Environment control device and environment control method

Abstract

To execute environment control which improves a comfort degree corresponding to a scene.SOLUTION: An environment control device 1 includes: a person specifying unit 12 for specifying an object person who becomes an object of environment control from a sensor value measured from an object environment which becomes an object of environment control; a comfort analyzing unit 13 for analyzing the comfort of the object person from the sensor value measured by the object person; a scene understanding unit 22 for understanding a scene formed from the object person existing in the object environment from the sensor values measured by the object environment and the object person; a comfort correcting unit 24 for acquiring a correction amount of comfort by the scene understood by the scene understanding unit 22; and an environment improving unit 16 for correcting the comfort of the object person acquired by the comfort analyzing unit 13 by the correction amount of comfort acquired by the comfort correcting unit 24, and for performing environment control according to the comfort after the correction.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to an environmental control device and an environmental control method. [Background technology]

[0002] In environmental control such as adjusting the temperature of an air conditioner, not only can users manually adjust the temperature using a remote control, but sensors can also be used to measure the user's condition and automatically adjust the temperature to suit that condition. Patent Document 1 describes an environmental control system that changes the airflow of an air conditioner or changes the illuminance of a lighting device depending on the result of judging a person's working state. This environmental control system calculates the working state of a person depending on the surface temperature of the human body detected by a surface temperature sensor and the stress level detected by a heart rate sensor. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-188854 Summary of the Invention [Problem to be solved by the invention]

[0004] It is assumed that there are multiple people in a room where environmental control is applied, and that these people are gathered for some purpose. For example, a scene where three women are holding a party in the same room in winter to eat hot pot dishes can be considered. In that case, if the measurement results of the individual sensor values, such as a woman who has just entered the room from outside and the surface temperature being cold, are taken into consideration alone, it is reasonable to implement environmental control such as raising the temperature of the room.

[0005] However, in a scene where a rise in body temperature is expected due to eating hot pot, raising the room temperature based only on the current sensor value may result in the room becoming too hot and the comfort level decreasing. In this way, environmental control based only on individual sensor values ​​without considering the entire scene may not be optimal. On the other hand, conventional environmental control based on sensor values, such as that disclosed in Patent Document 1, is not capable of handling environmental control that assumes such a scene.

[0006] Therefore, a main object of the present invention is to perform environmental control that improves the comfort level in accordance with the scene. [Means for solving the problem]

[0007] In order to solve the above problems, the environmental control device of the present invention has the following features. The present invention includes a person identification unit that identifies a target person who is a target of environmental control from a sensor value measured in a target environment that is a target of environmental control; an analysis unit that analyzes the comfort of the target person based on a sensor value measured from the target person; a scene understanding unit that understands a scene formed by the target person in the target environment from sensor values ​​measured in the target environment and the target person, respectively; a comfort correction unit that calculates a correction amount of comfort for each scene understood by the scene understanding unit; and an environment improvement unit that corrects the comfort of the target person determined by the analysis unit with the comfort correction amount determined by the comfort correction unit, and performs environmental control in accordance with the corrected comfort. Other means will be described later. Effect of the Invention

[0008] According to the present invention, it is possible to carry out environmental control that improves comfort in accordance with the scene. [Brief description of the drawings]

[0009] [Figure 1]FIG. 1 is a configuration diagram of an environmental system according to an embodiment of the present invention. [Diagram 2] FIG. 2 is an explanatory diagram of a first example showing the operation of the environmental system according to the present embodiment. [Diagram 3] 3 is a flowchart of a first example corresponding to the explanatory diagram of FIG. 2 according to the present embodiment. [Figure 4] FIG. 11 is an explanatory diagram of a second example showing the operation of the environmental system according to the present embodiment. [Diagram 5] 5 is a flowchart of a second example corresponding to the explanatory diagram of FIG. 4 according to the present embodiment. [Figure 6] FIG. 2 is a hardware configuration diagram of the environmental control device according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, one embodiment of the present invention will be described with reference to the drawings.

