JP6281164B2 - Play action recognition system, play action recognition program, play action recognition method, and play action recognition apparatus - Google Patents

Description

  The present invention relates to a play action recognition system, a play action recognition program, a play action recognition method, and a play action recognition device, and more particularly, for example, a play action recognition system, a play action recognition program, and a play used for children playing with playground equipment. The present invention relates to an action recognition method and a play action recognition device.

  An example of background art is disclosed in Patent Document 1. In the child confirmation monitoring system disclosed in Patent Document 1, a child with a transmitter and a plurality of sensors for investigating and supplementing the child are present in the nursery school. The sensor has a camera function, and by searching and supplementing the position of the transmitter, the child can be captured by the camera and a moving image showing the child's state can be generated. Then, when a moving image indicating the state of a certain child is requested, a target child is searched, and a moving image captured by a sensor closest to the child is distributed.

JP 2002-26904 A [H04L 12/18, H04L 12/28, H04N 7/173, H04N 7/18]

  However, in the child confirmation monitoring system of Patent Document 1, in order to confirm the behavior of the child in the nursery school, all the distributed moving images must be viewed, and the burden on the person who confirms is large. In addition, it is difficult to appropriately grasp what kind of behavior the child was doing just by confirming a part of the child's moving image.

  Therefore, a main object of the present invention is to provide a novel play action recognition system, play action recognition program, play action recognition method, and play action recognition apparatus.

  Another object of the present invention is to provide a play behavior recognition system, a play behavior recognition program, a play behavior recognition method, and a play behavior recognition device that can grasp the play behavior of a child.

  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.

1st invention can be moved arbitrarily in the space, the play equipment which outputs its own acceleration, the 1st acquisition means which acquires the acceleration which a play equipment outputs, The position and attitude | position of the child in space are acquired Second recognition means for recognizing the play behavior of the child based on the acceleration of the play equipment and the position and posture of the child, the recognition means based on the acceleration of the play equipment and the position and posture of the child A play behavior recognition system including first recognition means for recognizing first play behavior classified according to social behavior style, and further comprising classification means for classifying a child's personality based on the first play behavior .

In the first invention, the play equipment (10) of the play behavior recognition system (100: reference numerals exemplifying corresponding parts in the embodiment, the same applies hereinafter) can be arbitrarily moved in the space, Outputs its own acceleration. The first acquisition means (80, S5) acquires the acceleration output by the play equipment. For example, a plurality of distance image sensors are provided on the ceiling of the space, and depth information is output from the distance image sensors. Further, the position and posture of the child can be obtained from the depth information, and for example, it is temporarily stored in the central control device of the system. Then, the second acquisition means (80, S33) acquires the position and posture of the child stored in this way. For example, the acceleration and the position and posture of the child are stored in a table. And a recognition means (80, S35, S37) reads acceleration and a child's position and posture from the table, and recognizes a child's play behavior. The recognizing means includes first recognizing means (80, S35), and the first recognizing means is based on the acceleration of the playground equipment and the position and posture of the child, and the social behavior patterns such as “single play” and “bystand” The first play behavior classified by is recognized. Then, the classification means (80, S65) classifies the child's personality based on the recognized play behavior.

  According to the first invention, the childcare person can appropriately grasp what kind of play behavior the child is performing by confirming the recognized play behavior.

  In addition, if the recognized play behavior is automatically memorized, a childcare person such as a nursery teacher can easily create a document such as a childcare diary by referring to the memorized play behavior. In other words, it is possible to reduce the daily work performed by the childcare worker.

A second invention is dependent on the first invention, and the recognition means recognizes second play behavior classified by mental function based on the acceleration of the playground equipment and the position and posture of the child. (80, S37), and the classification means classifies the personality of the child based on the first play behavior and the second play behavior.

In the second invention, the second recognizing means (80, S37) is classified by mental functions such as “sensory play” and “exercise play” based on the acceleration of the play equipment and the position and posture of the child. Recognize second play behavior. The classifying means classifies personalities such as “cumulative type” and “continuous type” based on the first play behavior and the second play behavior.

According to 2nd invention, the precision of classification is improved by classifying a character using two play actions.

The third invention is dependent on the first invention or the second invention , and the first acquisition means and the second acquisition means determine the acceleration of the play equipment and the position of the child every first time (for example, 0.05 seconds). And the posture are recognized, and the recognition means recognizes the child's play behavior every second time (for example, 5 seconds) longer than the first time.

