JP2019096435A - Apparatus control system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To reduce the possibility of erroneously controlling a device due to a sound leaking from the outside. A device control system 1 includes a microphone (sound input unit) 11, a voice recognition unit 12, a human detection unit 13, and a control unit 14. The microphone 11 outputs an electric signal based on the input sound. The voice recognition unit 12 performs voice recognition based on an electric signal and outputs recognition information corresponding to the recognized voice. The human detection unit 13 detects the presence or absence of a person in the space where the sound input unit 11 is located, and outputs the detection result as detection information. The control unit 14 controls the device 2 in the space based on the recognition information and the detection information. [Selection diagram] Fig. 1

Description

  The present disclosure relates generally to device control systems, and more particularly to device control systems that control devices using speech recognition technology.

  Conventionally, a control device for a luminaire using sound as a signal for remote control is known, and is disclosed, for example, in Patent Document 1. The control device of the lighting fixture described in Patent Document 1 is provided with voice control means having a microphone and a voice recognition unit in each of a plurality of lighting fixtures. The voice control means is configured to be able to register in advance identification voices of individual lighting fixtures and command voices of lighting / extinguishing and dimming. Then, the instruction voice issued with the identification voice is recognized by the voice recognition unit through the microphone, whereby the lighting apparatus corresponding to the identification voice is controlled.

Unexamined-Japanese-Patent No. 2006-286275

  However, in the control device of the lighting fixture of Patent Document 1, for example, when the sound leaks from the outside of the room (space) where the lighting fixture (device) exists to the room where the lighting fixture exists, the sound of the voice recognition unit leaks. In response to this, there was a possibility of erroneous control of the luminaire.

  This indication is made in view of the above-mentioned point, and aims at providing a device control system which can reduce the possibility of controlling a device by mistake by the sound leaked from the outside.

  A device control system according to an aspect of the present disclosure includes a sound input unit, a voice recognition unit, a human detection unit, and a control unit. The sound input unit outputs an electrical signal based on the input sound. The voice recognition unit performs voice recognition based on the electric signal, and outputs recognition information corresponding to the recognized voice. The human detection unit detects the presence or absence of a person in the space where the sound input unit is present, and outputs the detection result as detection information. The control unit controls devices in the space based on the recognition information and the detection information.

  The present disclosure has the advantage that it is possible to reduce the possibility of erroneous control of the device due to the sound leaking from the outside.

FIG. 1 is a block diagram showing a configuration of a device control system according to an embodiment of the present disclosure. FIG. 2 is a front view showing a light switch having the above-mentioned device control system. FIG. 3 is a flowchart showing the operation of the device control system of the same. FIGS. 4A and 4B are conceptual diagrams for explaining the operation of the device control system of the same. FIG. 5 is a conceptual diagram for explaining the operation of the above-mentioned device control system. FIG. 6 is a block diagram showing a configuration of a device control system according to a first modified example of an embodiment of the present disclosure. FIG. 7 is a conceptual diagram showing a device control system according to a second modified example of the embodiment of the present disclosure.

(1) Outline Hereinafter, the device control system 1 of this embodiment will be described with reference to FIG. The device control system 1 according to the present embodiment is a system that controls devices installed in a facility using voice recognition technology. The facility is, for example, a detached house, each dwelling unit of an apartment house, a store, a hospital, a school, an office, a factory, or a commercial facility. In the present embodiment, a case where the device control system 1 is used for a detached house will be described as an example. Further, in the present embodiment, the device 2 to be controlled by the device control system 1 is a lighting device. Hereinafter, the “device 2” is also referred to as the “lighting device 2”.

  The lighting apparatus 2 includes a plurality of LEDs (Light Emitting Diodes) as light sources. Further, two or more of the plurality of LEDs are configured by LEDs of different emission colors. That is, in the present embodiment, the lighting apparatus 2 has a light source capable of dimming and toning. The device control system 1 controls the lighting device 2 based on, for example, voice emitted by a person. Specifically, the device control system 1 performs lighting, extinguishing, dimming, toning, and the like of the lighting device 2 based on the voice emitted by a person. The “voice” mentioned here is, in addition to speech sounds emitted by people through vocal organs, general sounds emitted intentionally by humans, such as, for example, whistling, finger snapping sounds, and clapping sounds. It contains.

