JP2015008405A - Information display selection system and information display selection method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To select a place suitable for the posture and direction of a user, and to present information in doors.SOLUTION: An information display selection system comprises a plurality of sensors which detect a location of a user and measure pressure, and a control device. The control device comprises a first database in which data for estimating the state of the user is collected, a second database in which data for estimating the orientation of the user is collected, and a third database in which the layout of indoor objects is registered. The information display selection system estimates the location and state of the user on the basis of the first database and information from the plurality of sensors and detects an orientation of the user on the basis of the second database and the information from the plurality of sensors. The system also selects a place to display the information on the basis of respective estimation results and data in the third database.

Description

  The present invention relates to an information display selection system and an information display selection method for presenting information by selecting a place suitable for a user's posture and direction in a home.

  In recent years, with the reduction in size, weight, and cost of a display device typified by a television, a plurality of display devices are arranged in the home, and an environment for enjoying video content such as a TV program is being prepared. In the near future, a case where a plurality of display devices are arranged in one space such as a living room in the home is also assumed. Under such circumstances, a technique for projecting video content such as a television program on a display device suitable for the posture and direction of the user is desired.

  In response to such a request, for example, for the purpose of adjusting the orientation of the image displayed on the display screen when the positional relationship between the orientation of the display screen and the orientation of the user changes, the camera and the acceleration sensor A technique is disclosed in which the direction of a user with respect to the orientation of a display device is detected and the orientation of an image displayed on the display device is adjusted according to the orientation of the user (see, for example, Patent Document 1).

  In addition, as a technique for extracting the user's posture and direction, for example, for the purpose of appropriately managing the power consumption in the home, the operation method of home appliances from the usage information, arrangement information, etc. of sensors and indoor devices A technique for determining is disclosed (for example, see Patent Document 2).

PCT / JP2011 / 065449 JP 2012-208613 A

  However, in the technology disclosed in Patent Document 1, the orientation of the user and the display device can be detected by using the camera and the acceleration sensor, but the use of the camera may infringe privacy, Since it is difficult to install a camera, there is a problem that the orientation of the user cannot be detected.

  Further, with the technology disclosed in Patent Document 2, it is possible to grasp the approximate location where the user is, but it is not possible to detect the user's orientation and state (standing position, sitting position, lying position). There was a problem that information could not be presented at an appropriate place because it was not possible.

  Accordingly, the present invention has been made in view of the above-described problems, and provides an information display selection system and an information display selection method for presenting information by selecting a location suitable for the user's posture and direction indoors. For the purpose.

  The present invention proposes the following matters in order to solve the above problems.

  (1) The present invention comprises a plurality of sensors for detecting a user's position and measuring a pressure, and a control device. The information display estimates a user's state and orientation and provides information to a suitable location of the user. A selection system, wherein the control device collects data for estimating a user's state, a second database that collects data for estimating a user's orientation, and an indoor device A state estimation means for estimating the position and state of the user based on the third database in which the arrangement of the registered information, information from the first database and the plurality of sensors, and the second database, Based on information from the plurality of sensors, direction estimation means for detecting the orientation of the user, estimation results of the state estimation means and the direction estimation means, and the third data Based on the base data, we propose an information display location selection system characterized by comprising selection means, the selecting where to display the information.

(2) In the information display location selection system according to (1), the state estimation unit includes:
Feature vector generation means for generating a feature vector from the image information and pressure information of the user detected from position information obtained from the plurality of sensors, and a model for state estimation is generated based on the generated feature vector An information display location selection system is provided that includes a state estimation model generation unit that performs and an output unit that outputs an estimation result using machine learning based on the generated model.

  (3) In the information display location selection system according to (1), the direction estimation unit divides the image information of the user detected from position information obtained from the plurality of sensors into a lattice shape, and pressure information Direction estimation data generation means for generating direction estimation data based on the presence or absence of a direction, direction estimation model generation means for generating a model for direction estimation based on the generated direction estimation data, and a machine based on the generated model An information display location selection system characterized by comprising an output means for outputting an estimation result using learning is proposed.

  (4) The present invention comprises a plurality of sensors for detecting the user's position and measuring the pressure, and a control device. The information display estimates the user's state and orientation and provides information to the user's appropriate location. A selection method, in which the control device collects data for estimating a user's state, a second database that collects data for estimating a user's orientation, and an indoor object A third database in which the arrangement of the first and second locations is registered, and a first step of estimating the position and state of the user based on the first database and information from the plurality of sensors, 2 based on the database 2 and information from the plurality of sensors, the second step of detecting the orientation of the user, the estimation results of the first step and the second step, and the previous Based on the data in the third database, has proposed an information display location selection method characterized by a third step of selecting a location for displaying said information, with a.

