Information Processing Method and Information Processing System

Abstract

To provide a technique capable of reducing the risk of contracting infectious diseases in a specific space where coughs and sneezes have been detected.SOLUTION: An information processing method causes a computer to execute the steps of: detecting coughing or sneezing by a person within a predetermined space: acquiring an image of the predetermined space taken when the cough or sneeze is detected; detecting the condition of the person's mouth from the image; generating a control signal for controlling at least one of the wind direction and air volume of air that is sent out from an airflow generator that generates airflow within a given space based on the state of the recognized person's mouth; and outputting the generated control signal.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present disclosure relates to an information processing method, an information processing program, and an information processing system for controlling the airflow in a predetermined space where a cough or a sneeze is detected.

Background Art

[0002] Many infectious diseases such as influenza are transmitted from person to person, for example, by contact infection, droplet infection, or airborne infection. In particular, the occurrence of infected persons in a facility, etc., may lead to a group infection throughout the facility, so countermeasures are urgently needed. For example, in a facility where many elderly people live, such as a nursing facility, infectious diseases are likely to become severe, and in the worst case, there is a risk that elderly people infected with the infectious disease may die. Therefore, in nursing facilities, infection control measures at the individual level, such as wearing masks by caregivers and thorough hand hygiene, are being carried out. Also, in the case of influenza, droplet infection or airborne infection is considered to be the main route of infection, and from the perspective of infection control measures, it is important whether or not a person has been exposed to a cough or a sneeze by an infected person.

[0003] For example, Patent Document 1 discloses a technique for detecting that an infected person has performed an operation that generates droplets, and when it is detected that the infected person has performed an operation that generates droplets, determining whether or not a subject was present at the location where the infected person performed the operation that generates droplets, and when it is determined that the subject was present, outputting the identification information of the subject.

[0004] Also, Non-Patent Document 1 discloses the results of a simulation of how droplets scatter when an infected person coughs in an air-conditioned room where the room is ventilated.

[0005] According to this result, when a person coughs with an initial velocity of 10 [m / s], the droplets reach a susceptor 1 [m] ahead in about 5 [s], and the susceptor is exposed. After that, the droplets spread around the susceptor over several tens of seconds or more.

[0006] However, since the ventilation conditions in this Non-Patent Document 1 are set to be more than the normally expected ventilation volume, the diffusion time of droplets is estimated to be short. However, roughly speaking, the behavior of droplets can be classified into two phases: a first phase in which droplets are scattered at high speed on the unsteady cough airflow between 5 and 10 [s], and a second phase in which the droplets rapidly decelerate due to air resistance and are transported by the indoor airflow after the first phase.

Prior Art Documents

Patent Documents

[0007]

Patent Document 1

Non-Patent Documents

[0008]

Non-Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0009] However, with the above conventional technology, it is impossible to reduce the risk of infection with an infectious disease in a predetermined space where a cough or sneeze is detected, and further improvement has been required.

[0010] The present disclosure has been made to solve the above problems, and provides a technique capable of reducing the risk of infection with an infectious disease in a predetermined space where a cough or sneeze is detected.

Means for Solving the Problems

[0011] An information processing method according to one aspect of the present disclosure includes a computer detecting a cough or a sneeze by a person in a predetermined space, acquiring an image of the predetermined space captured when the cough or the sneeze is detected, detecting a state of the mouth of the person from the image, and generating a control signal for controlling at least one of a wind direction and a wind volume of air sent from an airflow generator that generates an airflow in the predetermined space based on the recognized state of the mouth of the person, and outputting the generated control signal.

[0012] Note that this general or specific aspect may be implemented by an apparatus, a system, an integrated circuit, a computer program, or a computer-readable recording medium, or may be implemented by any combination of an apparatus, a system, a method, an integrated circuit, a computer program, and a computer-readable recording medium. The computer-readable recording medium includes, for example, a non-volatile recording medium such as a CD-ROM (Compact Disc-Read Only Memory).

Advantages of the Invention

[0013] According to the present disclosure, since the localized droplets can be diffused to make the concentration uniform, the risk of infection with an infectious disease in a predetermined space where a cough or a sneeze is detected can be reduced.

[0014] Further advantages and effects in one aspect of the present disclosure will be clarified from the specification and the drawings. Such advantages and / or effects are provided by some embodiments and the features described in the specification and the drawings, respectively, but it is not always necessary to provide all of them in order to obtain one or more of the same features.

Brief Description of the Drawings

[0015]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Figure 18

Figure 19

Figure 20

Figure 21

Figure 22

Figure 23

Figure 24

Figure 25

Figure 26

Embodiments for Carrying Out the Invention

[0016] (Knowledge on which the present disclosure is based) In the above prior art, it is possible to estimate a person at risk of infection, but it is difficult to prevent the infection of a susceptible person before infection. That is, as a result of a susceptible person being exposed to the cough or sneeze of an infected person, it is difficult to prevent infection by droplet infection or airborne infection.

[0017] People cough or sneeze in various states. For example, many people cover a part of their face such as the nose and mouth with their hands when coughing or sneezing. Also, people may cough or sneeze while wearing a mask. Depending on the state of a person when coughing or sneezing like this, the behavior of droplets is different.

[0018] For example, when coughing or sneezing with a part of the face covered with a hand, most of the droplets do not spread and adhere to the hand. Smaller droplets or droplet nuclei will leak through the gaps in the hand, but in that case, due to the pressure loss caused by covering with the hand, it is expected that the convection velocity will be about the same as the room air velocity. That is, in this case, it can be said that the droplets are localized around the infected person and are almost stationary. In this case, it is important to quickly diffuse the droplets remaining around the infected person to the surroundings.

[0019] To solve the above problems, an information processing method according to one aspect of the present disclosure includes a computer detecting a cough or sneeze by a person in a predetermined space, acquiring an image of the predetermined space captured when the cough or the sneeze is detected, detecting a state of the mouth area of the person from the image, and generating a control signal for controlling at least one of the wind direction and the air volume of the air sent from an airflow generating device that generates an airflow in the predetermined space based on the recognized state of the mouth area of the person, and outputting the generated control signal.

[0020] According to this configuration, when a cough or a sneeze by a person is detected in a predetermined space, the state of the person's mouth when coughing or sneezing is recognized from the acquired image, and based on the recognized state of the person's mouth, a control signal for controlling at least one of the wind direction and the air volume of the air sent from an air flow generating device that generates an air flow in the predetermined space is generated.

[0021] Therefore, by generating an air flow at the location where the droplets generated by the person's cough or sneeze are localized, the localized droplets can be diffused to make the concentration uniform, so that the risk of infection with an infectious disease in the predetermined space where the cough or sneeze is detected can be reduced.

[0022] Also, in the above information processing method, the recognition of the state of the person's mouth may recognize either a state where the person's mouth is not covered or a state where the person's mouth is covered with a hand.

[0023] According to this configuration, the location where the droplets generated by the person's cough or sneeze are localized is different between the state where the person's mouth is not covered and the state where the person's mouth is covered with a hand. Therefore, by determining the location where the air flow is generated based on whether the state of the person's mouth is either a state where the person's mouth is not covered or a state where the person's mouth is covered with a hand, the localized droplets can be more reliably diffused.

[0024] Also, in the above information processing method, the recognition of the state of the person's mouth may recognize any one of a state where the person's mouth is not covered, a state where the person's mouth is covered with a hand, and a state where the person's mouth is covered with a mask.