[0011] FIG. 1 is a configuration diagram of an environmental system 100. The environmental system 100 is configured by connecting an information appliance 5 and an environmental control device 1 via a network. Instead of configuring the information appliance 5 and the environmental control device 1 as separate devices as in Fig. 1, the information appliance 5 may include the components of the environmental control device 1.

[0012] The information appliance 5 includes an environment sensor 51 and an environment control unit 52 . For example, when the information appliance 5 is an air conditioner or other air conditioner, the environment sensor 51 is a temperature sensor that measures the indoor temperature and a humidity sensor that measures the indoor humidity, which are provided in the air conditioner, and the environment control unit 52 is a temperature adjustment function that adjusts the indoor temperature and a humidity adjustment function that adjusts the indoor humidity, which are provided in the air conditioner. Alternatively, when the information appliance 5 is a lighting device, an illuminance sensor included in the lighting device is used as the environment sensor 51, and an illumination function included in the lighting device is used as the environment control unit 52.

[0013] The environmental control device 1 has, as processing units, a sensor acquisition unit 11, a person identification unit 12, various analysis units (a comfort analysis unit 13, a thermal sensation estimation unit 14, and a comfort judgment unit 15), an environment improvement unit 16, a scene understanding unit 22, and a comfort correction unit 24. The environment control device 1 has a METs table 13D, a behavior DB 14C, and a scene correction amount storage section 23 in a storage section.

[0014] The sensor acquisition unit 11 acquires sensor values ​​from an environmental sensor 51 such as a thermometer that measures the state of the environment that is the target of the environmental control, and various sensors (not shown, sensors such as a surface temperature sensor, heart rate sensor, visible light camera, far-infrared camera, thermal camera, etc.) that measure the state of the person that is the target of the environmental control. Hereinafter, we will explain an embodiment in which a heart rate sensor is attached to a person who is the subject of environmental control as a vital sensor, and a thermal camera is installed in an air conditioner as a non-contact camera, but the example is not limited to these and the heart rate may also be estimated from an image acquired by a non-contact camera, for example. The person identification unit 12 identifies a target person who is a target of environmental control from a sensor value measured from a target environment that is a target of environmental control. For example, when the sensor acquisition unit 11 is a non-contact camera, the person identification unit 12 analyzes an image captured by the camera using an algorithm such as object detection or semantic segmentation to identify the presence or absence of a person and the area in the space captured by the image. In addition, a configuration may be adopted in which a specific individual can be identified by analyzing features such as the face and posture of the identified person area.

[0015] The comfort analysis unit 13 analyzes the comfort of the target environment for the target person identified by the person identification unit 12. For this reason, the comfort analysis unit 13 includes a temperature estimation unit 13A, a behavior analysis unit 13B, and a stress calculation unit 13C. The temperature estimation unit 13A estimates temperatures such as the skin temperature of the target person. In this embodiment, the estimation is performed based on the temperature corresponding to the person area estimated by the person identification unit 12 from the image of the thermal camera. At this time, the skin temperature of the target person may be estimated from a partial area such as the face, or may be estimated from the whole body. Also, the skin temperature of a specific location may be estimated using a surface temperature sensor or the like. The behavior analysis unit 13B analyzes the behavior of the target person, and obtains the exercise intensity of the behavior from the behavior of the analysis result by referring to the METs table 13D. In the process of analyzing the behavior of the target person, the behavior analysis unit 13B may receive an input directly from the target person, may estimate from the sensor values ​​of various sensors indicating the state of the target person, or may obtain from the behavior included in the scene (scene, situation, or state) output by the scene understanding unit 22 described later. In addition, it may be estimated using the change in the position or posture of the target person from the image of the thermal camera in this embodiment, or inferred by a neural network that classifies the behavior of the target person from the image, and the current exercise intensity may be corrected based on the history of the behavior information estimated in this way.

