JP3974098B2 - Relationship detection system - Google Patents

Description

  The present invention relates to a relationship detection system and an approach device, and in particular, for example, a relationship detection system for detecting a relationship between members in an organization including a plurality of members, and a member provided in a space where the organization exists. It is related with the approach device for making it.

Conventionally, for example, sociometry devised by Moreno (JL Moreno) is well known as a method for grasping the human relationships of members in an organization. Sociometry measures the structure of an organization, such as individual positions and relationships within a group, by investigating likes (acceptance) and dislikes (rejections) within the group. Specifically, it is often applied in order to grasp the relationships between students in the class in school education. In a study called sociometric test, for example, “Who likes in the class? Who does not want to play together?” Or “Who wants to sit next to you when you change seats? Is asked, and the name of the person who likes and dislikes is written to each person. Based on the results of this test, a so-called sociogram or a so-called socio-matrix table is created as necessary, for example, the position within an individual group, such as a popular person, an isolated child, or a rejected child within a group. Friends relations become clear. For example, Non-Patent Document 1 and Non-Patent Document 2 introduce software that outputs a sociogram or the like using information obtained by a sociometric test as input data in a PC.
“Sociometrics Frenzu”, [online], Suzuki Education Software Co., Ltd., [searched September 17, 2003], Internet <URL: http://www.suzukisoft.co.jp/products/frends/index. htm> “Sociometric Test for Windows”, [online], CS Development Office, [searched on September 17, 2003], Internet <URL: http://plaza5.mbn.or.jp/~cesdev/socio.html >

  In the past, each member directly answered the likes and dislikes in the sociometric test, so each member could set up an unclear question, and the answer could include a lie. In addition, depending on the method of surveying the content and timing of the questions, there was a strong risk of becoming a human rights issue or adversely affecting human relationships thereafter. Therefore, there is a problem that accurate information cannot be obtained and the relationship among members cannot be accurately grasped.

  Therefore, a main object of the present invention is to provide a relationship detection system and an access device that enable accurate grasping of member relationships.

The invention according to claim 1 is a relationship detection system for detecting a relationship between members in an organization including a plurality of members or between units classified by member characteristics, and identifies members existing in a predetermined area. Identification means for recording, recording means for recording an action history regarding whether or not a member is present in the predetermined area based on identification by the identification means, coexistence in the predetermined area extracted from the action history recorded by the recording means And a relationship grasping means for generating information on likes and dislikes between members or units based on a method and a predetermined rule that defines a relationship corresponding to a coexistence method in the predetermined region. If the members stay together at the same time, the rules governing the relationship between the members corresponding to the way the members coexist The rule that the other member comes after one member, the rule that the other member favors the one member, and the other member when the other member comes When a member leaves, the rule that the other member dislikes the one member, and when another member comes together, when the other member gathers, the other member becomes the certain member. The rule that a certain member is a leader, and if the other member leaves when a certain member comes, the other member Rules that dislike a member and that the member is a disliked person, and that the member is exclusive if it exists when there is no other member comprising at least one of the rules that tend a person of Seki A detection system.

According to the first aspect of the present invention, the recording means records a history of actions related to whether or not a member exists within a predetermined area. The predetermined area is set near the system, for example. The behavior of the members with respect to the predetermined area is the natural behavior of each member as usual, and the relationship between the members is reflected. Based on such behavior, that is, the coexistence method in the predetermined area extracted from the behavior history and the predetermined rule that defines the relationship corresponding to the coexistence method in the predetermined area, Generate information about likes and dislikes between units or units and understand relationships. The prescribed rule is that if the members stay at the same time, the members are in favor of each other. If the other member comes after one member, the other member Rule that favors a member, if one member arrives and the other member leaves, rule that the other member dislikes the other member, if a member comes When other members gather, the rule that the other members are favored by the certain member and that the certain member is a leader, and when a certain member comes A rule that other members dislike the certain member when the other member leaves, and that the certain member is a disliked person and a certain component If there is no other member Members comprises at least one rule that is a person exclusive tendencies. In other words, since the human relationship is reflected in the way of coexistence with others in the predetermined area, for example, an action pattern in which the coexistence method is patterned and the corresponding human relationship are defined in advance. Therefore, it is possible to easily and accurately grasp the relationship among members in the organization. Therefore, according to the invention of claim 1, it is possible to record extremely natural behaviors reflecting the usual relationships of members, and to clarify the relationship based on such information. It is possible to accurately grasp the relationship among members.

The invention according to claim 2 is a relation detection system for detecting a relation between members in an organization including a plurality of members or between units classified by the characteristics of the members, and is provided in a space where the organization exists. And the approach device for making the member approach spontaneously, the identification means for identifying the member existing in the predetermined area near the access device, the member exists in the predetermined area based on the identification by the identification means Recording means for recording behavior history regarding whether or not, and a coexistence method in a predetermined area extracted from the behavior history recorded by the recording means, and a predetermined rule defining a relationship corresponding to the coexistence method in the predetermined area based on the bets, including the relationship grasping means for generating information regarding likes and dislikes of between between members or units, predetermined rules on how the coexistence members in a predetermined region A predetermined rule that defines the relationship between the responding members, and when the members stay at the same time, the rule that the members have a mutual favor, the other member after one member The rule that the other member is favored by the other member, and if the other member leaves when the other member comes, the other member dislikes the one member Rule that, when a certain member comes and other members come together, the other member is favored by the certain member and the certain member is a leader The rule is that if a member comes and other members leave, the other member dislikes the certain member and the certain member is disliked The rules of being a member of the Nobody said one member when present when no includes at least one rule that is a person exclusive trend, a related detection system.

In the invention of claim 2, an access device for allowing members to approach spontaneously is provided in the space where the tissue exists. Such access devices are, for example, generally speaking to attract members' attention, attract members' attention, draw members' attention, or make them feel familiar. In the embodiment, a communication robot or the like is used as recited in claim 4. And a recording means records the action | operation log | history regarding whether a member exists in the predetermined area | region near the approach apparatus. Thus, the recorded member behavior is, for example, whether it is near the access device, i.e., who and who are coming together, for example. This is the natural behavior of each member as usual and reflects the relationship between the members. Then, the relationship grasping means is based on a method of coexistence in a predetermined area extracted from such behavior history and a predetermined rule that defines a relationship corresponding to the coexistence method in the predetermined area. Generate information about likes and dislikes between units and grasp relationships. The prescribed rule is that if the members stay at the same time, the members are in favor of each other. If the other member comes after one member, the other member Rule that favors a member, if one member arrives and the other member leaves, rule that the other member dislikes the other member, if a member comes When other members gather, the rule that the other members are favored by the certain member and that the certain member is a leader, and when a certain member comes A rule that other members dislike the certain member when the other member leaves, and that the certain member is a disliked person and a certain component If there is no other member Members comprises at least one rule that is a person exclusive tendencies. In other words, since the human relationship is reflected in the way of coexistence with others in the predetermined area, for example, an action pattern in which the coexistence method is patterned and the corresponding human relationship are defined in advance. Therefore, it is possible to easily and accurately grasp the relationship among members in the organization. Therefore, according to the invention of claim 2, it is possible to record extremely natural behavior reflecting the usual relationships of members, and to clarify the relationship based on such information, It is possible to accurately grasp the relationships among members in the organization.

The invention according to claim 3 is the relationship detection system according to claim 1 or 2, wherein the identification means includes an acquisition means for acquiring identification information of members existing in the predetermined area, and the recording means is the acquisition means. The action history is recorded based on the identification information acquired by.

In the invention of claim 3, the identification information of the members existing in the predetermined area is acquired by the acquisition means, and the recording means records the action history based on the acquired identification information. Therefore, by acquiring member identification information, the behavior of each member can be captured and distinguished, and the behavior history of the member can be reliably recorded by the identification information.