[0025] According to this configuration, the location where droplets generated by a person's cough or sneeze are localized is different between the state where the person's mouth is uncovered, the state where the person's mouth is covered with a hand, and the state where the person's mouth is covered with a mask. Therefore, based on whether the state of the person's mouth is in the state where the person's mouth is uncovered, the state where the person's mouth is covered with a hand, the state where the person's mouth is covered with a handkerchief or clothing, or the state where the person's mouth is covered with a mask, by determining the location where the airflow is generated, the localized droplets can be more reliably diffused.

[0026] Also, in the above information processing method, the recognition of the state of the person's mouth may recognize any one of the state where the person's mouth is uncovered, the state where the person's mouth is covered with a hand, the state where the person's mouth is covered with a handkerchief or clothing, and the state where the person's mouth is covered with a mask.

[0027] According to this configuration, the location where droplets generated by a person's cough or sneeze are localized is different between the state where the person's mouth is uncovered, the state where the person's mouth is covered with a hand, the state where the person's mouth is covered with a handkerchief or clothing, and the state where the person's mouth is covered with a mask. Therefore, based on whether the state of the person's mouth is in the state where the person's mouth is uncovered, the state where the person's mouth is covered with a hand, the state where the person's mouth is covered with a handkerchief or clothing, or the state where the person's mouth is covered with a mask, by determining the location where the airflow is generated, the localized droplets can be more reliably diffused.

[0028] Also, in the above information processing method, further, recognize the orientation of the person's face at the time when the person's cough or sneeze is detected from the image, and the wind direction may be made different between the case where the orientation of the face is facing forward and the case where the orientation of the face is facing downward.

[0029] According to this configuration, when a person coughs or sneezes with their face facing forward, the droplets will scatter forward in front of the person's face. When a person coughs or sneezes with their face facing downward, the droplets will be localized below a predetermined space. Therefore, by making the wind direction of the air sent from the airflow generator different when the person's face is facing forward and when the person's face is facing downward, it is possible to accurately generate an airflow at the location where the droplets are localized.

[0030] Further, in the above information processing method, the position coordinates of the person may be further calculated from the image, and the control signal may be generated based on the recognized state of the person's mouth and the recorded position coordinates.

[0031] According to this configuration, based on the state of the person's mouth when a cough or sneeze by the person is detected and the position coordinates of the person, the location where the droplets are localized can be more accurately specified.

[0032] Further, in the above information processing method, the airflow generator may be selected from a plurality of airflow generators based on the position coordinates.

[0033] According to this configuration, the airflow generator includes a plurality of airflow generators. Among the plurality of airflow generators, the airflow generator to be controlled is selected according to the calculated position coordinates of the person. Therefore, for example, by sending air to the location where the droplets are localized from the airflow generator closest to the position of the person who coughed or sneezed among the plurality of airflow generators, the localized droplets can be diffused more efficiently and quickly.

[0034] A program according to another aspect of the present disclosure is a program that causes a computer to execute a process, the process including detecting a cough or a sneeze by a person in a predetermined space, acquiring an image of the predetermined space captured when the cough or the sneeze is detected, detecting a state of the person's mouth from the image, generating a control signal for controlling at least one of a wind direction and an air volume of air sent from an air flow generating device that generates an air flow in the predetermined space based on the state of the mouth, and outputting the generated control signal.

[0035] According to this configuration, from the image acquired when a cough or a sneeze by a person is detected in a predetermined space, the state of the person's mouth when the person coughs or sneezes is recognized, and based on the recognized state of the person's mouth, a control signal for controlling at least one of the wind direction and the air volume of the air sent from an air flow generating device that generates an air flow in the predetermined space is generated.

[0036] Therefore, by generating an air flow at the location where the droplets generated by the person's cough or sneeze are localized, the localized droplets can be diffused and the concentration can be made uniform, so that the risk of infection with an infectious disease in the predetermined space where the cough or sneeze is detected can be reduced.

[0037] An information processing system according to another aspect of the present disclosure includes a camera that images a predetermined space, an air flow generating device that generates an air flow in the predetermined space, and an information processing device. The information processing device detects a cough or a sneeze by a person in the predetermined space, acquires an image of the predetermined space captured by the camera when the cough or the sneeze is detected, detects a state of the person's mouth from the image, generates a control signal for controlling at least one of the wind direction and the air volume of the air sent from the air flow generating device based on the state of the mouth, and outputs the generated control signal.

[0038] According to this configuration, when a cough or sneeze by a person is detected in a predetermined space, the state of the person's mouth when coughing or sneezing is recognized from the acquired image, and based on the recognized state of the person's mouth, a control signal is generated to control at least one of the wind direction and the air volume of the air sent from an air flow generating device that generates an air flow in the predetermined space.

[0039] Therefore, by generating an air flow at the location where the droplets generated by the person's cough or sneeze are localized, the localized droplets can be diffused to make the concentration uniform, so that the risk of infection with an infectious disease in the predetermined space where the cough or sneeze is detected can be reduced.

[0040] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. Note that the following embodiments are an example of embodying the present disclosure and do not limit the technical scope of the present disclosure.

[0041] (Embodiment 1) FIG. 1 is a diagram showing the configuration of an air flow control system according to Embodiment 1 of the present disclosure. The air flow control system shown in FIG. 1 is an example of an information processing system and includes an air flow control device 1 and an air flow generating device 2.

[0042] The air flow control device 1 is an example of an information processing device and controls the air flow in a predetermined space. The air flow control device 1 is disposed on a wall or ceiling in the predetermined space. The predetermined space may be any space where a camera or the like can be installed, for example, a community room in a nursing facility or a waiting room in a hospital. Also, the predetermined space may be a relatively narrow space such as inside a train.

[0043] The air flow generating device 2 generates an air flow in the predetermined space. The air flow generating device 2 is, for example, an air conditioning device having a cooling and / or heating function, an air purifier having an air purification function, or a blower having a blowing function. The air flow generating device 2 is disposed in the predetermined space. The air flow generating device 2 has a function of changing the wind direction and the air volume.

[0044] The airflow control device 1 is communicably connected to the airflow generation device 2 via a network. The network is, for example, an intranet or the Internet.

[0045] The airflow control device 1 includes a camera 11, a microphone 12, a processor 13, a memory 14, and a communication unit 15.

[0046] The camera 11 is installed in a predetermined space and photographs the inside of the predetermined space. The camera 11 acquires an image of a subject in the predetermined space. The subject is a person staying in the space where the airflow control device 1 is installed.

[0047] Here, the airflow control device 1 does not determine whether the subject is infected with an infectious disease, and treats a subject who coughs or sneezes as an infected person. When a person contracts an infectious disease, they transition through a period of infectivity and a period of symptoms, and usually the two periods are different. It is difficult with current technology to determine whether a person has infectivity before symptoms appear, and it is only after a considerable amount of time with infectivity that they can be determined to be an infected person. For this reason, the term "infected person" is used for an individual who has been confirmed to have infectivity by some measurement such as the appearance of symptoms or a doctor's diagnosis.

[0048] The camera 11 is a camera that monitors the interior of a room. It is installed on the ceiling or the like so that it can widely detect subjects, and continuously acquires video of the interior of the room. The camera 11 may further include a rotating part that sweeps the shooting area at regular intervals in order to photograph the entire interior of the room. In this way, by the camera 11 having a rotating part, it is possible to photograph the entire interior of a room with a single camera 11 even in a wider space of 20 tatami mats or more.

[0049] The microphone 12 is installed in a predetermined space and collects sound within the predetermined space. The microphone 12 acquires the voice of a subject in the predetermined space.