  The device control system 1 includes a microphone (sound input unit) 11, a voice recognition unit 12, a human detection unit 13, and a control unit 14. The microphone 11 outputs an electrical signal based on the input sound. The voice recognition unit 12 performs voice recognition based on the electrical signal output from the microphone 11 and outputs recognition information corresponding to the recognized voice. The "speech recognition" mentioned here includes not only the process of converting human speech into a character string but also natural language processing such as semantic analysis and context analysis. The human detection unit 13 detects the presence or absence of a person in a space R1 (see FIG. 4A) in which the microphone 11 is present, and outputs the detection result as detection information.

  The control unit 14 controls the device 2 in the space R1 based on the recognition information output from the voice recognition unit 12 and the detection information output from the human detection unit 13. That is, when there is a person in the space R1, the control unit 14 controls the device 2 in the space R1 according to the recognition information, and when there is no person in the space R1, the control unit 14 receives the recognition information but does not It is possible not to control a certain device 2.

  As described above, in the present embodiment, when there is no person in the space R1, even if the speech recognition unit 12 recognizes the speech emitted by the person, the control of the device 2 in the space R1 is not performed. It is possible to For this reason, in the present embodiment, there is an advantage that the possibility of erroneously controlling the device 2 by a sound leaking from the outside of the space R1 (for example, a voice emitted by a person outside the space R1) can be reduced. .

(2) Details Hereinafter, the configuration of the device control system 1 according to the present embodiment will be described in detail with reference to FIG. As described above, the device control system 1 according to the present embodiment includes the microphone 11, the voice recognition unit 12, the human detection unit 13, and the control unit 14. The device control system 1 further includes a storage unit 15 and an operation unit 16.

  The microphone (sound input unit) 11 outputs an electrical signal based on the input sound. Specifically, the microphone 11 collects a sound such as voice emitted by a person, converts it into an electric signal, and outputs the converted electric signal to the speech recognition unit 12 and the human detection unit 13 respectively. In the present embodiment, the microphone 11 has an analog-digital conversion unit (A / D conversion unit), converts an analog electric signal into a digital electric signal, and outputs it.

  The microphone 11 is built in the illumination switch 3 for switching on and off of the illumination device 2 (see FIG. 2). Similarly, the voice recognition unit 12, the human detection unit 13, the control unit 14, and the storage unit 15 are also incorporated in the illumination switch 3. The lighting switch 3 is installed on the wall of a space R1 (hereinafter, also referred to as "first room R1") in which the lighting device 2 is provided (see FIG. 4A). That is, the microphone 11, the human detection unit 13, and the lighting device 2 are all provided in the same space R1.

  The voice recognition unit 12 is configured of, for example, a microcomputer whose main configuration is a processor and a memory. That is, the speech recognition unit 12 is realized by a computer system having a processor and a memory. The computer system functions as the speech recognition unit 12 by the processor executing an appropriate program. The program may be pre-recorded in a memory, or may be provided through a telecommunication line such as the Internet or in a non-transitory recording medium such as a memory card.

  The human detection unit 13 and the control unit 14 are also configured by, for example, microcomputers, similarly to the voice recognition unit 12. That is, the human detection unit 13 and the control unit 14 are also realized by a computer system having a processor and a memory, like the voice recognition unit 12.

  The voice recognition unit 12 performs voice recognition based on the electrical signal output from the microphone 11 and outputs recognition information corresponding to the recognized voice. Specifically, the voice recognition unit 12 compares the electrical signal with a plurality of voice models stored in advance in the storage unit 15, and if there is a voice model that matches or is similar to the electrical signal, the microphone 11 It recognizes that the input sound contains an instruction voice. The “instruction sound” mentioned here is a sound representing an instruction to the lighting device 2. The instruction sound includes, for example, [ON (or ON)], [OFF (or OFF)], [Brighter], [Darker], [Light bulb color], or [Daylight White].

  When the voice recognition unit 12 recognizes the command voice, the voice recognition unit 12 outputs recognition information corresponding to the recognized command voice to the control unit 14. In the present embodiment, the recognition information is a command previously associated with the instruction voice. The “command” mentioned here means an instruction for instructing the computer system (here, the control unit 14) to execute a specific function. In the present embodiment, the plurality of commands are associated in advance with the plurality of instruction voices in one-to-one correspondence. For example, the command corresponding to the instruction sound of [lighting (or on)] is a lighting command, and the command corresponding to the instruction sound of [lighting off (or off)] is a light extinction command. Further, the command corresponding to the [more bright] instruction voice is a first dimming command, and the command corresponding to the [more dark] instruction voice is a second dimming command. Further, the command corresponding to the instruction sound of [bulb color] is a first color adjustment command, and the command corresponding to the instruction sound of [daylight white] is a second color adjustment command. The voice recognition unit 12 reads the command corresponding to the recognized instruction voice by referring to the information indicating the correspondence between the plurality of commands stored in the storage unit 15 and the plurality of instruction voices, and reads the read command. It outputs to the control unit 14.