The invention according to claim 4 is the relationship detection system according to claim 2 , wherein the access device includes an autonomous moving means for autonomously moving and an acquiring means for acquiring identification information of members existing in the predetermined area. Includes communication robots.

In the invention of claim 4, as an approaching device for bringing members closer, a communication robot that moves autonomously is provided in a space where an organization exists, and members existing in a predetermined area by an acquisition means provided in the communication robot. The identification information is acquired. The predetermined area is set, for example, near the communication robot. Therefore, the behavior of the member with respect to the predetermined area is, for example, whether or not the communication robot is coming to communicate. Such behavior with respect to communication robots reflects the usual relationship between the members. In other words, for example, members who normally have a favorable relationship will try to play with the communication robot together, and conversely, members who have a disliked relationship will not play together. Will. Therefore, by placing communication robots in the organization's space, each member's relationship can be highlighted and recorded in the usual natural behavior of the member. Accurately grasp.

  The invention according to claim 5 is the relationship detection system according to claim 3 or 4, wherein the acquisition means includes a wireless tag reading means for acquiring identification information from a wireless tag attached to each of a plurality of members. Including.

  According to a fifth aspect of the present invention, a plurality of members are each attached with a wireless tag in which identification information is registered, and the acquisition means includes a wireless tag reading means for acquiring identification information from the wireless tag. Therefore, according to the fifth aspect of the present invention, it is possible to easily and reliably record the action history for the predetermined area simply by attaching each member to the wireless tag.

  A sixth aspect of the present invention is the relationship detection system according to any one of the third to fifth aspects, wherein the obtaining means obtains the identification information from the infrared LED tag attached to each of the plurality of members. Including detection means.

  In the invention of claim 6, an infrared LED tag is attached to each of the plurality of members, and the acquisition means includes an infrared detection means for acquiring identification information from the infrared LED tag. Therefore, according to the sixth aspect of the present invention, it is possible to easily and surely record the history of the action on the predetermined area simply by attaching each member to the infrared LED tag.

The invention according to claim 7 is a relationship detection system according to any one of claims 1 to 6 , and displays a relationship between members or units based on information about likes and dislikes generated by the relationship grasping means. A display means is further provided.

In the invention of claim 7 , the relationship ascertained by the display means is displayed. Therefore, according to the invention of claim 7 , it is possible to clearly and easily grasp the relationship between members.

The invention according to claim 8 is the relationship detection system according to claim 7 , wherein the display means displays the relationship as a sociogram.

In the invention of claim 8 , since the grasped relationship is displayed as a sociogram shown in the figure, the relationship of the members in the organization can be grasped clearly and easily.

The invention according to claim 9 is the relationship detection system according to any one of claims 1 to 8 , wherein the information about likes and dislikes generated by the relationship grasping means is a degree of likes or dislikes between members or units, Or at least one of a leader, hated or exclusive in the organization.

In the invention of claim 9 , the relationship between members or units is grasped by, for example, the degree of likes or dislikes, or the person who is a leader in the organization, the person who is disliked, or of the exclusive tendency A special relationship is revealed. Therefore, it is possible to grasp the relationship between members or units in the organization clearly and easily.

The invention of claim 1 0, a and members provided in the space where the tissue is present in order to detect the relationship between units classified by members or between members of features in tissue comprising a plurality of members An identification device for identifying members existing in a predetermined area, and records an action history regarding whether the members exist in the predetermined area based on identification by the identification means Based on the recording means, and the coexistence method in the predetermined area extracted from the action history recorded by the recording means and the predetermined rule that defines the relationship corresponding to the coexistence method in the predetermined area, A relationship grasping means for generating information about likes and dislikes between units is provided , and the predetermined rule defines a relationship between members corresponding to the way members coexist in a predetermined area. If the members stay at the same time, the rule that the members have a mutual favor, if the other member comes after one member, the other member The rule that one member is favored, the rule that one member dislikes the other member when the other member leaves, the other member dislikes the one member And the other members come together, the rule that the other members are favored by the certain member and that the certain member is a leader, the certain member comes A rule that the other members dislike the certain member and that the certain member is disliked, and that the other member leaves Applicable when there are no other members That members includes at least one rule that is a person exclusive tendency is approaching device.

In the invention of claim 1 0, provided in a space existing tissues, including a plurality of members, access device for approach by a member function as the above relation detection system. That is, the identification unit identifies a member existing in the predetermined area, and the recording unit records an action history regarding whether the member exists in the predetermined area. The predetermined area is set, for example, in the vicinity of the access device, and therefore, the behavior of the member with respect to the predetermined area is whether or not the approach device has been reached. This is the natural behavior of each member as usual and reflects the relationship between the members. Then, the relationship grasping means is based on a method of coexistence in a predetermined area extracted from such behavior history and a predetermined rule that defines a relationship corresponding to the coexistence method in the predetermined area. Generate information about likes and dislikes between units and grasp relationships. The prescribed rule is that if the members stay at the same time, the members are in favor of each other. If the other member comes after one member, the other member Rule that favors a member, if one member arrives and the other member leaves, rule that the other member dislikes the other member, if a member comes When other members gather, the rule that the other members are favored by the certain member and that the certain member is a leader, and when a certain member comes A rule that other members dislike the certain member when the other member leaves, and that the certain member is a disliked person and a certain component If there is no other member Members comprises at least one rule that is a person exclusive tendencies. Therefore, according to the invention of claim 1 0, it is possible to record a very natural action that is usual relationships reflect members, it is possible to clarify the relationship on the basis of such information It is possible to accurately grasp the relationship among members in the organization.

The invention of claim 1 1, an access device dependent on claim 1 0, is formed as a stuffed animal in which the animal shape. In the invention of claim 1 1, for example, pulling the interest of members, since it is easy or feel an affinity, can be closer voluntarily members. Therefore, it is possible to record the usual natural behavior of the members, and to accurately grasp the relationship between the members based on the behavior.

The invention of claim 1 2, a proximity device dependent on claim 1 0, is formed as a further communication robots with autonomous movement means for moving autonomously. In the invention of claim 1 2, similarly to the claim 1 1, for example because it is easy to pulling the interest of members, it is possible to approach voluntarily by the members. Therefore, it is possible to record the extremely natural behavior of the members as usual, and to accurately grasp the relationship between the members based on the behavior.

  According to the present invention, the extremely natural behavior of each member can be recorded, and the relationship between the members can be grasped based on the history of such behavior. Therefore, since each member is not directly asked and answered “like” or “dislike”, the information as it is can be obtained, and as a result, the relationship between the members can be accurately grasped.

  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.

  Referring to FIG. 1, a relationship detection system (hereinafter also simply referred to as “system”) 10 of this embodiment detects a relationship between members in an organization including a plurality of members A, B, C. Is to do. Here, the relationship between each member in the organization is specifically a relationship between individual members when the organization is regarded as an individual member unit, and the organization has some characteristic or commonality. In the case of capturing in a predetermined unit based on, it is a relationship between the units. This relationship among members includes, for example, relationships such as likes-dislikes, acceptances-rejects, etc., and the positions of members in the organization such as leaders and dislikes. Such special relationships are also included. Such a relationship between the members is a relationship of partial parts constituting the entire organization, and is hereinafter also referred to as “organization structure”.

  The system 10 includes a communication robot (hereinafter, also simply referred to as “robot”) 12 as an approach device for allowing members to approach spontaneously, and the robot 12 is located in a real space where the tissue to be detected exists. Provided. That is, for example, when detecting the human relationship of a child in a class as an organizational structure, the robot 12 is placed in the classroom of the class. Although the detailed configuration of the robot 12 will be described later, the robot 12 is an autonomous mobile communication robot having a mechanism for autonomously moving, and is mainly intended for communication with a communication target such as a human. It is action-oriented and has a function to communicate using at least one of gesture and voice.