According to the third invention, the play behavior is recognized after the environmental data necessary for recognizing the play behavior is acquired. As a result, children's play behavior can be accurately recognized.

A fourth invention is dependent on the third invention, and the classifying means classifies the child's personality every third time (for example, 5 minutes) longer than the second time.

According to the fourth aspect of the invention, the personality is classified after the play behavior necessary for classifying the personality is recognized. This makes it possible to accurately classify the child's personality.

According to a fifth aspect of the present invention, a play equipment includes a processor (80) of a play behavior recognition system (100) having play equipment (10a, 10b) that can be arbitrarily moved in a space and outputs its own acceleration. Based on the first acquisition means (S5) for acquiring the output acceleration, the second acquisition means (S33) for acquiring the position and posture of the child in the space, and the position of the child and the position and posture of the child, It functions as a recognizing means (S35, S37) for recognizing a play action, and the recognizing means recognizes the first play action classified according to the social action style based on the acceleration of the play equipment and the position and posture of the child. It comprises a first recognition means (80, S35), and based on the first play behavior, classifying means for classifying the child's personality (80, S65) to function as a playing action certification Is a program.

In the fifth invention as well, as in the first invention, the childcare worker can appropriately grasp what kind of play behavior the child is performing by confirming the recognized play behavior.

According to a sixth aspect of the present invention, there is provided a processor (80) of a play behavior recognition system (100) having playground equipment (10a, 10b) that can be arbitrarily moved in a space and that outputs its own acceleration. Based on the first acquisition step (S5) of acquiring the acceleration to be output, the second acquisition step (S33) of acquiring the position and posture of the child in the space, and the acceleration of the play equipment and the position and posture of the child, A recognition step (S35, S37) for recognizing play behavior is executed, and the recognition step recognizes the first play behavior classified by social behavior based on the acceleration of the play equipment and the position and posture of the child. Furthermore , the play behavior recognition method further executes a classification step (S65) for classifying the personality of the child based on the first play behavior .

In the sixth invention as well, as in the first invention, the childcare worker can appropriately grasp what kind of play behavior the child is performing by confirming the recognized play behavior.

7th invention acquires the position and attitude | position of the child in the 1st acquisition means (S5) which acquires the acceleration output from the playground equipment (10a, 10b) which can be moved arbitrarily in space, and space Second acquisition means (80, S33) and recognition means (80, S35, S37) for recognizing the play behavior of the child based on the acceleration of the play equipment and the position and posture of the child , First recognition means (80, S35) for recognizing first play behavior classified according to social behavior based on the acceleration and the position and posture of the child, and further, based on the first play behavior, It is a play action recognition apparatus provided with the classification | category means (80, S65) which classify | categorizes a character .

In the seventh invention as well, as in the first invention, the childcare worker can appropriately recognize what kind of play behavior the child is performing by confirming the recognized play behavior.

  According to this invention, a child's play behavior can be grasped appropriately.

  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 play action recognition system according to an embodiment of the present invention. FIG. 2 is an illustrative view showing one example of a configuration of the play action recognition system shown in FIG. FIG. 3 is a block diagram showing an example of an electrical configuration of a circuit provided in the play equipment shown in FIG. FIG. 4 is a block diagram showing an example of the electrical configuration of the distance image sensor shown in FIG. FIG. 5 is a block diagram showing an example of the electrical configuration of the central control unit shown in FIG. 6 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. 7 is an illustrative view showing a list of first play actions recognized by the central controller shown in FIG. FIG. 8 is an illustrative view showing a list of second play actions recognized by the central controller shown in FIG. FIG. 9 is an illustrative view showing one example of a configuration of the first play action DB shown in FIG. 5. FIG. 10 is an illustrative view showing one example of a configuration of the second play action DB shown in FIG. 5. FIG. 11 is an illustrative view showing a list of personalities classified by the central control unit shown in FIG. 12 is an illustrative view showing one example of a configuration of the personality DB shown in FIG. FIG. 13 is an illustrative view showing one example of a memory map of a memory of the central control unit shown in FIG. FIG. 14 is a flowchart showing an example of acquisition processing of the processor of the central controller shown in FIG. FIG. 15 is a flowchart showing an example of the play action recognition process of the processor of the central control unit shown in FIG. FIG. 16 is a flowchart showing an example of the personality classification process of the processor of the central controller shown in FIG.