  In the present embodiment, the voice recognition unit 12 performs voice recognition regardless of the detection information from the human detection unit 13. That is, the speech recognition unit 12 performs speech recognition even when there is no person in the space R1. For this reason, this embodiment has an advantage that it is possible to realize functions other than the control of the lighting device 2 by using the voice recognition technology even in a situation where no person is present in the space R1.

  For example, it is conceivable that the speech recognition unit 12 has a function of measuring the environmental sound of the space R1 by performing speech recognition when there is no person in the space R1. In this case, the voice recognition unit 12 can perform voice recognition after removing the environmental sound in the space R1 from the sound input to the microphone 11, and can improve the recognition accuracy of the voice emitted by a person. Further, for example, the voice recognition unit 12 performs voice recognition when there is no person in the space R1, thereby recognizing whether or not a third person has invaded the space R1 by recognizing the broken sound of the window glass or the like. It is conceivable to have a function to determine whether or not. Specifically, when the human detection unit 13 detects that there is a person in the space R1 after the speech recognition unit 12 recognizes the broken sound of the window glass, there is a possibility that a third party has invaded the space R1. Is high. In such a case, a burglarproof effect can be expected by ringing a buzzer connected to the device control system 1.

  The human detection unit 13 detects the presence or absence of a person in the space R1 (that is, the space where the microphone 11 is located), and outputs the detection result as detection information. In the present embodiment, the human detection unit 13 detects the presence or absence of a person in the space R1 based on a sound input to the microphone 11, particularly a sound other than voice used in voice recognition by the voice recognition unit 12. Specifically, based on the sound pressure level of the sound input to the microphone 11 and the information on the direct wave and the reflected wave of the sound input to the microphone 11, the human detection unit 13 generates a sound in the space R1. Identify if it has occurred. The “direct wave” referred to here is a sound wave input from the sound source directly (that is, without being reflected by the object) to the microphone 11. Further, the “reflected wave” referred to here is a sound wave that is input to the microphone 11 after being reflected by an object (for example, a wall, a door or the like) among sound waves emitted from a sound generation source. For example, when a reflected wave is input after the direct wave is input to the microphone 11, the human detection unit 13 identifies that the sound is generated in the space R1.

  The human detection unit 13 detects that a person is present in the space R1 when it is determined that a sound is generated in the space R1. On the other hand, the person detection unit 13 detects that there is no person in the space R1 except in the above case. For example, even if a sound is input to the microphone 11, the human detection unit 13 detects that there is no person in the space R1 if it is determined that the sound is not generated in the space R1.

  The human detection unit 13 outputs detection information to the control unit 14, for example, by outputting a binary signal having two signal levels, L level (Low level) and H level (High level), to the control unit 14. While detecting that a person is present in the space R1, the human detection unit 13 outputs a binary signal of H level to the control unit 14 to detect detection information indicating that a person is present in the space R1. It is output to the control unit 14. On the other hand, while detecting that there is no person in the space R1, the person detection unit 13 outputs a binary signal of L level to the control unit 14 to detect that there is no person in the space R1. The information is output to the control unit 14.

  The control unit 14 controls the lighting device 2 in the space R1. Specifically, the control unit 14 transmits the control signal for controlling the lighting device 2 to the lighting device 2 by wired communication or wireless communication with the lighting device 2 in the space R1. Control. Based on the recognition information from the voice recognition unit 12 and the detection information from the human detection unit 13, the control unit 14 of the lighting device 2 in the space R1 (that is, the space where the microphone 11 and the human detection unit 13 exist). Take control. Specifically, the control unit 14 controls the lighting apparatus 2 according to the recognition information when receiving the recognition information from the voice recognition unit 12 while receiving the detection information that there is a person in the space R1. .

