KR101177625B1 - Emotion Illumination System Using Voice Analysis - Google Patents

Abstract

Emotional lighting system through the voice analysis according to an aspect of the present invention that can control the lighting based on the emotion of a plurality of users located in a specific space, the emotion of each user using the fundamental frequency of the voice information for each user A voice analyzer for determining a state value and calculating a final emotional state value using at least one of the determined emotional state values of each user; And a controller configured to determine an illumination value corresponding to the final emotional state value and to generate a luminaire control signal for driving the luminaire according to the determined illumination value.

Description

Emotion Illumination System Using Voice Analysis

The present invention relates to a lighting system, and more particularly to a emotional lighting system.

In general, an open space such as a commercial facility, a resting place, or a food and beverage facility where a large number of people can gather is installed and operated with a lighting device or a sound device for the convenience of the plurality of people.

However, the lighting device or sound device installed in the space is unilaterally controlled by an operator who has the authority to control the lighting device or sound device without considering the emotions of the plurality of people located in the space or the characteristics of the space. It was common to be.

Therefore, since the lighting device or the sound device is controlled differently from the emotions of a plurality of people located in the space, the usefulness and efficiency of using the space according to the purpose of using the space by the plurality of people may be deteriorated. There is a problem.

In order to overcome this problem, a method of controlling lighting or sound for each classified zone by artificially classifying the open space into a plurality of zones has been proposed.

This method can improve the usefulness of the space utilization by variously controlling the lighting or sound in one space, but there is still a disadvantage in that it cannot reflect the emotions of a plurality of users located in the space.

Accordingly, there is a need for an apparatus capable of controlling a lighting device or a sound device installed in the space in consideration of the emotions of a plurality of users located in the space.

Disclosure of Invention The present invention has been made in view of the above-described problem, and it is an object of the present invention to provide an emotional lighting system using voice analysis capable of controlling lighting based on the emotion of multiple users located in a specific space.

In order to achieve the above object, the emotional lighting system through the voice analysis according to an aspect of the present invention determines the emotional state value of each user by using the fundamental frequency of the voice information for each user, and determines the A voice analyzer configured to calculate a final emotional state value using at least one of emotional state values; And a controller configured to determine an illumination value corresponding to the final emotional state value and to generate a luminaire control signal for driving the luminaire according to the determined illumination value.

In order to achieve the above object, the emotional lighting system through the voice analysis according to another aspect of the present invention obtains an emotional state value of each user by using a fundamental frequency of voice information for each user received from an external device, A voice analyzer configured to determine the emotion group of each user by using the acquired emotion state value; And obtaining an illumination value corresponding to the determined emotion group of each user, and generating a luminaire control signal for driving the luminaire matched for each emotion group according to the illumination value corresponding to the emotion group of each user. It characterized in that it comprises a lighting fixture control.

According to another aspect of the present invention, an emotional lighting system using voice analysis classifies voice information of at least one user for each user, and emotional state values matched with a basic frequency of each user voice information. An analysis device for determining a final emotional state value by using at least one of the at least one and determining an illumination value corresponding to the final emotional state value; And a terminal device for recognizing and transmitting voice information of the at least one user to the analysis device and driving a lighting device according to an illumination value determined by the analysis device, wherein the analysis device and the terminal device are wired or wireless. It is characterized in that it comprises a connection via a network.

According to the present invention, since the lighting value can be determined based on the emotion of the user obtained through voice analysis of the multiple users located in the specific space, the emotion of the multiple users located in the space can be collected even in a space where many people can gather. In consideration of this, it is possible to control the lighting fixture, and accordingly, there is an effect that it can generate a positive effect on the psychological stability and treatment of people located in the space.

1 is a block diagram schematically showing the configuration of an emotional lighting system using voice analysis according to an embodiment of the present invention.
FIG. 2 is a diagram illustrating a configuration of a terminal device shown in FIG. 1.
3 is a block diagram schematically illustrating a configuration of a voice analyzer illustrated in FIG. 1.
4 is a flowchart showing a control method of the emotional lighting system according to an embodiment of the present invention.
5 is a flowchart showing a control method of the emotional lighting system according to another embodiment of the present invention.

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

1 is a block diagram of an emotional lighting system using voice analysis according to an embodiment of the present invention. As shown, the emotional lighting system 100 according to the present invention includes a terminal device 110, a network device 120, and the analysis device 130.

The terminal device 110 recognizes voice information of at least one user input through a voice input device (not shown) such as a microphone, and analyzes the recognized voice information through the network device 120 through the network device 120. To send.