[0016] The METs table 13D is a table in which each type of activity is associated with METs (Metabolic Equivalent), a unit that indicates the exercise intensity of the activity. For example, the following entries are preregistered in the METs table 13D. By using the METs values, the calories burned can be calculated, for example, by the formula "calories burned [kcal] = METs x time x body weight [kg]". Sitting on the sofa and relaxing = 1 METs Standing conversation = 1.8 [METs] Vacuuming = 3.3 [METs] Carrying luggage to an upper floor = 8.3 [METs]

[0017] The stress calculation unit 13C calculates the target person's internal discomfort as stress. The target person's internal state may be estimated from measurement data of a sensor attached to the target person, such as a heart rate sensor, or may use the results of remotely monitoring the target person, such as a thermographic image. Alternatively, the stress calculation unit 13C may infer stress from the target person's behavior output by the behavior analysis unit 13B.

[0018] The thermal sensation estimating section 14 has an external thermal sensation estimating section 14A and an internal thermal sensation estimating section 14B in order to estimate the thermal sensation of the target person. The apparent thermal sensation estimating unit 14A estimates the apparent thermal sensation of the target person based on the output result of the comfort analyzing unit 13, which is likely to reflect the apparent thermal sensation of the target person (details in FIG. 2). Alternatively, the apparent thermal sensation estimating unit 14A may take the objective thermal sensation of the target person, such as a predicted mean vote (PMV), as the apparent thermal sensation of the target person. The internal thermal sensation estimation unit 14B estimates the internal thermal sensation of the target person based on the output result of the comfort analysis unit 13 which is likely to reflect the internal thermal sensation of the target person (details in FIG. 2). Alternatively, the internal thermal sensation estimation unit 14B may take the subjective thermal sensation of the target person, such as a predicted percentage of dissatisfied (PPD), as the internal thermal sensation of the target person.

[0019] Furthermore, the thermal sensation estimating section 14 may predict the thermal sensation of the target person by referring to the behavior DB 14C in addition to the output result of the comfort analyzing section 13 (the temperature estimating section 13A and the behavior analyzing section 13B). The behavior DB 14C stores information that associates the target person's behavior with the target person's thermal sensation in advance, such as "when clothes are loosened, thermal sensation = feeling hot."

[0020] In addition, the environmental control device 1 may use the following questionnaire content directly input by the target person in place of the data calculated by each processing unit, or may evaluate the reliability of the data calculated by each processing unit (e.g., as feedback to machine learning). The response to the questionnaire asking "Please rate the comfort you are currently feeling" is reflected in the calculation data of the comfort analysis unit 13. The answer to the questionnaire "Please rate the thermal sensation you are currently feeling" is reflected in the calculation data of the thermal sensation estimation unit 14. The answer to the questionnaire "Please rate the level of stress you are feeling right now" is reflected in the calculation data of the stress calculation unit 13C.

[0021] The comfort determination unit 15 determines the comfort of the target person based on the output content of the thermal sensation estimation unit 14. The environment improvement unit 16 determines the content of the environmental control instruction to the environment control unit 52 by reflecting the correction amount calculated by the comfort correction unit 24 in the comfort of the target person determined by the comfort determination unit 15 (details in Figs. 2 and 4).

[0022] Here, the scene understanding unit 22 understands a scene formed by a target person in the target environment from the sensor values ​​measured in the target environment and the target person, respectively. For example, the scene understanding unit 22 inputs a captured image of the target environment input from the sensor acquisition unit 11 into an inference model prepared in advance, and outputs a scene shown in the captured image as a caption or outputs classification information of a plurality of predefined scene types. The inference model is, for example, a machine learning model generated by learning in advance using an image as an input and a caption or a scene type label as a teacher. A correction amount corresponding to each scene is registered in advance in the scene correction amount storage unit 23. The comfort correction unit 24 determines a correction amount of comfort for the scene determined by the scene understanding unit 22 by referring to the scene correction amount storage unit 23.