[0050] In addition, in the first embodiment, the camera 11 and the microphone 12 may be provided inside the airflow control device 1 or outside the airflow control device 1. When the camera 11 and the microphone 12 are provided outside the airflow control device 1, the airflow control device 1 is communicably connected to the camera 11 and the microphone 12 by wire or wirelessly.

[0051] The processor 13 includes an image processing unit 131, a cough / sneeze detection unit 132, a person state determination unit 133, and a control signal generation unit 134. The memory 14 is, for example, a semiconductor memory and includes an image storage unit 141, a device information storage unit 142, and an airflow control table storage unit 143.

[0052] The image storage unit 141 stores the image captured by the camera 11. The camera 11 stores the image captured within a predetermined space in the image storage unit 141.

[0053] The image processing unit 131 acquires the image captured within a predetermined space from the image storage unit 141. The image processing unit 131 performs image processing on the acquired image and extracts human features such as the face, nose, mouth, hands, clothing, presence or absence of a mask, and the position of the subject indoors. Note that the image processing unit 131 may use machine learning or deep learning for feature extraction, or may use a widely known feature extractor such as a Haar-Like extractor for face detection. When extracting features, the image processing unit 131 detects information such as the centroid position or area of each extracted feature such as the mouth and face, together with the position information of the subject indoors.

[0054] The cough / sneeze detection unit 132 detects a cough or sneeze by a person in a predetermined space. When the subject coughs or sneezes, the cough / sneeze detection unit 132 detects the cough or sneeze.

[0055] The cough / sneeze detection unit 132 detects that a person has coughed or sneezed in the indoor space. The cough / sneeze detection unit 132 uses the sound collected by the microphone 12 and the image captured by the camera 11 to detect a cough or sneeze by a person in a predetermined space.

[0056] For example, the cough / sneeze detection unit 132 determines whether the volume of the sound collected by the microphone 12 is equal to or greater than a threshold value. When the cough / sneeze detection unit 132 determines that the volume of the sound collected by the microphone 12 is equal to or greater than the threshold value, it determines that a cough or sneeze has been made by a person in a predetermined space. As the threshold value, for example, 70 dB may be used. Note that since the detected volume varies depending on the distance between the microphone 12 and the person, the cough / sneeze detection unit 132 may calculate the distance between the microphone 12 and the person from the image and correct the threshold value according to the calculated distance.

[0057] In addition, the cough / sneeze detection unit 132 may perform spectral analysis of the sound collected by the microphone 12 and detect a cough or sneeze by an algorithm such as machine learning based on the analysis result. In this case, since it is possible to detect using a spectral pattern peculiar to a cough or sneeze, the detection accuracy is improved.

[0058] In addition, the cough / sneeze detection unit 132 detects at least one of a cough and a sneeze by a person in a predetermined space from the image. The camera 11 is acquiring a moving image. Therefore, the cough / sneeze detection unit 132 can detect the motion pattern of the target person using the features extracted by the image processing unit 131. For example, a person performs characteristic motions such as covering the mouth with a hand or closing the eyes as motions immediately before coughing or sneezing. Therefore, the cough / sneeze detection unit 132 can detect that a person in a predetermined space has coughed or sneezed by detecting the characteristic motions when coughing or sneezing.

[0059] The cough / sneeze detection unit 132 can utilize the motion pattern detected from the image captured by the camera 11. For example, the cough / sneeze detection unit 132 may determine using a classifier that has learned the characteristic motion immediately before a cough or a sneeze through machine learning.

[0060] More simply, the cough / sneeze detection unit 132 may calculate the distance between the center-of-gravity position of the face extracted from the image and the center-of-gravity position of the hand, and determine whether the distance between the center-of-gravity position of the face and the center-of-gravity position of the hand is equal to or less than a threshold value.

[0061] FIG. 2 is a diagram for explaining a first method of detecting from an image that a subject has coughed or sneezed in Embodiment 1.

[0062] The cough / sneeze detection unit 132 determines whether the distance between the position of the face of the person included in the image and the position of one hand of the person included in the image is equal to or less than a threshold value. When it is determined that the distance is equal to or less than the threshold value, a cough or a sneeze is detected.

[0063] First, the image processing unit 131 extracts from the image G1 a face region FR indicating the face of the subject, a right hand region RH indicating the right hand of the subject, and a left hand region LH indicating the left hand of the subject. At this time, the extracted face region FR, right hand region RH, and left hand region LH are rectangular. Further, the image processing unit 131 calculates the center-of-gravity position of the face region FR, the center-of-gravity position of the right hand region RH, and the center-of-gravity position of the left hand region LH.

[0064] The cough / sneeze detection unit 132 determines whether the horizontal width fw of the face region FR, the distance r1 between the center-of-gravity position of the face region FR and the center-of-gravity position of the right hand region RH, and the distance r2 between the center-of-gravity position of the face region FR and the center-of-gravity position of the left hand region LH satisfy the following formula (1).

[0065] min(r1 / fw,r2 / fw)<0.5····(1) In the above formula (1), min( ) is a function that returns the minimum value among the given arguments. That is, the cough / sneeze detection unit 132 compares the smaller value between r1 / fw and r2 / fw with 0.5.

[0066] When the cough / sneeze detection unit 132 determines that the above formula (1) is satisfied, it determines that the person in the predetermined space has coughed or sneezed. On the other hand, when the cough / sneeze detection unit 132 determines that the above formula (1) is not satisfied, it determines that the person in the predetermined space is not coughing and is not sneezing.

[0067] In addition, the cough / sneeze detection unit 132 may determine whether the area of the mouth extracted from the image is less than or equal to a threshold value.

[0068] FIG. 3 is a diagram for explaining a second method of detecting from an image that a subject has coughed or sneezed in the first embodiment.

[0069] The cough / sneeze detection unit 132 determines whether the area of the mouth of the person included in the image is less than or equal to a threshold value, and when it determines that the area is less than or equal to the threshold value, it may detect a cough or a sneeze.

[0070] First, the image processing unit 131 extracts a mouth region MR indicating the mouth of the subject from the image G2. At this time, the extracted mouth region MR is rectangular. Further, the image processing unit 131 calculates the area S(t) of the mouth region MR.

[0071] The cough / sneeze detection unit 132 determines whether the area S(t) of the mouth region MR is less than or equal to a threshold value. Specifically, the cough / sneeze detection unit 132 determines whether the area S(t) of the mouth region MR and the geometric mean value S0 of the time-series values of the area of the mouth region MR satisfy the following formula (2).

[0072] S(t) / S0 < 0.2 ····(2) When the cough / sneeze detection unit 132 determines that the above formula (2) is satisfied, it determines that a person in a predetermined space has coughed or sneezed. On the other hand, when the cough / sneeze detection unit 132 determines that the above formula (2) is not satisfied, it determines that a person in a predetermined space is not coughing and a person in a predetermined space is not sneezing.

[0073] FIG. 4 is a diagram showing an example of the time-series change of the area of the mouth of the subject or the distance between the face and hand of the subject in the first embodiment.

[0074] As shown in FIG. 4, the area S(t) of the mouth of the subject or the distance r(t) between the face and hand of the subject is below the threshold value at time t1. Therefore, the cough / sneeze detection unit 132 detects that the subject has coughed or sneezed at time t1.

[0075] Note that the detection method may be switched according to the state of the subject. For example, for a person wearing a mask, since the mouth is covered with the mask, a trained classifier may be used or detection may be performed using the distance between the hand and the face. The memory 14 may store the extracted features or the detected motion patterns, and the control signal generation unit 134 may refer to this information as necessary.