  When such a robot 12 is arranged in the organization, each member A, B, C,... Is interested in the robot 12 and is expected to spontaneously approach the robot 12 and attempt communication. . However, it is impossible for the robot 12 to communicate with many people at a time, and only a limited number of people can exist in front of the robot 12. For this reason, it is considered that the behavior of each member approaching or leaving the robot 12 reflects the human relationship. That is, for example, members who are normally in a friendly relationship will try to stay together in front of the robot 12, and conversely, members who have a disliked relationship will not try to stay together. Let's go. Thus, it can be said that the structure of each member appears in the manner of coexistence in the predetermined area in front of the robot 12 of each member. Therefore, by introducing the robot 12 into the target tissue, the tissue structure can be naturally raised. This organizational structure manifests itself in the usual natural behavior of each member, and has the accuracy that cannot be obtained through direct research.

  Therefore, the behavior of the members in the predetermined area in which such an organizational structure is reflected is detected by the robot 12, and the history of the behavior is recorded. In order to catch and distinguish the member who is taking action, the identification information of the member is acquired by acquisition means such as various sensors provided in the robot 12, for example. In this embodiment, the wireless tag 14 and the infrared LED tag 16 are attached to or attached to each member at an appropriate position such as a chest or an abdomen on the front side. Predetermined areas set near the robot 12 such as which member has come to the robot 12 or left by acquiring the identification information issued from each of these tags 14 and 16 It becomes possible to grasp the behavior to the inside with certainty.

  For example, an RFID tag is used as the wireless tag 14. RFID (Radio Frequency Identification) is an automatic recognition technology using a non-contact IC tag using electromagnetic waves. The RFID tag 14 includes an IC chip and an antenna provided with a memory for identification information, a control circuit for communication, and the like. Information that can identify the member is stored in advance in the memory, and the identification information is output from the antenna by electromagnetic waves, radio waves, or the like having a predetermined frequency. As a transmission method, in this embodiment, it is recorded whether or not a member is coming to the robot 12 for communication. For example, an electromagnetic induction method having a relatively long communication distance (up to about 1 m) or a microwave. It is desirable to use a system (up to about 5m). In these cases, each member can be easily recognized by wearing the wireless tag 14 when entering the predetermined detectable area of the robot 12.

  An electrostatic coupling method (about several millimeters) or an electromagnetic coupling method (about several centimeters) having a relatively short communication distance may be used. In these cases, each member who comes to the robot 12 is used. In addition, it is necessary to make the wireless tag 14 read close to the wireless tag reader 18 (see FIG. 3).

  Further, when the infrared LED tag 16 is used together as in this embodiment, it is desirable not to use an optical RFID using infrared rays. Furthermore, the power supply system may be either an active type with a built-in battery or a passive type without a battery, but it is necessary to ensure an appropriate communication distance region. The form or shape of the tag is also arbitrary, and may be any of a card shape, a label shape, a coin shape, a stick shape, and the like.

  The infrared LED tag 16 includes an infrared LED, its drive circuit, a built-in battery, and the like. The infrared LED is controlled to emit light in a predetermined blinking pattern so that the member to which the tag 16 is attached can be identified. The form of the infrared LED tag 16 is also arbitrary like the RFID tag 16. Further, when each member enters a predetermined area that can be detected by the robot 12, the member can be easily recognized only by wearing the infrared LED tag 16.

  The data recorded by the robot 12 is processed inside the robot 12 or after being transferred to the external computer 20 such as a PC, and the relationship between the members is grasped and output. The grasped tissue structure is output as a sociogram, for example, and displayed on a display means such as a CRT or LCD of the external computer 20.

  FIG. 2 is a front view showing the appearance of the robot 12, and the hardware configuration of the robot 12 will be described with reference to FIG. The robot 12 includes a carriage 22, and wheels 24 for autonomously moving the robot 12 are provided on the lower surface of the carriage 22. The wheel 24 is driven by a wheel motor 26 (see FIG. 3), and the carriage 22, that is, the robot 12, can be moved in any direction, front, rear, left, and right. As described above, the robot 12 is movable in the tissue space, but may be fixedly provided at a predetermined position in the space depending on circumstances.

  Although omitted in FIG. 2, a collision sensor 28 (see FIG. 3) is attached to the front surface of the carriage 22, and the collision sensor 28 detects contact of a person and other obstacles to the carriage 22. That is, when contact with an obstacle is detected while the robot 12 is moving, the driving of the wheels 24 is immediately stopped and the movement of the robot 12 is suddenly stopped.

  In this embodiment, the height of the robot 12 is set to about 100 cm so as not to give intimidation to a person, particularly a child. However, this height can be changed.

  A polygonal column sensor mounting panel 30 is provided on the carriage 22, and an ultrasonic distance sensor 32 is mounted on each surface of the sensor mounting panel 30. The ultrasonic distance sensor 32 measures the distance between the sensor mounting panel 30, that is, the person around the robot 12 mainly.

  Further, on the carriage 22, the lower part is surrounded by the sensor mounting panel 30 so that the body of the robot 12 stands upright. This body is constituted by a lower body 34 and an upper body 36, and the lower body 34 and the upper body 36 are connected to each other by a connecting portion 38. Although illustration is omitted, the connecting portion 38 has a built-in lifting mechanism, and by using this lifting mechanism, the height of the upper body 36, that is, the height of the back of the robot 12 can be changed. The lifting mechanism is driven by a waist motor 40 (see FIG. 3), as will be described later.

  The height of the robot 12 described above is that when the upper body 36 is at its lowest position. Therefore, the height of the back of the robot 12 can be 100 cm or more.

  One omnidirectional camera 42, one infrared camera 44, and one microphone 46 are provided in the approximate center of the upper body 36. The omnidirectional camera 42 photographs the surroundings of the robot 12 and is distinguished from an eye camera 48 described later. As this omnidirectional camera 42, for example, a camera using a solid-state imaging device such as a CCD or a CMOS can be adopted.

  The infrared camera 44 is for detecting infrared rays and includes a predetermined number of infrared detection elements. When a member exists in the field angle area of the infrared camera 44, infrared rays emitted from the infrared LED tag 16 are acquired, and the members are identified by the blinking pattern of the infrared rays. The microphone 46 captures ambient sounds, particularly voices of people who are communication targets. The installation positions of the omnidirectional camera 42, the infrared camera 44, and the microphone 46 are not limited to the upper body 36 and can be changed as appropriate.

  Upper arms 52R and 52L are provided on both shoulders of the upper body 36 by shoulder joints 50R and 50L, respectively. The shoulder joints 50R and 50L each have three axes of freedom. That is, the shoulder joint 50R can control the angle of the upper arm 52R around each of the X axis, the Y axis, and the Z axis. The Y axis is an axis parallel to the longitudinal direction (or axis) of the upper arm 52R, and the X axis and the Z axis are orthogonal to the Y axis from different directions. On the other hand, the shoulder joint 50L can control the angle of the upper arm 52L around each of the A axis, the B axis, and the C axis. The B axis is an axis parallel to the longitudinal direction (or axis) of the upper arm 52L, and the A axis and the C axis are axes orthogonal to the B axis from different directions.

  Further, forearms 56R and 56L are provided at the respective distal ends of the upper arms 52R and 52L via elbow joints 54R and 54L. The elbow joints 54R and 54L can control the angles of the forearms 56R and 56L around the axes of the W axis and the D axis, respectively.

  In the X axis, Y axis, Z axis, W axis, A axis, B axis, C axis, and D axis that control the displacement of the upper arms 52R and 52L and the forearms 56R and 56L, "0 degree" is the home position, respectively. In this home position, as shown in FIG. 2, the upper arms 52R and 52L and the forearms 56R and 56L are directed downward.