[0023] FIG. 2 is a diagram illustrating a first example of the operation of the environmental system 100. As shown in FIG. Fig. 3 is a flowchart of a first example corresponding to the explanatory diagram of Fig. 2. Fig. 2 will be explained below with reference to Fig. 3 as needed. Scene 200 is an image captured indoors on a cold winter day by the environmental sensor 51. This scene 200 shows a group of three friends enjoying a hot pot meal. The scene understanding unit 22 inputs a captured image of the scene 200 into an inference model prepared in advance, and outputs the following caption 210 (S101). This is a photo taken inside a room. Three people having fun. Eating hot pot. The hotpot is hot.

[0024] Furthermore, table 220 associates the output results of each processing unit with information on the necessity of environmental control (possibility of changing the room temperature) derived from the output results in the environment (indoors) of scene 200. The contents of table 220 will be described below. The thermometer or thermal camera as the sensor acquisition unit 11 shown in the first row of table 220 outputs "Indoor temperature = cold" (S102). In scene 200, the indoor temperature is high around the hot pot dish, but the indoor temperature is low throughout the room due to the winter chill. From this output of "Indoor temperature = cold", an environmental control of "Room temperature change possibility = yes (turn on the heater to raise the room temperature)" can be derived.

[0025] Hereinafter, the process of outputting the room temperature change possibility by the comfort analysis unit 13 (S103) will be described as (Process 1) to (Process 3). (Process 1) The surface temperature sensor or thermal camera serving as temperature estimation unit 13A shown in the second row of table 220 outputs "skin temperature = suitable temperature." In scene 200, although "room temperature = cold," three people are sitting around the hot pot, so the skin temperature is high compared to the room temperature. As a result, from the output of "skin temperature = suitable temperature," environmental control of "room temperature change possibility = none" can be derived.

[0026] (Process 2) The behavior analysis unit 13B shown in the third row of table 220 outputs "3 people sitting still" based on the image recognition results of scene 200. In the METs table 13D, this behavior is associated with 1 [METs] and low exercise intensity (low calorie consumption). As a result, since people who do not exercise have a small increase in body temperature due to metabolism, the output of "sitting still" can lead to environmental control that corrects the results of the first and second rows of table 220 to "room temperature change possibility = yes (turn on the heater to raise the room temperature)". (Process 3) The heart rate sensor serving as the stress calculation unit 13C shown in the fourth row of table 220 outputs "tension state." As a result, since the output of "tension state" indicates tension and discomfort, environmental control can be derived to correct the results in the first and second rows of table 220 to "room temperature change possibility = yes (turn on the heater to raise the room temperature)."

[0027] In this way, from table 220, three decisions of "room temperature change possibility = yes" and one decision of "room temperature change possibility = no" are detected from scene 200. Here, the thermal sensation estimator 14 executes the integration process (S104) of the room temperature change possibility for the results obtained in the output process (S103) of the comfort analyzer 13 as the following (Process 4) and (Process 5). (Process 4) The apparent thermal sensation estimation unit 14A integrates the output result of the temperature estimation unit 13A and the output result of the behavior analysis unit 13B (for example, averaging the two results) and estimates the apparent thermal sensation of the target person to be “possibility of room temperature change = slightly likely.” (Process 5) The internal thermal sensation estimating section 14B estimates the internal thermal sensation of the target person to be "room temperature change possibility=yes" based on the output result of the stress calculating section 13C.

[0028] Furthermore, the comfort judgment unit 15 integrates the "room temperature change possibility = slightly possible" output by the external thermal sensation estimation unit 14A and the "room temperature change possibility = possible" output by the internal thermal sensation estimation unit 14B, and judges the comfort of the target person to be "room temperature change possibility = quite possible" (S105). The integration method can be, for example, calculating an average value. In addition, sensitivity can be set according to the importance of the processing units, and the ratio of each process to be integrated (e.g., sensor acquisition unit sensitivity 10%, temperature estimation unit sensitivity 40%, behavior analysis unit sensitivity 30%, stress calculation unit sensitivity 20%, total 100%) can be set in advance. Alternatively, if the output result of one or both of the thermal sensation estimators is “Possibility of changing room temperature=Yes”, the comfort judgment unit 15 may determine the output result of the comfort judgment unit 15 to be “Possibility of changing room temperature=Yes” (S105).