[0076] Also, when extracting the features of a person, the area of the detected mouth or the distance between the hand and the mouth changes depending on the distance between the camera 11 and the person. Therefore, the cough / sneeze detection unit 132 may calculate the area of the mouth or the distance between the hand and the mouth using a length standardized based on the horizontal width of the face or the like. By using the standardized length, the cough / sneeze detection unit 132 can determine whether a cough or sneeze has occurred without depending on the position of the camera 11 and the subject. Also, a plurality of grid patterns with known sizes and positions may be arranged in a predetermined space, and the image processing unit 131 may perform camera calibration based on the sizes and positions of the grid patterns included in the image. By performing camera calibration, the absolute position of the subject in the predetermined space can be determined more accurately.

[0077] Note that the airflow control device 1 may be provided with a plurality of cameras. Thereby, not only can a wide range be photographed without sweeping one camera, but camera calibration also becomes easier.

[0078] Also, in order to improve the detection accuracy of coughing or sneezing, the cough / sneeze detection unit 132 detects coughing or sneezing by a person in a predetermined space from an image and sound. For example, when it is determined that the volume of the sound collected by the microphone 12 is equal to or greater than a threshold value, and it is determined that the distance between the position of the face of the person included in the image photographed by the camera 11 and the position of one hand of the person included in the image is equal to or less than a threshold value, it may be detected that the subject has coughed or sneezed. When detecting coughing or sneezing using only sound without using an image, there is a possibility of false detection, but the detection accuracy of coughing or sneezing can be improved by combining the detection using an image and sound. The memory 14 may store the detection result of coughing or sneezing, and the control signal generation unit 134 may refer to this information as necessary.

[0079] Note that in the first embodiment, the cough / sneeze detection unit 132 may detect that the subject has coughed or sneezed using the sound collected by the microphone 12 without using an image.

[0080] The person state determination unit 133 recognizes the state of the mouth of the person when the person coughs or sneezes from the image acquired when coughing or sneezing by the person is detected.

[0081] The person state determination unit 133 recognizes any one of the states where the person's mouth is not covered, the state where the person's mouth is covered with a hand, the state where the person's mouth is covered with a handkerchief or clothing (e.g., the sleeve of an upper garment), and the state where the person's mouth is covered with a mask. Also, the person state determination unit 133 recognizes the direction of the person's face when the person coughs or sneezes from the image acquired when a cough or sneeze by the person is detected. Further, the person state determination unit 133 calculates the position coordinates of the person in a predetermined space from the image acquired when a cough or sneeze by the person is detected.

[0082] The person state determination unit 133 refers to the image when a cough or sneeze is detected by the cough / sneeze detection unit 132 and recognizes the state of the subject. The state of the subject's mouth area refers to any one of the states where a part of the face such as the subject's mouth area is covered with a hand when coughing or sneezing, the state where a part of the face such as the subject's mouth area is covered with a handkerchief or the sleeve of clothing, the state where the subject's face is not covered with anything, and the state where a part of the face such as the subject's mouth area is covered with a mask. The control signal generation unit 134 calculates the airflow control pattern of the airflow generator 2 based on the state of the subject.

[0083] For example, when the subject coughs or sneezes with the mouth covered with a hand, large droplets will adhere to the hand, so it hardly contributes to droplet infection or airborne infection. However, small droplets or particles with a small particle size such as droplet nuclei may leak through the gaps in the hand. However, since the pressure loss is high due to being covered with a hand, small particles stay around the subject and are gradually exhausted by indoor ventilation.

[0084] Also, when the subject coughs or sneezes while wearing a mask, most of the droplets will be collected on the mask filter. However, depending on the wearing state of the mask, there is a possibility that fine particles with a particle size of about 0.3 [μm], which are difficult to be collected by the filter, may leak through the gaps in the mask.

[0085] Therefore, when the subject coughs or sneezes with their mouth covered by their hand or wearing a mask, there is a possibility that the virus is localized around the subject. To prevent airborne infection, it is necessary to quickly disperse the localized virus. Thus, for example, since the position of the subject can be recognized by image processing, when the subject coughs or sneezes with their mouth covered by their hand or wearing a mask, the airflow generator 2 controls the wind direction so that air is sent in the direction where the subject is located. Thereby, the localized virus can be quickly dispersed. Note that the airflow generator 2 may control not only the wind direction but also the wind speed. By controlling the wind speed based on the positional relationship between the subject and the airflow generator 2, the airflow can be controlled more efficiently.

[0086] Next, when the subject coughs or sneezes with their mouth uncovered, the droplets or droplet nuclei are scattered into the air at high speed along with the cough airflow. Statistically, the initial velocity of a cough is about 10 [m / s] and it has been found to last for about 0.5 [s]. In fact, in Non-Patent Document 1 as well, 10 [m / s] is used as the initial velocity of a cough. And when the subject coughs or sneezes with their mouth uncovered, the virus scatters up to about 1 to 1.5 [m] ahead in about 5 to 10 [s], and then rapidly decelerates due to air resistance. It is difficult to disperse the droplets or droplet nuclei by airflow within 5 to 10 [s] after a cough or sneeze occurs. However, if it is 1 [m] ahead of the subject who rapidly decelerates due to air resistance, the virus will be localized around it for dozens of seconds or more after reaching 1 [m] ahead of the subject. Therefore, when the subject coughs or sneezes with their mouth uncovered, by controlling the wind direction so that air is sent about 1 to 1.5 [m] ahead from the front of the subject, the small droplets or droplet nuclei after deceleration can be dispersed.

[0087] Even if the subject coughs or sneezes with their mouth uncovered, the direction in which the droplets fly changes depending on whether the face is facing forward or downward. When the subject coughs or sneezes facing forward with their mouth uncovered, as described above, the droplets or droplet nuclei reach 1 to 1.5 [m] ahead in about 5 to 10 seconds and rapidly decelerate. Also, droplets with a larger particle size decelerate more slowly due to inertia and reach a farther distance than smaller droplets. When the subject coughs or sneezes facing downward with their mouth uncovered, the droplets or droplet nuclei will stay in the lower part of the room.

[0088] Therefore, the person state determination unit 133 determines the orientation of the subject's face. By controlling the airflow according to the orientation of the face, it is possible to efficiently prevent airborne infection. Also, in this case, when there are multiple airflow generation devices 2, by using the airflow generation device 2 closest to the subject, it is possible to more efficiently prevent airborne infection.

[0089] In this way, the position where the droplets stay differs depending on the state of the subject's mouth area and the orientation of the subject's face when the person coughs or sneezes.

[0090] The person state determination unit 133 classifies the state of the subject's mouth area into a plurality of patterns by image processing from images of the time before and after the detection of coughing or sneezing by the subject. For example, the person state determination unit 133 performs pattern classification using a learned machine learning algorithm. By using a learned machine learning algorithm, pattern classification can be performed with high accuracy.

[0091] Also, as a simple implementation method, the person state determination unit 133 may determine the state of the mouth of a person from an image processing algorithm. As the image processing algorithm, for example, a Haar-Like extractor can detect a face, a mouth, and hands, and can also detect a mask, a handkerchief, and the sleeves of an upper garment by color extraction. By using such a simple image processing algorithm, it is not necessary to perform the supervised learning process required for machine learning, so that it can be easily implemented in the system.

[0092] In this way, after the state of the target person is classified, airflow control for suppressing airborne infection is performed. At that time, the best control method varies depending on the type, number, and positional relationship of the airflow generation devices 2 provided in the room.