  Although not shown in the figure, the shoulder portion including the shoulder joints 50R and 50L of the upper body 36, the upper arms 52R and 52L, and the forearms 56R and 56L described above are each shown by touch sensors (shown comprehensively in FIG. 3). : 58), and these touch sensors 58 detect whether or not a person has touched each part of the robot 12.

  Spheres 60R and 60L corresponding to hands are fixedly provided at the tips of the forearms 56R and 56L, respectively. However, if a finger or palm function is required, a “hand” in the shape of a human hand can be used.

  Although the shape, dimensions, etc. of the robot 12 are set as appropriate, in other embodiments, for example, the upper body 36 includes a front surface, a back surface, a right side surface, a left side surface, a top surface, and a bottom surface, and the right side surface and the left side surface. You may form so that the surface may face diagonally forward. That is, the width of the front surface may be shorter than the width of the back surface, and the shape of the upper body 36 viewed from above may be a trapezoid.

  In such a case, the shoulder joints 50R and 50L are provided on the right side surface and the left side surface via left and right support portions whose surfaces are parallel to the left and right side surfaces, respectively. The rotation range of the upper arm 52R and the upper arm 52L is restricted by the left and right side surfaces or the surface (attachment surface) of the support portion, and the upper arms 52R and 52L do not rotate beyond the attachment surface.

  However, if the inclination angle of the left and right side surfaces, the distance between the B axis and the Y axis, the lengths of the upper arms 52R and 52L, the lengths of the forearms 56R and 56L, etc. are appropriately set, the upper arms 52R and 52L exceed the front. Since it can rotate to the inner side, the arms of the robot 12 can cross forward even if there is no degree of freedom of the arms by the W axis and the D axis. Therefore, even when the degree of freedom of arms is small, it is possible to execute close and intimate communication behavior such as embracing a person in front.

  A head 64 is provided above the center of the upper body 36 via a neck joint 62. The neck joint 62 has a degree of freedom of three axes, and the angle can be controlled around each of the S axis, the T axis, and the U axis. The S-axis is an axis that extends from the neck directly upward (vertically upward), and the T-axis and the U-axis are axes that are orthogonal to the S-axis in different directions. The head 64 is provided with a speaker 66 at a position corresponding to a human mouth. The speaker 66 is used for the robot 12 to communicate with people around it by voice or sound. However, the speaker 66 may be provided in another part of the robot 12, for example, the trunk.

  The head 64 is provided with eyeballs 68R and 68L at positions corresponding to the eyes. Eyeball portions 68R and 68L include eye cameras 48R and 48L, respectively. Hereinafter, the right eyeball portion 68R and the left eyeball portion 68L may be collectively referred to as the eyeball portion 68, and the right eye camera 48R and the left eye camera 48L may be collectively referred to as the eye camera 48.

  The eye camera 48 captures a human face approaching the robot 12, other parts or objects, and captures a corresponding video signal. As the eye camera 48, a camera similar to the omnidirectional camera 42 described above can be used.

  For example, the eye camera 48 is fixed in the eyeball part 68, and the eyeball part 68 is attached to a predetermined position in the head 64 via an eyeball support part (not shown). The eyeball support unit has two degrees of freedom and can be controlled in angle around each of the α axis and the β axis. The α axis and the β axis are axes provided with respect to the head 64, the α axis is an axis in a direction toward the top of the head 64, the β axis is orthogonal to the α axis and the front side of the head 64 ( It is an axis in a direction perpendicular to the direction in which the face is facing. In this embodiment, when the head 64 is at the home position, the α axis is set to be parallel to the S axis, and the β axis is set to be parallel to the U axis. In such a head 64, when the eyeball support portion is rotated around each of the α axis and the β axis, the tip (front) side of the eyeball portion 68 or the eye camera 48 is displaced, and the camera axis, that is, the line-of-sight direction is changed. Moved.

  In the α axis and β axis that control the displacement of the eye camera 48, “0 degree” is the home position. At this home position, the camera axis of the eye camera 48 is the head 64 as shown in FIG. The direction of the front side (face) is directed, and the line of sight is in the normal viewing state.

  Further, for example, an antenna 70 of the wireless tag reader 18 is provided on the right shoulder next to the head 64. The antenna 70 receives electromagnetic waves or radio waves on which identification information transmitted from the RFID tag 14 is superimposed.

  FIG. 3 is a block diagram showing an electrical configuration of the robot 12. With reference to FIG. 3, the robot 12 includes a CPU 72 for controlling the whole. The CPU 72 is also called a microcomputer or a processor, and is connected to the memory 76, the motor control board 78, the sensor input / output board 80, and the audio input / output board 82 via the bus 74.

  Although not shown, the memory 76 includes a ROM and a RAM, in which a control program for the robot 12 is stored in advance, and the RAM is used as a work memory and a buffer memory. The control program includes, for example, a program for executing a communication action, a program for communicating with the external computer 20, and a program for acquiring identification information and recording a member's action history. The memory 76 also stores voice data or voice data (speech synthesis data) to be generated from the speaker 66 when performing the communication action, angle data for presenting a predetermined gesture, and the like.

  The motor control board 78 is configured by a DSP, for example, and controls driving of each axis motor such as each arm, head, and eyeball. That is, the motor control board 78 receives the control data from the CPU 72 and controls two angles of the α axis and β axis of the right eyeball portion 68R (in FIG. 3, collectively referred to as “right eyeball motor”). .) Control the rotation angle of 84. Similarly, the motor control board 78 receives control data from the CPU 72, and controls two angles of the α axis and β axis of the left eyeball portion 68L (in FIG. 3, collectively referred to as “left eyeball motor”). Controls the rotation angle of 86.

  The motor control board 78 receives the control data from the CPU 72, and controls the angles of the X axis, Y axis and Z axis of the right shoulder joint 50R and the W axis angle of the right elbow joint 54R. The rotation angles of a total of four motors (one collectively shown as “right arm motor” in FIG. 3) 88 including one motor to be controlled are adjusted. Similarly, the motor control board 78 receives the control data from the CPU 72 and determines the angles of the three motors for controlling the angles of the A-axis, B-axis and C-axis of the left shoulder joint 50L and the D-axis angle of the left elbow joint 54L. The rotation angle of a total of four motors (one collectively shown as “left arm motor” in FIG. 3) 90 with one motor to be controlled is adjusted.

  Further, the motor control board 78 receives control data from the CPU 72, and controls three angles of the S-axis, T-axis, and U-axis of the head 64 (collectively "head motor" in FIG. 3). The rotation angle of 92 is controlled. Furthermore, the motor control board 78 receives the control data from the CPU 72 and controls the rotation angle of two motors 26 (hereinafter collectively referred to as “wheel motors”) 26 that drive the waist motor 40 and the wheels 24. To do.

  In this embodiment, a motor other than the wheel motor 26 is a stepping motor or a pulse motor in order to simplify the control. However, as with the wheel motor 26, a DC motor may be used.

  Similarly, the sensor input / output board 80 is also constituted by a DSP, and takes in signals from each sensor and gives them to the CPU 72. That is, data relating to the reflection time from each of the ultrasonic distance sensors 32 is input to the CPU 72 through the sensor input / output board 80. Further, a video signal from the omnidirectional camera 42 is input to the CPU 72 after being subjected to predetermined processing by the sensor input / output board 80 as required. Similarly, the video signal from the eye camera 48 is also input to the CPU 72. Further, signals from the plurality of touch sensors described above (collectively indicated as “touch sensor 58” in FIG. 3) are provided to the CPU 72 via the sensor input / output board 80. Further, the signal from the collision sensor 28 described above is also given to the CPU 72 in the same manner. The infrared image from the infrared camera 44 is processed by the sensor input / output board 80, whereby the identification information emitted from the infrared LED tag 16, the positional information in the image, and the like are acquired and then given to the CPU 72.

  Similarly, the voice input / output board 82 is also configured by a DSP, and voice or voice in accordance with voice synthesis data provided from the CPU 72 is output from the speaker 66. Also, the voice input from the microphone 46 is taken into the CPU 72 via the voice input / output board 82.