[0029] In this way, the external thermal sensation estimating section 14A estimates the external thermal sensation of the target person based on the surface temperature of the target person and the behavior of the target person among the sensor values ​​measured from the target person (Process 1 in S104). The internal thermal sensation estimating section 14B estimates the internal thermal sensation of the target person based on the stress of the target person among the sensor values ​​measured from the target person (Process 2 in S104). Then, when at least one of the target person's external thermal sensation and the target person's internal thermal sensation is lower than a predetermined value, the comfort determining unit 15 calculates the target person's comfort as low (S105).

[0030] On the other hand, the comfort correction unit 24 calculates the correction amount for the comfort of the target person determined by the comfort judgment unit 15 by referring to the scene correction amount storage unit 23 for the caption 210 output from the scene 200. For example, the scene correction amount storage unit 23 has pre-registered rules for each scene, such as "environmental control is not possible in a scene where multiple people are having fun" and "heating should not be used in a scene where hot food is being eaten." As a result, the comfort correction unit 24 creates an environmental control instruction 230 in which the output of the comfort determination unit 15, "Room temperature change possibility = high", is corrected to "There is no need to raise the room temperature" (S106). Then, in accordance with the environmental control instruction 230, the environment improvement unit 16 did not execute environmental control (turn on the heater to change the room temperature) for the environmental control unit 52 this time.

[0031] FIG. 4 is a diagram illustrating a second example of the operation of the environmental system 100. In FIG. Fig. 5 is a flowchart of a first example corresponding to the explanatory diagram of Fig. 4. Fig. 4 will be explained below with reference to Fig. 5 as needed. Scene 310 is an image captured in a cold kitchen by the environment sensor 51. This scene 310 captures the mother cooking. Scene 320 is an image captured in a warm living room by the environment sensor 51. This scene 320 shows a mother who has moved in from scene 310 feeding her child with food.

[0032] The scene understanding unit 22 inputs a captured image of a kitchen scene 310 into an inference model prepared in advance, and outputs the following caption 311 (S101A). This is a photo of the kitchen. -Has a mother. -Cooking food.

[0033] Moreover, in the table 330 relating to the mother, in the kitchen scene 310, the output results of each processing unit are associated with information on the necessity of environmental control (possibility of changing the room temperature) derived from the output results as follows: The sensor acquisition unit 11 shown in the first line outputs "Indoor temperature = cold" (S102A). From the output "Indoor temperature = cold", an environmental control of "Room temperature change possibility = yes (turn on the heater to raise the room temperature)" can be derived.

[0034] Hereinafter, the output process (S103A) of the room temperature change possibility for the mother by the comfort analysis unit 13 will be described as (Process 1) to (Process 3). (Process 1) From the output of temperature estimation unit 13A shown in the second line, "skin temperature = low," an environmental control of "room temperature change possibility = yes" can be derived. (Process 2) From the output of the behavior analysis unit 13B shown in the third line, "cook, move rooms," an environmental control of "room temperature change possibility=none" can be derived. (Process 3) From the output "active state" of the stress calculation unit 13C shown in the fourth line, an environmental control "room temperature change possibility=yes" can be derived.

[0035] Moreover, the scene understanding unit 22 inputs a captured image of a living room scene 320, which is another scene, into an inference model prepared in advance, and outputs the following caption 321 (S101B). This is a photo taken in the living room. There is a mother and child. The child is eating. The mother is smiling.

[0036] Furthermore, in the children-related table 340, in the living room scene 320, the output results of each processing unit are associated with information on the necessity of environmental control (possibility of changing the room temperature) derived from the output results as follows: The sensor acquisition unit 11 shown in the first line outputs "room temperature = warm" (S102B). From the output "room temperature = warm", an environmental control of "room temperature change possibility = none" can be derived.