  According to the present invention, since the state and orientation of the user indoors can be grasped, there is an effect that it is possible to select a display place where the user can browse comfortably and display information. Further, even if the user moves indoors or changes his / her posture, the display location can be appropriately selected, so that there is an effect that information can be browsed comfortably.

It is a figure which shows the structure of the information display selection system which concerns on this invention. It is a figure which shows the structure of the control apparatus which concerns on this invention. It is the figure which illustrated sensor output data in the standing position concerning the present invention. It is the figure which illustrated creation of the feature vector in the supine posture concerning the present invention. It is a figure which shows the process of the information display selection system which concerns on this invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.
Note that the constituent elements in the present embodiment can be appropriately replaced with existing constituent elements and the like, and various variations including combinations with other existing constituent elements are possible. Therefore, the description of the present embodiment does not limit the contents of the invention described in the claims.

<Embodiment>
The embodiment of the present invention will be described with reference to FIGS.

<Configuration of information display selection system>
As shown in FIG. 1, the information display selection system according to the present embodiment includes a plurality of sensors 100A, 100B, 100C, 100D,..., 100N, and a control device 200, which are connected via a network 300. Connected individually. Details of the control device 200 will be described later.

  Here, the sensor is, for example, a piezoelectric element that measures a pressure value, and is preliminarily arranged in a matrix on the floor surface of one indoor room. The position of each sensor arranged in this matrix is known in advance by the control device 200. Therefore, for example, when the pressure value is transmitted from the sensor 100A to the control device 200, the control device 200 can instantly grasp the place where the pressure is applied and the pressure value. The position of each sensor is also associated with the orientation in advance. In addition, although the example which arrange | positions a sensor on a floor surface was demonstrated above, you may use what arranged the sensor in the matrix form, for example on the carpet.

<Configuration of control device>
The configuration of the control device according to the embodiment of the present invention will be described with reference to FIGS.

  As shown in FIG. 2, the control device 200 according to the embodiment of the present invention includes a first database 210, a second database 220, a third database 230, a state estimation unit 240, and a direction estimation unit 250. And a selection unit 260.

  The first database 210 is a database that collects data for estimating the state of the user. The second database 220 is a database that collects data for estimating the orientation of the user. The third database 230 is a database in which arrangements of indoor devices are registered. In the third database, for example, the east direction from the center of an indoor room is set as the X axis and the north direction is set as the Y axis, and the arrangement type of the indoor device and the coordinate value thereof are associated and registered.

  The state estimation unit 240 estimates the position and state of the user based on the first database 210 and information from the plurality of sensors 100. Specifically, a feature vector is generated from user image information and pressure information detected from position information obtained from a plurality of sensors 100, and a model for state estimation is generated based on the generated feature vector. . Then, an estimation result is output using machine learning based on the generated model. Here, the states are standing, sitting, lying, and the like.

  The feature vector is, for example, the maximum pressure obtained from the number of detected images, the length of the long side in the user image information detected from the position information of the plurality of sensors, the length of the width, and the pressure information of the plurality of sensors. The state is expressed as a label using a value or the like. Note that the length of the long side represents the maximum value (cm) of the length of the chord / diagonal line in the image having the largest area among the detection data from the position information of the plurality of sensors. The length of the width represents the maximum value (cm) of the length of the chord / diagonal line perpendicular to the long side.

  FIG. 3 exemplifies image information and pressure information in the standing position, and indicates that the darker the color, the higher the pressure. In this case, the feature vector is expressed as label; number of detection data, long side length, width length, maximum pressure value = 1: 2, 23.0, 9.4, 1080. In the sitting position (chair sitting position, long sitting position, semi-sitting position, etc.), when sitting on a chair, it is expressed as 2: 2, 23.0, 9.4, 120 and sat on the floor with the legs extended. The state is represented as 2: 3, 90.0, 22.4, 380. Furthermore, in the supine position (such as supine, sideways, etc.), it is expressed as 3: 6, 160, 36.3, 250.

  The direction estimation unit 250 detects the direction of the user based on the second database and information from a plurality of sensors. Specifically, the user's image information detected from the position information obtained from the plurality of sensors 100 is divided into a lattice shape, and direction estimation data is generated based on the presence or absence of pressure information, and based on the generated direction estimation data, Generate a model for direction estimation. Then, an estimation result is output using machine learning based on the generated model.

  Further, for example, eight types of orientations of east, west, south, north, northwest, northeast, southwest, southeast and 10 types of labels (upper (ceiling), lower (floor)) are attached to the feature vector. Then, the image information obtained from the plurality of sensors 100 is divided into a lattice shape, and a portion with pressure is represented as 1 and a portion without pressure is represented as 0.