  The CPU 72 is connected to the communication LAN board 94 and the wireless tag reader 18 via the bus 74. The communication LAN board 94 is configured by a DSP, gives transmission data sent from the CPU 72 to the wireless communication device 96, and transmits the transmission data from the wireless communication device 96 to the wireless communication device 96 via a network such as a wireless LAN, although not shown. To be transmitted to the external computer 20. The communication LAN board 94 receives data via the wireless communication device 96 and gives the received data to the CPU 72. That is, the communication LAN board 94 and the wireless communication device 96 allow the robot 12 to perform wireless communication with the external computer 20 or the like.

  The wireless tag reader 18 receives the radio wave on which the identification information transmitted from the RFID tag 14 is superimposed via the antenna 70, amplifies the radio signal, separates the identification information from the radio signal, and stores the information. Demodulate (decode) and give to CPU72. However, the RFID information may be decoded by an external computer and given to the CPU 72.

  Further, the CPU 72 is connected to a user information database (hereinafter referred to as “user DB”) 98 and an action history database (hereinafter referred to as “history DB”) 100 via a bus 74. However, these databases may be provided so as to be accessible on the external computer 20 or an external network.

  The user DB 98 is a database in which user information, that is, information on members belonging to the detection target organization is registered. In this embodiment, a user information table as shown in FIG. 4 is stored. In the user DB 98, for example, a member name, identification information of the RFID tag 14 to be attached, identification information (flashing pattern) of the infrared LED tag 16 and the like are stored in association with the member ID. In FIG. 4, for example, the member A is equipped with an RFID tag 14 in which identification information “AAAA” is registered, and an infrared LED tag 16 that emits light with a blinking pattern of “Ta”. I understand.

  The history DB 100 is a database for recording a history of member behavior. This action means an action regarding whether or not the member is coming to the robot 12 for communication. That is, a change with time is recorded as to whether or not a member is present in a predetermined area near the robot 12 that can be detected by the acquisition means (in this embodiment, the wireless tag reader 18 and the infrared camera 44).

  As an example of the communication behavior, the robot 12 can take the following various behaviors. For example, if there is a reply talking with "Hello", hold out one of the arms 52 and 60 to say "Let's shake hands" forward. If there is no reply talking with "Hello", I referred to as a "bye-bye". When a human face is recognized in the image data from the eye camera 48, the face side of the head 64 and the eyeball unit 68 are directed toward the face of the person. When touched, the face side of the head 64 is directed toward the touched part. As described above, the robot 12 can actively present a communication action by itself, recognize a human reaction to the action, and further present different actions according to the recognition result. Reaction operation can also be performed.

  In this embodiment, since identification information is given to each member to be a communication partner by the RFID tag 14 and the infrared LED tag 16, it is also possible to execute an individual communication action in accordance with an actual communication partner. . For example, if voice data corresponding to each member's name is stored, identification information can be acquired to identify the member in communication and call the member's name. It is also possible to record an execution history that shows what communication behavior has been performed with which member, and to execute the communication behavior based on the history. For example, you can call “Nice to meet you” for members who have come for the first time, “Long time” for members who have come after a long time, and if you have information to contact everyone, you have not heard yet Appropriate actions can be performed such as conveying information only when members come. Since the robot 12 can also perform such personal communication behavior, even if each member is equipped with the RFID tag 14 or the infrared LED tag 16 or the like, there is no particular sense of incongruity or doubt, and it is natural. You can record your actions.

  Such a robot 12 is disposed in a space where an organization exists, for example, in a classroom of a class when detecting the organizational structure of a class child. The robot 12 executes a communication action for each of the above-mentioned members who have come to communicate, attempts to acquire identification information at regular intervals (for example, at intervals of one second), and configures based on the acquired data. An employee's action history is recorded in the history DB 100. Specifically, the identification information from the RFID tag 14 and the identification information from the infrared LED tag 16 are fetched at regular intervals, and information on members existing in a predetermined area is recorded.

  For example, as shown in FIG. 5, the data recorded in the history DB 100 includes information on members detected by the wireless tag reader 18 and information on members detected by the infrared camera 44 at each capture time. Including. Since the identification information of the infrared LED tag 16 is an on / off pattern, the blinking pattern can be specified by performing data capture and analysis over a predetermined time including the capture time.

  As the member information, for example, the member ID obtained by collating the acquired identification information with the user DB 98 is described. The description of the member information is not limited to this. For example, as the detection by the RFID tag reader 18, the acquired RFID identification information may be described as it is, or the member name is described. Also good. Similarly, as the detection by the infrared camera 44, the acquired identification information may be described, or the member name or the like may be described.

  In the example of FIG. 5, for example, at time t <b> 20, three members A, B, and C are detected by the wireless tag reader 18, and two members A and B are detected by the infrared camera 44. I understand. The reason that the detected members differ depending on the type of acquisition means as at this time t20 is that the predetermined area that can be detected differs for each acquisition means.

  FIG. 6 shows an example of a relationship between a predetermined area that can be detected by the wireless tag reader 18 and a predetermined area that can be detected by the infrared camera 44. The detection area (indicated by a long broken line) by the wireless tag reader 18 is determined by the communication distance of the applied RFID, and is a range from the robot 12 (antenna 70) to the communication distance of the RFID. Further, the detection area (dotted line display) by the infrared camera 44 is determined by the angle of view of the infrared camera 44, and the infrared camera 44 is provided on the front side of the robot 12, and thus is on the front side of the robot 12. In FIG. 6, members A, B, and C exist in a predetermined area by the wireless tag reader 18, and members A and B also exist in a predetermined area by the infrared camera 44. Therefore, in this case, a measurement result such as the time t20 in FIG. 5 described above is obtained.

  Considering the positional relationship between the members A, B and C, the members A and B exist together in front of the robot 12 in order to communicate with the robot 12, while the member C For example, it is unclear whether you are watching by the side or trying to join a friend, but in any case, it can be determined that members A and B are not present together. That is, among the members A, B, and C, only the members A and B detected by both the wireless tag reader 18 and the infrared camera 44 can be regarded as coming in front of the robot 12. In this way, by using a plurality of acquisition means of the wireless tag reader 18 and the infrared camera 44, members not coming in front of the robot 12 are eliminated, and the measurement accuracy of the behavior of each member is increased. Thus, more accurate tissue structure detection is possible.

  In addition, when the angle of view of the infrared camera 44 is relatively large, communication with the robot 12 is not performed, and even members who are watching from a remote position are detected. It is desirable to record information as detected member information by excluding information detected at the end of a wide visual field and applying only information detected in a predetermined range of the visual field.

  After the detected member information is recorded in the history DB 100, the matching members are extracted based on the detection result by the wireless tag reader 18 and the detection result by the infrared camera 44. Then, as shown in FIG. 7, the extracted members are determined as members existing in the predetermined area at that time. That is, the predetermined region in this case is a portion where the detection region by the wireless tag reader 18 and the detection region by the infrared camera 44 overlap. For example, the members who came in front of the robot 12 at time t20 are A and B. The determined action history data may be recorded in the history DB 100. By combining a plurality of acquisition means in this way, the predetermined region can be set more accurately and a more accurate action history can be recorded, so that a more accurate tissue structure can be detected.

  Such action history determination processing may be performed by transferring the recorded action history data to the external computer 20 and executed by the CPU of the external computer 20.

  Then, the organizational structure is grasped based on the confirmed action history. This organizational structure grasping process may be performed by the CPU 72 inside the robot 12, or the recorded action history data or confirmed action history data is transferred to the external computer 20 and executed by the CPU of the external computer 20. It may be broken.