  With reference to FIG. 1, the play action recognition system 100 of this embodiment is used in a space (environment) such as a nursery where children are raised. In the nursery school, children can freely move and play, and playground equipment 10 (10a, 10b,...) Is placed. A plurality of distance image sensors 12 (12a, 12b,...) Are provided on the ceiling in the nursery, and a plurality of microphones 14 (14a, 14b,...) Are provided on the wall.

  Each playground equipment 10 can be arbitrarily moved in the nursery school. As will be described in detail later, each playground equipment 10 is provided with a circuit including a microphone 36 and an acceleration sensor 38 (both see FIG. 3). Further, in the embodiment, the play equipment 10 is a stuffed animal in which cotton or the like is put, and the circuit is in a state of being wrapped in cotton in the stuffed animal. For this reason, the circuit is protected by the cotton in the play equipment 10, and the circuit in the inside does not affect the child.

  The plurality of distance image sensors 12 are provided on the ceiling in the nursery school for the purpose of detecting the position and posture of the child. The plurality of microphones 14 are provided on a wall in the nursery school for the purpose of measuring noise in the nursery school, particularly the volume of sound around the floor.

  Then, the play behavior recognition system 100 recognizes, for each child in the nursery school, the first play behavior classified by the social behavior style and the second play behavior classified by the mental function. Furthermore, the play behavior recognition system 100 classifies each child's personality based on the first play behavior and the second play behavior.

  The space of the embodiment is a nursery school where playground equipment is placed, but the play behavior recognition system 100 can also be used in a kindergarten, school nursery school, and the like.

  Also, for simplicity, only three children are shown in FIG. 1, but more children may be raised in the nursery school, or one or two children may be raised. . Similarly, although only two microphones 14 and play equipment 10 are shown, more microphones 14 and play equipment 10 may be placed in the nursery school, or one microphone 14 and play equipment 10 may be provided.

  When there is no need to distinguish between the playground equipment 10a and 10b, the playground equipment 10a is simply referred to as “playground equipment 10”. Further, when it is not necessary to distinguish the distance image sensors 12a, 12b,. When there is no need to distinguish between the microphones 14a, 14b,..., They are simply referred to as “microphone 14”.

  Referring to FIG. 2, the central control device 16 of the play behavior recognition system 100 is also called a play behavior recognition device, and is connected to the distance image sensor 12, the microphone 14, and the like. In addition, the central control device 16 performs wireless communication with the play equipment 10 via the network 1000. The central control device 16 acquires information output from the distance image sensor 12 and the microphone 14 every first time (for example, 0.05 seconds), and also includes a microphone 36 and an acceleration sensor 38 provided in the play equipment 10. Also get the information. Then, the central control device 16 creates a table of environmental data (see FIG. 6) including information on the position and posture of each child, the acceleration of the playground equipment 10, and the volume of sound in the nursery, from the acquired information of each sensor. To remember.

  A child ID (hereinafter referred to as C-ID) is given to a child whose position is detected in the nursery school. In addition, the children in the nursery school are identified using a dedicated tag, the order of attending the school (the order of entering the space) and the position when confirming attendance, etc., and a dedicated C-ID is assigned to each child. Is granted.

  FIG. 3 is a block diagram showing an electrical configuration of a circuit provided in the play equipment 10. Referring to FIG. 3, the circuit provided in play equipment 10 includes a processor 30 and the like. The processor 30 may be called a microcomputer or a CPU. The processor 30 is connected to a memory 32, an A / D converter 34, an acceleration sensor 38, a wireless LAN module 40, and the like.

  The processor 30 controls the entire circuit provided in the play equipment 10. The memory 32 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 30. For example, audio information and acceleration information, which will be described later, are temporarily stored in the RAM buffer.

  A microphone 36 is connected to the A / D converter 34, and an audio signal from the microphone 36 is converted into digital audio information by the A / D converter 34 and input to the processor 30. In addition, the sound collected by the microphone 36 is used together with the sound collected by the microphone 14 to measure the volume of noise in the nursery school.

  The acceleration sensor 38 detects how much acceleration is applied in a certain direction with respect to the sensor. For example, the acceleration sensor 38 is a three-axis acceleration sensor that can detect acceleration in three axial directions at a time. . According to this acceleration sensor 38, it is possible to detect how the playground equipment 10 is used, for example, when a child is playing.

  The wireless LAN module 40 transmits the transmission data given from the processor 30 to the central control device 16 via the network 1000. For example, the transmission data is acceleration information of the playground equipment 10 detected by the acceleration sensor 38, voice information of voice collected by the microphone 36, and the like.