  For example, when the lighting information is included in the recognition information, the control unit 14 performs lighting control to increase the light output of the lighting device 2 to a predetermined value in order to light the lighting device 2. When the turn-off command is included in the recognition information, the control unit 14 performs turn-off control to reduce the light output of the lighting device 2 in order to turn off the lighting device 2. When the first dimming command is included in the recognition information, the control unit 14 performs dimming control to increase the light output of the lighting device 2 by a predetermined amount. When the second dimming command is included in the recognition information, the control unit 14 executes the dimming control to reduce the light output of the lighting device 2 by a predetermined amount. When the first color adjustment command is included in the recognition information, the control unit 14 performs the color adjustment control so that the light emission color of the lighting device 2 becomes a light bulb color. When the second color adjustment command is included in the recognition information, the control unit 14 performs the color adjustment control so that the light emission color of the lighting device 2 becomes daylight white.

  On the other hand, while receiving the detection information that there is no person in the space R1, the control unit 14 does not control the lighting device 2 according to the recognition information even if it receives the recognition information from the voice recognition unit 12. For example, even when the control unit 14 receives the recognition information including the lighting command from the voice recognition unit 12, the lighting control of the lighting device 2 is not performed unless there is a person in the space R1.

  The storage unit 15 includes, for example, a rewritable nonvolatile memory such as an EEPROM (Electrically Erasable Programmable Read-Only Memory). The storage unit 15 stores information representing the correspondence between the plurality of voice models, the plurality of commands, and the plurality of instruction voices and the plurality of commands.

  The operation unit 16 receives a touch operation. Specifically, the operation unit 16 includes a touch sensor. The touch sensor is used to measure (detect) a motion (touch operation) of a person on the operation surface 150 (see FIG. 2) set on the front surface of the light switch 3. The touch sensor detects and outputs the position touched by a person on the operation surface 150.

  The control unit 14 controls the lighting device 2 according to the operation of the person on the operation surface 150 measured by the touch sensor. Specifically, the control unit 14 determines which of a plurality of different operations set in advance that the operation measured by the touch sensor corresponds to, and controls the lighting device 2 corresponding to the determined operation. Run. That is, the control unit 14 controls the lighting device 2 according to the touch operation received by the operation unit 16 regardless of the presence or absence of the recognition information.

(3) Operation Hereinafter, the operation of the device control system 1 of the present embodiment will be described with reference to FIG. First, when a sound is input to the microphone 11 (step S1), the microphone 11 outputs an electrical signal based on the input sound. Next, the voice recognition unit 12 performs voice recognition based on the electrical signal from the microphone 11 (step S2). As a result of the speech recognition, if the voice input to the microphone 11 includes the instruction voice (step S3: Yes), the voice recognition unit 12 outputs the recognition information including the command corresponding to the instruction voice to the control unit 14 Do. On the other hand, as a result of the speech recognition, if the sound input to the microphone 11 does not include the instruction speech (Step S3: No), the speech recognition unit 12 outputs nothing to the control unit 14.

  Next, the human detection unit 13 detects the presence or absence of a person in the space R1 (step S4). Although detection by the human detection unit 13 is performed after voice recognition by the voice recognition unit 12 in the example shown in FIG. 3, the present invention is not limited to this timing. It is preferable that the detection by the human detection unit 13 be performed regardless of the execution timing of the speech recognition by the speech recognition unit 12. When a person is present in the space R1 as a result of detection by the person detection unit 13 (step S5: Yes), the control unit 14 controls the device 2 according to the recognition information from the speech recognition unit 12 (step S6). On the other hand, as a result of detection by the human detection unit 13, when no person exists in the space R1 (step S5: No), the control unit 14 does not execute control of the device 2.

  Hereinafter, a specific example of the operation of the device control system 1 will be described with reference to FIGS. 4A, 4B, and 5. In the following, it is assumed that a space different from the space R1 separated by the wall and the door (hereinafter, also referred to as "second room R2") exists next to the space (first room) R1. Moreover, below, it is assumed that the lighting equipment 2 in the first room R1 is turned off.

  First, as shown to FIG. 4A, when person A1 exists in 1st room R1, the person detection part 13 detects that person A1 exists in 1st room R1 based on the sound resulting from the action of person A1. Do. Therefore, the control unit 14 receives, from the person detection unit 13, detection information indicating that the person A1 is present in the first room R1 while the person A1 is staying in the first room R1. Here, when the person A1 who is in the first room R1 issues a voice V1 including an instruction voice of [lighting (or on)], the voice recognition unit 12 recognizes the instruction voice, and recognizes that the lighting command is included. The information is output to the control unit 14. Since the control unit 14 receives the detection information that there is a person in the first room R1, the control unit 14 performs lighting control of the lighting device 2 according to the lighting command. Thereby, as shown to FIG. 4B, the illuminating device 2 lights. Thus, when person A1 exists in 1st room R1, control part 14 performs control of lighting equipment 2 according to the directions sound which person A1 emits.