[0093] The device information storage unit 142 stores device information associating the type information of the airflow generation devices arranged in a predetermined space with the position information of the airflow generation devices in the predetermined space. The type information of the airflow generation device is information indicating whether the airflow generation device arranged in the predetermined space is an air conditioner having a cooling and / or heating function, an air purifier having an air purification function, or a blower having a blowing function. The position information of the airflow generation device is represented by coordinates in a predetermined space, for example. Note that it is possible to recognize how many airflow generation devices exist in a predetermined space based on the device information.

[0094] The control signal generation unit 134 generates a control signal for controlling at least one of the wind direction and the air volume of the air sent from the airflow generation device 2 that generates an airflow in a predetermined space based on the state of the mouth of the person recognized by the person state determination unit 133. Also, the control signal generation unit 134 makes the wind direction of the air sent from the airflow generation device 2 different when the face of the person is facing forward and when the face of the person is facing downward. Further, the control signal generation unit 134 generates a control signal based on the state of the mouth of the person recognized by the person state determination unit 133 and the position coordinates calculated by the person state determination unit 133.

[0095] The airflow control table storage unit 143 stores an airflow control table that associates the state of the mouth area of a person, the orientation of the person's face, and the control content of the airflow generator. The airflow control table associates the situation when the subject coughs or sneezes with the control content of the airflow generator for suppressing airborne infection in a predetermined space.

[0096] The control signal generation unit 134 acquires, from the airflow control table stored in the airflow control table storage unit 143, the control content corresponding to the state of the mouth area of the person and the orientation of the person's face recognized by the person state determination unit 133, and generates a control signal for controlling the airflow generator 2 with the acquired control content.

[0097] The control signal generation unit 134 outputs the generated control signal to the communication unit 15. The communication unit 15 transmits the control signal generated by the control signal generation unit 134 to the airflow generator 2.

[0098] In addition, in the first embodiment, the control content of the airflow generator varies depending on the type of the airflow generator and the number of airflow generators. Hereinafter, when the airflow control system includes one airflow generator and the airflow generator is an air conditioner, when the airflow control system includes one airflow generator and the airflow generator is an air purifier, and when the airflow control system includes two airflow generators and the two airflow generators are an air conditioner and an air purifier respectively, the airflow control table will be described.

[0099] FIG. 5 is a diagram showing an example of a first airflow control table when the airflow control system includes one airflow generator and the airflow generator is an air conditioner. The air conditioner is disposed on the wall surface near the ceiling in a predetermined space. Also, the air conditioner sends air downward from the horizontal direction.

[0100] First, as shown in FIG. 5, when the mouth is not covered and the face orientation is the front, the control content for controlling the wind direction so that air is sent 1 meter forward in the face orientation is associated.

[0101] That is, when coughing or sneezing is detected and a part of the face such as the mouth is not covered and the face is facing forward, the droplets generated from the subject will reach about 1 to 1.5 [m] in front of the direction the subject's face is facing in about 5 seconds. After that, the droplets with a small particle size will be subject to air resistance due to drag and will be localized around there for a while. Therefore, the airflow generating device 2 can control the wind direction so that air is sent 1 meter in front of the direction of the subject's face, thereby diffusing the localized droplets and suppressing airborne infection.

[0102] Therefore, when the mouth is not covered and the face is facing forward, the control signal generation unit 134 generates a control signal for controlling the wind direction so that air is sent 1 meter in front of the direction of the subject's face. For example, when the airflow generating device 2 is an air conditioner and the air conditioner is equipped with a louver, the airflow generating device 2 adjusts the angle of the louver so as to control the wind direction so that air is sent 1 meter in front of the direction of the subject's face. Thereby, airborne infection can be suppressed.

[0103] FIG. 6 is a diagram showing an example of the simulation result of the wind speed distribution when the air cleaner is not driven and the air conditioner is driven to generate an air current in a direction 30 degrees from the horizontal direction in a space where the air conditioner and the air cleaner are arranged. The wind speed distribution shown in FIG. 6 shows the simulation result by CFD (Computational Fluid Dynamics).

[0104] In FIG. 6, an air conditioner 201 and an air cleaner 202 are arranged in a space of about 20 tatami mats. The air conditioner 201 is sending air downward at 30 degrees from the horizontal direction. For the numerical calculation, COMSOL Multiphysics, a commercial finite element method simulation software, was used. As is clear from FIG. 6, by controlling the louver of the air conditioner 201, an air current can be generated at a necessary location in the space.

[0105] Next, as shown in FIG. 5, when the mouth is uncovered and the face is facing downward, control content for controlling the air flow direction so that air is sent downward by 90 degrees is associated.

[0106] That is, when a cough or a sneeze is detected and a part of the face such as the mouth area is uncovered and the face is facing downward, the droplets will be localized in the lower part of the room. In this case, for a normal adult or a subject with a height of at least over 150 [cm], the risk of infection by airborne infection is low. However, for a subject with a relatively low height such as a child below elementary school age or a subject with a weak resistance, the risk of infection by airborne infection becomes high. Since the air conditioner is usually installed near the ceiling of the room, the air flow direction can be controlled to be downward by 90 degrees. Therefore, the air flow generator 2 can control the air flow direction so that air is sent downward by 90 degrees from the horizontal direction, diffuse the droplets localized in the lower part of the room, and suppress airborne infection.

[0107] Therefore, when the mouth is uncovered and the face is facing downward, the control signal generation unit 134 generates a control signal for controlling the air flow direction of the air flow generator 2 to be vertically downward. For example, when the air flow generator 2 is an air conditioner and the air conditioner is equipped with a louver, the air flow generator 2 adjusts the angle of the louver so as to control the air flow direction of the air conditioner to be vertically downward. Thereby, a region with a high wind speed can be generated near the floor surface of the room, and the droplets localized in the lower part of the room can be efficiently diffused.

[0108] FIG. 7 is a diagram showing an example of a simulation result of the wind speed distribution when the air cleaner is not driven and the air conditioner is driven to generate an air flow downward by 90 degrees from the horizontal direction in a space where the air conditioner and the air cleaner are arranged. Note that the wind speed distribution shown in FIG. 7 shows the simulation result by CFD.

[0109] In Fig. 7, an air conditioner 201 and an air purifier 202 are arranged within a space of about 20 tatami mats. The air conditioner 201 is sending out air downward at 90 degrees from the horizontal direction. For numerical calculations, COMSOL Multiphysics, a commercial finite element method simulation software, was used. As is clear from Fig. 7, when air is sent vertically downward from the air conditioner 201, a region with a high wind speed can be generated at a height of about several tens of centimeters from the floor surface.

[0110] Next, as shown in Fig. 5, when the mouth is covered with a hand, control content for controlling the wind direction so that air is sent toward the subject is associated.

[0111] That is, when a cough or a sneeze is detected and the subject covers a part of the face such as the mouth area with a hand, the scattering of droplets can be suppressed, but the droplets will be localized around the subject. Therefore, the airflow generating device 2 can quickly diffuse the droplets localized near the subject by directing the wind direction toward the subject and suppress airborne infection.

[0112] Therefore, when the mouth is covered with a hand, the control signal generation unit 134 generates a control signal for controlling the wind direction so that air is sent toward the subject. For example, when the airflow generating device 2 is an air conditioner and the air conditioner is provided with a louver, the airflow generating device 2 adjusts the angle of the louver so as to control the wind direction so that air is sent toward the subject. Thereby, airborne infection can be suppressed.