[0037] Hereinafter, the process of outputting the room temperature change possibility by the child-related comfort analysis unit 13 (S103B) will be described as (Process 1) to (Process 3). (Process 1) From the output of temperature estimation unit 13A shown in the second line, "skin temperature = optimum temperature," an environmental control of "room temperature change possibility = none" can be derived. (Process 2) From the output of the behavior analysis unit 13B shown in the third line, "eating while sitting," an environmental control, "room temperature change possibility=yes," can be derived. (Process 3) From the output "Relax" of the stress calculation unit 13C shown in the fourth line, an environmental control of "room temperature change possibility=none" can be derived.

[0038] The process in which the environmental control device 1 determines whether or not environmental control is required in the living room scene 320 will be described below. From the table 330 relating to the mother, three judgments of "room temperature change possibility = yes" and one judgment of "room temperature change possibility = no" are detected from the kitchen scene 310. Then, the comfort analysis unit 13 may correct the second line of the table 330 relating to the mother, "skin temperature = low", to "skin temperature = comfortable temperature", because the mother moves from the kitchen to the living room. In other words, when the target person moves within the target environment, the comfort analysis unit 13 analyzes the comfort of the target person by using the sensor value predicted from the target environment after the movement instead of the sensor value measured from the target person. This allows the system to take into account changes in the environment, since although immediately after moving from a cold environment to a warm one, the "skin temperature = low" in the cold environment before the move is expected to change to "skin temperature = appropriate temperature" as the body warms up.

[0039] From the table 340 relating to children, one judgment "room temperature changeable=Yes" and three judgments "room temperature changeable=No" are detected from the living room scene 320.

[0040] The thermal sensation estimator 14 integrates the room temperature change possibilities for the mother and the child (S104A, S104B) in the same manner as in the description of Fig. 2. Furthermore, the comfort judger 15 integrates the output result of the external thermal sensation estimator 14A and the output result of the internal thermal sensation estimator 14B to judge the comfort of the mother (here, "there is some possibility that the room temperature can be changed") (S105A) and the comfort of the child (here, "there is almost no possibility that the room temperature can be changed") (S105B). Here, the comfort correction unit 24 calculates the correction amount for the comfort of the target person determined by the comfort judgment unit 15 by referring to the scene correction amount storage unit 23 for the caption 321 output from the living room scene 320. For example, the scene correction amount storage unit 23 has a rule registered in advance to the effect that "prioritize the comfort of the child over that of the parent."

[0041] Therefore, when there are multiple target persons in the target environment, the comfort correction unit 24 obtains a correction amount for comfort according to the sensor value measured from the target person with a high priority who is registered in advance (S106W). For example, the comfort correction unit 24 prioritizes the child's comfort "almost no possibility of changing the room temperature" over the mother's comfort, thereby correcting the environmental control instruction 350 to "there is no need to increase the room temperature." Then, the environment improvement unit 16, in accordance with the environment control instruction 230, did not execute environment control (turn on the heater to change the room temperature) to the environment control unit 52 this time.

[0042] FIG. 6 is a diagram showing the hardware configuration of the environmental control device 1. As shown in FIG. The environmental control device 1 is configured as a computer 900 having a CPU 901 , a RAM 902 , a ROM 903 , a HDD 904 , a communication I / F 905 , an input / output I / F 906 , and a media I / F 907 . The communication I / F 905 is connected to an external communication device 915. The input / output I / F 906 is connected to an input / output device 916. The media I / F 907 reads and writes data from a recording medium 917. Furthermore, the CPU 901 executes a program (also called an application or its abbreviation, an app) loaded into the RAM 902, thereby improving and controlling each processing unit. This program can also be distributed via a communication line, or recorded on a recording medium 917 such as a CD-ROM and distributed.

[0043] The environmental control device 1 of the present embodiment described above uses various sensors such as a non-contact camera to estimate the target environment in which the target person is present and each state of the target person. The environmental control device 1 then predicts the comfort of the target person and performs control to improve the environment so as to improve the comfort of the target person according to the prediction. Here, the environmental control device 1 focuses on the scene formed by the target environment and the situation of the target person, not just the state of the target person, and performs environmental control appropriate for the scene. This makes it possible to execute environmental control that improves the comfort level in response to the scene.

