set an active state in which content is output and a standby state in which power consumption is suppressed compared to the active state. For example, the processor 36 activates the robot 10 when receiving an active signal from the central controller 24.

  The memory 38 includes a ROM and a RAM. The ROM stores in advance a control program for controlling the operation of the circuit. The RAM is used as a work memory or a buffer memory for the processor 36. The ROM stores greetings and music contents.

  A speaker 30 is connected to the D / A converter 40. The D / A converter 40 converts the content into an audio signal and supplies it to the speaker 30 via an amplifier. Accordingly, audio based on the content is output from the speaker 30.

  An image of a child photographed by the camera 32 is input to the processor 36. The processor 36 performs image recognition processing on the image, and determines whether a child is awake using the recognition result.

  The wireless LAN module 42 transmits the transmission data given from the processor 36 to the central control device 24 via the network 1000, and gives the reception data sent from the central control device 24 to the processor 36. For example, the transmission data is an image of a child photographed by the camera 32, and the reception data is a signal for causing the robot 10 to transition to the active state.

  FIG. 5 is a block diagram showing an electrical configuration of the distance image sensor 12. Referring to FIG. 5, distance image sensor 12 includes a control IC 60 and the like. An A / D converter 62, a camera 66, a depth sensor 68, a depth camera 70, an I / O 72, and the like are connected to the control IC 60.

  The control IC 60 includes a cache memory and the like, and controls the operation of the distance image sensor 12. For example, the control IC 60 operates according to a command from the central controller 24 and transmits the detected result to the central controller 24.

  A microphone 64 is connected to the A / D converter 62, and an audio signal from the microphone 64 is converted into a digital audio signal by the A / D converter 62 and input to the control IC 60. The sound collected by the microphone 64 is used to measure the volume of noise in the space together with the sound collected by the microphone 14.

  The camera 66 is a camera for photographing RGB information of the space in which the distance image sensor 12 is installed, that is, a color image. In addition, the camera 66 is provided in the distance image sensor 12 so as to be able to capture a space that is substantially the same as the space that is captured by the depth camera 70 described later.

  The depth sensor 68 is, for example, an infrared projector, and the depth camera 70 is, for example, an infrared camera. The depth sensor 68 irradiates the front of the distance image sensor 12 with, for example, infrared laser light. A special pattern is drawn in the space by the irradiated laser light, and the depth camera 70 captures the drawn pattern. The captured image is input to the control IC 60, and the control IC 60 analyzes the image to measure the depth information of the space irradiated with the laser light.

  The I / O 72 is a digital port capable of input / output control, and an audio signal, RGB information, and depth information are output from the output port and provided to the central controller 24. On the other hand, a control signal is output from the central control device 24 and applied to the input port.

  The distance image sensor 12 outputs RGB information and depth information and is sometimes called an RGB-D sensor.

  The distance image sensor 12 of the embodiment employs a product called Kinect (registered trademark) manufactured by Microsoft (registered trademark). However, in other embodiments, Xtion manufactured by ASUS (registered trademark), D-IMAGEr (registered trademark), which is a three-dimensional distance image sensor manufactured by Panasonic (registered trademark), and the like are employed as the distance image sensor 12. Also good.

  FIG. 6 is a block diagram showing an electrical configuration of the central controller 24. Referring to FIG. 6, the central control device 24 includes a processor 80, sometimes called a microcomputer or CPU. The processor 80 is connected to the distance image sensor 12, the temperature sensor 16, the humidity sensor 18, the illuminance sensor 20, the memory 82, the A / D converter 84, the output device 86, the input device 88, the communication LAN board 90, and the like.

  The distance image sensor 12 outputs depth information as described above. This depth information includes the shape of the child (person) in the space and the distance to the child. For example, when the child is sensed by the distance image sensor 12 provided on the ceiling, the shape of the child sleeping on the bed is obtained as the depth information.

  Further, the processor 80 obtains depth information from the distance image sensor 12 and obtains position information (for example, position coordinates (X, Y, Z) of feature points such as the center of gravity) of the child on the bed (world coordinate system). Can be calculated. In the embodiment, the moving speed of the child is calculated from the time series change of the child position information, and the acceleration representing the moving of the child is calculated from the speed.