  FIG. 4 is a block diagram showing an electrical configuration of the distance image sensor 12. Referring to FIG. 4, 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 16 and transmits the detected result to the central controller 16.

  A microphone 64 is connected to the A / D converter 62, and an audio signal from the microphone 64 is converted into digital audio information 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 nursery school together with the sound collected by the microphone 14 and the microphone 36.

  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 audio information, RGB information, and depth information are output from the output port and provided to the central transmission control device 16. On the other hand, a control signal is output from the central control device 16 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. 5 is a block diagram showing an electrical configuration of the central controller 16. Referring to FIG. 5, central controller 16 includes distance image sensors 12a and 12b, a processor 80, and the like. The processor 80 is sometimes called a microcomputer or CPU. The processor 80 includes a plurality of distance image sensors 12a and 12b, a memory 82, an A / D converter 84, an output device 86, an input device 88, a first play action database (DB) 90, and a second play action database 92. The personality database 94 and the communication LAN board 96 are connected.

  The distance image sensor 12 outputs depth information as described above. This depth information includes the shape of the child in the space and the distance to the child. For example, when a child is sensed by the distance image sensor 12 provided on the ceiling, the shape of the head and both shoulders as seen from above and the distance to the head and both shoulders are obtained as depth information. .

In addition, 35 distance image sensors 12 are installed at predetermined positions (known) in the nursery school, and the processor 80 acquires depth information from each of them, and the position of the child (for example, the world coordinate system) (for example, , The position coordinates (x, y) of feature points such as the center of gravity, and the child's posture (for example, head orientation (θ _H ) and shoulder orientations (θ _B )) can be calculated.

  Further, since the distance image sensor 12 includes the microphone 64, the central control device 16 can also estimate the sound generation source from the position of the distance image sensor 12 to which audio information is input.

  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.

  The processor 80 controls the operation of the central controller 16. The processor 80 also includes an RTC that outputs date and time information. The memory 82 includes a ROM, an HDD, and a RAM. In the ROM and the HDD, a control program for controlling the operation of the central control device 16 is stored in advance. The RAM is used as a work memory or a buffer memory for the processor 80.

  A plurality of microphones 14 a and 14 b are connected to the A / D converter 84. Audio signals from the microphones 14 are converted into digital audio information by the A / D converter 84 and input to the processor 80. The sound collected by the microphone 14 is used together with the sound collected by the microphone 36 and the microphone 64 to measure the volume of noise in the nursery school. In other embodiments, each microphone 14 may be independently connected to the processor 80. In this case, the processor 80 can specify the microphone 14 to which audio information is input.

  The output device 86 is, for example, a display, and the input device 88 is, for example, a mouse or a keyboard. Then, an administrator of the play behavior recognition system 100 (for example, a nursery school nursery school) can confirm the result recognized by this system using the output device 86 and the input device 88.

  The first play behavior DB 90 stores the first play behavior recognized for each of the children in the nursery in chronological order. The second play behavior DB 92 stores the second play behavior recognized for each of the children in the nursery in chronological order. The personality DB 94 stores the results of classifying the personalities of the children in the nursery in chronological order.

  The communication LAN board 96 is configured by a DSP, for example, and provides transmission data given from the processor 80 to the wireless communication device 98, and the wireless communication device 98 transmits the transmission data to other devices via the network 1000. The communication LAN board 96 receives data via the wireless communication device 98 and gives the received data to the processor 80.

  FIG. 6 is an illustrative view showing one example of a configuration of an environment data table. The environmental data includes the position and posture of each child at a certain date and time, the analysis result of the acceleration output by each playground equipment 10, and the volume of sound acquired by each playground equipment 10, each distance image sensor 12, and each microphone 14. It is data to include. The environmental data table stores environmental data including these pieces of information for each row. Referring to FIG. 6, the environmental data table includes columns of date / time, children, play equipment, and microphone. The child column includes a column of C-IDs (“001”, “002”,...) Corresponding to the children in the nursery school. The row of play equipment includes columns of acceleration, dispersion, and number of waveforms.

  The date and time column stores the date and time when the environmental data was acquired. 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 column of C-ID in the child column, for example, “X ₁ , Y ₁ ” is stored as the position of the child corresponding to “C-ID: 001”, and “θ _H1 (head orientation)” and “Θ _B1 (body orientation)” is stored. For example, it is possible to determine whether or not children are playing together based on their positions and postures.