[0113] Next, as shown in Fig. 5, when the mouth is covered with a handkerchief or the sleeve of an upper garment, control content for changing the operation mode to strong operation is associated.

[0114] That is, when coughing or sneezing is detected and the subject covers a part of the face such as the mouth with a handkerchief or the sleeve of an upper garment, the droplets will adhere to the handkerchief or the sleeve of the upper garment. In this case, although the scattering of droplets can be suppressed, a part of the virus adhering to the handkerchief or the sleeve of the upper garment will be dispersed into the space. Therefore, the airflow generating device 2 can homogenize the dispersed virus and suppress airborne infection by changing the operation mode to strong operation for a predetermined time.

[0115] Therefore, when the mouth is covered with a handkerchief or the sleeve of an upper garment, the control signal generation unit 134 generates a control signal for changing the operation mode to strong operation. For example, when the airflow generating device 2 is an air conditioning device, the airflow generating device 2 adjusts the wind speed to make the speed of sending out air faster, or adjusts the air volume to send out more air. Thereby, the distribution of droplets in the room can be homogenized and airborne infection can be suppressed.

[0116] Next, as shown in FIG. 5, when the mouth is covered with a mask, control content for controlling the wind direction so that air is sent toward the subject is associated.

[0117] That is, when coughing or sneezing is detected and the subject is wearing a mask, many droplets are collected on the filter of the mask, but fine particles with a particle size of about 0.3 [μm] that are difficult to be collected by the filter leak out from the mask. Or, even when the mask is not worn correctly, fine particles leak out from the gap of the mask. That is, the leaked droplets will be localized around the subject. Therefore, the airflow generating device 2 can quickly disperse the droplets localized around the subject by directing the wind direction toward the subject and suppress airborne infection.

[0118] Therefore, when the mouth is covered with a mask, the control signal generation unit 134 generates a control signal for controlling the wind direction so that air is sent toward the subject. For example, when the airflow generating device 2 is an air conditioner and the air conditioner is provided with a louver, the airflow generating device 2 adjusts the angle of the louver so as to control the wind direction so that air is sent toward the subject. Thereby, airborne infection can be suppressed.

[0119] FIG. 8 is a diagram showing an example of a second airflow control table when the airflow control system includes one airflow generating device and the airflow generating device is an air purifier. The air purifier is placed on the floor surface in the space. Further, the air purifier sends out the purified air upward from above the air purifier in a direction above the horizontal direction.

[0120] First, as shown in FIG. 8, when the mouth is not covered and the face is facing forward, the control content for controlling the wind direction so that air is sent 1 meter in front of the face direction is associated.

[0121] That is, when a cough or sneeze is detected and a part of the face such as the mouth area is not covered and the face is facing forward, the fine droplets are localized 1 to 1.5 [m] in front of the direction in which the subject's face is facing. Therefore, the airflow generating device 2 can control the wind direction so that air is sent 1 meter in front of the face direction of the subject, diffuse the localized droplets, and suppress airborne infection.

[0122] Therefore, when the mouth is not covered and the face is facing forward, the control signal generation unit 134 generates a control signal for controlling the wind direction so that air is sent 1 meter in front of the face direction of the subject. For example, when the airflow generating device 2 is an air purifier and the air purifier is provided with a louver, the airflow generating device 2 adjusts the angle of the louver so as to control the wind direction so that air is sent 1 meter in front of the face direction of the subject. Thereby, airborne infection can be suppressed.

[0123] FIG. 9 is a diagram showing an example of a simulation result of the wind speed distribution when, in a space where an air conditioner and an air purifier are arranged, the air conditioner is not driven and the air purifier is driven to generate an air flow 90 degrees upward from the horizontal direction. Further, FIG. 10 is a diagram showing an example of a simulation result of the wind speed distribution when, in a space where an air conditioner and an air purifier are arranged, the air conditioner is not driven and the air purifier is driven to generate an air flow 45 degrees upward from the horizontal direction. Note that the wind speed distributions shown in FIGS. 9 and 10 represent simulation results by CFD.

[0124] In FIGS. 9 and 10, an air conditioner 201 and an air purifier 202 are arranged in a space of about 20 tatami mats. Note that a commercial finite element method simulation software, COMSOL Multiphysics, was used for the numerical calculation. In FIG. 9, the air purifier 202 is sending out air vertically upward by controlling the louver. Further, in FIG. 10, the air purifier 202 is sending out air in a direction 45 degrees from the horizontal direction by controlling the louver. As is clear from FIGS. 9 and 10, by controlling the wind direction of the louver of the air purifier 202, an air flow can be generated at a necessary location in the space.

[0125] Next, as shown in FIG. 8, control content for changing the operation mode to strong operation is associated with the case where the mouth is not covered and the face is facing downward.

[0126] That is, when a cough or a sneeze is detected and a part of the face such as the mouth area is not covered and the face is facing downward, the droplets will be localized in a lower place in the room. The air purifier is placed on the floor in a predetermined space. Also, in many air purifiers, the control direction of the air flow by the louver is the horizontal direction or upward from the horizontal direction.

[0127] Therefore, when the mouth is uncovered, the face is facing downward, and the airflow generating device 2 is an air cleaner, the control signal generation unit 134 generates a control signal for changing the operation mode to the strong operation mode. When the airflow generating device 2 is an air cleaner, since the airflow generating device 2 cannot control the wind direction to be vertically downward, the operation mode is changed to the strong operation mode. Thereby, the airflow throughout the room can be circulated, and the diffusion of droplets can be promoted indirectly. Also, many air cleaners intake air from the lower part or the side surface of the main body. Therefore, when the operation mode is changed to the strong operation mode, more air will be taken in from the lower part or the side surface of the air cleaner, so that the droplets localized in the lower places in the room can be efficiently collected or diffused.

[0128] Next, as shown in FIG. 8, when the mouth is covered with a hand, the control content for controlling the wind direction so that air is sent toward the subject is associated. Also, as shown in FIG. 8, when the mouth is covered with a handkerchief or the sleeve of an upper garment, the control content for changing the operation mode to the strong operation mode is associated. Also, as shown in FIG. 8, when the mouth is covered with a mask, the control content for controlling the wind direction so that air is sent toward the subject is associated.

[0129] Note that the description of the control content when the subject covers a part of the face such as the mouth with a hand, a handkerchief, or the sleeve of an upper garment when a cough or a sneeze is detected, or when the subject is wearing a mask is the same as the case where the airflow control system includes one air conditioning device, so the description is omitted.

[0130] FIG. 11 is a diagram showing an example of a third airflow control table when the airflow control system includes two airflow generating devices, and the two airflow generating devices are an air conditioning device and an air cleaner, respectively. The air conditioning device is arranged on the wall surface near the ceiling in a predetermined space. Also, the air conditioning device sends out air downward from the horizontal direction. The air cleaner is placed on the floor surface in the space. Also, the air cleaner sends out the purified air upward from the upper part of the air cleaner in the horizontal direction.

[0131] In such a case, in addition to the state of the subject, the distance between the subject and the airflow generating device can be taken into account, and the best condition option of the airflow control table shown so far will be selected.

[0132] First, as shown in FIG. 11, when the mouth is not covered and the face is facing forward, the control content for controlling the wind direction is associated such that air is sent from the airflow generating device closest to the subject 1 meter forward in the direction of the face.

[0133] That is, when a cough or sneeze is detected and a part of the face such as the mouth area is not covered and the face is facing forward, the airflow generating device with the closest distance to the subject among the plurality of airflow generating devices is selected, and the wind direction is controlled by the louver or the like of the selected airflow generating device so that air is sent 1 meter forward from the front of the subject's face. By doing so, air infection can be suppressed earlier.

[0134] In this case, the control signal generation unit 134 generates a control signal based on the state of the mouth area of the recognized person and the calculated position coordinates. Also, the control signal generation unit 134 selects the airflow generating device to be controlled according to the calculated position coordinates among the plurality of airflow generating devices.

[0135] Therefore, when the mouth is not covered and the face is facing forward, the control signal generation unit 134 selects the airflow generating device closest to the subject among the plurality of airflow generating devices, and generates a control signal for controlling the wind direction so that air is sent 1 meter forward in the direction of the subject's face from the selected airflow generating device. The communication unit 15 transmits the control signal to the selected airflow generating device.

[0136] Next, as shown in FIG. 11, when the mouth is not covered and the face is facing downward, the control content for controlling the wind direction is associated such that air is sent downward 90 degrees from the airflow generating device which is an air conditioner.

[0137] That is, when a cough or a sneeze is detected and a part of the face such as the mouth is not covered and the face is facing downward, the airflow generator that is an air conditioner is selected from among the plurality of airflow generators, and the louver of the selected airflow generator is used to control the wind direction to be vertically downward. By doing so, the droplets localized in the lower part of the room can be diffused.

[0138] Therefore, when the mouth is not covered and the face is facing downward, the control signal generation unit 134 selects the airflow generator that is an air conditioner from among the plurality of airflow generators, and generates a control signal for controlling the wind direction of the selected airflow generator to be vertically downward. The communication unit 15 transmits the control signal to the selected airflow generator.

[0139] In addition, when there is no air conditioner among the plurality of airflow generators and all of the plurality of airflow generators are air purifiers, the control signal generation unit 134 may select the airflow generator closest to the subject from among the plurality of airflow generators and generate a control signal for changing the operation mode of the selected airflow generator to strong operation.

[0140] Next, as shown in FIG. 11, when the mouth is covered with a hand or when the mouth is covered with a mask, the control content for controlling the wind direction so that air is sent from the airflow generator closest to the subject toward the subject is associated.

[0141] That is, when a cough or a sneeze is detected and the subject covers a part of the face such as the mouth with a hand, or when the subject is wearing a mask, the droplets are localized around the subject. Therefore, the airflow generator closest to the subject is selected from among the plurality of airflow generators, and the louver of the selected airflow generator is used to control the wind direction so that air is sent toward the subject. By doing so, the droplets localized around the subject can be quickly diffused.

[0142] Therefore, when the mouth is covered by a hand or by a mask, the control signal generation unit 134 selects the airflow generator closest to the subject from among the plurality of airflow generators, and generates a control signal for controlling the wind direction so that air is sent from the selected airflow generator toward the subject. The communication unit 15 transmits the control signal to the selected airflow generator.

[0143] Next, as shown in FIG. 11, when the mouth is covered with a handkerchief or the sleeve of an upper garment, control content for changing the operation mode of the airflow generator closest to the subject to strong operation is associated.

[0144] That is, when a cough or a sneeze is detected and the subject covers a part of the face such as the mouth with a handkerchief or the sleeve of an upper garment, the operation mode of the airflow generator closest to the subject is changed to strong operation. By doing so, droplets can be efficiently removed.

[0145] Therefore, when the mouth is covered with a handkerchief or the sleeve of an upper garment, the control signal generation unit 134 selects the airflow generator closest to the subject from among the plurality of airflow generators, and generates a control signal for changing the operation mode of the selected airflow generator to strong operation. The communication unit 15 transmits the control signal to the selected airflow generator. For example, the airflow generator adjusts the wind speed so as to make the speed of sending air faster, or adjusts the air volume so as to send more air.

[0146] At this time, the subject may move around in the room, and the airflow generator closest to the subject may vary over time. In such a case, the control signal generation unit 134 may calculate the distance between the subject and each of the plurality of airflow generators at regular intervals, select the airflow generator closest to the subject, and change the operation mode of the selected airflow control device. By doing so, droplets can be efficiently diffused according to the movement of the subject.

[0147] Note that the first airflow control table, the second airflow control table, and the third airflow control table in the first embodiment are examples. In addition, the third airflow control table can be used not only in an airflow control system including one air conditioner and one air purifier, but also in an airflow control system including a plurality of air conditioners and an airflow control system including a plurality of air purifiers.

[0148] Subsequently, the airflow generation device 2 shown in FIG. 1 will be described.

[0149] The airflow generation device 2 generates an airflow within a predetermined space. The airflow generation device 2 is, for example, an air conditioner or an air purifier. Note that the airflow generation device 2 may be an air curtain or a DC fan provided indoors in order to generate a specific airflow pattern. By doing so, by devising the installation location of the airflow generation device 2 in advance, airflow control can be performed more easily. Note that the airflow control system may include a plurality of airflow generation devices. Thereby, more complex airflow control can be performed.

[0150] The airflow generation device 2 includes a communication unit 21, a processor 22, a memory 23, an airflow generation unit 24, and a wind direction change unit 25.

[0151] The communication unit 21 communicates with the airflow control device 1 and receives a control signal transmitted by the airflow control device 1. The control signal mainly includes an instruction to change the wind direction or the air volume of the air sent from the airflow generation device 2, but may also include an instruction to turn on the power of the airflow generation device 2 that is not powered on.

[0152] In addition, the communication unit 21 may transmit the position of the airflow generation device 2 to the airflow control device 1. By doing so, not only can the positional relationship between the target person and the airflow generation device 2 be utilized during the calculation of airflow control, but also when there are a plurality of airflow generation devices 2, by controlling the airflow generation device 2 closest to the target person, airflow control can be performed more efficiently.

[0153] The processor 22 includes an air flow control unit 221. The air flow control unit 221 controls the air flow generation unit 24 and the air flow direction change unit 25 according to the control signal received by the communication unit 21.

[0154] The memory 23 is, for example, a semiconductor memory and stores various information. When the air flow control unit 221 temporarily changes the operation mode of the air flow generation device 2, it stores the control parameters in the operation mode before the change in the memory 23. Then, when the air flow control unit 221 returns the operation mode of the air flow generation device 2 to the operation mode before the change, it reads out the control parameters before the change stored in the memory 23 and changes them to the read control parameters.

[0155] The air flow generation unit 24 is, for example, a fan motor and sends air into a predetermined space. When the air flow generation device 2 is an air conditioner, the air flow generation unit 24 may send out warm air or cold air generated by the refrigerant into a predetermined space, or may send out the taken-in air as it is. When the air flow generation device 2 is an air purifier, the air flow generation unit 24 sends out the purified air into a predetermined space.

[0156] The air flow direction change unit 25 controls the air flow generated from the air flow generation unit 24. The air flow direction change unit 25 controls the air flow direction. The air flow direction change unit 25 is, for example, a louver. The air flow direction change unit 25 changes the air flow direction of the air sent out from the air flow generation unit 24 by adjusting the direction of the louver.

[0157] Subsequently, the operation of the air flow control device 1 in the first embodiment will be described.

[0158] FIG. 12 is a first flowchart for explaining the operation of the air flow control device in the first embodiment, and FIG. 13 is a second flowchart for explaining the operation of the air flow control device in the first embodiment.

[0159] First, in step S1, the processor 13 determines whether the power of the airflow control device 1 is on. Here, if it is determined that the power of the airflow control device 1 is off (NO in step S1), the process ends.