  In another embodiment, the position and posture of the child may be detected using a two-dimensional or three-dimensional LRF instead of the distance image sensor 12. In other embodiments, the movement of the child may be detected by arranging an acceleration sensor under the bed or the like.

  Sensor information acquired from each of the temperature sensor 16, the humidity sensor 18, and the illuminance sensor 20 is input to the processor 80. Then, the processor 80 creates environment data based on the input sensor information and stores it in a table.

  The output device 86 is, for example, a display, and the input device 88 is, for example, a mouse or a keyboard. For example, the childcare person can use the output device 86 and the input device 88 to check the state of the central control device 24 and input information to the central control device.

  The communication LAN board 90 is configured by, for example, a DSP, and sends transmission data given from the processor 80 to the wireless communication device 92. The wireless communication device 92 sends the transmission data to the robot 10 or the portable terminal 22 via the network 1000. To do. Further, the communication LAN board 90 receives data via the wireless communication device 92 and gives the received data to the processor 80.

  FIG. 7 is an illustrative view showing one example of a configuration of the environment data table. The environmental data is data including a child's movement at a certain date and time, sound generated in the space, temperature in the space, humidity and illuminance, and time related to the child's action. The environmental data table stores environmental data including these pieces of information for each row. Therefore, the environment data table shown in FIG. 7 includes columns of date and time, child movement, microphone, temperature, humidity, illuminance, sleep time, and waking time.

  The date and time column stores the date and time when the environmental data was created. As the format of the date and time stored, “yy” indicates “year”, “mm” indicates “month”, “dd” indicates “day”, and “H” indicates “hour”. , “M” indicates “minute”, and “S” indicates “second”.

  In the child movement column, acceleration “a” is stored as a value indicating the child movement. For example, when the movement of a sleeping child increases, the possibility that the child will wake up increases, and this is used to determine whether the child is in such a state.

  In the microphone column, “MB” is stored as the maximum volume of the sound acquired from the microphone 64 or the microphone 14 of the distance image sensor 12. For example, if a loud sound suddenly occurs, there is a high possibility that the child will get up, and this is used to determine whether such a situation exists.

  In the temperature column, the temperature “t” acquired by the temperature sensor 16 is stored. For example, when the space becomes extremely hot or cold, there is a high possibility that the child will wake up, so it is used to determine whether the space is in such a situation.

  In the humidity column, the humidity “h” acquired by the humidity sensor 18 is stored. For example, if the humidity of the space becomes extremely high, there is a high possibility that the child will wake up, and this is used to determine whether the space is in such a situation.

  In the illuminance column, the illuminance “il” acquired by the illuminance sensor 20 is stored. For example, if the space becomes brighter, the possibility that the child will wake up becomes higher, so it is used to determine whether the space is in such a situation.

  In the sleep time column, “ST” is stored as the time since the child went to bed. “WT” is stored as the time since the child got up in the column of the time of staying up. When the time “ST” is determined that the child has gone to bed, the corresponding variable is counted, and when the time “WT” is determined that the child has woken up, the corresponding counter is counted. The time “ST” and the time “WT” are stored in the environment data table based on the corresponding variables. Further, in the embodiment, the sleep and wake-up of the child are determined based on the change in the position information of the child, and the corresponding variables are initialized when the child goes to sleep or wakes up. In other embodiments, the child's sleep or wake-up may be determined based on a notification from the childcare worker.

  For example, if the sleep time “ST” is longer than the average sleep time, the child is likely to get up. In addition, the longer the wake-up time “WT”, the lower the possibility that the child will get up. Therefore, the sleep time “ST” and the waking time “WT” are used to determine whether the child is in these states. In the embodiment, the average sleep time of the child is stored in the memory 82.

  The central controller 24 stores such environmental data every first time in the environmental data table. Then, the central controller 24 predicts the child's getting up every second time.

  In addition, the information on the child's movement, maximum volume, temperature, humidity, illuminance, sleep time, and waking time included in the environmental data is information for predicting the child's wake-up and is collectively called the wake-up factor. Sometimes.