In the column of acceleration in the row of playground equipment, “Aa” is stored as an average value of accelerations output from each playground equipment 10. “Σ ² ” is stored as the variance of the acceleration output from each play equipment 10 in the dispersion row in the play equipment row. In the column of the number of waveforms in the row of playground equipment, the number of times the waveform drawn by arranging and connecting the values of the accelerations on a two-dimensional plane crosses the straight line defined by the average of acceleration (“Aa”). Stored as “number of waveforms”. Then, it is possible to determine how the playground equipment 10 was used from these pieces of information in the playground equipment 10.

  In the row of microphones, “AB” is stored as an average of sound volumes obtained from each play equipment 10, each distance image sensor 12, and each microphone 14. Here, “AB” indicates an average of the volume of noise in the nursery school. For example, in the play behavior of a child, the volume of noise in the space changes depending on the play behavior. Therefore, it can utilize as an element for discriminating each play action by utilizing the sound volume of each microphone. The unit of “AB”, which is the average of the volume, is “dB”.

  Then, the central control device 16 stores such environmental data for each first time in the environmental data table.

  FIG. 7 is an illustrative view showing specific contents of the first play behavior classified by the social behavior style. The first play behavior of the embodiment is divided into six types: “do nothing”, “alone play”, “side view”, “parallel play”, “joint play” and “cooperative play”.

  “No action” means that the child has no purpose, such as sitting still or looking around. “Single play” refers to a state in which other children are not interested in playing alone. “Bystand” refers to a state of standing by the side and watching another child playing. “Parallel play” means a state where other children play the same way but there is no specific negotiation (exchange) between the children. “Coalition play” is to play together while exchanging playground equipment and tools with other children, but there is no overall unity. “Cooperative play” refers to a state where the organization is played for the purpose or is played according to the common purpose and rules while sharing the roles.

  In the embodiment, the environment data of the child who has performed the first play action is used as teacher data, and the teacher data is learned by a machine learning method such as SVM (Support vector machine). As a result, a discrimination model for the first play behavior is created. When unknown environmental data for a second time (for example, 5 seconds) is input to a child who has performed a certain first play action for this discrimination model, the first play action and the first play action are similar. At least one or more likelihoods indicating the ratio of the images being obtained are obtained. Then, the discrimination model outputs the first play action with the highest likelihood as a recognition result.

  For example, when environmental data of a child who has performed a certain first play action is input as unknown data to the discrimination model for the first play action, the “associative play” with a likelihood of 80% and the likelihood is 70. % Of “cooperative play” is output, this discriminant model outputs “associative play” having the highest likelihood as a recognition result.

  FIG. 8 is an illustrative view showing specific contents of the second play behavior classified by mental function. The second play behavior of the embodiment is divided into five types: “sensory play”, “exercise play”, “acceptance play”, “imitation play”, and “configuration play”.

  “Sensory play” refers to a state of playing mainly using sensory organs by looking at, listening to, or touching sand or water. “Exercise play” refers to a state where the user is playing with limbs or whole body exercise. “Accepted play” indicates a state where the user is playing while watching or listening to picture books, television, music, and the like. “Imitation play” refers to a state in which children play while imitating various lives around the child (for example, the adult world, human relationships, life, and labor). “Structural play” refers to a state of enjoying the process by assembling or making it, such as origami, plastic model, building blocks and clay.

  In the embodiment, similarly to the first play behavior, when a discrimination model of the second play behavior is created and unknown environment data when the second play behavior is performed is input to the discrimination model, the second play behavior of the child is obtained. Be recognized.

  FIG. 9 is an illustrative view showing one example of a configuration of the first play action DB 90. Referring to FIG. 9, the first play behavior DB 90 includes a table corresponding to each child in the nursery school. Each table includes a column of date, number, and first play action, and the recognized first play action is stored in chronological order. For example, referring to the table of C-ID: 001, the child corresponding to this table is recognized as “bystand” after “single play” is recognized three times continuously on March 5, 2013. ing.

  FIG. 10 is an illustrative view showing one example of a configuration of the second play action DB 92. Referring to FIG. 10, the second play action DB 92 includes a table corresponding to each child, similarly to the first play action DB 90, and the configuration of the table is substantially the same. The recognized second play behavior is also stored in chronological order. For example, referring to the table of C-ID: 001, the child corresponding to this table has “exercise play” twice consecutively after “sensory play” is recognized on March 5, 2013. Recognized and "sensory play" is recognized again.