  Next, as shown in FIG. 5, when there is no person in the first room R1, the person detection unit 13 detects that there is no person in the first room R1 because no sound is generated in the space R1. For this reason, the control unit 14 receives, from the person detection unit 13, detection information indicating that there is no person in the first room R1 while there is no person in the first room R1. Here, people A2 and A3 who are in the second room R2 are in conversation, and at least one of the voices V2 and V3 emitted by the people A2 and A3 is voice recognition as an instruction voice of [ON (or ON)]. It is assumed that the voice which can be recognized by the unit 12 is included. In this case, voices V2 and V3 leaked from the second room R2 to the first room R1 may be input to the microphone 11. In addition, the voice recognition unit 12 may recognize instruction voices included in the voices V2 and V3 and output recognition information including a lighting command to the control unit 14. However, since the control unit 14 receives the detection information that there is no person in the first room R1, even if it receives the recognition information from the voice recognition unit 12, it does not execute the control of the lighting device 2 according to the recognition information. . Therefore, the lighting apparatus 2 maintains the light-off state. As described above, when there is no person in the first room R1, the control unit 14 temporarily transmits an audio including an instruction voice to the first room R1 from another space such as the second room R2, Control of the lighting apparatus 2 is not performed.

  As described above, in the present embodiment, when there is no person in the space (first room) R1, even in the case where the voice recognition unit 12 recognizes the voice emitted by the person as the instruction voice, it is in the space R1. It is possible not to control the device 2. For this reason, in the present embodiment, there is an advantage that the possibility of erroneously controlling the device 2 by a sound leaking from the outside of the space R1 (for example, a voice emitted by a person outside the space R1) can be reduced. .

(4) Modifications The above-described embodiment is only one of various embodiments of the present disclosure. The above-mentioned embodiment can be variously changed according to design etc. if the object of the present disclosure can be achieved. Hereinafter, modifications of the above-described embodiment will be listed. The modifications described below can be applied in combination as appropriate.

(4.1) First Modified Example In the first modified example, as shown in FIG. 6, the device control system 1 is provided in a distributed manner in the lighting switch 3 and the server 4. It is different. In the present modification, the illumination switch 3 includes the microphone 11, the human detection unit 13, the control unit 14, and the operation unit 16 in the device control system 1. The lighting switch 3 further includes a first communication unit 17.

  The server 4 is provided at a location distant from a building where the light switch 3 is installed, for example, at a facility owned by a provider of the light switch 3 or a provider of a service using the light switch 3. The server 4 mainly includes a computer system (including a microcomputer) including, for example, a processor and a memory. That is, the computer system functions as the server 4 by executing an appropriate program on the processor. The server 4 includes a voice recognition unit 12 and a storage unit 15 in the device control system 1. The server 4 further includes a second communication unit 18.

  The first communication unit 17 of the light switch 3 and the second communication unit 18 of the server 4 are configured to be able to communicate in both directions via the network NT1 such as the Internet, for example. In the present modification, a wireless communication method using the network NT1 is applied as the communication method between the first communication unit 17 and the second communication unit 18.

  Hereinafter, among the operations of the device control system 1 of the present modification, an operation different from the above-described embodiment will be described. In the present modification, the microphone 11 collects a sound such as voice emitted by a person, converts it into an electric signal, and outputs the converted electric signal to the human detection unit 13 and the first communication unit 17, respectively. When the first communication unit 17 receives the electric signal from the microphone 11, the first communication unit 17 transmits the received electric signal to the second communication unit 18 via the network NT1. When the second communication unit 18 receives the electric signal from the first communication unit 17, the second communication unit 18 outputs the received electric signal to the voice recognition unit 12.

  The voice recognition unit 12 performs voice recognition based on the electric signal from the second communication unit 18, and outputs recognition information corresponding to the recognized voice to the second communication unit 18. When the second communication unit 18 receives the recognition information from the voice recognition unit 12, the second communication unit 18 transmits the received recognition information to the first communication unit 17 via the network NT1. When the first communication unit 17 receives the recognition information from the second communication unit 18, the first communication unit 17 outputs the received recognition information to the control unit 14. The control unit 14 controls the lighting device 2 based on the detection information from the human detection unit 13 and the recognition information from the second communication unit 18.