  FIG. 4 illustrates a method for creating a feature vector in the case of a supine posture. As described above, in the case of lying on the back, the label is “9”. As shown in FIG. 4, when grid-like data is arranged from the upper left to the lower right, the feature vector is 9: 00010111111111100010.

  Note that, for example, in the case of standing, the direction may be estimated by rotating the lattice with the center as the base point in accordance with the orientation of a room in the target room. Alternatively, the direction may be estimated by rotating the lattice around the center using the coordinate axes exemplified in the third database.

<Processing of information display selection system>
Processing of the information display selection system according to the embodiment of the present invention will be described with reference to FIG.

  First, the control device 200 estimates the position and state of the user based on information from the first database 210 and the plurality of sensors 100A, 100B, 100C, 100D,..., 100N (step S100). The direction of the user is detected based on the database 220 of 2 and information from the plurality of sensors 100A, 100B, 100C, 100D,..., 100N (step S200).

  Then, based on the estimation results of the first step S100 and the second step S200 and the data of the third database 230, a place for displaying information is selected (step S300).

  As described above, according to the present embodiment, since the user's state (for example, standing, sitting, and lying) and the direction can be estimated, for example, when sitting on a sofa and watching TV, the user When it is detected that the user is sitting on the sofa, the TV image is displayed on the display on the opposite side. Also, if you move to the kitchen to start cooking while watching TV, the TV image will be displayed on the wall of the kitchen. Can do. In other words, by detecting the user's state and orientation, even if the user's state and orientation change, it is possible to project an image or the like at an appropriate position, so that the user is in an indoor room No matter what action the user takes, the user can view the desired video.

  The processing of the control device in the information display selection system is recorded on a recording medium readable by the computer system, and the control device of the present invention is realized by causing the control device to read and execute the program recorded on this recording medium. can do. The computer system here includes an OS and hardware such as peripheral devices.

  Further, the “computer system” includes a homepage providing environment (or display environment) if a WWW (World Wide Web) system is used. The program may be transmitted from a computer system storing the program in a storage device or the like to another computer system via a transmission medium or by a transmission wave in the transmission medium. Here, the “transmission medium” for transmitting the program refers to a medium having a function of transmitting information, such as a network (communication network) such as the Internet or a communication line (communication line) such as a telephone line.

  The program may be for realizing a part of the functions described above. Furthermore, what can implement | achieve the function mentioned above in combination with the program already recorded on the computer system, what is called a difference file (difference program) may be sufficient.

  The embodiments of the present invention have been described in detail with reference to the drawings. However, the specific configuration is not limited to the embodiments, and includes designs and the like that do not depart from the gist of the present invention.

DESCRIPTION OF SYMBOLS 100; Sensor group 200; Control apparatus 210; 1st database 220; 2nd database 230; 3rd database 240; State estimation part 250; Direction estimation part 260;

Claims (4)

An information display selection system comprising a plurality of sensors for detecting a user's position and measuring pressure and a control device, estimating a user's state and orientation, and providing information to a suitable location of the user,
The control device is
A first database that collects data for estimating a user's condition;
A second database collecting data for estimating user orientation;
A third database in which the arrangement of indoor equipment is registered;
State estimating means for estimating the position and state of the user based on the first database and information from the plurality of sensors;
Direction estimation means for detecting the orientation of the user based on the second database and information from the plurality of sensors;
Selection means for selecting a place to display the information based on the estimation result of the state estimation means and the direction estimation means and the data of the third database;
An information display location selection system characterized by comprising: The state estimating means includes
Feature vector generation means for generating a feature vector from the image information and pressure information of the user detected from position information obtained from the plurality of sensors;
State estimation model generation means for generating a model for state estimation based on the generated feature vector;
Output means for outputting an estimation result using machine learning based on the generated model;
The information display location selection system according to claim 1, further comprising: The direction estimating means includes
Direction estimation data generation means for dividing the image information of the user detected from position information obtained from the plurality of sensors into a grid and generating direction estimation data according to the presence or absence of pressure information;
Direction estimation model generation means for generating a model for direction estimation based on the generated direction estimation data;
Output means for outputting an estimation result using machine learning based on the generated model;
The information display location selection system according to claim 1, further comprising: An information display selection method comprising a plurality of sensors for detecting a user's position and measuring a pressure, and a control device, estimating a user's state and orientation, and providing information to a suitable location of the user,
The control device is
A first database that collects data for estimating a user's condition;
A second database collecting data for estimating user orientation;
A third database in which the arrangement of indoor objects is registered;
With
A first step of estimating the position and state of the user based on information from the first database and the plurality of sensors;
A second step of detecting the orientation of the user based on the second database and information from the plurality of sensors;
A third step of selecting a place to display the information based on the estimation results of the first step and the second step and the data of the third database;
An information display location selecting method characterized by comprising: