JP6944663B2 - Machine learning device, output device, output device control system, output system, lighting device control system, wall and ceiling - Google Patents

Description

The present disclosure relates to machine learning devices, output devices, output device control systems, output systems, lighting device control systems, walls and ceilings.

Conventionally, a technique for producing a space by emitting light into the space has been proposed. For example, in JP2011-210594A, using an indirect lighting device installed on a wall surface called a peripheral unit, light from a light source that is concealed and cannot be directly seen is reflected by a reflective panel or ceiling. By indirectly injecting into the space, the space is created so that the height of the ceiling and the size of the wall surface are emphasized.

However, in the technique disclosed in JP2011-210594A, the actual situation is that sufficient proposals have not been made for emitting light so as to bring a human psychological state into a desirable state.

The present disclosure has been made in consideration of the above points, and is a machine learning device, an output device, an output device control system, an output system, and a lighting device control system that can make a state of an object such as a human into a desirable state. , Walls and ceilings are intended to be provided.

The machine learning device according to the present disclosure is
At least one physical quantity for the subject and at least one of the output devices during and after operation of an output device that produces an output that affects the state of the subject, including at least one of humans, animals, and plants. A state variable observation unit that observes state variables consisting of two operating conditions,
It includes a learning unit that learns the operating conditions by updating a function that determines the operating conditions based on the observed state variables.

In the machine learning device according to the present disclosure
The operating conditions include the amount of driving power of the output device, the brightness, illuminance and chromaticity of the light output from the output device, the temperature of the heat output from the output device, and the humidity of the air output from the output device. And include at least one of at least one absolute amount, amount of change, change gradient with time and change pattern of absolute amount of flow rate, odor, sound and vibration output from the output device.
The physical quantity is measured by the imaging data of the target imaged by the imaging device, the voice data of the target collected by the sound collecting device, the surface temperature data of the target measured by the temperature measuring device, and the electromagnetic wave measuring device. It may include at least one data of the operation data of the object based on the reflected wave of the electromagnetic wave from the object and medical data indicating the health condition of the object, or a physical quantity obtained from the at least one data. ..

In the machine learning device according to the present disclosure
The learning unit
A reward calculation unit that calculates a reward for the result of determining the operating conditions based on the observed state variables, and
It has a function update unit that updates the function based on the calculated reward, and
By repeating the update of the function, the operating condition in which the reward is most obtained may be learned.

In the machine learning device according to the present disclosure
The reward calculation unit
It has a reward condition setting unit that sets reward conditions for calculating the reward.
The reward may be calculated based on the set reward conditions.

In the machine learning device according to the present disclosure
The learning unit
A learning result storage unit that stores the function updated by the function update unit as a learning result may be further provided.

The output device according to the present disclosure is
A machine learning device that learns at least one operating condition of an output device that produces an output that affects the state of an object, including at least one of humans, animals, and plants.
A decision-making unit for determining the operating conditions and the optimum adjustment amount of the operating conditions based on the learning result of the machine learning device is provided.
The machine learning device
A state variable observation unit that observes a state variable composed of at least one physical quantity related to the target and at least one operating condition of the output device during operation and at least one of the output devices.
It has a learning unit that learns the operating conditions by updating a function that determines the operating conditions based on the observed state variables.
The decision-making unit determines the operating condition and the optimum adjustment amount based on the learning result of the learning unit and the current state variable.

In the output device according to the present disclosure
The learning unit may learn or iteratively learn the adjustment of the operating conditions while the output device is operating.

In the output device according to the present disclosure
An execution unit that operates the output device according to the determined operating conditions may be further provided.

The output device control system according to the present disclosure is
An output device that produces an output that affects the condition of an object, including at least one of humans, animals, and plants.
A physical quantity measuring unit that measures at least one physical quantity related to the target during and after the operation of the output device is provided.
The output device is
A machine learning device that learns at least one operating condition of the output device, and
It has a decision-making unit that determines the operating conditions and the optimum adjustment amount of the operating conditions based on the learning result of the machine learning device.
The machine learning device
A state variable observation unit that observes a state variable composed of the measured physical quantity and at least one operating condition of the output device during operation and at least one of the output devices.
It has a learning unit that learns the operating conditions by updating a function that determines the operating conditions based on the observed state variables.
The decision-making unit determines the operating condition and the optimum adjustment amount based on the learning result of the learning unit and the current state variable.

The output system according to the present disclosure is
Multiple output device control systems that control output devices that produce outputs that affect the state of the subject, including at least one of humans, animals, and plants.
A communication unit for connecting the plurality of output device control systems to each other is provided.
The output device control system is
With the output device
It has a physical quantity measuring unit that measures at least one physical quantity related to the target during and after the operation of the output device.
The output device is
A machine learning device that learns at least one operating condition of the output device, and
It has a decision-making unit that determines the operating conditions and the optimum adjustment amount of the operating conditions based on the learning result of the machine learning device.
The machine learning device
A state variable observation unit that observes a state variable composed of the measured physical quantity and at least one operating condition of the output device during operation and at least one of the output devices.
It has a learning unit that learns the operating conditions by updating a function that determines the operating conditions based on the observed state variables.
The decision-making unit determines the operating condition and the optimum adjustment amount based on the learning result of the learning unit and the current state variable.
The communication unit transmits / receives at least one of the physical quantity observed by the state variable observation unit and the learning result of the learning unit between the plurality of output device control systems.

In the output system according to the present disclosure
Further equipped with a host computer connected to the communication unit,
The computer
At least one of the physical quantity observed by the state variable observation unit and the learning result of the learning unit may be stored.

The output device according to the present disclosure is
An output device that produces output that affects the condition of an object, including at least one of humans, animals, and plants.
A state variable observation unit that observes a state variable composed of at least one physical quantity related to the target and at least one operating condition of the output device during operation and at least one of the output devices.
It is provided with a condition determination unit that determines the operating conditions based on the observed state variables.
The operating conditions include the amount of driving power of the output device, the brightness, illuminance and chromaticity of the light output from the output device, the temperature of the heat output from the output device, and the humidity of the air output from the output device. And include at least one of at least one absolute amount, amount of change, change gradient with time and change pattern of absolute amount of flow rate, odor, sound and vibration output from the output device.
The physical quantity is measured by the imaging data of the target imaged by the imaging device, the voice data of the target collected by the sound collecting device, the surface temperature data of the target measured by the temperature measuring device, and the electromagnetic wave measuring device. It includes at least one data of the operation data of the object based on the reflected wave of the electromagnetic wave from the object and medical data indicating the health condition of the object, or a physical quantity obtained from the at least one data.

The lighting device control system according to the present disclosure is
A luminaire control system that controls a luminaire that outputs light so as to affect the condition of an object, including at least one of humans, animals, and plants.
A state variable observation unit that observes a state variable composed of at least one physical quantity related to the target and at least one operating condition of the lighting device during operation and at least one after the lighting device.
It is provided with a condition determination unit that determines the operating conditions based on the observed state variables.
The operating conditions are the absolute amount of at least one of the driving power amount of the lighting device, the brightness, the illuminance and the chromaticity of the light output from the lighting device, the amount of change, the change gradient and the change of the absolute amount with time. Contains at least one of the patterns
The physical quantity is measured by the imaging data of the target imaged by the imaging device, the voice data of the target collected by the sound collecting device, the surface temperature data of the target measured by the temperature measuring device, and the electromagnetic wave measuring device. It includes at least one data of the operation data of the object based on the reflected wave of the electromagnetic wave from the object and medical data indicating the health condition of the object, or a physical quantity obtained from the at least one data.

In the lighting device control system according to the present disclosure,
The illuminating device includes an optical member having a light emitting surface.
The amount of light emitted from a certain position on the light emitting surface may be less than the amount of light emitted from another position on the light emitting surface located on one side of the light emitting surface in the direction along the light emitting surface. ..

In the lighting device control system according to the present disclosure,
The lighting device may include a decorative sheet including a light emitting region facing the light emitting surface and a non-light emitting region adjacent to the light emitting region.

In the lighting device control system according to the present disclosure,
The non-light emitting region may be adjacent to the light emitting region from the other side in the direction along the light emitting surface.

In the lighting device control system according to the present disclosure,
The optical member includes a light guide plate and includes a light guide plate.
A light source may be provided facing the light guide plate from one side in the direction along the light emitting surface.

The wall of this disclosure is
The above-mentioned lighting device control system is provided.

The ceiling according to this disclosure is
The above-mentioned lighting device control system is provided.

The fixtures according to this disclosure are
The above-mentioned lighting device control system is provided.

The moving body according to the present disclosure is
The above-mentioned lighting device control system is provided.

According to the present disclosure, the state of an object such as a human can be made into a desirable state.

FIG. 1 is a block diagram showing a machine learning device according to the present embodiment. FIG. 2 is a flowchart showing an operation example of the machine learning device according to the present embodiment. FIG. 3 is a block diagram showing a machine learning device according to the first modification of the present embodiment. FIG. 4 is a block diagram showing a machine learning device according to a second modification of the present embodiment. FIG. 5 is a block diagram showing an output device according to a third modification of the present embodiment. FIG. 6 is a block diagram showing a machine learning device according to a fourth modification of the present embodiment. FIG. 7 is a block diagram showing an output device according to a fifth modification of the present embodiment. FIG. 8 is a block diagram showing an output device control system according to a sixth modification of the present embodiment. FIG. 9 is a block diagram showing an output system according to a seventh modification of the present embodiment. FIG. 10 is a block diagram showing an output system according to an eighth modification of the present embodiment. FIG. 11 is a perspective view showing a lighting device control system according to a ninth modification of the present embodiment. FIG. 12 is a plan view showing a lighting device control system according to a ninth modification of the present embodiment. FIG. 13 is a cross-sectional view showing a lighting device control system according to a ninth modification of the present embodiment. FIG. 14 is an enlarged cross-sectional view showing a surface light source device included in the lighting device control system according to the ninth modification of the present embodiment. FIG. 15 is a block diagram showing a lighting device control system according to a ninth modification of the present embodiment. FIG. 16 is a flowchart showing an operation example of the lighting device control system according to the ninth modification of the present embodiment. FIG. 17 is an enlarged cross-sectional view showing a surface light source device included in the lighting device control system according to the tenth modification of the present embodiment. FIG. 18 is an enlarged cross-sectional view showing a surface light source device included in the lighting device control system according to the eleventh modification of the present embodiment. FIG. 19 is an exploded perspective view showing a surface light source device included in the lighting device control system according to the twelfth modification of the present embodiment. FIG. 20 is a cross-sectional view showing a lighting device included in the lighting device control system according to the thirteenth modification of the present embodiment. FIG. 21 is a cross-sectional view showing a lighting device included in the lighting device control system according to the 14th modification of the present embodiment. FIG. 22 is a cross-sectional view showing a lighting device included in the lighting device control system according to the fifteenth modification of the present embodiment. FIG. 23 is a cross-sectional view showing a lighting device included in the lighting device control system according to the sixteenth modification of the present embodiment. FIG. 24 is an exploded perspective view showing a surface light source device included in the lighting device control system according to the seventeenth modification of the present embodiment. FIG. 25 is an enlarged cross-sectional view showing a surface light source device included in the lighting device control system according to the eighteenth modification of the present embodiment. FIG. 26 is a perspective view showing a lighting device control system according to a nineteenth modification of the present embodiment. FIG. 27 is an enlarged cross-sectional view showing a surface light source device included in the lighting device control system according to the twentieth modification of the present embodiment. FIG. 28 is a perspective view showing an output device control system according to the 21st modification of the present embodiment. FIG. 29 is a perspective view showing an output device control system according to a 21st modification of the present embodiment, which is different from FIG. 28. FIG. 30 is a cross-sectional view showing a voice output device control system as an example of the output device control system. FIG. 31 is a cross-sectional view showing an fragrance control system as an example of an output device control system. FIG. 32 is a cross-sectional view showing an air conditioner control system as an example of an output device control system. FIG. 33 is a block diagram showing an output system according to the 22nd modification of the present embodiment.

Hereinafter, the machine learning device, the output device, the output device control system, the output system, and the lighting device control system according to the present embodiment will be described with reference to the drawings. In the drawings attached to the present specification, the scale, aspect ratio, etc. are appropriately changed from those of the actual product and exaggerated for the convenience of illustration and comprehension.

In addition, terms such as "parallel", "orthogonal", and "identical" that specify shapes, geometric conditions, and their degrees as used in the present specification are not bound by strict meanings. The interpretation shall include the range in which similar functions can be expected.

Moreover, in the present specification, the terms "sheet", "film", and "board" are not distinguished from each other based solely on the difference in designation. For example, "board" is a concept that includes members that can be called sheets or films.

Further, in the drawings referred to in the present embodiment and its modifications, the same parts or parts having the same functions are designated by the same reference numerals or similar reference numerals, and the repeated description thereof may be omitted.

FIG. 1 is a block diagram showing a machine learning device 100 according to the present embodiment. The machine learning device 100 according to the present embodiment is a device that learns at least one operating condition of an output device that outputs an output that affects the state of a target including at least one of humans, animals, and plants.

As shown in FIG. 1, the machine learning device 100 includes a state variable observation unit 101 and a learning unit 102.

The state variable observation unit 101 has at least one physical quantity and at least one physical quantity related to the object during operation and at least one after the operation of the output device that outputs an output that affects the state of the object including at least one of human, animal, and plant. Observe a state variable consisting of at least one operating condition of the output device.

The learning unit 102 learns the operating conditions by updating the function that determines the operating conditions based on the state variables observed by the state variable observing unit 101. The learning unit 102 may perform various machine learning such as supervised learning, unsupervised learning, semi-supervised learning, reinforcement learning, translation and multitasking learning. The function that determines the operating conditions may be, for example, an action value function.

The operating conditions are, for example, the amount of driving power of the output device, the brightness of the light output from the output device, the illuminance and chromaticity, the temperature of the heat output from the output device, the humidity and flow rate of the air output from the output device, and so on. It includes at least one of an absolute amount, a change amount, a change gradient with time, and an absolute amount change pattern of at least one of odor, sound, and vibration output from an output device. In addition to this, the operating conditions may include the flow rate of water vapor output from the output device, the atmospheric pressure adjusted as the output of the output device, and the like. Adjustment of water vapor output and atmospheric pressure may be performed, for example, as a measure against heat stroke.

Examples of the output device that outputs light include a lighting device. Examples of the output device that outputs heat and air include an air conditioner. As an output device that outputs an odor, for example, an fragrance device can be mentioned. Examples of the output device that outputs sound include an audio output device provided with a speaker. Examples of the output device that outputs vibration include a controller of a game machine and a massage chair. Further, as an output device that outputs at least one of light, sound, and vibration, a communication robot can be mentioned. Further, the output device may have a function of sucking sound, a function of sucking scent, a function of sucking carbon dioxide and outputting oxygen.

The physical quantity is, for example, the imaging data of the object imaged by the imaging device, the voice data of the object collected by the sound collecting device, the surface temperature data of the object measured by the temperature measuring device, and the object measured by the electromagnetic wave measuring device. It includes at least one of the motion data of the subject based on the reflected wave of the electromagnetic wave from the subject and medical data indicating the health condition of the subject, or a physical quantity obtained from at least one data. Medical data includes, but is not limited to, for example, brain waves, saliva, heartbeat, pulse, body temperature, pupil movement, respiratory volume, expiratory components, sweating volume and blood pressure.

The learning unit 102 has a reward calculation unit 103 and a function update unit 104.

The reward calculation unit 103 calculates a reward for the result of determining the operating conditions based on the state variables measured by the state variable observation unit 101.

The function update unit 104 updates the function based on the reward calculated by the reward calculation unit 103.

The learning unit 102 learns the operating conditions in which the most reward is obtained by repeating the updating of the function by the function updating unit 104.

The machine learning device 100 is composed of hardware such as a computer, for example. At least a part of the machine learning device 100 may be configured by software such as a program or data. All of the machine learning device 100 may be provided outside the output device, or at least a part thereof may be provided inside the output device. Further, the machine learning device 100 may be capable of coordinating a part of the constituent parts with the other constituent parts by communication through a network. The communication may be either wired or wireless, and various communications such as Bluetooth, Wifi, and infrared communications can be used. Further, the machine learning device 100 may have a part of the components on a device capable of communicating with other components via an external network, for example, a server or a database on the cloud.

Next, an operation example of the machine learning device 100 of FIG. 1 will be described with reference to FIG. FIG. 2 is a flowchart showing an operation example of the machine learning device 100 according to the present embodiment. The flowchart of FIG. 2 is repeated as needed.

As shown in FIG. 2, first, the learning unit 102 starts learning to determine the operating conditions (step S1). In the following example, the learning unit 102 shall perform reinforcement learning by Q-learning.

After the learning starts, at least one operating condition of the output device is selected based on the action value function which is an example of the function for determining the operating condition (step S2). The action value function is the latest action value function updated by the function update unit 104 of the learning unit 102. Further, the selection of the operating conditions may be performed by the machine learning device 100, or may be performed by a configuration other than the machine learning device 100 such as the decision-making unit 107 described with reference to FIG.

After the operating conditions are selected, the output device is operated under the selected operating conditions (step S3). The operation of the output device may be performed by the machine learning device 100, or may be performed by a configuration other than the machine learning device 100 such as the execution unit 110 described with reference to FIG.

After the output device is activated, the state variable observation unit 101 of the learning unit 102 acquires the state variable (step S4).

After the state variable is acquired, the reward calculation unit 103 of the learning unit 102 calculates the reward.

Specifically, first, the reward calculation unit 103 determines whether or not the state variable is smaller than the threshold value (step S5). The state variable is the difference between the target physical quantity and the observed physical quantity under the current operating conditions, and the threshold value may be the threshold value of the difference between the target physical quantity and the observed physical quantity, but is limited to these. Not done.

Then, when the state variable is smaller than the threshold value (step S5: Yes), the reward calculation unit 103 increases the reward (step S6).

On the other hand, when the state variable is not smaller than the threshold value (step S5: No), the reward calculation unit 103 reduces the reward (step S7).

After the reward is calculated, the function update unit 104 of the learning unit 102 updates the action value function (step S8).

ここで、ｓ_ｔ，ａ_ｔは、時刻ｔにおける環境と行動を表す。行動ａ_ｔにより、環境はｓ_ｔ＋１に変化し、その環境の変化によって、報酬ｒ_ｔ＋１が算出される。また、ｍａｘの付いた項は、環境ｓ_ｔ＋１の下で、その時に分かっている最もＱ値の高い行動ａを選んだ場合のＱ値にγを掛けたものになる。ここでγは０＜γ≦１の割引率であり、αは０＜α≦１の学習係数である。Here, the Q-learning carried out by the learning unit 102 is a method of learning the value Q (s, a) for selecting the action a, that is, the action value function under a certain environmental state s. Then, in Q-learning, the action a having the highest Q (s, a) is selected in a certain state s. In Q-learning, various actions a are taken under a certain state s by trial and error, and the correct Q (s, a) is learned using the reward at that time. The update formula of the action value function Q (s, a) is expressed by the following formula (1).

_Here, s _{t, a} t represents the environment and action at time t. By the action _{a t,} the environment is changed to _{s t + 1,} by a change in its environment, reward _{r t + 1} is calculated. Further, the term with max is obtained by multiplying the Q value when the action a having the highest Q value known at that time is selected under _{the environment st + 1.} Here, γ is a discount rate of 0 <γ ≦ 1, and α is a learning coefficient of 0 <α ≦ 1.

This update equation, the evaluation value _{Q (s t, a} t) of in action a in state s than, the evaluation value _Q of the next best of the action in the environmental state by a of _{(s t + 1, maxa t} + 1) if it is _{greater, Q (s t, a t} ) to increase the, smaller _{Conversely, Q (s t, a t} ) show that also small. That is, the value of one action in one state is brought closer to the value of the best action in the next state. In other words, the learning unit 102 updates the most suitable state for executing the output of the output device, that is, at least one optimum operating condition.

After updating the action value function in this way, the selection of operating conditions based on the action value function is repeated (step S2).

According to the present embodiment, the state variable observation unit 101 observes the state variables during and after the operation of the output device, and the learning unit 102 determines the operating conditions based on the observed state variables. You can learn to determine operating conditions by updating the function. As a result, the output device can be operated under the optimum operating conditions for the target based on the learning result, so that the target state can be set to a desirable state.

(First modification)
Next, a more specific aspect of the machine learning device 100 will be described with reference to FIG. FIG. 3 is a block diagram showing a machine learning device 100 according to a first modification of the present embodiment.

In the example of FIG. 3, the reward calculation unit 103 has a reward condition setting unit 105. The reward condition setting unit 105 sets the reward condition for calculating the reward.

The reward calculation unit 103 calculates the reward based on the reward conditions set by the reward condition setting unit 105.

The reward condition set by the reward condition setting unit 105 is, for example, a condition that the reward is increased or decreased according to the magnitude relationship between the state variable and its threshold value, as shown in step S5 of the flowchart of FIG. The reward condition setting unit 105 may change the threshold value of the state variable according to the type of the state variable. Further, the reward condition setting unit 105 may change the increase / decrease range of the reward according to the magnitude of the difference between the state variable and the threshold value.

According to the first modification, the reward can be calculated easily and appropriately based on the reward condition set by the reward condition setting unit 105.

(Second modification)
Next, a more specific aspect of the machine learning device 100 will be described with reference to FIG. FIG. 4 is a block diagram showing a machine learning device 100 according to a second modification of the present embodiment.

In the example of FIG. 4, the learning unit 102 further includes a learning result storage unit 106 in addition to the configuration of FIG. The learning result storage unit 106 stores the function updated by the function update unit 104 as a learning result.

According to the second modification, since the function updated by the function update unit 104 can be stored in the learning result storage unit 106, the selection of the operating conditions of the output device based on the updated function is output. This can be done even when the device is stopped.

(Third variant)
Next, a specific embodiment of the output device will be described with reference to FIG. FIG. 5 is a block diagram showing an output device 108 according to a third modification of the present embodiment.

In the example of FIG. 5, the output device 108 includes the machine learning device 100 shown in FIG. 4 and the decision-making unit 107.

The decision-making unit 107 determines the operating conditions and the optimum adjustment amount of the operating conditions based on the learning result of the machine learning device 100. More specifically, the decision-making unit 107 adjusts the operating conditions and the optimum adjustment based on the learning result of the learning unit 102 stored in the learning result storage unit 106 and the current state variable observed by the state variable observation unit 101. Determine the amount. Here, the optimum adjustment amount is an optimum adjustment amount from the current operating conditions for reaching the determined operating conditions.

The output device 108 operates according to operating conditions adjusted based on the optimum adjustment amount, and outputs light, heat, air, odor, sound, vibration, or the like.

The learning unit 102 learns or repeatedly learns the adjustment of the operating conditions by the decision-making unit 107 while the output device 108 is in operation.

The decision-making unit 107 is composed of hardware such as a computer, for example. At least a part of the decision-making unit 107 may be composed of software. A part of the decision-making unit 107 may be able to cooperate with other components by communication through a network. Further, the decision-making unit 107 may have a part of the components on a device capable of communicating with other components via an external network, for example, a server or a database on the cloud.

According to the third modification, the output device 108 can operate according to the optimum operating conditions determined by itself based on its own learning result without relying on an external machine learning device.

(Fourth modification)
Next, with reference to FIG. 6, a specific mode of the output device different from that of FIG. 5 will be described. FIG. 6 is a block diagram showing an output device 108 according to a fourth modification of the present embodiment.

In the example of FIG. 6, the output device 108 includes a state variable observation unit 101 and an operating condition determination unit 109.

The operating condition determination unit 109 determines the operating conditions of the output device 108 by a predetermined determination method based on the state variables observed by the state variable observation unit 101. For example, the operating condition determination unit 109 may determine the operating condition corresponding to the observed state variable by referring to the table in which the state variable and the operating condition are associated with each other.

The output device 108 operates according to the operating conditions determined by the operating condition determining unit 109, and outputs light, heat, air, odor, sound, vibration, or the like.

According to the fourth modification, the target state can be made into a desired state by a simple configuration in which the machine learning device 100 is omitted.

(Fifth variant)
Next, with reference to FIG. 7, a more specific mode of the output device than that of FIG. 5 will be described. FIG. 7 is a block diagram showing an output device 108 according to a fifth modification of the present embodiment.

In the example of FIG. 7, the output device 108 further includes an execution unit 110 in addition to the configuration of FIG.

The execution unit 110 operates the output device 108 according to the operating conditions determined by the decision-making unit 107. More specifically, the execution unit 110 adjusts the current operating conditions based on the optimum adjustment amount so as to be the operating conditions determined by the decision-making unit 107, and sets the output device 108 according to the adjusted operating conditions. It works.

The operating conditions adjusted by the execution unit 110 are observed as state variables by the state variable observation unit 101.

The execution unit 110 is composed of hardware such as a computer, for example. At least a part of the execution unit 110 may be configured by software. A part of the components of the execution unit 110 may be able to cooperate with other components by communication through a network. Further, the execution unit 110 may be located on a device in which a part of the components can communicate with other components via an external network, for example, a server or a database on the cloud.

(Sixth variant)
Next, an example of the output device control system will be described with reference to FIG. FIG. 8 is a block diagram showing an output device control system 112 according to a sixth modification of the present embodiment.

In the example of FIG. 8, the output device control system 112 includes a physical quantity measuring unit 111 in addition to the output device 108 shown in FIG. 7.

The physical quantity measuring unit 111 measures the physical quantity constituting the state variable, and outputs the measured physical quantity to the state variable observing unit 101.

The physical quantity measuring unit 111 includes, for example, an imaging device, a sound collecting device, a temperature measuring device, an electromagnetic wave measuring device, a medical data measuring device, and the like. The physical quantity measuring unit 111 may be in the form of a smartphone or a smart watch.

According to the sixth modification, the operating conditions of the output device 108 optimal for the target can be learned based on the measurement result of the physical quantity related to the target, so that the target can be in a desirable state. Further, by measuring the physical quantity by the physical quantity measuring unit 111 which is separate from the output device 108, the degree of freedom of the type of the physical quantity and the degree of freedom of the position of the physical quantity measuring unit 111 can be improved.

(7th variant)
Next, an example of an output system will be described with reference to FIG. FIG. 9 is a block diagram showing an output system 114 according to a seventh modification of the present embodiment.

The output system 114 includes an output device control system 112 shown in FIG. 8, another output device control system 112a, and a communication unit 113.

The communication unit 113 connects a plurality of output device control systems 112 and 112a to each other.

The communication unit 113 transmits / receives at least one of the physical quantity observed by the state variable observation unit 101 and the learning result of the learning unit 102 between the plurality of output device control systems 112 and 112a.

According to the seventh modification, the physical quantity or learning result from another output device control system 112a can be acquired and used for learning the operating conditions, so that the output device control system 112 owns the output device 108. It is possible to learn more optimal operating conditions even when the operation is not performed. Alternatively, even when one of the plurality of output device control systems does not have the learning function, it is possible to select the optimum operating conditions based on the learning results of the other output device control systems.

(8th variant)
Next, a more specific aspect of the output system 114 will be described with reference to FIG. FIG. 10 is a block diagram showing an output system 114 according to an eighth modification of the present embodiment.

In the example of FIG. 10, the output system 114 further includes a host computer 115 in addition to the configuration of FIG.

The host computer 115 is connected to the communication unit 113. The host computer 115 stores at least one of the physical quantity observed by the state variable observation unit 101 and the learning result of the learning unit 102.

According to the eighth modification, by storing the physical quantity and the learning result in the host computer 115, the plurality of output device control systems 112 and 112a access the host computer 115 at an arbitrary timing suitable for each of the other output device control systems 112 and 112a. You can acquire the physical quantity and learning result obtained from the output device control system of the above and use it for your own learning.

(9th variant)
Next, an example of the lighting device control system will be described with reference to FIGS. 11 to 16. FIG. 11 is a perspective view showing a lighting device control system 1 according to a ninth modification of the present embodiment. FIG. 12 is a plan view showing a lighting device control system 1 according to a ninth modification of the present embodiment.
FIG. 13 is a cross-sectional view showing a lighting device control system 1 according to a ninth modification of the present embodiment. FIG. 14 is an enlarged cross-sectional view showing a surface light source device 21 included in the lighting device control system 1 according to the ninth modification of the present embodiment. FIG. 15 is a block diagram showing a lighting device control system 1 according to a ninth modification of the present embodiment. FIG. 16 is a flowchart showing an operation example of the lighting device control system 1 according to the ninth modification of the present embodiment.

The lighting device control system 1 is a system that controls the light emitted into the space with the intention of effectively producing the atmosphere of the space so as to generate a desirable psychological state for the user of the space.

In the example shown in FIGS. 11 to 16, the lighting device control system 1 is provided in the room R surrounded by the ceiling CE, the side wall W, and the floor F, and illuminates and directs the space S in the room R. Can be used for The room R exemplified in FIGS. 11 and 12 is a rectangular room partitioned by four adjacent side walls W, a ceiling CE, and a floor F. A table T is installed in the center of the room R. Further, a doorway D is provided on one side wall W.
The lighting device control system 1 can be effectively applied to the production of a room other than a rectangle. In the illustrated example, the lighting device control system 1 can give rise to a desirable psychological state for the person H seated in the chair C, i.e. the user H in the room R.

The lighting device control system 1 is an example of an output device, and is a lighting device 20 that emits light L that creates an atmosphere of the space S in the space S of the room R, the physical quantity measuring unit 111 described above, and a machine learning device. This is an example of a decision-making unit and an execution unit, and includes a lighting device control unit 4 that controls the emission of light L by the lighting device 20. All of the illuminating device control units 4 may be provided inside the illuminating device 20 as a part of the illuminating device 20, or at least a part thereof may be provided outside the illuminating device 20.

The ceiling CE is provided with a base lighting device 3 that emits illumination light Lx into the space S.

The lighting device 20 is located on the side wall W and includes a surface light source device 21, a board 5, a decorative sheet 6, an auxiliary building material 7, and a fastener 9. The surface light source device 21 is concealed from the space S by the decorative sheet 6 so as not to be directly seen by the user H of the space S. However, the decorative sheet 6 is not an essential configuration for the present disclosure, and can be removed as needed.

(Surface light source device 21)
Hereinafter, the surface light source device 21 will be described in detail. The surface light source device 21 is provided on the side wall W and emits light L into the space S. In the example of FIG. 13, the surface light source device 21 is provided at a position on the upper end side of the side wall W extending toward the upper d11 in the vertical direction d1 perpendicular to the floor F.

The position of the surface light source device 21 does not enter the field of view when, for example, the user H of the room R seated at the seating position of the table T so as to face the side wall W turns his / her line of sight below the horizontal direction d2. , The position may be in the field of view when the line of sight is directed above the horizontal direction d2. By arranging the surface light source device 21 at such a position, the user H can concentrate when he / she is looking at the front for a meeting or when he / she is looking at his / her hand to see a document or a PC. At times, the space S can be effectively produced while ensuring the concealment of the surface light source device 21 so as not to interfere with the concentration. The effect of the light source device 21 can be enhanced.

However, the arrangement position of the surface light source device 21 is not limited to the example shown in FIG. For example, the surface light source device 21 may be provided at a position on the lower end side of the side wall W, or may be provided at a position on the center side of the side wall W in the vertical direction d1. Further, the surface light source device 21 may be provided on the ceiling CE. Further, when the surface light source device 21 is provided on the ceiling CE, it is preferable that the ceiling CE is a system ceiling from the viewpoint of ease of introduction. The system ceiling is a ceiling that integrally assembles the finishing plate of the ceiling and the equipment installed on the ceiling. In the conventional ceiling, a board is attached to the base and the equipment is set later, whereas in the system ceiling, the board and the equipment are assembled in advance on the runner or frame on the ceiling surface. It is a method of fitting and setting. Further, when the surface light source device 21 is provided on the wall, the wall may be replaced by a partition.

As shown in FIG. 13, the surface light source device 21 includes a light emitting surface 210a, and includes an optical member 210 that converts light emitted from a light emitting body 220, which is a light source, into planar light. The amount of light emitted from a certain position on the light emitting surface 210a is smaller than the amount of light emitted from another position on the light emitting surface 210a located above d11 in the vertical direction d1 along the light emitting surface 210a. The amount of emitted light from the light emitting surface 210a may decrease continuously from the upper d11 to the lower d12.

The amount of light emitted from a certain position on the light emitting surface 210a is smaller than the amount of light emitted from another position on the light emitting surface 210a located above the position d11, thereby effectively enhancing the atmosphere of the space S. Is possible. In particular, by reducing the amount of light emitted at the edge of the lower d12 in the vertical direction d1 of the light emitting surface 210a, the seam of light between the light emitting surface 210a and the outer region of the light emitting surface 210a can be made inconspicuous. .. This makes it possible to more effectively enhance the atmosphere of the space S and more reliably generate a desirable psychological state for the user H. In FIG. 11, the amount of emitted light from the lighting device 20 is shown by shading, and the region where the amount of emitted light is large is represented by “dense”.

To explain a more specific configuration of the surface light source device 21, the surface light source device 21 is covered with a decorative sheet 6 that forms a decorative surface that is the foremost surface of the lighting device 20. The decorative sheet 6 includes a light emitting region Z1 facing the light emitting surface 210a of the optical member 210 and a non-light emitting region Z2 adjacent to the light emitting region Z1. By separately illuminating the decorative sheet 6 with the surface light source device 21 separately from the base lighting device 3 whose main purpose is to improve the brightness of the space S, it is possible to impart a spaciousness to the finite space S. In particular, by limiting the light emitting region Z1 of the decorative sheet 6 to a limited range and further concealing the light emitting surface 210a of the optical member 210 with the decorative sheet 6, the seam of light on the decorative sheet 6, that is, the light emitting region Z1 and the non-light emitting region Z1 are not emitted. The seam with the region Z2 is less noticeable than the seam between the light emitting surface 210a and the outer region thereof when the light emitting surface 210a is exposed. With this device, the space S can be produced in a state where the presence of the light source is effectively diluted, thereby further effectively enhancing the atmosphere of the space S and more reliably using the space S. H can produce the desired psychological state.

The surface light source device 21 is formed in a plate shape as a whole, and a part or all of the surface light source device 21 constitutes the lighting device 20. As shown in FIG. 13, the lighting device 20 may function as an inner wall material of a room, that is, a building material panel in a state of being stacked on the side wall W. In such an example, all or part of the components of the lighting device 20 may be treated as an assembly kit for manufacturing the lighting device 20 and may be distributed or sold. Alternatively, the lighting device 20 alone may form the inner wall of the room.

Here, a specific example of the surface light source device 21 will be described. FIG. 14 is an enlarged cross-sectional view showing a surface light source device 21 included in the lighting device control system 1 according to the present embodiment. The surface light source device 21 shown in FIG. 14 is configured as an edge light type surface light source device 21. The surface light source device 21 includes a light emitting body 220 and an optical member 210. The optical member 210 includes a light diffusion sheet 212, a reflection sheet 213, and a light guide plate 211. As the surface light source device 21, for example, a surface light source device using a direct type LED, a surface light source device using an EL (Electro Luminescence) sheet, or the like may be used, or any of the above and an edge light type surface light source. It may be configured in combination with an apparatus.

The light emitter 220 emits light. The specific embodiment of the light emitter 220 is not particularly limited, and various members capable of selectively emitting light of at least two colors can be widely used. Specifically, for example, a cold cathode tube, a point-shaped full-color light emitting diode (LED), an incandescent light bulb, a laser oscillator, or the like can be used as the light emitting body 220. In the example shown in FIG. 13, the light emitting body 220 is held by the auxiliary building material 7. A plurality of light emitting bodies 220 are arranged at intervals along the vertical direction of the paper surface, that is, the horizontal direction of FIG. 13, which is the longitudinal direction of the auxiliary building material 7. When the auxiliary building material 7 is removable, a plurality of light emitting bodies 220 can be removed from the side wall W together with the auxiliary building material 7, and a part or all of the plurality of light emitting bodies 220 can be replaced.

It is known that the color of the light L emitted from the lighting device 20 affects the psychological state of human beings. For example, when the space S is illuminated with a young grass-colored illumination light or a magenta illumination light, it is said that the user H of the space S is energized. Similarly, when a mauve-colored illumination light or a gray-colored illumination light is used, it is said to have an effect of removing drowsiness from the user H. In addition, when skin-colored illumination light is used, it is said to have an effect of causing concentration on the user H. Further, when the lemon-colored illumination light or the skin-colored illumination light is used, it is said that there is an effect of imparting comfort to the user H and putting the user H in a relaxed state. The lighting device control system 1 aims to positively work on the psychological state of the user H by the illumination light L of the lighting device 20 and effectively influence the psychological state of the user H.

In the illustrated example, the light emitted from each light emitting body 220 of the surface light source device 21 is the illumination light L. Therefore, in order to cause the user H to have a desired psychological state, each light emitting body 220 can select the color of the light so that the light in the wavelength range corresponding to the desired psychological state can be emitted. As an example, each light emitting body 220 is a plurality of types of light emitting bodies 220 capable of emitting light in different wavelength ranges from each other. In this case, by adjusting the output of each light emitter 220, it becomes possible to illuminate with illumination light of various colors by additive color mixing. Typically, the surface light source device 21 illuminates by including a light emitting body capable of emitting red light, a light emitting body capable of emitting green light, and a light emitting body capable of emitting blue light. The color of the light L can be selected from the entire range of colors on the chromaticity diagram.

The light guide plate 211 is a plate-shaped member having a pair of main surfaces 211a and 211b and side surfaces located between the pair of main surfaces 211a and 211b. One main surface forms the light emitting surface 211a, and the other main surface forms the back surface 211b. The main surfaces 211a and 211b typically have a rectangular shape in a plan view. The main surfaces 211a and 211b have a pair of side edges extending along the vertical direction d1 and a pair of side edges extending along the horizontal direction d2 orthogonal to the vertical direction d1.

As shown in FIG. 14, the light guide plate 211 has an incoming light plane 211d located on the upper end side in the vertical direction d1. The light entry surface 211d extends in the horizontal direction d2 along the auxiliary building material 7. The light receiving surface 211d faces the light emitting body 220 held by the auxiliary building material 7. That is, the light emitting body 220 is provided facing the light guide plate 211 from the upper d11 side in the vertical direction d1 perpendicular to the floor F. The plurality of light emitters 220 are arranged at intervals along the horizontal direction d2, which is the longitudinal direction of the light entry surface 211d.

As shown in FIG. 14, the light emitted from the light emitting body 220 enters the light guide plate 211 and travels in the light guide plate 211. The main surface 211b of the light guide plate 211 is provided with a recess 211c that functions as an extraction element. The recess 211c changes the traveling direction of the light L1 and L2 traveling in the light guide plate 211. The light emitted from the light emitting body 220 enters the light guide plate 211 from the light receiving surface 211d and travels in the light guide plate 211 by being reflected, especially totally reflected. The light L1 and L2 traveling in the light guide plate 211 are incident on the pair of main surfaces 211a and 211b of the light guide plate 211 at an incident angle less than the total reflection critical angle by changing the traveling direction by the recess 211c, and particularly by scattering. Then, it becomes possible to emit light from the light guide plate 211.

Further, by controlling the distribution of the recess 211c in the vertical direction d1, as described above, the amount of light emitted from a certain position of the light emitting surface 210a can be adjusted to the amount of light emitted from a certain position of the light emitting surface 210a at another position of the light emitting surface 210a located above the position d11. It can be less than the amount of light emitted from the position.

The light whose traveling direction is changed in the recess 211c is emitted from the light guide plate 211 via any of the pair of main surfaces 211a and 211b. A light diffusion sheet 212 is provided so as to face the light emitting surface 211a of the light guide plate 211. The lights L1 and L2 emitted from the light emitting surface 211a of the light guide plate 211 are then incident on the light diffusion sheet 212. The light diffusing sheet 212 has a light diffusing function, and can arrange the luminance angle distribution caused by the transmitted light. The light diffusion sheet 212 forms a light emitting surface 210a of the optical member 210. The light diffused by the light diffusing sheet 212 is emitted from the optical member 210 and directed toward the decorative sheet 6. For the light diffusion sheet 212, various configurations capable of exhibiting the light diffusion function can be adopted. The diffusion characteristics of the light diffusion sheet 212 may be isotropic or anisotropic.

A reflective sheet 213 is provided facing the back surface 211b of the light guide plate 211. The reflective sheet 213 can reflect the light emitted from the back surface 211b and direct it toward the light guide plate 211 and the light diffusion sheet 212. By providing the reflective sheet 213, the amount of light emitted from the light emitting surface 210a of the optical member 210 can be increased. Thereby, the utilization efficiency of the light emitted from the light emitting body 220 can be improved. As the reflective sheet 213, various configurations capable of exhibiting the light reflection function can be adopted. The reflection characteristic of the reflection sheet 213 may be specular reflection or diffuse reflection. The diffuse reflection property of the reflective sheet 213 may be isotropic or anisotropic.

(Cosmetic sheet 6)
As shown in FIGS. 11 and 13, the decorative sheet 6 is exposed in the space S. Then, the decorative sheet 6 forms a surface on the most emitted light side of the lighting device 20. As the decorative sheet 6, for example, interior materials such as wallpaper, floors and ceilings of buildings can be used.

The decorative sheet 6 includes a light emitting region Z1 facing the light emitting surface 210a of the optical member 210 and a non-light emitting region Z2 deviated from the position facing the light emitting surface 210a. The non-light emitting region Z2 is adjacent to the light emitting region Z1. The decorative sheet 6 is irradiated with light from the back surface side by the optical member 210 in the light emitting region Z1. The decorative sheet 6 has visible light transmission at least in the light emitting region Z1. Therefore, at least a part of the light emitted from the light emitting surface 210a of the optical member 210 can pass through the light emitting region Z1 of the decorative sheet 6. Since the decorative sheet 6 is transmitted and illuminated in this way, a white wallpaper having a relatively high transmittance is preferably used as the decorative sheet 6. However, even a wallpaper having a relatively low transmittance, for example, a wood grain wallpaper, can be sufficiently effectively transmitted and illuminated to produce an effect of producing the atmosphere of the space S, and the pattern of the decorative sheet 6 is not particularly limited. .. The visible light transmittance in the light emitting region Z1 of the decorative sheet 6 is preferably 1.0% or more, and more preferably 5.0% or more. Further, from the viewpoint of eliminating the presence of the surface light source device 21, the visible light transmittance in the light emitting region Z1 of the decorative sheet 6 is preferably 20% or less. The visible light transmittance is measured by using an infrared visible ultraviolet spectrophotometer (UV3100PC manufactured by Shimadzu Corporation) in the wavelength range of 380 nm or more and 780 nm or less according to JIS A5759-2008, and is specified in the same standard. It is calculated by the calculation formula to be calculated.

As shown in FIG. 13, the light emitting region Z1 and the non-light emitting region Z2 are arranged in the vertical direction d1. The light emitting region Z1 is located on the upper d11 side in the vertical direction d1, and the non-light emitting region Z2 is adjacent to the light emitting region Z1 from the lower D12 side in the vertical direction d1.

From the viewpoint of expecting the effect of enhancing the atmosphere of the space by the surface light source device 21, it is preferable to make the boundary between the light emitting region Z1 and the non-light emitting region Z2 of the decorative sheet 6 inconspicuous. From this point, it is preferable that the decorative sheet 6 has the same configuration in the light emitting region Z1 and the non-light emitting region Z2.

In order to make the presence of the surface light source device 21 inconspicuous, an example in which the amount of light emitted from the light emitting surface 210a changes along the vertical direction d1 has been described. However, not limited to this example, the surface light source device 21 can be made inconspicuous by changing the amount of light emitted from the light emitting region Z1 of the decorative sheet 6 along the vertical direction d1. Therefore, at least one of the amount of light emitted from the light emitting surface 210a and the transmittance of the decorative sheet 6 may change along the vertical direction d1.

For example, the visible light transmittance of the decorative sheet 6 at a certain position is lower than the visible light transmittance of the decorative sheet 6 at another position located above d11 in the vertical direction d1 from the position. Therefore, the amount of light emitted from the decorative sheet 6 can be reduced at a position close to the non-light emitting region Z2 located below d12. According to the lighting device 20, the brightness in the light emitting region Z1 can be made darker in the region near the non-light emitting region Z2 than in the region separated from the non-light emitting region Z2. As a result, the presence of the surface light source device 21 can be effectively diminished.

Further, the decorative sheet 6 may be provided with a through hole. By providing the through hole, it is possible to efficiently output the illumination light. Also, when applied to output devices other than lighting devices such as audio output devices, air conditioners, and fragrances, sound, wind, odor, etc. can be efficiently output by providing through holes in the decorative sheet 6. Is possible.

(Board 5, auxiliary building material 7, fastener 9)
As shown in FIG. 13, the board 5 is a plate-shaped member. The board 5 is arranged so as to face at least the non-light emitting region Z2 of the decorative sheet 6. The decorative sheet 6 may be attached to the board 5. In this case, the board 5 can stably support the decorative sheet 6.

In the example shown in FIG. 13, the board 5 is arranged facing both the non-light emitting region Z2 and the light emitting region Z1. The board 5 is provided with a recess 51 at a position facing the light emitting region Z1. The optical member 210 is housed in the recess 51 of the board 5. According to the example of FIG. 3, the board 5 can stably support the optical member 210. The fastener 9 is provided on the board 5, and the optical member 210 is fixed on the board 5. Further, the board 5 and the optical member 210 may be fixed by a bonding layer containing an adhesive, an adhesive, or the like in addition to or instead of the fastener 9.

The light emitting surface 210a of the optical member 210 is preferably located on the same surface as the surface 5a of the board 5 facing the non-light emitting region Z2 of the decorative sheet 6. The decorative sheet 6 is laminated on the board 5 and the optical member 210 positioned in this way. In this case, it becomes difficult to form a step between the surface 5a of the board 5 and the light emitting surface 210a of the optical member 210, and the design of the decorative sheet 6 deteriorates due to the step being visually recognized through the decorative sheet 6. It can be effectively suppressed. Further, the presence of the surface light source device 21 can be effectively made inconspicuous when the lighting device 20 emits light, and the effect of enhancing the atmosphere of the space S by the lighting device 20 becomes more remarkable.

The board 5 is determined according to the use of the decorative sheet 6. As an example, the board 5 is an inorganic non-metal board made of a single board made of wood of a seed tree, a plywood, an laminated material, a parkicle board, a wooden board material such as a porcelain board, a cement-based material such as concrete or mortar, a gypsum board, a calcium silicate or the like. It can be a plate or a metal plate made of iron, aluminum, or the like. The board 5 preferably has flame resistance and fire resistance.

In FIG. 13, the decorative sheet 6 is shown with a gap between the board 5 and the optical member 210 along with the illustration of the fastener 9. However, the decorative sheet 6 may be attached to the board 5 and the optical member 210 without leaving a gap.

The auxiliary building material 7 is a member provided at the joint portion between the ceiling CE and the side wall W. The auxiliary building material 7 covers the joint between the ceiling CE and the side wall W, and improves the design of the lighting device 20. As the auxiliary building material 7, members called "surrounding edges" and "skirting boards" can be used. However, it is also possible to omit the auxiliary building material 7.

(Base lighting device 3)
Next, the base lighting device 3 will be described. As shown in FIGS. 11 and 13, the base illuminating device 3 is attached to the ceiling CE and emits the illuminating light Lx into the space S from above. The base lighting device 3 may be fixed to the ceiling CE or may be suspended from the ceiling CE. The base lighting device 3 assists in grasping the space S through human vision.
Therefore, as the base lighting device 3, a general fixture for indoor lighting can be used. The illumination light Lx emitted from the base illumination device 3 is not particularly limited, but natural illumination can be made possible by using a white system.

(Physical quantity measuring unit 111)
The physical quantity measuring unit 111 is located in the space S in order to measure the physical quantity related to the user H in the space S. The physical quantity measuring unit 111 may be installed at a predetermined position in the space S, may be temporarily carried into the space S to measure the physical quantity, or may be worn by the user H of the space S. Alternatively, it may be carried.

As described above, the physical quantity measuring unit 111 includes an imaging device, a sound collecting device, a temperature measuring device, an electromagnetic wave measuring device, a medical data measuring device, and the like. In the case of an imaging device, the physical quantity obtained from the imaging data of the user H or the imaging data can be acquired as a physical quantity. In the case of the sound collector, the physical quantity obtained from the voice data of the user H or the voice data can be acquired as the physical quantity. In the case of the temperature measuring device, the physical quantity obtained from the surface temperature data or the surface temperature data of the user H can be acquired as the physical quantity. In the case of the electromagnetic wave measuring device, it is possible to acquire the operation data of the user H based on the reflected wave of the electromagnetic wave from the user H or the physical quantity obtained from the operation data as the physical quantity. In the case of a medical data measuring instrument, the medical data of the user H can be acquired as a physical quantity.

(Lighting device control unit 4)
The lighting device control unit 4 operates as a machine learning device, a decision-making unit, and an execution unit based on the physical quantity measured by the physical quantity measurement unit 111.

Specifically, the lighting device control unit 4 is a state variable composed of at least one physical quantity related to the user H and at least one operating condition of the lighting device 20 during and after the operation of the lighting device 20. To observe. The physical quantity is measured by the physical quantity measuring unit 111 as described above. For example, the image data of the user H imaged by the imaging device and the voice of the user H collected by the sound collecting device. The data, the surface temperature data of the user H measured by the temperature measuring device, the operation data of the user H based on the reflected wave of the electromagnetic wave from the user H measured by the electromagnetic wave measuring device, and the health condition of the user H. It includes at least one of the indicated medical data, or a physical quantity obtained from the at least one data.

Further, the lighting device control unit 4 learns the operating conditions by updating the function that determines the operating conditions based on the observed state variables. The operating conditions are the amount of driving power of the lighting device 20, the brightness of the light output from the lighting device 20, the absolute amount of at least one of the illuminance and the chromaticity, the amount of change, the change gradient with time, and the change pattern of the absolute amount. Includes at least one of them.

In learning, the lighting device control unit 4 calculates a reward for the result of determining the operating conditions based on the observed state variables. Further, the lighting device control unit 4 updates the function based on the calculated reward. Then, the lighting device control unit 4 learns the operating conditions in which the most reward is obtained by repeating the update of the function.

In calculating the reward, the lighting device control unit 4 sets the reward condition for calculating the reward. Then, the lighting device control unit 4 calculates the reward based on the set reward condition.

Further, the lighting device control unit 4 stores the updated function as a learning result.

Further, the lighting device control unit 4 determines the operating conditions and the optimum adjustment amount of the operating conditions based on the stored learning result. Specifically, the lighting device control unit 4 determines the operating conditions and the optimum adjustment amount based on the learning result and the current state variable. The lighting device control unit 4 may learn or repeatedly learn the adjustment of operating conditions while the lighting device 20 is in operation.

Further, the lighting device control unit 4 controls the electric power supplied to the light emitting body 220 of the surface light source device 21 from a power source (not shown) according to the determined operating conditions, and as shown in FIG. 15, according to the operating conditions. The lighting device 20 is operated.

The lighting device control unit 4 is composed of hardware such as a computer, for example. At least a part of the lighting device control unit 4 may be configured by software. Further, the lighting device control unit 4 may be able to cooperate with some of the constituent units by communication with other constituent units via a network. Further, the lighting device control unit 4 may have a part of the components on a device capable of communicating with other components via an external network, for example, a server or a database on the cloud.

Next, an operation example of the lighting device control system 1 will be described with reference to FIG. FIG. 16 is a flowchart showing an operation example of the lighting device control system 1 according to the present embodiment.
The flowchart of FIG. 16 is repeated as needed.

As shown in FIG. 16, first, the lighting device control unit 4 starts learning to determine the operating conditions (step S1). The lighting device control unit 4 shall perform reinforcement learning by Q-learning.

After starting the learning, the lighting device control unit 4 selects at least one operating condition of the lighting device 20 based on the action value function (step S2). The action value function is the latest action value function updated by the lighting device control unit 4.

After selecting the operating conditions, the lighting device control unit 4 operates the lighting device 20 under the selected operating conditions (step S3).

After operating the lighting device 20, the lighting device control unit 4 acquires a state variable composed of the current operating conditions and the physical quantity measured by the physical quantity measuring unit 111 (step S4).

After acquiring the state variable, the lighting device control unit 4 calculates the reward.

Specifically, first, the lighting device control unit 4 determines whether or not the state variable is smaller than the threshold value (step S5).

Then, when the state variable is smaller than the threshold value (step S5: Yes), the lighting device control unit 4 increases the reward (step S6).

On the other hand, when the state variable is not smaller than the threshold value (step S5: No), the lighting device control unit 4 reduces the reward (step S7).

As an example, in order to generate vitality as a desirable psychological state for the user H of the space S, a young grass-colored light L is emitted from the light emitting device 20 under the operating conditions selected based on the behavioral value function. Suppose you are. The operating condition may be, for example, the amount of driving power for each light emitting body 220 of each color of the light emitting device 20 for emitting the young grass-colored light L. The state variable is the difference between the target body temperature of the user H under the current operating conditions and the observed body temperature obtained from the imaging data measured by the physical quantity measuring unit 111, and the threshold is the target body temperature and the observation. It is assumed that it is the threshold value of the difference from the body temperature. In this case, if the difference between the target body temperature and the observed body temperature is smaller than the threshold value, it is judged that the user H is energized by the young grass-colored light L, and the reward for the determination result of the current operating conditions is increased. Let me. On the other hand, when the difference between the target body temperature and the observed body temperature is larger than the threshold value, it is determined that the user H is not lively due to the young grass-colored light L, and the reward for the determination result of the current operating conditions is reduced. Of course, the reward may be calculated based on a physical quantity other than body temperature, such as the amount of spoken voice of user H.

After calculating the reward, the lighting device control unit 4 updates the action value function (step S8).

After updating the action value function, the selection of operating conditions based on the action value function is repeated (step S2).

According to the ninth modification, the lighting device control unit 4 observes the state variables during and after the operation of the lighting device 20, and determines the operating conditions based on the observed state variables. By updating, you can learn to determine operating conditions. As a result, the lighting device 20 can be operated under the optimum operating conditions for the user H in the space S based on the learning result, so that the user H can generate a desirable psychological state.

(10th variant)
In the example of FIG. 14, the recess 211c is illustrated as the extraction element of the light guide plate 211. As another example, as shown in FIG. 17, the extraction element can be a light scattering layer 215 laminated on the light guide plate 211. The light scattering layer 215 has a support layer 215a that functions as a binder, and a light scattering element 215b dispersed in the support layer 215a. The support layer 215a can be formed of a resin having visible light transmission. The light scattering element 215b has a function of changing the traveling direction of light traveling in the light scattering layer 215 by reflection, refraction, diffraction, or the like. The light scattering element 215b may have a refractive index different from that of the support layer 215a, or may be formed of a material having light reflectivity such as metal. Specific examples of the light scattering element 215b include a metal compound, a porous substance containing a gas, resin beads holding the metal compound in the surroundings, white fine particles, air bubbles, and particles having a refractive index different from that of the surroundings. In the example of FIG. 17, the lights L1 and L2 traveling in the light guide plate 211 can change the traveling direction by colliding with the light scattering element 215b in the light scattering layer 215, and then can be emitted from the light guide plate 211. It becomes.

The refractive index of the support layer 215a of the light scattering layer 215 is preferably equal to or higher than the refractive index of the light guide plate 211. When the refractive index of the support layer 215a of the light scattering layer 215 is lower than the refractive index of the light guide plate 211, the light L3 traveling in the light guide plate 211 is totally reflected at the interface between the light guide plate 211 and the light scattering layer 215. It may not be possible to enter the light scattering layer 215. Such light L3 travels through the light guide plate 211 to the opposite surface 211e after being incident on the light guide plate 211 from the light entry surface 211d. The presence of such light reduces the energy efficiency of the light emitter 220. By setting the refractive index of the support layer 215a to be equal to or higher than the refractive index of the light guide plate 211, total reflection at the interface between the light guide plate 211 and the light scattering layer 215 is effectively prevented, and the light scattering layer 215 serves as an extraction element. It can work more effectively.

(11th variant)
As yet another example, as shown in FIG. 18, the light scattering element 215b functioning as an extraction element may be dispersed in the light guide plate main body 211. In the light guide plate 211 shown in FIG. 18, the light L traveling in the light guide plate 211 is scattered by colliding with the light scattering element 215b and can be emitted from the light guide plate 211. The light scattering element 215b can be configured in the same manner as the light scattering element 215b described above.

Further, the light guide plate 211 may include a plurality of types of extraction elements. In the example shown in FIG. 18, the light guide plate 211 contains a light scattering element 215b and further has a recess 211c.

Further, the light scattering ability caused by the recess 211c in each region of the light guide plate 211 is not constant and may be different. That is, the light scattering ability of the light guide plate 211 may be changed in each region along the plate surface. In other words, the light scattering ability of the light guide plate 211 in a certain region may be different from the light scattering ability in another region deviated from the region along the plate surface. By changing the light scattering ability in each region along the panel surface of the light guide plate 211, it is possible to adjust the amount of light emitted from each region.

The light scattering ability is the strength of the ability of the light guide plate 211 to scatter the light passing through the inside thereof. As an example, the degree of light scattering ability can be evaluated using a haze value [%] measured in accordance with JIS-K7361-1, and a high haze value [%] means that the light scattering ability is high. It will be. Therefore, in the illustrated example, the transmission haze value transmitted through the light guide plate 211 in the normal direction to the plate surface is not constant in each region of the light guide plate 211, but has different values.
The haze value [%] can be measured by a method conforming to JIS K7136 using a haze meter (manufactured by Murakami Color Technology Laboratory, product number; HM-150).

(12th variant)
As another modification, the surface light source device 21 shown in FIG. 19 has a reflection sheet 213, a light guide plate 211, an adjustment sheet 59, and a light diffusion sheet 212. A light emitting body 220 is provided so as to face the light guide plate 211 from above d11 in the vertical direction d1. The adjusting sheet 59 includes a transparent base material 59a having visible light transmission and a light absorbing portion 59b provided on the base material 59a. The light absorbing unit 59b contains, for example, a pigment having visible light absorption, and has a visible light absorbing function. As an example, the light absorbing unit 59b contains carbon black or titanium black.

The adjustment sheet 59 is a layer for reducing the amount of light emitted from the decorative sheet 6 at a position close to the non-light emitting region Z2 located in the lower d12 in the vertical direction d1. The light absorption capacity of the adjustment sheet 59 in each region is not uniform and changes. For example, the light absorption capacity of the adjustment sheet 59 in a certain region is adjusted to the light absorption capacity of the adjustment sheet 59 in another region located above d11 in the vertical direction d1 from the region and close to the illuminant 220. By making it stronger than that, the amount of emitted light from the region located at the lower d12 in the vertical direction d1 and close to the non-light emitting region Z2 can be reduced. Further, the light absorption capacity of the adjustment sheet 59 in an arbitrarily selected region is set to be equal to or higher than the light absorption capacity of the adjustment sheet 59 in another region located above d11 in the vertical direction d1 from the region. It is possible to reduce the amount of emitted light as it approaches the non-light emitting region Z2 located below d12 in the vertical direction d1. According to these adjustment sheets 59, the brightness in the light emitting region Z1 can be made darker in the region near the non-light emitting region Z2 than in the region separated from the non-light emitting region Z2. As a result, the presence of the surface light source device 21 can be effectively diminished.

The visible light absorption capacity can be adjusted by adjusting the content density of the pigment, the arrangement density of the light absorption unit 59b, the thickness of the light absorption unit 59b, and the like.

(13th variant)
Further, as another modification, as shown in FIG. 20, the decorative sheet 6 may be arranged so as to face two or more surfaces of the surface light source device 21. In the example shown in FIG. 20, the optical member 210 has a pair of main surfaces 50b and side surfaces 50c located between the pair of main surfaces 50b. One main surface 50b includes a light emitting surface 210a. In the illustrated example, the decorative sheet 6 faces one main surface 50b including the light emitting surface 210a and the side surface 50c adjacent to the main surface 50b. More precisely, the decorative sheet 6 shown in FIG. 20 covers one main surface 50b including the light emitting surface 210a and four side surfaces 50c adjacent to the main surface 50b. In the example shown in FIG. 20, the lighting device 20 including the decorative sheet 6 and the surface light source device 21 is treated as one member and attached to the side wall W. Further, a panel material 70 including a board 5 and a decorative sheet 6 covering one main surface and a side surface of the board 5 is attached to the side wall W together with the lighting device 20. The lighting device 20 shown in FIG. 20 can be installed in regions of various sizes and shapes by combining with the panel material 70 whose shape and size are adjusted.

(14th variant)
As a modification related to FIG. 20, the lighting device 20 in the modification shown in FIG. 21 has a support frame 34 for holding the surface light source device 21 in addition to the decorative sheet 6 and the surface light source device 21. There is. The support frame 34 reinforces the surface light source device 21 and facilitates the installation of the surface light source device 21 on the outside such as the side wall W. The decorative sheet 6 may be directly bonded to the surface light source device 21, or may be bonded to the support frame 34 so as to face the surface light source device 21. In the example shown in FIG. 21, the decorative sheet 6 faces a region in its light emitting region Z1 that is not covered by the support frame 34 of the surface light source device 21. Further, the decorative sheet 6 faces the support frame 34 that covers the surface light source device 21 in the non-light emitting region Z2. Further, in the example shown in FIG. 21, the lighting device 20 has a support plate 35 supported by the support frame 34 together with the surface light source device 21. The support plate 35 is a member for imparting rigidity to the lighting device 20, and can be, for example, a metal plate material such as aluminum. The support plate 35 can be applied not only to the example shown in FIG. 21 but also to other examples, but it can be omitted from the example of FIG.

(15th variant)
Further, as another modification, as shown in FIG. 22, the non-light emitting region Z2 of the decorative sheet 6 may be extended to a region facing the side surface of the surface light source device 21 via the support frame 34.

(16th variant)
Further, in the above-mentioned specific example, the light guide plate 211 faces only the light emitting region Z1 and does not face the non-light emitting region Z2. However, the present invention is not limited to this example, and as shown in FIG. 23, the light guide plate 211 may face both the light emitting region Z1 and the non-light emitting region Z2 of the decorative sheet 6. As described above, the light traveling in the light guide plate 211 can be emitted from the light guide plate 211 by the extraction element. Therefore, no light is emitted from the region of the light guide plate 211 where the extraction element is not provided. That is, by providing the extraction element only in the region of the light guide plate 211 facing the light emitting region Z1, the region of the light guide plate 211 facing the decorative sheet 6 side is designated as the light emitting surface 210a. The region that functions and faces the non-light emitting region Z2 does not function as a light emitting surface 210a from which light is emitted. Therefore, in FIG. 23, the same action and effect as the above-mentioned specific example can be obtained.

(17th variant)
In FIG. 19, an example of the lighting device 20 provided with the adjusting sheet 59, that is, the adjusting layer between the light diffusing sheet 212 and the decorative sheet 6 has been described. On the other hand, as shown in FIG. 24, the adjustment sheet 59 may be provided on the reflection sheet 213 side of the light source. According to the example of FIG. 24, since it is possible to prevent the user from recognizing the existence of the adjustment sheet 59, it is possible to suppress the deterioration of the design due to the adjustment sheet 59.

(18th variant)
So far, an example of the lighting device 20 in which the light emitting surface 210a and the reflective sheet 213 are flat has been described. On the other hand, as shown in FIG. 25, the light emitting surface 210a and the reflective sheet 213 may be curved in the direction intersecting the vertical direction d1, that is, in the direction intersecting the light emitting surface 210a. By bending the light emitting surface 210a and the reflective sheet 213, the degree of freedom in the direction of the light emitted from the lighting device 20 can be increased, so that the atmosphere of the space can be produced more effectively.

(19th variant)
So far, an example in which the lighting device 20 is located on the side wall W has been described. On the other hand, in the example of FIG. 26, the lighting device 20 is located on the ceiling CE. The specific configuration of the surface light source device 21 concealed by the decorative sheet 6 has already been described. However, in the example of FIG. 26, since the light emitting surface 210a is parallel to the ceiling CE, the direction in which the amount of light emitted from the light emitting surface 210a changes is different from that of the example of FIG. Specifically, the amount of light emitted from a certain position on the light emitting surface 210a is the amount of light emitted from another position on the light emitting surface 210a located on one side in a direction parallel to the ceiling CE from that position. Less than.

Since wiring for lighting is often already installed in the ceiling CE, the lighting device 20 can be installed at low cost by utilizing the existing wiring. Further, in the case of the system ceiling, the lighting device 20 can be installed more simply.

(20th variant)
So far, an example in which the surface light source device 21 has the light guide plate 211 has been described. On the other hand, as shown in FIG. 27, the light guide plate 211 may be omitted in the surface light source device 21. The configuration of FIG. 27 corresponds to a configuration in which the light guide plate 211 is omitted from the configuration of FIG. The light emitting body 220, the light diffusing sheet 212, and the reflecting sheet 213 may be fixed to the auxiliary building material 7 shown in FIG. 13 or the like or the support frame 34 shown in FIG. 21 or the like.

In the example of FIG. 27, the surface light source device 21 is conspicuous by further providing the adjusting sheet 59 having the light absorbing portion 59b described with reference to FIG. 24 and reducing the reflectance of the reflecting sheet 213 toward the lower d12. Can be eliminated.

According to the twentieth modification, since the light guide plate 211 can be omitted, the cost can be reduced, and the surface light source device 21 can be made lighter and easier to handle.

(21st modification)
In FIG. 11, an example in which the lighting device 20 is installed on the side wall W of the room R as an example of the output device has been described. Further, in FIG. 26, an example in which the lighting device 20 is installed on the ceiling CE of the room R has been described.

On the other hand, as shown in FIG. 28, an output device 108 other than the lighting device 20 such as the air conditioner, the fragrance, and the sound output device described above may be installed on the side wall W of the room R.

Further, as shown in FIG. 29, an output device 108 other than the lighting device 20 such as the air conditioner, the fragrance, and the sound output device described above may be installed on the ceiling CE of the room R.

Further, the lighting device control system 1 of the present disclosure can be applied not only to a room in a building but also to the production of a space in a moving body such as a passenger cabin or a cabin. That is, the illuminator control system 1 may control the illuminator 20 that outputs light into the interior space of the moving body so as to affect the state of the object, including at least one of humans, animals and plants. ..

Further, the lighting device control system 1 of the present disclosure can also be applied to furniture including furniture such as a desk T and a chair C illustrated in FIG.

Next, an example in which the output device 108 other than the lighting device 20 shown in FIGS. 28 and 29 is an audio output device will be described in more detail. FIG. 30 is a cross-sectional view showing a voice output device control system 1A including a voice output device 108A. The voice output device control system 1A is a system that controls the sound output to the space S with the intention of causing a desirable psychological state for the user of the space S.

The audio output device control system 1A is an example of an output device, and is an audio output device 108A that outputs sound in the space S of the room R, the physical quantity measurement unit 111 described above, a machine learning device, a decision unit, and an execution unit. It is an example of the unit, and includes an audio output device control unit 4A that controls sound output by the audio output device 108A. Here, the specific mode of the sound output from the voice output device 108A is not particularly limited, and for example, a human voice, a voice music with a human voice, an instrumental music without a human voice, an environmental sound, or the like. There may be.

In the example of FIG. 30, the sound output device 108A is built in a hollow plate-shaped panel 22 arranged along the side wall W, and constitutes a building material integrated with the panel 22. The front wall portion 221 of the panel 22 is covered with the decorative sheet 6. In order to efficiently output sound toward the space S, a through hole 23 may be provided in the front wall portion 221 of the panel 22.