  As described above, in the present modification, the speech recognition process by the speech recognition unit 12 is executed not by the illumination switch 3 but by the server 4. In this modification, there is an advantage that it is possible to reduce the load of arithmetic processing in the illumination switch 3 by making the server 4 execute voice recognition processing with a relatively large processing load.

(4.2) Second Modified Example In the second modified example, as shown in FIG. 7, the presence / absence of a person is not detected based on the sound input to the microphone 11, but the presence / absence of a person is detected by the human sensor 5. Is different from the above-described embodiment in that That is, in the present modification, the human detection unit 13 is the human sensor 5.

  The human sensor 5 is provided, for example, on the ceiling material of the space (first room) R1. The human sensor 5 is, for example, a pyroelectric infrared sensor, and detects the presence or absence of a person in the detection area. The dotted line shown in FIG. 7 represents the detection area of the human sensor 5. That is, the human sensor 5 detects the presence or absence of a person in the detection area (here, the first room R1). The human sensor 5 transmits a detection signal including detection information to the control unit 14 of the lighting switch 3 by wired communication or wireless communication. The control unit 14 controls the lighting device 2 based on the recognition information from the voice recognition unit 12 and the detection information from the human sensor 5.

  Hereinafter, an example of the operation of the device control system 1 of the present modification will be described using FIG. In the example shown in FIG. 7, since no person exists in the first room R1, the human sensor 5 detects that no person exists in the first room R1. For this reason, the control unit 14 receives, from the human detection sensor 5, detection information indicating that there is no person in the first room R1 while there is no person in the first room R1. Here, people A2 and A3 who are in the second room R2 are in conversation, and at least one of the voices V2 and V3 emitted by the people A2 and A3 is voice recognition as an instruction voice of [ON (or ON)]. It is assumed that the voice which can be recognized by the unit 12 is included. In this case, since the control unit 14 receives the detection information that there is no person in the first room R1, even if the recognition information is received from the voice recognition unit 12, the control of the lighting apparatus 2 according to the recognition information is executed. do not do.

  In the present variation, the space R1 may not be a space surrounded by a shield such as a room. For example, in a space which is not partitioned by a shield, the human sensor 5 may be installed so that the specific area is the space R1 and the detection area. In this case, the control unit 14 can control the lighting device 2 according to the presence or absence of a person in a specific area.

(5) Other Modifications Hereinafter, other modifications will be listed. The modifications described below, including the modifications listed in “(4) Modifications”, can be appropriately combined and applied.

  The execution subject of the device control system 1 in the present disclosure includes a computer system. A computer system has a processor and memory as hardware. The processor executes the program stored in the memory of the computer system to implement the function as the execution subject of the device control system 1 in the present disclosure. The program may be pre-recorded in the memory of the computer system, but may be provided through a telecommunication line. Also, the program may be provided by being recorded in a non-transitory recording medium such as a memory card readable by a computer system, an optical disk, a hard disk drive and the like. A processor of a computer system is configured of one or more electronic circuits including a semiconductor integrated circuit (IC) or a large scale integrated circuit (LSI). The plurality of electronic circuits may be integrated into one chip or may be distributed to a plurality of chips. The plurality of chips may be integrated into one device or may be distributed to a plurality of devices.

  In the above embodiment, the speech recognition unit 12 may change the speech recognition mode according to the presence or absence of a person in the space R1. In other words, the voice recognition unit 12 may change the voice recognition mode in accordance with the detection information from the human detection unit 13. In this aspect, the voice recognition unit 12 receives the detection information from the human detection unit 13. For example, while receiving the detection information that there is no person in the space R1, the speech recognition unit 12 does not have to recognize the speech emitted by the person, so the speech recognition mode measures the environmental sound of the space R1. Change to mode. In this case, the voice recognition unit 12 may filter, for example, the frequency of voice emitted by a person. Further, while receiving the detection information that there is a person in the space R1, the speech recognition unit 12 changes the mode of the speech recognition to a mode in which the speech emitted by the person is recognized. In this case, the speech recognition unit 12 may filter the frequency of the environmental sound in the space R1, for example.

  In the above-mentioned embodiment, control part 14 may change a command which responds according to the person's existence in space R1. In other words, the control unit 14 may change the received recognition information in accordance with the detection information from the person detection unit 13. For example, when there is a person in the space R1, the control unit 14 recognizes recognition information including a lighting command, a lighting off command, a first dimming command, a second dimming command, a first toning command, or a second toning command. Accept On the other hand, when there is no person in the space R1, the control unit 14 receives only the recognition information including the turn-off command. In this aspect, for example, when a person goes out of the space R1 without turning off the lighting device 2, if a voice instructing the turning off of the lighting device 2 is emitted, the lighting device 2 is not turned back to the space R1. It is possible to turn off.