  Thus, in the central controller 16, the first play behavior and the second play behavior are recognized for each child in the nursery school, and the recognition result is stored in the database. The childcare person (for example, a childcare person) checks the contents of the first play action DB 90 and the second play action 92 by using the central control device 16, and what kind of play action each child performs. Can be grasped appropriately.

  In addition, since the recognized play behavior is automatically stored, the childcare person can easily create a document such as a childcare diary by referring to the play behavior stored in the database. Furthermore, since the childcare person can grasp the first play behavior and the second play behavior of the child who is raising the child, it can be used as a reference when making a childcare plan for the child. In this way, it is possible to reduce work routinely performed by a childcare worker.

  In the embodiment, the first play action and the second play action are recognized every second time and stored in the database.

  FIG. 11 is an illustrative view showing specific contents of children's personalities classified based on the first play behavior and the second play behavior. The child personality of the embodiment is divided into five types: “undifferentiated type”, “cumulative type”, “continuous type”, “segmental type”, and “unified type”. These play behaviors are classified based on the recognized frequency and length of play behaviors.

  A child with an “undifferentiated” personality causes another play behavior every few minutes, and each child has a behavior that is not organized. A child with a “cumulative” character continues to play for about 10 minutes, but acts loosely and unrelatedly. A child with a “continuous” character acts to continue for about an hour without getting cluttered, developing a play in an irrelevant direction or returning it to its original state. Children with a “segmental” character play a single unit of play at a rate of two or three per hour. A child with a “unified” personality plays one play with a certain person for about an hour.

  In the embodiment, the first play behavior and the second play behavior are used as teacher data, and a personality discrimination model is created. Then, by inputting all of the unknown first play behavior and second play behavior recognized during the third time (for example, 5 to 60 minutes) into the created discrimination model, Personality is classified. The child personality is classified every third time longer than the second time. In addition, the time of play action becomes long in proportion to a child's growth. Therefore, when classifying personality, you may change 3rd time according to the age of the child used as object.

  FIG. 12 is an illustrative view showing one example of a configuration of the personality DB 94. Referring to FIG. 12, personality DB 94 includes a table corresponding to each child in the nursery school, like other databases. The table corresponding to each child includes date and personality columns, and the classified personalities are stored in chronological order for each child. For example, referring to the table of C-ID: 001, on March 5, 2013, the personality of the child corresponding to this ID is classified as “cumulative” and then as “continuous”.

  In this way, children's personality can be classified using the children's play behavior. The childcare person can help to understand the development status of each child objectively by confirming and analyzing the personality of each child. In the embodiment, the accuracy of classification is improved by classifying personalities using two play actions.

  In the embodiment, the first play action and the second play action are recognized every second time longer than the first time necessary for acquiring the environmental data. That is, the play behavior is recognized after the environmental data necessary for recognizing the play behavior is acquired. As a result, children's play behavior can be accurately recognized. Similarly, the personality is classified every third time that is longer than the second time required to recognize the first play behavior and the second play behavior. That is, the personality is classified after recognizing the play behavior necessary for classifying the personality. This makes it possible to accurately classify the child's personality.

  The above has outlined features of the embodiment. Hereinafter, the embodiment will be described in detail with reference to the memory map shown in FIG. 13 and the flowcharts shown in FIGS.

  FIG. 13 is an illustrative view showing one example of a memory map of the memory 82 of the central controller 16 shown in FIG. As shown in FIG. 13, the memory 82 includes a program area 302 and a data storage area 304. The program storage area 302 obtains information from each sensor as a program for operating the central control device 16 and stores the environment data in the environment data table, the first play action and the second play. A play action recognition program 312 for recognizing actions, a personality classification program 314 for classifying the personality of children, and the like are stored. Although illustration is omitted, the program for operating the central control device 16 includes a program for confirming the contents of each database.

  The data storage area 304 stores an environment data table 330 and the like. The environmental data table 330 is, for example, a table having the configuration shown in FIG. 6, and stores environmental data. 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 16.

  The processor 80 of the central control device 16 performs an acquisition process shown in FIG. 14, a play action recognition process shown in FIG. 15, and a personality classification process shown in FIG. Handle multiple tasks, including

  FIG. 14 is a flowchart of the acquisition process. When the central controller 16 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 depth information and audio information output from the distance image sensor 12.