  In the embodiment, teacher data is learned by a machine learning method such as SVM (Support Vector Machine) using the wake-up factor for the second time as teacher data from a predetermined time before the child wakes up. As a result, a discrimination model for predicting wakeup within a predetermined time is created. When an unknown wake-up factor for the second time is input to this discrimination model, the probability that the child will wake up within a predetermined time is output as a prediction result. When the probability is greater than the threshold value, it is determined that the child wakes up within a predetermined time.

  For example, when a wake-up factor for the second time is input as unknown data for a discrimination model that predicts wake-up, the probability is output as 85%. It is judged to get up. If the threshold is 90%, it is determined that the child will not get up within a predetermined time.

  Referring to FIG. 8, for example, when the probability output as a prediction result is larger than a threshold value, central controller 24 informs portable terminal 22 possessed by the childcare person that the child will wake up within a predetermined time. Send a message. The childcare person can grasp the timing when the child wakes up by checking the message. Therefore, the childcare person can use the time until the child wakes up to prepare for childcare. Therefore, the burden on the childcare worker is reduced.

  Further, in the embodiment, when the child is expected to wake up, the robot 10 transitions to the active state. When the robot 10 transitions to the active state, a child is photographed by the camera 32 of the robot 10, and face recognition processing is added to the photographed image. The robot 10 determines at regular intervals whether the recognized child's eyes are open, that is, whether he / she has woken up. When the robot 10 recognizes that the child has woken up, for example, it greets "Good morning" or plays music. Thereby, since the childcare action performed after the child wakes up is assisted, the burden on the childcare worker is reduced. In particular, since the robot 10 recognizes the child's wake-up, the content is output to the child at an appropriate timing.

  In the embodiment, the wake-up prediction is recognized every second time longer than the first time necessary for acquiring the environmental data. That is, wake-up is predicted after environmental data (wake-up factor) necessary for predicting child wake-up is acquired. This makes it possible to accurately predict the child's getting up.

  The above has outlined features of the embodiment. Hereinafter, the embodiment will be described in detail with reference to the memory map of the memory 82 of the central controller 24 shown in FIG. 9, the memory map of the memory 38 of the robot 10 shown in FIG. 10, and the flowcharts shown in FIGS. To do.

  FIG. 9 is an illustrative view showing one example of a memory map of the memory 82 of the central controller 24 shown in FIG. As shown in FIG. 9, the memory 82 includes a program area 302 and a data storage area 304. In the program storage area 302, information is acquired from each sensor as a program for operating the central controller 24, and an acquisition program 310 for storing environmental data in the environmental data table and a wake-up are predicted and notified. The wake-up notification program 312 is stored. Although illustration is omitted, the program for operating the central controller 24 includes a program for creating a message to be notified.

  The data storage area 304 is stored in the environmental data table 330 and the average sleep time data 332, and is provided with a sleep flag 334 and the like. The environmental data table 330 is, for example, a table having the configuration shown in FIG. 7, and stores environmental data. The average sleep time data 332 is data including a value calculated using the sleep time stored in the environment data table 330.

  The sleep flag 334 is a flag used when measuring the sleep time “ST” and the waking time “WT”. For example, the sleep flag 334 is composed of a 1-bit register. When the sleep flag 334 is turned on (established), a data value “1” is set in the register. On the other hand, when the sleep flag 334 is turned off (not established), a data value “0” is set in the register.

  For example, the sleep flag 334 is turned on when it is determined that the child has gone to bed, and turned off when the child wakes up. When the sleep flag 334 is turned on, that is, when the child goes to bed, a variable for counting the sleep time “ST” is initialized, and measurement of the sleep time “ST” is started. Also, the counting of the variable corresponding to the waking time “WT” is stopped. On the other hand, when the sleep flag 334 is turned off, that is, when the child wakes up, a variable for counting the wake-up time “WT” is initialized, and measurement of the wake-up time “WT” is started. The Also, the count of the variable corresponding to the sleep time “ST” is stopped.

  Although not shown, the data storage area 304 is also provided with a buffer for temporarily storing the results of various calculations, and other counters and flags necessary for the operation of the central controller 24.