  In the embodiment described above, the control unit 14 may change the control content of the device 2 according to the presence or absence of a person in the space R1. In other words, the control unit 14 may change the control content of the device 2 in accordance with the detection information from the human detection unit 13. For example, assume that the lighting device 2 has a nightlight. When a person is present in the space R1, the control unit 14 performs control to turn off the light source except for the night light when receiving recognition information including the turn-off command. That is, in this case, the all-night light continues to be lit. On the other hand, when a person does not exist in the space R1, the control unit 14 performs control to turn off all the light sources including the night light, when receiving recognition information including the turn-off command. As described above, the control unit 14 changes the control content of the lighting device 2 according to the presence or absence of a person in the space R1 even when a command instructing the same control is received.

  In the above embodiment, the operation unit 16 is not an essential component of the device control system 1. That is, the control unit 14 does not control the device 2 according to the touch operation (manual operation) using the operation unit 16, but performs only control of the device 2 according to the recognition information from the voice recognition unit 12. It may be

  In the above-described embodiment, the voice recognition unit 12 performs voice recognition independently of the detection information from the human detection unit 13. However, the present invention is not limited to this. For example, the voice recognition unit 12 may be configured to stop the operation when there is no person in the space R1. In this aspect, the voice recognition unit 12 receives the detection information from the human detection unit 13, and stops the operation if it is detection information that there is no person in the space R1.

  In the above embodiment, a relay control unit may be provided instead of the control unit 14. The relay control unit controls a relay provided in a power supply path from the power supply (for example, a commercial power supply) to the lighting apparatus 2. In this case, the relay control unit controls the supply of power from the power supply to the lighting device 2 by controlling the on / off of the relay, and controls the state of the lighting device 2. In the device control system 1, the control unit 14 and the relay control unit may coexist. For example, the relay control unit turns on the relay when there is a person in the space R1, and turns off the relay when there is no person in the space R1. The control unit 14 controls the lighting device 2 according to the recognition information from the voice recognition unit 12 when a person is present in the space R1.

  In the above-described embodiment, the voice recognition unit 12, the human detection unit 13, and the control unit 14 are respectively configured by mutually different microcomputers (computer systems), but the present invention is not limited thereto. For example, the functions of the voice recognition unit 12, the human detection unit 13, and the control unit 14 may be realized by one or two microcomputers (computer systems).

  In the above-mentioned embodiment, although lighting installation 2 is provided with the light source in which both light control and color control are possible, it is not the meaning limited to this. For example, the lighting apparatus 2 may include a light source capable of only one of dimming and toning. In addition, the lighting device 2 may include a light source that can only be turned on and off.

  In the above-mentioned embodiment, although only one device 2 is provided in the space R1, a plurality of devices 2 may be provided. In this case, the control unit 14 may collectively control the plurality of devices 2 in accordance with the recognition information, or may control them individually. Moreover, in the above-mentioned embodiment, although only one illumination switch 3 is provided in space R1, the several illumination switch 3 may be provided.

  In the above-described embodiment, the functions of the device control system 1 may be integrated in one case, or may be distributed to a plurality of cases. Also, some functions of the device control system 1 may be realized by, for example, cloud (cloud computing).

  In the embodiment described above, the device 2 is not limited to the lighting device, and may be, for example, an air conditioner, a ventilation fan, an electric shutter, an air cleaner, a water heater, a television receiver, a washing machine, or a refrigerator.

(Summary)
As described above, the device control system (1) according to the first aspect includes the sound input unit (microphone) (11), the speech recognition unit (12), the human detection unit (13), and the control unit 14) and. The sound input unit (11) outputs an electrical signal based on the input sound. The voice recognition unit (12) performs voice recognition based on the electric signal, and outputs recognition information corresponding to the recognized voice. The human detection unit (13) detects the presence or absence of a person in a space (first room) (R1) in which the sound input unit (11) is present, and outputs the detection result as detection information. The control unit (14) controls the device (2) in the space (R1) based on the recognition information and the detection information.

  According to this aspect, there is an advantage that it is possible to reduce the possibility of erroneous control of the device (2) due to the sound leaking from the outside.