[0044] Furthermore, the present invention is not limited to the above-described embodiments, and various other application examples and modifications are possible without departing from the gist of the present invention described in the claims. For example, the above-described embodiments are detailed and specific descriptions of the configuration of the environmental control device 1 in order to easily explain the present invention, and are not necessarily limited to those including all of the components described. It is also possible to replace a part of the configuration of one embodiment with a component of another embodiment. It is also possible to add a component of another embodiment to the configuration of one embodiment. It is also possible to add, replace, or delete other components from a part of the configuration of each embodiment.

[0045] In addition, the above-mentioned configurations, functions, processing units, etc. may be realized in part or in whole by hardware, for example, by designing them as integrated circuits. As the hardware, a broad processor device such as an FPGA (Field Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit) may be used. Furthermore, each component of the environmental control device 1 according to the embodiment described above may be implemented in any hardware as long as the respective hardware can transmit and receive information to each other via a network. Furthermore, the process executed by a certain processing unit may be realized by a single piece of hardware, or may be realized by distributed processing by multiple pieces of hardware. [Explanation of symbols]

[0046] 1. Environmental control equipment 5. Information appliances 11 Sensor acquisition unit 12 Person identification section 13 Comfort Analysis Section (Analysis Section) 13A Temperature estimation part 13B Behavior Analysis Department 13C Stress Calculation Section 13D METs table 14 Thermal sensation estimation unit (analysis unit) 14A External thermal sensation estimation part 14B Internal warm / cold sensation estimation section 14C Behavior DB 15 Comfort judgment section (analysis section) 16 Environmental Improvement Department 22 Scene Understanding Department 23 Scene correction amount storage section 24 Comfort correction section 51 Environmental Sensors 52 Environmental Control Section 100 Environmental Systems

Claims

1. a person identification unit that identifies a target person who is a target of the environmental control from a sensor value measured from a target environment that is a target of the environmental control; an analysis unit that analyzes the comfort of the target person based on a sensor value measured from the target person; a scene understanding unit that understands a scene formed by the target person in the target environment from sensor values ​​measured in the target environment and the target person, respectively; a comfort correction unit that calculates a correction amount of comfort for each scene understood by the scene understanding unit; and an environment improvement unit that corrects the comfort of the target person obtained by the analysis unit with a correction amount of comfort obtained by the comfort correction unit, and controls the environment according to the corrected comfort. Environmental control device.

2. The analysis unit includes: An external thermal sensation of the target person is estimated based on the surface temperature of the target person and the behavior of the target person among the sensor values ​​measured from the target person, and an internal thermal sensation of the target person is estimated based on the stress of the target person among the sensor values ​​measured from the target person; When at least one of the external thermal sensation of the target person and the internal thermal sensation of the target person is lower than a predetermined value, the comfort of the target person is calculated as being low. The environmental control device according to claim 1 .

3. When the target person moves in the target environment, the analysis unit analyzes the comfort of the target person by using a sensor value predicted from the target environment after the movement instead of a sensor value measured from the target person. The environmental control device according to claim 1 .

4. The comfort correction unit is characterized in that, when a plurality of target persons are present in the target environment, a correction amount of comfort is calculated based on a sensor value measured from a target person having a high priority who is registered in advance. The environmental control device according to claim 1 .

5. The environmental control device includes a person identification unit, an analysis unit, a scene understanding unit, a comfort correction unit, and an environment improvement unit, a step of the person identification unit identifying a target person who is a target of environmental control from a sensor value measured from a target environment that is a target of environmental control; The analysis unit analyzes the comfort of the target person from the sensor value measured from the target person; A step in which the scene understanding unit understands a scene formed by the target person in the target environment from sensor values ​​measured in the target environment and the target person, respectively; The comfort correction unit calculates a comfort correction amount for each scene understood by the scene understanding unit; the environment improvement unit corrects the comfort of the target person obtained by the analysis unit with the amount of comfort correction obtained by the comfort correction unit, and performs environmental control according to the corrected comfort. Environmental control methods.

Images