  Specifically, the relationship between the members is determined by comparing the action history with a predetermined conversion rule. The conversion rule defines how members coexist in a predetermined area and the corresponding human relationship. It is thought that the human relations appear in the way of coexistence with others in a predetermined area with the human robot 12 interposed. Therefore, the way of coexistence is patterned, and the human relations for each action pattern Whether it is such is determined in advance as a rule.

  FIG. 8 shows some typical rules as examples of conversion rules. FIG. 8A shows a case in which two members A and B always stay at the same time in front of the robot 12. In this case, the human relationship between members A and B favors each other. It is determined that the relationship is possessed. FIG. 8B shows a case where the member A comes before the robot 12 and the member B comes after that. The human relationship in this case is determined to be a relationship in which the member B has a favor for A. FIG. 8C shows a case where the member B stays in front of the robot 12 and B leaves when the member A comes after that. The human relationship in this case is determined to be a relationship in which member B hates A.

  FIG. 9 shows some of the more complex rules as examples of conversion rules. FIG. 9A shows a case where people gather when the member A comes in front of the robot 12. In this case, it is determined that the gathered people have a favorable relationship with the member A, and that A is highly likely to be a leader. In this case, the degree of favor is set to be weaker than the favor in the one-to-one relationship shown in FIG. FIG. 9B shows a case where people are gathering in front of the robot 12 and then they leave when the member A comes. In this case, the people who have left are in a relationship that hates the member A, and further, it is determined that A is likely to be a disliked person. In this case, the degree of dislike is set to be weaker than dislike in the one-to-one relationship shown in FIG. FIG. 9C shows a case where the robot 12 plays with the member A when there is no other member A. In this case, the member A is determined as a person who has a tendency to hate other people (exclusive tendency).

  For example, in the case of the action history shown in FIG. 7, since the members A and B stayed at the same time from the time t10 to the time t30, the members A and B favor each other for the number of times of acquisition. It is determined that you have it. Further, since the member C arrives at time t30, it is determined that the member C has a favor for the members A and B. Further, since the member B has already disappeared at the time t40 due to the arrival of the member C at the time t30, the member B is determined to dislike the member C.

  Thus, the organization structure can be easily grasped by determining the relationship between the members based on the action history data and the conversion rules. Then, relation data is generated based on the determination result. For example, as shown in FIG. 10, the relationship data includes information related to the human relationship for each member (member ID), for example, the degree of likes and dislikes. The relationship data also includes special relationship information determined by the conversion rules, such as a person who is a leader, a person who is disliked, a person who has an exclusive tendency, and the like. For example, a member who is a leader or hated is also described as to which member has such a special relationship. As a result, the organizational structure can be clearly and easily understood.

  The degree of likes and dislikes are calculated by, for example, accumulating the number of times determined to be like and the number of times determined to be dislike for each of the other members, and dividing each total by the total number of stays. The Therefore, the degree of liking increases as the time spent together (the number of stays increases). Further, although omitted in FIG. 10, for the direction of likes and dislikes, for example, the number of times determined to be unilaterally like, mutually like or unilaterally dislike is accumulated and determined to be the largest. To do.

  It goes without saying that the relational data obtained in this way can be improved in accuracy by setting the measurement time longer and increasing the amount of acquired data. Depending on the size of the organization, for example, it may be possible to arrange the robot 12 in the organization for one day to several days, or about one week to several weeks. In addition, it is necessary to ensure sufficient time to give all members the opportunity to communicate with the robot 12 at least once.

  Then, based on the generated relational data, the organizational structure is output in an appropriate form. In other words, for example, a sociogram showing the organizational structure shown in FIG. 11 or a sociometric matrix (not shown) shown in the table is displayed on the display of the external computer 20 or outputted to a printer. To do. When the relation data is generated inside the robot 12, the generated relation data is transferred to the external computer 20 and displayed on the display.

  The sociogram can be generated by converting the information on the human relationship between the members as described above by using a general graph analysis technique such as principal component analysis, spring model analysis, etc. it can. This sociogram can clearly show the structure of the tissue.

  For example, in the sociogram screen of FIG. 11, each member is indicated by a circle with a name written thereon, and the relationship between each member is indicated by an arrow connecting each other. This arrow is the same as the arrow used in the determination results shown in FIG. 8 and FIG. 9, the black arrow indicates “like”, and the white arrow with an x mark indicates “dislike”. Their degree is indicated by the length and thickness of the arrows. The length is shortened as the degree of liking is high, and is lengthened as the degree of dislike is high. Also, regarding the thickness, the higher the degree of likes and dislikes, the thicker.

  This sociogram highlights, for example, the existence of a close group, and can also find dislikes (bullyed children). You can also see who likes and dislikes most and is most involved in the overall organization. For example, in the sociogram shown in FIG. 11, there are a group including members A, B, C, and D and a group including members F, G, and H in the organization. You can clearly see that it has been rejected. Therefore, the organizational structure can be clearly and easily grasped by displaying and outputting the organizational structure in an appropriate form. Using the organizational structure found by the system 10, for example, in school education, it can be used for various communication support such as discovery of a bullied child, class management, student guidance, and the like.

  In this way, it is possible to clearly grasp the relationship among members in the organization as measured by the robot 12. Furthermore, by taking measurements continuously or periodically (for example, monthly, semester, season, etc.), it is possible to capture dynamic temporal changes in human relationships, such as the elimination of bullying. The results of communication support can also be confirmed.

  FIG. 12 shows an example of an operation history recording process operation of the robot 12. When the robot 12 is placed in the target tissue and the recording of the action history is started, the CPU 72 of the robot 12 first starts the communication action in step S1. As a result, the robot 12 executes the communication behavior with the members in parallel with the recording of the behavior history. Next, in step S3, the timer starts counting, and in step S5, it is determined whether or not the current time is the data fetch time. In this embodiment, since the data is taken in at a constant cycle (for example, at intervals of 1 second), it is determined whether a certain time has elapsed. If “YES” in the step S5, in a subsequent step S7, the CPU 72 checks the RFID tag reading device 18 to determine whether or not there is RFID identification information. If there is, the RFID identification information in the step S9. And is stored in a predetermined area of the memory 76. On the other hand, if “NO” in the step S7, the process proceeds to a step S11 as it is.

  In step S 11, the CPU 72 checks the sensor input / output board 80 to determine whether there is infrared tag identification information. If there is, the CPU 72 acquires the infrared tag identification information in step S 13 to obtain a predetermined area of the memory 76. To remember. On the other hand, if “NO” in the step S11, the process proceeds to a step S15 as it is.

  In step S <b> 15, the CPU 72 refers to the user DB 98 (FIG. 4), acquires the member ID corresponding to the identification information by RFID and the identification information by infrared LED, and stores them in a predetermined area of the memory 76.

  Subsequently, in step S17, the CPU 72 records each member ID in the history DB 100 in association with the time of taking in the identification information (FIG. 5). Since the capture time is every fixed time, in FIG. 5, the capture times are sequentially indicated by tn (n is a positive integer). And it returns to step S5 again, it is judged whether it is taking-in time, and if it is "YES", acquisition and recording of identification information will be repeated.

  On the other hand, if “NO” in the step S5, it is determined whether or not a predetermined capturing end time is exceeded in a step S19. If “NO” in the step S19, the process returns to the step S5 again to repeat the acquisition and recording of the identification information. On the other hand, if “YES” in the step S19, the action history recording process is ended. In this way, the action history DB 100 as shown in FIG. 5 can be obtained.

  FIG. 13 shows an example of the action history determination process. The processing of FIG. 13 and the processing of FIG. 14 and FIG. 16 to be described later may be processed by the CPU 72 inside the robot 12 as described above. After the recording is finished, the data in the history DB 100 is transferred to the external computer 20 and the action history data is processed by the external computer 20.