  In the device control system (1) according to the second aspect, in the first aspect, the human detection unit (13) detects the presence or absence of a human based on the sound.

  According to this aspect, it is not necessary to separately prepare a sensor for detecting the presence or absence of a person, such as a human sensor, in order to detect the presence or absence of a person based on the sound input to the sound input unit (11). It has the advantage of As a result, this aspect has the advantage that the cost can be reduced.

  In the device control system (1) according to the third aspect, in the second aspect, the human detection unit (13) detects the sound in the space (R1) based on the information of the direct wave and the reflected wave of the sound. Identify if it has occurred.

  According to this aspect, there is an advantage that it is easy to detect the presence or absence of a person with high accuracy based on the sound input to the sound input unit (11).

  In the device control system (1) according to the fourth aspect, in any of the first to third aspects, the control unit (14) receives detection information indicating that there is no person in the space (R1). , Do not control the device (2) according to the recognition information.

  According to this aspect, there is an advantage that it is possible to reduce the possibility of unnecessarily controlling the device (2) in a situation where there is no person in the space (R1).

  In the device control system (1) according to the fifth aspect, in any one of the first to fourth aspects, the voice recognition unit (12) performs voice recognition regardless of detection information.

  According to this aspect, there is an advantage that it is possible to realize functions other than the control of the device (2) by using the speech recognition technology even in a situation where no person is present in the space (R1).

  In the device control system (1) according to the sixth aspect, in any of the first to fifth aspects, the voice recognition unit (12) changes the mode of voice recognition in accordance with the detection information.

  According to this aspect, there is an advantage that appropriate speech recognition can be performed according to the presence or absence of a person in the space (R1).

  In the device control system (1) according to the seventh aspect, in any of the first to sixth aspects, the control unit (14) changes the recognition information to be received according to the detection information.

  According to this aspect, there is an advantage that control of the appropriate device (2) can be performed according to the presence or absence of a person in the space (R1).

  In the device control system (1) according to the eighth aspect, in any of the first to seventh aspects, the control unit (14) changes the control content of the device (2) according to the detection information.

  According to this aspect, there is an advantage that control of the appropriate device (2) can be performed according to the presence or absence of a person in the space (R1).

  The device control system (1) according to the ninth aspect further includes an operation unit (16) that receives a touch operation in any of the first to eighth aspects. The control unit (14) controls the device (2) according to the touch operation received by the operation unit (16).

  According to this aspect, there is an advantage that the device (2) can be controlled without the person in the space (R1) emitting a voice for controlling the device (2).

  In the device control system (1) according to the tenth aspect, in any of the first to ninth aspects, the device (2) is a lighting device (2).

  According to this aspect, there is an advantage that it is possible to reduce the possibility of erroneously controlling the lighting apparatus (2) due to the sound leaking from the outside.

  The configurations according to the second to tenth aspects are not essential to the device control system (1), and can be omitted as appropriate.

1 Device control system 11 Microphone (sound input unit)
12 voice recognition unit 13 person detection unit 14 control unit 16 operation unit 2 lighting device (device)

Claims (10)

A sound input unit that outputs an electrical signal based on the input sound;
A voice recognition unit that performs voice recognition based on the electrical signal and outputs recognition information corresponding to the recognized voice;
A human detection unit that detects the presence or absence of a person in a space where the sound input unit is present, and outputs the detection result as detection information;
A control unit configured to control an apparatus in the space based on the recognition information and the detection information. The device control system according to claim 1, wherein the person detection unit detects the presence or absence of the person based on the sound. The device control system according to claim 2, wherein the human detection unit identifies whether the sound is generated in the space based on information of the direct wave and the reflected wave of the sound. The device according to any one of claims 1 to 3, wherein the control unit does not control the device according to the recognition information while receiving the detection information indicating that the person is not present in the space. Control system. The device control system according to any one of claims 1 to 4, wherein the voice recognition unit performs the voice recognition regardless of the detection information. The device control system according to any one of claims 1 to 5, wherein the voice recognition unit changes a mode of the voice recognition according to the detection information. The device control system according to any one of claims 1 to 6, wherein the control unit changes the received recognition information according to the detection information. The device control system according to any one of claims 1 to 7, wherein the control unit changes control content of the device according to the detection information. It further comprises an operation unit that accepts touch operations,
The device control system according to any one of claims 1 to 8, wherein the control unit controls the device according to the touch operation received by the operation unit. The device control system according to any one of claims 1 to 9, wherein the device is a lighting device.

Images