  FIG. 10 is an illustrative view showing one example of a memory map of the memory 38 of the robot 10 shown in FIG. As shown in FIG. 10, the memory 38 includes a program area 402 and a data storage area 404. The program storage area 404 stores, for example, a wake-up correspondence program 410 for outputting content after transitioning to the active state as a program for operating the robot 10. Although illustration is omitted, the program for operating the robot 10 includes a program for performing face recognition and the like.

  The data storage area 404 is also provided with a buffer for temporarily storing the results of various calculations, and other counters and flags necessary for the operation of the robot 10.

  The processor 80 of the central controller 24 processes a plurality of tasks including the acquisition process shown in FIG. 11 and the wake-up notification process shown in FIG. 12 under the control of the Linux (registered trademark) -based OS and other OSs. To do.

  FIG. 11 is a flowchart of the acquisition process. When the central controller 24 is turned on and an execution command for the acquisition process is issued, the acquisition process is executed. An execution instruction for the acquisition process is issued every first time.

  When the acquisition process is executed, the processor 80 acquires the current time in step S1. For example, the current time is acquired from the RTC that the processor 80 has. Subsequently, in step S3, the processor 80 acquires information of the distance image sensor 12. That is, the processor 80 acquires the depth information and the audio signal output from the distance image sensor 12.

  Subsequently, the processor 80 acquires an audio signal from the microphone 14 in step S5, acquires a temperature from the temperature sensor 16 in step S7, acquires humidity from the humidity sensor 18 in step S9, and acquires illuminance from the illuminance sensor in step S11. To get. That is, the volume, temperature, humidity, and illuminance of the sound around the child are acquired.

  Subsequently, in step S13, the processor 80 calculates each time. That is, each of the sleeping time “ST” and the waking time “WT” is calculated based on the corresponding variable. The processor 80 that executes the process of step S3-13 functions as an acquisition unit.

  Subsequently, in step S15, the processor 80 creates environment data. That is, the child's movement (acceleration) is calculated based on the depth information, and the maximum volume is selected from the microphone 14 and the microphone 64 of the distance image sensor 12. Then, the temperature, humidity, and illuminance, and each time calculated in step S13 are added to these values to form one environmental data.

  Subsequently, in step S17, the processor 80 stores the current time and environment data. That is, the environmental data is associated with the current time information acquired in step S <b> 1 and stored in the environmental data table 330. Then, when the process of step S17 ends, the processor 80 ends the acquisition process.

  FIG. 12 is a flowchart of the wake-up notification process. When the central controller 24 is turned on and a notification processing execution command is issued, the wake-up notification processing is executed. Note that the execution instruction for the wake-up notification process is issued every second time.

  When the wake-up notification process is executed, in step S31, the processor 80 determines whether there is a child in the bed. That is, it is determined whether the position of the child is detected by the distance image sensor 12. If “NO” in the step S31, that is, if there is no child in the bed, the processor 80 ends the wake-up notification process.

  If “YES” in the step S31, that is, if there is a child in the bed, the processor 80 acquires environmental data for a second time from the current time in a step S33. That is, the child's movement, the maximum volume, the temperature, the humidity, the illuminance, the sleeping time, and the waking time, which are wake-up factors, are read from the environment data table 330. Subsequently, in step S35, the processor 80 executes a wake-up prediction process. That is, the wake-up factor for the second time is input to the discrimination model for predicting wake-up. In addition, the processor 80 which performs the process of step S35 functions as a prediction means.

  Subsequently, in step S37, the processor 80 determines whether or not the probability of the prediction result is greater than a threshold value. That is, the processor 80 determines whether the probability that the child will wake up after a predetermined time is greater than the threshold value. If “NO” in the step S37, that is, if the probability of the prediction result is smaller than the threshold value, the processor 80 ends the wake-up notification process.

  On the other hand, if “YES” in the step S37, that is, if the probability of the prediction result is larger than the threshold value, the processor 80 notifies that the user gets up within a predetermined time in a step S39. For example, as shown in FIG. 8, a message indicating that the child will get up within a predetermined time is transmitted from the central control device 24 to the portable terminal 22. The processor 80 that executes the process of step S39 functions as a notification unit.