In addition, the terminal device 110 receives a lighting device control signal from the analysis device 130 through the network device 120 to control a lighting device (not shown) connected to the terminal device 110.

The terminal device 110 may be installed on the ceiling or wall of a specific space at regular intervals. In this case, the specific space may be an open space such as a commercial facility or a food and beverage facility that can be collected by a plurality of users.

As illustrated in FIG. 1, the terminal device 110 includes a voice recognition unit 112 and a luminaire driver 114.

The voice recognition unit 112 is connected to the voice input device to recognize voice information of at least one user input through the voice input device, and recognizes the voice information of the at least one user by the network device 120. Transmission to the analysis device 130 through.

In this case, the voice input device may be provided in plural in front, rear, left and right of the terminal device 110 to receive the voice information more efficiently.

In one embodiment, the voice recognition unit 112 may transmit the identification information of the terminal device 110 when transmitting the voice information to the analysis device 130. The identification information of the terminal device 130 is used for identifying the location of the terminal device 130 or the terminal device is installed, etc., in which the voice information is transmitted from the analysis device 130.

Next, the luminaire driver 114 controls the luminaire connected to the luminaire driver 114 according to the luminaire control signal transmitted from the analysis device 130 through the network device 120.

Meanwhile, the terminal device 110 may further include an acoustic device driver 116 as shown in FIG. 1. The acoustic device driver 116 controls an acoustic device such as a speaker connected to the acoustic device driver 116 according to the acoustic device control signal transmitted from the analysis device 130 through the network device 120. .

As described above, the voice recognition unit 112, the luminaire driving unit 114, and the acoustic unit driving unit 116 are each independently inserted into the first frame 210 as illustrated in FIG. 2, and the voice input unit ( 222, the luminaire 224, and the acoustic device 226 may be installed on the second frame 220.

In this case, in order to avoid interference between the acoustic device 226 and the voice input device 222, the voice input device 222 may be installed at an edge of the second frame 220.

Meanwhile, the first frame 210 and the second frame 220 may be coupled to each other by the auxiliary connection unit 230 connected to the first frame 210 and the second frame 220, the terminal device 110 is It may be connected to the network device 120 through an integrated terminal 231 and a communication cable 232 installed on the back of the first frame 210.

Referring back to FIG. 1, the network device 120 transmits voice information of at least one user transmitted from one or more terminal devices 110 through wireless or wired to the analysis device 130 through wireless or wired. .

In addition, the network device 120 transmits the luminaire control signal or the acoustic device control signal transmitted from the analysis device 130 to the terminal device 110 through a wireless or wired.

In one embodiment, when the data protocol between the terminal device 110 and the analysis device 130 is different, the network device 120 can communicate voice information of the at least one user with the analysis device 130. The format may be converted into a format and transmitted to the analysis apparatus 130, or the lighting apparatus control signal or the acoustic apparatus control signal may be converted into a format that can communicate with the terminal apparatus 110 and then transmitted to the terminal apparatus 110.

Next, the analysis device 130 obtains an emotional state value from at least one user's voice signal transmitted from the terminal device 110 and determines an illumination value according to the obtained emotional state value. In addition, the analysis device 130 generates a luminaire control signal for driving the luminaire according to the determined illumination value and transmits it to the terminal device 110 through the network device 120.

As shown in FIG. 1, the analysis apparatus 130 includes a voice analyzer 300, a controller 310, and a database 320.

First, the voice analyzer 300 classifies voice information of at least one user for each user, analyzes the classified voice information for each user, and determines an emotional state value of each user, and determines the emotion of each determined user. The state value is used to calculate one final emotional state value.

The voice analyzer 300 will be described in more detail with reference to FIG. 3.

3 is a block diagram schematically illustrating a configuration of a voice analyzer according to an exemplary embodiment of the present invention. As shown in FIG. 3, the speech analyzer 300 includes a basic frequency obtaining unit 302, a speech information classifying unit 304, an emotional state value determining unit 306, and a final emotional state value calculating unit 308. It includes.

The basic frequency obtaining unit 302 receives voice information of at least one user from the network device 120 and obtains a basic frequency of each voice information from the received voice information of the at least one user. Here, the fundamental frequency means a unit frequency when the voice information is expressed in Fourier series.

In one embodiment, the fundamental frequency acquisition unit 302, the basic frequency of each of the speech autocorrelation function (Autocorrelation Function) (Average Magnitude Difference Function (AMDF), Zero Crossing Rate (ZCR), and cepstrum Can be obtained using one.

Next, the voice information classifier 304 obtains voice information for each user by classifying voice information of at least one user for each user according to the basic frequency of each voice acquired by the basic frequency acquirer 302.