The voice output device control unit 4A observes a state variable composed of at least one physical quantity related to the user H and at least one operating condition of the voice output device 108A during and after the operation of the voice output device 108A. do. The physical quantity is measured by the physical quantity measuring unit 111. The audio output device control unit 4A learns the operating conditions by updating the function that determines the operating conditions based on the observed state variables. The operating conditions include at least one of a drive power amount of the audio output device 108A, an absolute amount of sound output from the audio output device 108A, a change amount, a change gradient with time, and an absolute amount change pattern.

In learning, the voice output device control unit 4A calculates a reward for the result of determining the operating conditions based on the observed state variables. Further, the voice output device control unit 4A updates the function based on the calculated reward. Then, the voice output device control unit 4A learns the operating conditions in which the most reward is obtained by repeating the update of the function.

In calculating the reward, the voice output device control unit 4A sets the reward condition for calculating the reward. Then, the voice output device control unit 4A calculates the reward based on the set reward condition.

Further, the voice output device control unit 4A stores the updated function as a learning result.

Further, the voice output device control unit 4A determines the operating condition and the optimum adjustment amount of the operating condition based on the stored learning result. Specifically, the voice output device control unit 4A determines the operating conditions and the optimum adjustment amount based on the learning result and the current state variable.

Further, the audio output device control unit 4A controls the drive power of the audio output device 108A supplied to the audio output device 108A from a power source (not shown) according to the determined operating conditions, so that the audio output device 4A conforms to the operating conditions. The operation of 108A is executed.

According to such a configuration, the voice output device 108A can be operated under the optimum operating conditions for the user H in the space S based on the learning result, so that the user H can generate a desirable psychological state. ..

Next, an example in which the output device 108 other than the lighting device 20 shown in FIGS. 28 and 29 is an fragrance device will be described in more detail. FIG. 31 is a cross-sectional view showing an fragrance control system 1B including the fragrance 108B. The fragrance control system 1B is a system that controls the odor output to the space S with the intention of causing a desirable psychological state for the user of the space S.

The fragrance control system 1B is an example of an output device, and includes an fragrance 108B that outputs an odor in the space S of the room R, the physical quantity measurement unit 111 described above, and a machine learning device, a decision-making unit, and an execution unit. As an example, the fragrance control unit 4B for controlling the output of odor by the fragrance 108B is provided.

In the example of FIG. 31, the fragrance 108B is built in a hollow plate-shaped panel 22 arranged along the side wall W, and constitutes a building material integrated with the panel 22. The front wall portion 221 of the panel 22 is covered with the decorative sheet 6. The specific embodiment of the fragrance 108B is not particularly limited, and for example, the aroma oil may be diffused by heating, ultrasonic vibration, or the like. A through hole 23 may be provided in the front wall portion 221 of the panel 22 in order to efficiently output the odor toward the space S.

The fragrance control unit 4B observes a state variable composed of at least one physical quantity related to the user H and at least one operating condition of the fragrance 108B during and after the operation of the fragrance 108B. The physical quantity is measured by the physical quantity measuring unit 111. The fragrance control unit 4B learns the operating conditions by updating the function that determines the operating conditions based on the observed state variables. The operating conditions include at least one of the driving power amount of the fragrance 108B, the absolute amount of odor output from the fragrance 108B, the amount of change, the change gradient with time, and the change pattern of the absolute amount.

In learning, the fragrance control unit 4B calculates a reward for the result of determining the operating conditions based on the observed state variables. In addition, the fragrance control unit 4B updates the function based on the calculated reward. Then, the fragrance control unit 4B learns the operating conditions in which the most reward is obtained by repeating the update of the function.

In calculating the reward, the fragrance control unit 4B sets the reward condition for calculating the reward. Then, the fragrance control unit 4B calculates the reward based on the set reward conditions.

Further, the fragrance control unit 4BA stores the updated function as a learning result.

Further, the fragrance control unit 4B determines the operating conditions and the optimum adjustment amount of the operating conditions based on the stored learning result. Specifically, the fragrance control unit 4B determines the operating conditions and the optimum adjustment amount based on the learning result and the current state variable.

Further, the fragrance control unit 4B controls the driving power of the fragrance 108B supplied to the fragrance 108B from a power source (not shown) according to the determined operating conditions, so that the fragrance 108B operates according to the operating conditions. Run.

According to such a configuration, the fragrance 108B can be operated under the optimum operating conditions for the user H in the space S based on the learning result, so that the user H can generate a desirable psychological state.

Next, an example in which the output device 108 other than the lighting device 20 shown in FIGS. 28 and 29 is an air conditioner will be described in more detail. FIG. 32 is a cross-sectional view showing an air conditioner control system 1C including the air conditioner 108C. The air conditioner control system 1C is a system that controls heat and air output to the space S with the intention of causing a desirable psychological state for the user of the space S.

The air conditioner control system 1C is an example of an output device, and is an air conditioner 108C that outputs heat and air in the space S of the room R, the physical quantity measurement unit 111 described above, a machine learning device, a decision unit, and an execution unit. It is an example of the unit, and includes an air conditioner control unit 4C that controls heat and air output by the air conditioner 108C.

In the example of FIG. 32, the air conditioner 108C is built in a hollow plate-shaped panel 22 arranged along the side wall W, and constitutes a building material integrated with the panel 22. The front wall portion 221 of the panel 22 is covered with the decorative sheet 6. A through hole 23 may be provided in the front wall portion 221 of the panel 22 in order to efficiently output heat and air toward the space S.

The air conditioner control unit 4C observes a state variable composed of at least one physical quantity related to the user H and at least one operating condition of the air conditioner 108C during and after the operation of the air conditioner 108C. The physical quantity is measured by the physical quantity measuring unit 111. The air conditioner control unit 4C learns the operating conditions by updating the function that determines the operating conditions based on the observed state variables. The operating conditions include at least one of the driving power amount of the air conditioner 108C, the heat output from the air conditioner 108C, the absolute amount of air, the amount of change, the change gradient with time, and the change pattern of the absolute amount.

In learning, the air conditioner control unit 4C calculates a reward for the result of determining the operating conditions based on the observed state variables. Further, the air conditioner control unit 4C updates the function based on the calculated reward. Then, the air conditioner control unit 4C learns the operating conditions in which the most reward is obtained by repeating the update of the function.

In calculating the reward, the air conditioner control unit 4C sets the reward condition for calculating the reward. Then, the air conditioner control unit 4C calculates the reward based on the set reward condition.

Further, the air conditioner control unit 4C stores the updated function as a learning result.

Further, the air conditioner control unit 4C determines the operating conditions and the optimum adjustment amount of the operating conditions based on the stored learning result. Specifically, the air conditioner control unit 4C determines the operating conditions and the optimum adjustment amount based on the learning result and the current state variable.

Further, the air conditioner control unit 4C controls the drive power of the air conditioner 108C supplied to the air conditioner 108C from a power source (not shown) according to the determined operating conditions, thereby operating the air conditioner 108C according to the operating conditions. Run.

According to such a configuration, the air conditioner 108C can be operated under the optimum operating conditions for the user H in the space S based on the learning result, so that the user H can generate a desirable psychological state.

(22nd variant)
In FIG. 9, an example in which the learning result by the learning unit 102 belonging to one output device control system 112 is used to select the optimum operating conditions in the other output device control system 112 has been described.

On the other hand, as shown in FIG. 33, the learning unit 102 exists independently for any of the plurality of output device control systems 112, and the state variables and learning with each output device control system 112. The results may be exchanged and exchanged. For example, the plurality of output control systems 112 are lighting device control systems provided in each of the plurality of conference rooms in the building, and the learning unit 102 is a server communicatively connected to each lighting device control system. You may. In this case, the server may be located inside or outside the building, and may be located not only in Japan but also in a foreign country. Similar to the example of FIG. 9, in the example of FIG. 33, the learning result by one learning unit 102 can be fed back to a plurality of output device control systems 112.

Although specific examples and modified examples for one embodiment have been described above, it is naturally possible to apply a plurality of examples in combination as appropriate.

Although some embodiments of the present disclosure have been described, these embodiments are presented as examples and are not intended to limit the scope of the disclosure. These embodiments can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the gist of the invention. These embodiments and variations thereof are included in the scope and the equivalent of the present disclosure described in the claims as well as included in the scope and gist of the present disclosure.

Claims (2)

A lighting device control system that controls a lighting device that outputs light into the space so as to generate a desirable psychological state for the user of the space.
A state variable observation unit that observes a state variable composed of at least one physical quantity related to a user of the space and at least one operating condition of the lighting device during operation and at least one after the lighting device.
A condition determining unit for determining the operating conditions that causes a desirable psychological state for the user of the space based on the observed state variables is provided.
The operating conditions are the absolute amount of at least one of the driving power amount of the lighting device, the brightness, the illuminance and the chromaticity of the light output from the lighting device, the amount of change, the change gradient and the change of the absolute amount with time. Contains at least one of the patterns
The physical quantity is the image data of the user of the space imaged by the imaging device, the voice data of the user of the space collected by the sound collecting device, and the surface of the user of the space measured by the temperature measuring device. At least one of temperature data, motion data of the user of the space based on the reflected wave of the electromagnetic wave from the user of the space measured by the electromagnetic wave measuring device, and medical data indicating the health condition of the user of the space. Includes one piece of data, or a physical quantity obtained from at least one piece of data.
The lighting device is
An optical member having a light emitting surface and
A decorative sheet including a light emitting region facing the light emitting surface and a non-light emitting region adjacent to the light emitting region is provided.
The amount of light emitted from a certain position on the light emitting surface is less than the amount of light emitted from another position on the light emitting surface located on one side of the light emitting surface in the direction along the light emitting surface.
The visible light transmittance of the decorative sheet is 1.0% or more and 20% or less.
A lighting device control system that controls the lighting device so that the light output into the space through the decorative sheet causes a desired psychological state for the user of the space. The lighting device control system according to claim 1, wherein the non-light emitting region is adjacent to the light emitting region on the other side opposite to the one in the direction along the light emitting surface.

Images