  Subsequently, the processor 80 transmits an active signal to the robot 10 in step S41. That is, an active signal is transmitted to the robot 10 in order to change the robot 10 to the active state. Then, when the process of step S41 ends, the processor 80 ends the wake-up notification process.

  The processor 36 of the robot 10 processes a plurality of tasks including a wake-up handling process shown in FIG. 13 under the control of a Linux (registered trademark) -based OS and other OSs.

  FIG. 13 is a flowchart of the wake-up response process. When the robot 10 receives the active signal and transitions to the active state, the wake-up handling process is executed.

  When the wake-up response process is executed, the processor 36 executes an active timer in step S61. In other words, the active timer is executed to measure the time since the robot 10 was activated. The active timer expires when a third time longer than the second time elapses.

  Subsequently, in step S63, the processor 36 executes face recognition processing. That is, the image is captured by the camera 32 and image recognition processing is added to the captured image. Subsequently, in step S65, the processor 36 determines whether or not the user has woken up. That is, as a result of the face recognition process, it is determined whether the face of a child with open eyes has been recognized. If “YES” in step S65, that is, if the face of a child with open eyes is recognized, the processor 36 outputs the content in step S67. For example, the robot 10 utters a greeting such as “Good morning”. Then, when the process of step S67 ends, the processor 36 proceeds to the process of step S71. The processor 36 that executes the processes of steps S63 and S65 functions as a determination unit.

  If “NO” in the step S65, that is, if the face of a child with open eyes is not recognized, the processor 36 determines whether or not the active timer has expired in a step S69. That is, it is determined whether the third predetermined time has elapsed since the robot 10 became active. If “NO” in the step S69, that is, if the third predetermined time has not elapsed since the robot 10 became active, the processor 36 returns to the process of the step S63.

  On the other hand, if “YES” in the step S69, that is, if the third predetermined time elapses after the robot 10 enters the active state, the processor 36 shifts to the standby state in a step S71. That is, unlike the prediction, there is a possibility that the child does not get up, so the robot 10 transitions to the standby state. Then, when the process of step S71 ends, the processor 36 ends the wake-up handling process.

  In another embodiment, the robot 10 may include a motor and wheels, and may freely move in a space where a child is present. In this case, when the wake-up notification process is executed, the processor 80 issues a movement command to the robot 10 so that the robot 10 can head for the child within a predetermined time. At this time, if the robot 10 is in the standby state, after the transition to the active state, the robot 10 moves to a place where it can go to the child within a predetermined time, and the robot 10 enters the standby state again.

  In another embodiment, the robot 10 may further include a microphone, and may be able to communicate with a child who gets up. In this case, since the time during which the child's attention can be attracted by communication becomes longer, the burden on the childcare worker can be further reduced.

  In still another embodiment, the central control device 24 may determine whether the child has woken up, and the determination result may be transmitted to the robot 10. In this case, in the wake-up response process of the robot 10, the process of step S63 is omitted. In step S65, it is determined whether a signal notifying that the wake-up has been received from the central controller 24 is determined.

  In the embodiment, SVM is used as a machine learning method. However, in other embodiments, multiple regression analysis, a neural network, or an algorithm such as C4.5 may be used. For example, when multiple regression analysis is employed, coefficients are calculated using each value of the wake-up factor as an explanatory variable. When the probability of the wake-up prediction result is Z and the sleep time variable is X, the mathematical formula 1 is obtained by multiple regression analysis.

[Equation 1]
Z = intercept + sX
At this time, if data indicating that the child wakes up is obtained when the child's sleep time is 12 hours, if “intercept = 1/13” and “s = 1/13”, the child's sleep time When it becomes 12 hours, the probability Z of the wake-up prediction is 100%.

  In another embodiment, simple threshold processing may be used without using machine learning. If there is a sudden loud noise, the child is likely to get up. Therefore, when the maximum sound is also higher than the first predetermined value, it may be predicted that the child will wake up within a predetermined time. In other words, the child's wake-up can be predicted using the maximum value of the sound generated in the space.