The emotional state value determiner 306 obtains an emotional state value matching the fundamental frequency of each user's voice information from the database 320. In one embodiment, the emotion state value matched with the fundamental frequency of each voice information in the database 320 is information on the activity state of the brain obtained using a Function Magnetic Resonance Imaging (FMRI) technique. May be a numerical value for each emotional state.

In one embodiment, the emotional state value of each user may have a value between 0 and 200. In this case, the closer the emotional state value is to 0, the closer the emotion state is to the extreme anger state, and the closer the emotional state value to 200, the closer the emotional state is to the extreme bliss state.

Next, the final emotional state value calculating unit 308 calculates the final emotional state value using at least one of the emotional state values of each user determined by the emotional state value determining unit 306.

In an embodiment, the final emotional state value calculator 308 may determine the smallest emotional state value among the emotional state values of each user as the final emotional state value.

In another embodiment, the final emotional state value calculator 308 may determine the average of the emotional state values of each user as the final emotional state value.

Referring back to FIG. 1, the controller 310 determines an illumination value corresponding to the final emotional state value, and generates a luminaire control signal for driving the luminaire according to the determined illumination value.

In detail, the controller 310 searches the database 320 to determine an illumination value matched with the final emotional state value on the database 320 as an illumination value to be included in the luminaire control signal.

In another embodiment, the controller 310 searches the database 320 to determine the emotion group to which the final emotion state value belongs on the database 320, and the lighting value matched with the determined emotion group in the database. It can also be obtained from the determination of the illumination value.

Here, the emotion group is divided into the final emotional state values for each section, for example, the final emotional state value 0 ~ 40 represents the first emotional group in the extreme anger state, the final emotional state value 41 ~ 80 is anger state The second emotional group indicates a third emotional group with a final emotional state value of 81 to 120, and a final emotional state value of 121 to 160 indicates a fourth emotional group with a blissful state. 161 to 200 represent a fifth emotional group that is extremely blissful.

Next, the basic frequency of each voice information is recorded and matched with the emotional state value in the database 320, and the final emotional state value or each emotional group is recorded with the illumination value.

In addition, the information about each terminal device 110 is recorded in the database 320 by matching with identification information of each terminal device 110. In this case, the information on each terminal device 110 includes location information on which the terminal device 110 is installed.

In the above-described embodiment, the analysis device 130 calculates one final emotional state value using at least one of the emotional state values of each user, and determines an illumination value corresponding to the calculated one final emotional state value. It described as doing.

However, in the modified embodiment, the analysis device 130 does not separately calculate one final emotional state value, determines an emotion group to which each emotional state value belongs, and determines an illumination value corresponding to the determined emotion group of each user. Can be.

In detail, the analysis device 130 determines an emotion group to which each emotion state value belongs, and determines an illumination value matched with each emotion group on the database 320.

Here, the emotion group means that the emotion state values are divided by intervals.

Thereafter, the analysis device 130 transmits a luminaire control signal for driving the luminaires to the terminal device 110 according to the illumination value corresponding to each emotion group.

For the implementation of this embodiment, the database 320 records each emotion group in accordance with a range of emotion state values belonging to each emotion group and an illumination value corresponding to each emotion group, and the lighting fixtures are previously described for each emotion group. Each group is matched and driven according to the lighting value of each emotion group.

Therefore, since the lighting fixtures are matched in advance for each emotion group, for example, the lighting value corresponding to the first emotion group is used to control the lighting fixture matched with the first emotion group, and the illumination corresponding to the second emotion group. The value is used to control the luminaire that is matched with the second emotion group.

That is, according to this embodiment, the lighting values corresponding to each emotion group are displayed through the respective lighting fixtures matched with each emotion group, and as a result, the lights of the color corresponding to the lighting value corresponding to each emotion group are mutually different. It is displayed mixed.

Meanwhile, when voice information of a plurality of users is received from a plurality of terminal devices 110, the analysis device 130 may calculate the illumination value for each terminal device 110.

However, when voice information of a plurality of users is received from a plurality of terminal devices 110 having an installed distance less than or equal to a reference value, the analysis device 130 may calculate one illumination value commonly applied to all the terminal devices 110. Can be.

Specifically, the analysis device 130 calculates a final emotional state value for each terminal device 110, and then determines one illumination value matching the smallest final emotional state value among the calculated final state values, The luminaire control signal including the determined one lighting value is transmitted to the plurality of terminal devices 110.

In this case, the analysis device 130 may obtain the installation distance of the terminal device 110 from the database 320.