  Subsequently, in step S5, the processor 80 acquires acceleration information of the play equipment 10. That is, the processor 80 acquires acceleration information measured by the acceleration sensor 38 of the play equipment 10. Subsequently, in step S <b> 7, the processor 80 acquires audio information from the microphone 14. That is, the processor 80 acquires sound information of the sound collected by the microphone 14. The processor 80 that executes the process of step S5 functions as a first acquisition unit.

  Subsequently, in step S9, the processor 80 creates environmental data from the information of each sensor. That is, the position and posture of the child are calculated from the depth information, the average, variance, and number of waveforms of acceleration are calculated from the acceleration information, and the sound (from the plurality of microphones 14, the microphone 36 of the play equipment 10, and the microphone 64 of the distance image sensor 12) The average (noise) volume is calculated. These values are used as one environment data.

  Subsequently, in step S11, 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.

  FIG. 15 is a flowchart of the play action recognition process. When the central controller 16 is turned on and a play action recognition process execution command is issued, the play action recognition process is executed. Note that an execution command for the play action recognition process is issued every second time.

  When the play action recognition process is executed, the processor 80 initializes the variable Ci in step S31. The variable Ci is a variable for designating an arbitrary C-ID. In step S31, the value of the variable Ci is set to “1”.

  Subsequently, in step S33, the processor 80 acquires environmental data for the second time from the current time corresponding to the Ci th child. For example, if the variable Ci is “1”, the C-ID is “001”, that is, the environmental data corresponding to the first child is read for 5 seconds. The environmental data corresponding to the child includes the position and posture corresponding to the C-ID of the child specified by the variable Ci, the acceleration of the play equipment 10, and the average of the volume of each microphone. The processor 80 that executes the process of step S33 functions as a second acquisition unit.

  Subsequently, the processor 80 recognizes the first play action in step S35, and recognizes the second play action in step S37. For example, environmental data for the second time from the current time of C-ID; 001 is input to the discrimination model for the first play action and the second play action. And from each discrimination | determination model, what has the highest likelihood is output as a recognition result. Note that the processor 80 that executes the processes of steps S35 and S37 functions as a recognition unit. In particular, the processor 80 that executes the process of step S35 functions as first recognition means, and the processor 80 that executes the process of step S37 functions as second recognition means.

  Subsequently, in step S39, the processor 80 stores each play action in the database. For example, when the action of “single play” is recognized as the first play action and the action of “sensory play” is recognized as the second play action, “single play” is stored in the first play action DB 90, and “Sense play” is stored in the 2-play action DB 92.

  Subsequently, in step S41, the processor 80 increments the variable Ci. That is, the value of the variable Ci is incremented to specify the next C-ID. Subsequently, in step S43, the processor 80 determines whether or not the variable Ci is larger than the maximum value. The maximum value is the total number of children in the nursery school. Therefore, in step S43, it is determined whether all children's play behaviors have been recognized. If “NO” in the step S43, that is, if all the children's play behaviors are not recognized, the processor 80 returns to the process of the step S33. On the other hand, if “YES” in the step S43, when the play behaviors of all the children are recognized, the processor 80 ends the play behavior recognition process.

  FIG. 16 is a flowchart of personality classification processing. When the central controller 16 is turned on and a command for executing the personality classification process is issued, the personality classification process is executed. An execution command for the personality classification process is issued every third time.

  When the personality classification process is executed, the processor 80 initializes the variable Ci in step S61. That is, the value of the variable Ci is set to “1” as in the process of step S31.

  Subsequently, in step S63, the processor 80 acquires each play action for the third time from the current time corresponding to the Ci th child. For example, if the variable Ci is “1”, in the first play action DB 90 and the second play action DB 92, from the table of C-ID: 001, the first play action and the second play for the third time from the current time. Action is acquired.

  Subsequently, in step S65, the processor 80 classifies the personality of the Ci th child. That is, the first play behavior and the second play behavior of the Ci-th child acquired in step S63 are input to the discrimination model for classifying the personality. The result output from the discrimination model is the personality of the Ci th child. Subsequently, in step S67, the processor 80 stores the personality in a database. That is, the personality of the child whose C-ID is “Ci” is stored in the table whose C-ID is “Ci” in the personality DB 94. The processor 80 that executes the process of step S65 functions as a classification unit.

  Subsequently, in step S69, the processor 80 increments the variable Ci. That is, as in step S41, the value of the variable Ci is incremented to specify the next C-ID. Subsequently, in step S71, the processor 80 determines whether or not the variable Ci is larger than the maximum value. That is, as in step S43, the processor 80 determines whether all the child personalities have been classified. If “NO” in the step S71, if all the child personalities are not classified, the processor 80 returns to the process of the step S63. On the other hand, if “YES” in the step S71, that is, if all the child personalities are classified, the processor 80 ends the personality classification processing.

  In addition, the robot etc. which have the microphone 36 and the acceleration sensor 38 may be employ | adopted for the play equipment 10 of another Example. Further, the appearance of the play equipment 10 is not limited to a stuffed animal, but may be a building block or a ball.

  In other embodiments, personalities may be classified without using the second play behavior. In yet another embodiment, the types of the first play behavior, the second play behavior, and the personality may be different from those in the embodiment, or the numbers may be different.

  In the embodiment, SVM is used as the machine learning method. However, in another embodiment, a neural network or an algorithm such as C4.5 may be used.

  In other embodiments, the first play behavior and the second play behavior of the child may be recognized without using the average volume of the microphone 14, the microphone 36 of the play equipment 10, and the microphone 64 of the distance image sensor 12. .

  In still another embodiment, the memory 82 may store a map of the space. Then, the first play behavior and the second play behavior may be recognized in consideration of the position of the child on the map.

  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 10a, 10b ... Playground equipment 12a, 12b ... Distance image sensor 14a, 14b ... Microphone 16 ... Central controller 30 ... Processor 36 ... Microphone 38 ... Acceleration sensor 64 ... Microphone 80 ... Processor 82 ... Memory 90 ... 1st play action DB
92 ... 2nd play action DB
94 ... Personality DB
100 ... Playing action recognition system 1000 ... Network

Claims (7)

A playground equipment that can be moved arbitrarily in space and outputs its own acceleration,
First acquisition means for acquiring an acceleration output by the play equipment;
Second acquisition means for acquiring the position and posture of the child in the space; and recognition means for recognizing the play behavior of the child based on the acceleration of the play equipment and the position and posture of the child ,
The recognizing means includes first recognizing means for recognizing a first play action classified according to a social action style based on the acceleration of the play equipment and the position and posture of the child,
An action recognition system comprising classification means for classifying the child's personality based on the first play action . The recognizing means includes second recognizing means for recognizing a second play action classified by a mental function based on the acceleration of the play equipment and the position and posture of the child,
It said classification means, on the basis of the first play action and the second idle behavior, classifying the child's personality, play behavior recognition system of claim 1, wherein. The first acquisition unit and the second acquisition unit acquire the acceleration of the play equipment and the position and posture of the child every first time,
It said recognition means, the first time recognizes the play behavior of the child for each long second time than, according to claim 1 or 2, wherein the play behavior recognition system. 4. The play behavior recognition system according to claim 3 , wherein the classification means classifies the child's personality every third time longer than the second time. A processor of a play action recognition system having a play equipment that can be arbitrarily moved in a space and outputs its own acceleration,
First acquisition means for acquiring an acceleration output by the play equipment;
Second acquisition means for acquiring the position and posture of the child in the space, and function as a recognition means for recognizing the play behavior of the child based on the acceleration of the play equipment and the position and posture of the child ;
The recognizing means includes first recognizing means for recognizing a first play action classified according to a social action style based on the acceleration of the play equipment and the position and posture of the child,
A play behavior recognition program that functions as a classification means for classifying the child's personality based on the first play behavior . A processor of a play action recognition system having a play equipment that can be arbitrarily moved in a space and outputs its own acceleration,
A first acquisition step of acquiring an acceleration output by the play equipment;
A second acquisition step of acquiring the position and posture of the child in the space; and a recognition step of recognizing the play behavior of the child based on the acceleration of the play equipment and the position and posture of the child ;
The recognizing step recognizes a first play action classified according to a social action style based on the acceleration of the play equipment and the position and posture of the child;
A behavior recognition method for executing a classification step of classifying the personality of the child based on the first play behavior . First acquisition means for acquiring acceleration output from a playground equipment that can be arbitrarily moved in space;
Second acquisition means for acquiring the position and posture of the child in the space; and recognition means for recognizing the play behavior of the child based on the acceleration of the play equipment and the position and posture of the child ,
The recognizing means includes first recognizing means for recognizing a first play action classified according to a social action style based on the acceleration of the play equipment and the position and posture of the child,
A play action recognition device comprising classification means for classifying the child's personality based on the first play action .

Images