  As shown in FIG. 13, the CPU of the external computer 20 first sets the initial value of the variable n for designating the fetch time in step S31 to 1, and then in step S33, the history data at the time tn. It is determined whether the member ID detected by the RFID reader 18 is recorded for the data. Here, the history data is processed in order from the data of the first capture time. If “NO” in the step S33, the process proceeds to a step S45. On the other hand, if “YES” in the step S33, the member ID by the RFID tag 14 is read from the history data and obtained in a succeeding step S35.

  Subsequently, in step S37, it is determined whether or not the member ID by the infrared tag is recorded for the data at the time tn of the history data. If “NO” in the step S37, the process proceeds to a step S45. On the other hand, if “YES” in the step S37, the member ID by the infrared LED tag 16 is read from the history data and obtained in a succeeding step S39.

  In the following step S41, the member ID by the RFID tag 14 and the member ID by the infrared LED tag 16 are compared, and the member ID common to both is extracted. In this way, only the member ID detected by both the RFID reader 18 and the infrared camera 44 is extracted as existing in the predetermined area.

  In step S43, the extracted member ID is recorded in the predetermined area of the memory as the confirmed action history data in association with the time tn.

  In step S45, it is determined whether or not the time tn is the capture end time, that is, whether or not the extraction process has been completed for all the capture times tn of the history data. If “NO”, the variable is determined in step S47. n is incremented, the process returns to step S33, and the extraction process for the next capture time tn is repeated. On the other hand, if “YES” in the step S45, the action history determination process is ended. In this manner, the member ID that can be regarded as existing in the predetermined area is extracted for all the capture times tn of the history data, and the confirmed action history data is generated.

  Based on this confirmed action history data, the process of grasping the relationship between members is executed. Specifically, as described above, for example, the relationship is determined based on a predetermined conversion rule as shown in FIGS. 8 and 9, for example, so that the determination can be easily performed by pre-processing the confirmed action history data. Like that. That is, action pattern data obtained by extracting the change in the member ID before and after the measurement time from the confirmed action history data is generated by action pattern data generation processing as shown in FIG.

  In the first step S61 in FIG. 14, the CPU of the external computer 20 sets the initial value of the variable m for designating the capture time to 0, and then in step S63, the time tm of the confirmed action history data is set. The member ID data and the member ID data for the next time tm + 1 are read and acquired.

  Subsequently, in step S65, the two member IDs are compared, and the member ID common to both members, the member ID increased at the next time tm + 1, the member ID decreased, and the like are extracted. To do.

  In step S67, the extracted common member ID, increased member ID, decreased member ID, and the like are recorded as behavior pattern data in association with the time tm + 1, for example.

  In a succeeding step S69, it is determined whether or not the time tm + 1 is the capture end time, that is, whether or not the above-described extraction processing or the like has been performed for all adjacent time pairs of the confirmed action history data. If “NO” in this step S69, the variable m is incremented in a succeeding step S71, and the process returns to the step S63 to repeat the processing for the next set of times. On the other hand, if “YES” in the step S69, the action pattern data generation process is ended.

  In this manner, common pattern ID, increased ID, decreased ID, etc. are extracted before and after all measurement times in the confirmed action history data, and action pattern data as shown in FIG. 15 is generated. As a result, since the confirmed behavior history data can be understood as the behavior pattern of the member, the determination based on the conversion rule that defines the behavior pattern of the member and the corresponding relationship can be easily performed.

  FIG. 16 shows an example of the relationship grasping and display processing operations. First, in step S91, the CPU of the external computer 20 selects one member ID for which a relationship is to be obtained. Next, in step S93, the initial value of the variable m for designating the extraction time in the behavior pattern data is set to 0, and in the subsequent step S95, the data at time tm + 1 of the behavior pattern data is read and acquired.

  In step S97, it is determined whether there is a common ID, an increased ID, or a decreased ID for the data. If “NO” in the step S97, the process proceeds to a step S105.

  On the other hand, if “YES” in the step S97, the relationship between the selected ID and another ID is determined based on the conversion rule for the data in a step S99, and the result is recorded. For example, according to the example shown in FIG. 8 and FIG. 9, when the selected ID exists in the common ID, it can be determined that the other IDs like the other common IDs. In addition, when the selected ID is an increase ID, it is unilaterally favored with respect to the ID of the common ID, or the ID that has increased in the range that goes back a predetermined time before the common ID. Can be determined. Further, when the selected ID is a decrease ID, it can be determined that the ID or the like increased in a range up to a predetermined time before is unilaterally disliked. Furthermore, when there is an increase of a predetermined number of IDs within a predetermined time after the selected ID exists in the increased ID, the selected ID is a leader of the increased number of IDs. Can be determined. In addition, when there is a decrease in a predetermined number of IDs within a predetermined time after the selection ID exists in the increase ID, the selection ID is a person who is disliked from the decreased plurality of IDs. It can be determined that there is. Further, when only the selected ID exists in the common ID for a predetermined time or more, the selected ID can be determined as a person with an exclusive tendency to hate other people.

  Subsequently, in step S101, the number of the same relation, that is, the number of the same ID determined to be the same is accumulated, and in step S103, it is determined whether or not to end the determination for the selected ID. If “NO” in this step S103, that is, if the processing has not been completed for all extraction times of the behavior pattern data, the process proceeds to a step S105, the variable m is incremented, and the process returns to the step S95 to be next. The processing is repeated for the data of the extraction time.

  On the other hand, if “YES” in the step S103, the degree of each relationship with respect to other IDs of the selected ID is calculated and recorded based on the total number of times and the total number of stays in the subsequent step S107. In step S109, it is determined whether or not all member IDs have been processed. If “NO”, the process returns to step S91 to select another ID, and the process is repeated for the other ID. In this way, for example, relational data as shown in FIG. 10 is generated.

  In step S111, data for drawing a sociogram is generated based on the relation data using a general graph analysis technique. In the subsequent step S113, for example, a sociogram as shown in FIG. 11 is displayed on the display of the external computer 20, and this relationship grasping and display processing is terminated.

  According to this embodiment, the information for identifying the member is acquired by the acquisition means provided in the robot 12 as the access device introduced into the organization, and the behavior history of each member in the predetermined area is recorded. , Can record the natural behavior of each member. And based on such an action history, the relationship between the members reflected in it can be found and clarified. Therefore, it is possible to find the relationship between the members from the information as it is, without asking the members to like or dislike other members, so the relationship (organizational structure) between each member can be accurately determined. I can grasp it.

  In the above-described embodiment, the wireless tag reader 18 or the infrared camera 44 provided in the robot 12 is used to acquire the identification information. However, these acquisition means are located near or around the robot 12. It may be provided to detect a predetermined area set near the robot 12 or the front. In this case, these acquisition means may be connected to the external computer 20, and all processing such as action history recording and related data generation may be performed by the external computer 20.

  Further, in each of the above-described embodiments, the robot 12 is introduced into the space where the organization exists, and the behavior of each member when the robot 12 is interposed is recorded, but in the space where the organization exists. What is introduced is not limited to the robot 12. That is, similar to the robot 12, for example, it is configured by attracting the members' interest over a relatively long period of time, attracting the members' attention, attracting the members' attention, or feeling familiarity. It is also possible to introduce an approach device that allows a member to approach voluntarily and record the behavior history of members in a predetermined area near the approach device. In this case, a means for acquiring identification information such as the RFID tag reader 18 and the infrared camera 44 is installed in the proximity device itself for approaching its members or in the vicinity or vicinity of the proximity device and detected. A predetermined area is set near the access device. As an approach device for making such a member approach voluntarily, other than the robot 12, for example, a PC, a video game machine connected to a display, a display, a teaching material, or an animal (dog, cage, etc.) Various objects such as various devices and tools, such as a stuffed doll with the shape of

  In each of the above-described embodiments, the system 10 includes the robot 12 (access device) and the external computer 20. However, all the functions of the external computer 20 are provided in the access device such as the robot 12. That is, for example, the approach device such as the robot 12 may be provided with a display, a program for generating and outputting the relation data from the action history data, and the like. In this case, the robot 12 that is an approach device or the above-described stuffed animal itself becomes the relationship detection system 10.

  In each of the above-described embodiments, the action measurement accuracy is improved by using a plurality of acquisition means having different detectable predetermined areas such as the wireless tag reader 18 and the infrared camera 44. In some cases, the measurement may be performed by using only one of them.

  In each of the above-described embodiments, the wireless tag 14 and the infrared LED tag 16 are attached to each member in order to acquire information for identifying the member. This information may be acquired from the members themselves. For example, by acquiring an image of a member's face by an image sensor such as a CCD camera (eye camera 48 or omnidirectional camera 42 in the robot 12) and collating it with a member's face image database prepared in advance. You may make it identify. Alternatively, it is also possible to identify by providing a device that reads a member's fingerprint, iris, etc. and collating them with a database in the same manner.

  Further, in each of the above-described embodiments, the case where the relationship between individual members is mainly grasped as an organizational structure has been described. However, a predetermined unit (basic group) is determined based on some characteristic or commonality among members. The relationship between the units may be determined separately. As examples of elements for classifying an organization into predetermined units, various factors such as sex, age, school year, generation, school of origin, hometown, occupation, job rank, hobby, and the like can be considered. Also in this case, the structure of the organization can be grasped from various viewpoints, and it can be used for various communication support in the organization. The details of each of these elements may be investigated in advance and registered in the user DB 98 in association with the member ID. Or, for example, when classifying by elements that can be obtained from the appearance of the member, such as the color of the member's skin (white, black, yellow, brown, etc.) or the color of the hair, the identification information is obtained by an image sensor, for example. You may make it detect directly from the member itself.

It is an illustration figure which shows the outline | summary of the relationship detection system of one Example of this invention. It is an illustration figure (front view) which shows the external appearance of the communication robot of FIG. It is a block diagram which shows the internal structure of the communication robot of FIG. It is an illustration figure which shows an example of the content of user DB of FIG. It is an illustration figure which shows an example of the content of log | history DB of FIG. It is an illustration figure which shows the relationship between the detection area by a wireless tag reader, and the detection area by an infrared camera. It is an illustration figure which shows an example of the log | history of the confirmed action. It is an illustration figure which shows an example of the relationship between the action pattern in a predetermined area | region, and the member corresponding to it. It is an illustration figure which shows another example of the relationship between the action pattern in a predetermined area | region, and the member corresponding to it. It is an illustration figure which shows an example of the content of the relationship data produced | generated. It is an illustration figure which shows an example of the sociogram displayed. It is a flowchart which shows an example of operation | movement of the recording process of the action history in a robot. It is a flowchart which shows an example of operation | movement of the determination process of action history. It is a flowchart which shows an example of operation | movement of the production | generation process of action pattern data. It is an illustration figure which shows an example of the content of the action pattern data produced | generated. It is a flowchart which shows an example of the operation | movement of the grasping | ascertainment of a relationship, and a display process.

Explanation of symbols

DESCRIPTION OF SYMBOLS 10 ... Relationship detection system 12 ... Communication robot 14 ... Wireless tag 16 ... Infrared LED tag 18 ... Wireless tag reader 20 ... External computer 44 ... Infrared camera

Claims (12)

A relationship detection system for detecting a relationship between the members in an organization including a plurality of members or between units classified by the characteristics of the members,
An identification means for identifying the member existing in the predetermined area;
Recording means for recording a history of actions related to whether the member exists in the predetermined area based on identification by the identification means;
Based on the coexistence method in the predetermined area extracted from the action history recorded by the recording means and the predetermined rule that defines the relationship corresponding to the coexistence method in the predetermined area A relationship grasping means for generating information about likes and dislikes between or between the units ,
The predetermined rule is a predetermined rule that defines a relationship between the members corresponding to how the members coexist in the predetermined area, and when the members stay at the same time, the members The rule that the other member comes after one member, the rule that the other member favors the one member, the other member when the other member comes The rule that the other member dislikes the one member when the other member leaves, the other member who gathers when the other member comes, the other member The rules that a member is a leader, and if other members leave when a member arrives, the other members Hate the members At least one of the rules that a member is a disliked person and a rule that a member is an exclusive person when there is no other member Relationship detection system , including two . A relationship detection system for detecting a relationship between the members in an organization including a plurality of members or between units classified by the characteristics of the members,
An access device provided in a space where the tissue exists and for allowing the member to approach spontaneously;
Identifying means for identifying the member present in a predetermined area near the access device;
Recording means for recording a history of actions related to whether the member exists in the predetermined area based on identification by the identification means, and the predetermined area extracted from the history of actions recorded by the recording means Based on a coexistence method and a predetermined rule that defines the relationship corresponding to the coexistence method in the predetermined area, and a relationship grasping means for generating information on likes and dislikes between the members or between the units ,
The predetermined rule is a predetermined rule that defines a relationship between the members corresponding to how the members coexist in the predetermined area, and when the members stay at the same time, the members The rule that the other member comes after one member, the rule that the other member favors the one member, the other member when the other member comes The rule that the other member dislikes the one member when the other member leaves, the other member who gathers when the other member comes, the other member The rules that a member is a leader, and if other members leave when a member arrives, the other members Hate the members At least one of the rules that a member is a disliked person and a rule that a member is an exclusive person when there is no other member Relationship detection system , including two . The identification means includes acquisition means for acquiring identification information of the member existing in the predetermined area,
The relationship detection system according to claim 1, wherein the recording unit records a history of the behavior based on the identification information acquired by the acquisition unit.   The relation detection system according to claim 2, wherein the approaching device includes a communication robot including an autonomous moving means for autonomously moving and an acquiring means for acquiring identification information of the member existing in the predetermined area.   5. The relationship detection system according to claim 3, wherein the acquisition unit includes a wireless tag reading unit that acquires the identification information from a wireless tag attached to each of the plurality of members.   The relation detection system according to claim 3, wherein the acquisition unit includes an infrared detection unit that acquires the identification information from an infrared LED tag attached to each of the plurality of members. Wherein based on the information about the likes and dislikes generated by the relationship grasping means further comprises display means for displaying a relationship between or among the units the members, relationship detection system according to any one of claims 1 to 6. The relationship detection system according to claim 7 , wherein the display unit displays the relationship as a sociogram. The information about the likes and dislikes generated by the relation grasping means is the degree of likes or dislikes between the members or the units, or a person who is a leader in the organization, a person who is disliked or an exclusive tendency at least one containing, relationship detection system according to any one of claims 1 to 8 persons. In an organization including a plurality of members, provided in a space in which the organization exists and closes the members in order to detect a relationship between the members or units classified according to the characteristics of the members. An access device for
An identification means for identifying the member existing in the predetermined area;
Recording means for recording a history of actions related to whether the member exists in the predetermined area based on identification by the identification means, and the predetermined area extracted from the history of actions recorded by the recording means Based on a coexistence method and a predetermined rule that defines the relationship corresponding to the coexistence method in the predetermined area, and a relationship grasping means for generating information on likes and dislikes between the members or between the units ,
The predetermined rule is a predetermined rule that defines a relationship between the members corresponding to how the members coexist in the predetermined area, and when the members stay at the same time, the members The rule that the other member comes after one member, the rule that the other member favors the one member, the other member when the other member comes The rule that the other member dislikes the one member when the other member leaves, the other member who gathers when the other member comes, the other member The rules that a member is a leader, and if other members leave when a member arrives, the other members Hate the members At least one of the rules that a member is a disliked person and a rule that a member is an exclusive person when there is no other member Access device , including two . 11. Access device according to claim 10 , formed as an animal-shaped stuffed animal. The access device according to claim 10 , wherein the access device is formed as a communication robot further including an autonomous moving means for autonomously moving.

Images