In another exemplary embodiment, when voice information of a plurality of users is received from the plurality of terminal devices 110, only final voice information regarding the voice information of the terminal device 110 that transmits the user voice information having a signal strength greater than or equal to a threshold is received. The state value and the lighting value may be calculated, and the luminaire control signal including the calculated lighting value may be transmitted to all of the plurality of terminal devices 110.

Meanwhile, in the above-described embodiment, the analysis apparatus 130 is described as generating only a luminaire control signal for controlling the luminaire through analysis of the voice information transmitted from the terminal device 110, but in the modified embodiment In this regard, the analysis device 130 may generate an acoustic device control signal for controlling the acoustic device through analysis of voice information transmitted from the terminal device 110.

In detail, the analyzing apparatus 130 determines an emotional state value of each user through analyzing voice information of at least one user, and determines a final emotional state value using at least one of the determined emotional state values. Thereafter, the analysis device 130 reads out the sound reproduction scenario recorded in the database 320 by matching the final emotional state value, and generates an acoustic instrument control signal including the read sound reproduction scenario.

In order to implement such an embodiment, a sound reproduction scenario may be matched and recorded for each final emotional state value in the database 320.

Hereinafter, a control method of the emotional lighting system according to the present invention.

4 is a flowchart showing a control method of the emotional lighting system according to an embodiment of the present invention.

As shown, first, at least one user voice information input through the voice input device is recognized (S400).

Thereafter, the recognized voice information of at least one user is classified for each user (S410). In an embodiment, the voice information of the at least one user may be classified for each user by using a fundamental frequency of each voice information.

Here, the fundamental frequency refers to a unit frequency when the voice information is expressed as a Fourier series, and the fundamental frequency may be obtained using any one of an autocorrelation function, AMDF, ZCR, and cepstrum.

Next, emotion state values matching with the fundamental frequency of each user's voice information are obtained from a database (S420). Here, the emotional state value matched with the fundamental frequency of the voice information in the database may be a value obtained by quantifying information on the activity state of the brain obtained by using the functional magnetic resonance imaging technique for each emotional state.

Thereafter, a final emotional state value is obtained using at least one of the obtained emotional state values (S430). In one embodiment, the final emotional state value may be the smallest value of the acquired emotional state values or an average value of the obtained emotional state values.

Next, after acquiring an illumination value matched with the final emotional state value from the database (S440), the luminaire is driven according to the obtained illumination value (S450).

5 is a flowchart showing a control method of the emotional lighting system according to another embodiment of the present invention.

Since the processes from S500 to S520 are the same as those of S400 to S420 described above, detailed descriptions thereof will be omitted.

After S520, an emotion group to which the emotion state value of each user belongs is determined in a database (S530). Here, each emotion group may be classified according to the emotion state value.

For example, an emotional state value of 0 to 40 represents a first emotional group in an extreme anger state, an emotional state value of 41 to 80 represents a second emotional group in anger state, and an emotional state value of 81 to 120 represents a calm state A third emotion group is represented, and an emotional state value of 121 to 160 represents a fourth emotional group in a blissful state, and an emotional state value of 161 to 200 represents a fifth emotional group in an extremely blissful state.

Therefore, since the lighting fixtures are matched in advance for each emotion group, for example, the lighting value corresponding to the first emotion group is used to control the lighting fixture matched with the first emotion group, and the illumination corresponding to the second emotion group. The value is used to control the luminaire that is matched with the second emotion group.

Next, after acquiring lighting values matched with each emotion group in the database (S540), the lighting apparatus matched with each emotion group is driven according to the illumination value for each emotion group (S540).

According to this embodiment, the lighting values corresponding to each emotion group are displayed through the respective lighting fixtures matched with each emotion group, so that the lights of the color corresponding to the lighting value corresponding to each emotion group are mixed with each other. Is displayed.

The control method of the emotional lighting system using the above-described voice analysis may be implemented in the form of program instructions that can be executed by various computer means and recorded in a computer-readable recording medium. In this case, the computer-readable recording medium may include program instructions, data files, data structures, and the like, alone or in combination. On the other hand, the program instructions recorded on the recording medium may be those specially designed and configured for the present invention or may be available to those skilled in the art of computer software.

On the other hand, those skilled in the art will understand that the present invention described above can be implemented in other specific forms without changing the technical spirit or essential features.

Therefore, it is to be understood that the embodiments described above are exemplary in all respects and not restrictive. The scope of the present invention is defined by the appended claims rather than the detailed description and all changes or modifications derived from the meaning and scope of the claims and their equivalents are to be construed as being included within the scope of the present invention do.