  Furthermore, if the sleep time “ST” is longer than the average sleep time, the child is likely to get up. Therefore, when the sleep time “ST” is larger than a predetermined multiple (second predetermined value) of the average sleep time, the child may be predicted to wake up within the predetermined time. In other words, the child's sleep time can be used to predict the child's wake-up.

  In other embodiments, the child's turning may be detected based on the depth information of the distance image sensor 12. Then, the environment data may include the number of times of turning over. Furthermore, the environmental data may include the average noise in the space and the amount of exercise (exercise time) of the child before going to bed. Then, when predicting the child's wake-up, the number of times of turning over, the average noise in the space, and the amount of exercise of the child before going to sleep may be further used.

  Moreover, the threshold value for predicting wake-up may be arbitrarily set by the childcare worker, or may be automatically set by the central control device 24.

  The message transmitted to the portable terminal 22 may be transmitted by e-mail or may be transmitted using dedicated software. Further, the destination of the message transmission is not limited to the portable terminal 22 and may be transmitted to a terminal such as a PC. Further, instead of the text message, video or audio that conveys the situation from the time when waking up is predicted to the second time before may be transmitted to the mobile terminal 22.

  In still another embodiment, the robot 10 may output the content without determining the child's getting up after the transition to the active state.

  In another embodiment, the robot 10 may always be in an active state. In this case, the central controller 80 notifies the robot 10 that the child's getting up is predicted in the process of step S41.

  In the above-described embodiment, the word “greater than” is used for the threshold value, but “greater than the threshold value” includes the meaning of “greater than or equal to the threshold value”. Further, “smaller than a threshold” includes the meanings of “below the threshold” and “below the threshold”.

  In addition, the plurality of programs described in the present embodiment may be stored in the HDD of a data distribution server and distributed to a system having the same configuration as that of the present embodiment via a network. In addition, storage programs such as CDs, DVDs, and BDs (Blu-ray (registered trademark) Disc) are sold or distributed with these programs stored in storage media such as USB memory and memory card. May be. When the plurality of programs downloaded through the server and storage medium described above are applied to a system having the same configuration as that of this embodiment, the same effect as that of this embodiment can be obtained.

  The specific numerical values given in this specification are merely examples, and can be appropriately changed according to a change in product specifications.

DESCRIPTION OF SYMBOLS 10 ... Robot 12 ... Distance image sensor 14 ... Microphone 16 ... Temperature sensor 18 ... Humidity sensor 20 ... Illuminance sensor 22 ... Portable terminal 24 ... Central control device 30 ... Speaker 32 ... Camera 36 ... Processor 38 ... Memory 64 ... Microphone 80 ... Processor 82 ... Memory 100 ... Wake-up notification system 1000 ... Network

Claims (8)

An acquisition means for acquiring a wake-up factor;
A wake-up notification system comprising: prediction means for predicting whether a child will wake up by the wake-up factor; and notification means for notifying a prediction result when the child is predicted to wake up. The wake-up factor includes a maximum value of a sound volume generated in the space where the child is present,
The wake-up notification system according to claim 1, wherein the prediction means predicts whether the child wakes up using the maximum value. The wake-up factor includes sleep time of the child,
The wake-up notification system according to claim 1, wherein the prediction unit predicts whether the child wakes up using the sleep time. A robot that outputs content;
The wakeup notification system according to any one of claims 1 to 3, wherein the robot outputs content when the child is predicted to wake up. A judgment means for judging whether the child has woken up;
The wake-up notification system according to claim 4, wherein when it is determined that the child has woken up, the robot outputs content. Wake up notification system processor,
An acquisition means for acquiring a wake-up factor;
A prediction unit that predicts whether a child will wake up by the wake-up factor, and a wake-up prediction program that functions as a notification unit that notifies a prediction result when the child is predicted to wake up. The wake-up notification system processor
An obtaining step for obtaining a wake-up factor;
A prediction method for predicting whether or not a child wakes up by the wake-up factor, and a notification step of notifying a prediction result when the child is predicted to wake up. An acquisition means for acquiring a wake-up factor;
A wake-up notification device comprising: prediction means for predicting whether a child wakes up by the wake-up factor; and notification means for notifying a prediction result when the child is predicted to wake up.

Images