100: emotional lighting system 110: terminal device
120: network device 130: analysis device

Claims (22)

A voice information classification unit which receives voice information of a plurality of users and obtains voice information for each user by classifying voice information of the plurality of users by user using a basic frequency of each voice information;
An emotion state value determining unit which extracts an emotion state value matching the fundamental frequency of each user's voice information and determines the emotion state value of each user;
A final emotional state value calculator which selects the smallest value among the emotional state values of each user, or determines a value calculated by averaging the emotional state values of each user as a final emotional state value; And
Determine at least one of an illumination value and an acoustic reproduction scenario corresponding to the final emotional state value, and generate a control signal for driving at least one of the luminaire and the acoustic appliance according to at least one of the determined illumination value and the acoustic reproduction scenario. Including a control unit
The emotional state value is an emotional lighting system using a voice analysis, characterized in that the value of the brain activity information obtained by using the Functional Magnetic Resonance Imaging (FMRI) technique is a numerical value for each emotional state. delete The method of claim 1,
A basic frequency acquisition unit for acquiring a fundamental frequency of each user's voice information using any one of an autocorrelation function, an average magnitude difference function (AMDF), a zero crossing rate (ZCR), and a cepstrum; Emotional lighting system using a voice analysis, characterized in that. The method of claim 1,
The basic frequency is the emotional lighting system using the voice analysis, characterized in that the unit frequency converted from the voice information of each user to the Fourier series. delete delete The voice information of the plurality of users,
Emotional lighting system using the voice analysis, characterized in that the user voice information having a signal strength of more than a threshold. delete The method of claim 1,
The control unit, the emotional lighting system using the voice analysis, characterized in that for determining the illumination value corresponding to the final emotional state value as the illumination value. The method of claim 1,
The controller may be configured to determine an emotion group to which the final emotional state value belongs, and to determine the illumination value corresponding to the determined emotion group as the illumination value. The method of claim 1,
And a database in which the fundamental frequency, the final emotional state value, and the illumination value are matched and recorded with each other. The method of claim 1,
Emotional lighting system using a voice analysis further comprises a voice recognition unit for recognizing the voice information of each user and provided to the voice information classification unit. The method of claim 1,
Emotional lighting system using the voice analysis, characterized in that it further comprises a luminaire driving unit for driving the luminaire in accordance with the luminaire control signal generated by the control unit. A voice information classification unit that receives voice information of a plurality of users from an external device and obtains voice information for each user by classifying voice information of the plurality of users by user using a basic frequency of each voice information;
An emotion state value determining unit which extracts an emotion state value matching the fundamental frequency of each user's voice information and determines the emotion state value of each user; And
The emotion group of each user is determined using the emotion state value, an illumination value corresponding to the determined emotion group of each user is obtained, and a lighting device matched to each emotion group is assigned to the emotion group of each user. A luminaire controller for generating a luminaire control signal for driving in accordance with a corresponding illumination value,
The emotional state value is an emotional lighting system using a voice analysis, characterized in that the value of the brain activity information obtained by using the Functional Magnetic Resonance Imaging (FMRI) technique is a numerical value for each emotional state. delete delete 15. The method of claim 14,
The emotion group divides the emotion state value by section, and includes a first emotion group representing an extreme anger state, a second emotion group representing an anger state, a third emotion group representing a calm state, and a fourth representing a euphoria state And an emotional group, and a fifth emotional group representing an extreme bliss state. The voice information of a plurality of users is classified for each user, and the smallest value among the emotional state values matching the basic frequency of each user's voice information is determined as the final emotional state value or calculated by averaging the emotional state values of the respective users. An analysis device that determines a value as the final emotional state value and determines an illumination value corresponding to the final emotional state value; And
Recognizing and transmitting the voice information of the plurality of users to the analysis device, and comprises a terminal device for driving the luminaire according to the illumination value determined by the analysis device,
The emotional state value is an emotional lighting system using a voice analysis, characterized in that the value of the brain activity information obtained by using the Functional Magnetic Resonance Imaging (FMRI) technique is a numerical value for each emotional state. delete delete 19. The method of claim 18,
When the voice information of the plurality of users is received from at least one terminal device, the analysis device calculates the final emotional state value and the illumination value for each terminal device, the emotional lighting system using voice analysis. . 19. The method of claim 18,
When the voice information of the plurality of users is received from terminal devices having an installed distance less than or equal to a reference value, the analysis device calculates the final emotional state value for each terminal device, and the smallest final emotional state value among the calculated final state values. Emotional lighting system using the voice analysis, characterized in that for determining the one illumination value corresponding to the terminal provided.

Images