[0160] On the other hand, if it is determined that the power of the airflow control device 1 is on (YES in step S1), in step S2, the camera 11 captures an image within a predetermined space. The camera 11 stores the captured image in the image storage unit 141. Note that the camera 11 stores a moving image in the image storage unit 141.

[0161] Next, in step S3, the image processing unit 131 acquires an image from the image storage unit 141.

[0162] Next, in step S4, the image processing unit 131 extracts the features of the subject from the image. Here, the features of the subject are, for example, the face, eyes, mouth, right hand, left hand, clothing, and mask of the subject. The image processing unit 131 also detects the centroid position of each feature.

[0163] Next, in step S5, the cough / sneeze detection unit 132 acquires audio from the microphone 12.

[0164] Next, in step S6, the cough / sneeze detection unit 132 determines whether it has detected a cough or a sneeze by the subject in a predetermined space. Here, the cough / sneeze detection unit 132 calculates a first distance between the center-of-gravity position of the face extracted from the image and the center-of-gravity position of the right hand, and calculates a second distance between the center-of-gravity position of the face extracted from the image and the center-of-gravity position of the left hand. The cough / sneeze detection unit 132 determines whether the shorter of the first distance and the second distance is less than or equal to a threshold value. When the cough / sneeze detection unit 132 determines that the shorter of the first distance and the second distance is less than or equal to the threshold value, it determines whether the volume of the sound acquired from the microphone 12 is greater than or equal to the threshold value. When the cough / sneeze detection unit 132 determines that the shorter of the first distance and the second distance is less than or equal to the threshold value and the volume of the sound is greater than or equal to the threshold value, it determines that it has detected a cough or a sneeze by the subject in the predetermined space. Also, when the cough / sneeze detection unit 132 determines that the shorter of the first distance and the second distance is greater than the threshold value, or when it determines that the volume of the sound is less than the threshold value, it determines that it has not detected a cough by the subject in the predetermined space and has not detected a sneeze by the subject in the predetermined space.

[0165] Here, when it is determined that a cough or a sneeze by the subject in the predetermined space has not been detected (NO in step S6), the process returns to step S1.

[0166] On the other hand, when it is determined that a cough or a sneeze by the subject in the predetermined space has been detected (YES in step S6), in step S7, the person state determination unit 133 acquires, from the image storage unit 141, an image at the time when a cough or a sneeze by the subject in the predetermined space has been detected.

[0167] Next, in step S8, the person state determination unit 133 recognizes the state of the mouth area of the target person when the target person coughs or sneezes. Here, the person state determination unit 133 determines, from the image at the time when a cough or sneeze by the target person in a predetermined space is detected, whether the state of the mouth area of the target person is a state where the person's mouth is not covered, a state where the person's mouth is covered with a hand, a state where the person's mouth is covered with a handkerchief, a state where the person's mouth is covered with the sleeve of an upper garment, or a state where the person's mouth is covered with a mask.

[0168] Note that the person state determination unit 133 may recognize the state of the mouth area of the target person not only from the image at the time when a cough or sneeze is detected, but also from the images of the time before and after the time when a cough or sneeze is detected.

[0169] Next, in step S9, the person state determination unit 133 recognizes the orientation of the face of the target person when the target person coughs or sneezes, from the image at the time when a cough or sneeze by the target person in a predetermined space is detected. At this time, the person state determination unit 133 determines whether the face of the target person is facing forward or downward when the target person coughs or sneezes.

[0170] Next, in step S10, the person state determination unit 133 recognizes the position of the target person in a predetermined space when the target person coughs or sneezes, from the image at the time when a cough or sneeze by the target person in a predetermined space is detected.

[0171] Next, in step S11, the control signal generation unit 134 reads out device information from the device information storage unit 142. The device information includes type information of the airflow generation device 2 existing in a predetermined space and position information of the airflow generation device 2 in the predetermined space. When a plurality of airflow generation devices exist in the predetermined space, the device information includes type information of each of the plurality of airflow generation devices 2 existing in the predetermined space and position information of each of the airflow generation devices 2 in the predetermined space.

[0172] Next, in step S12, the control signal generation unit 134 determines whether there are a plurality of airflow generation devices in a predetermined space based on the device information. Here, if it is determined that there are no plurality of airflow generation devices in the predetermined space, that is, if it is determined that there is one airflow generation device in the predetermined space (NO in step S12), in step S13, the control signal generation unit 134 determines whether the type of the airflow generation device is an air conditioner.

[0173] Here, if it is determined that the type of the airflow generation device is an air conditioner (YES in step S13), in step S14, the control signal generation unit 134 reads out from the airflow control table storage unit 143 the first airflow control table used when the airflow generation device is one air conditioner.

[0174] On the other hand, if it is determined that the type of the airflow generation device is not an air conditioner, that is, if it is determined that the type of the airflow generation device is an air purifier (NO in step S13), in step S15, the control signal generation unit 134 reads out from the airflow control table storage unit 143 the second airflow control table used when the airflow generation device is one air purifier.

[0175] Furthermore, in step S12, if it is determined that there are a plurality of airflow generation devices in the predetermined space (YES in step S12), in step S16, the control signal generation unit 134 reads out from the airflow control table storage unit 143 the third airflow control table used when the airflow generation devices are one air conditioner and one air purifier.

[0176] Next, in step S17, the control signal generation unit 134 refers to the first airflow control table, the second airflow control table, or the third airflow control table, and determines the control content corresponding to the state of the mouth of the subject recognized by the person state determination unit 133 and the direction of the face of the subject.

[0177] Next, in step S18, the control signal generation unit 134 generates a control signal according to the determined control content. For example, when the control content for controlling the wind direction is determined such that air is sent 1 meter in front of the face direction, the control signal generation unit 134 specifies the position 1 meter in front of the face direction of the subject, calculates the wind direction from the position of the airflow generation device 2 to the specified position, and generates a control signal for sending air in the calculated wind direction. Also, when the control content for controlling the wind direction is determined such that air is sent toward the subject, the control signal generation unit 134 calculates the wind direction from the position of the airflow generation device 2 to the position of the subject, and generates a control signal for sending air in the calculated wind direction.

[0178] Also, when the control content for controlling the wind direction is determined such that air is sent 90 degrees downward, the control signal generation unit 134 generates a control signal for sending air 90 degrees downward. Also, when the control content for changing the operation mode to strong operation is determined, the control signal generation unit 134 generates a control signal for changing the operation mode to strong operation.

[0179] Also, when the control content for controlling the wind direction is determined such that air is sent 1 meter in front of the face direction from the airflow generation device closest to the subject, the control signal generation unit 134 selects the airflow generation device closest to the subject from among the plurality of airflow generation devices. At this time, the control signal generation unit 134 calculates the distances between the position of the subject and each of the plurality of airflow generation devices, and selects the airflow generation device with the shortest calculated distance as the airflow generation device closest to the subject. Then, the control signal generation unit 134 specifies the position 1 meter in front of the face direction of the subject, calculates the wind direction from the position of the airflow generation device closest to the subject to the specified position, and generates a control signal for sending air in the calculated wind direction.

[0180] Also, when the control content for controlling the wind direction is determined so that air is sent from the airflow generator closest to the subject toward the subject, the control signal generation unit 134 selects the airflow generator closest to the subject from among the plurality of airflow generators. At this time, the control signal generation unit 134 calculates the distance between the position of the subject and each of the plurality of airflow generators, and selects the airflow generator with the shortest calculated distance as the airflow generator closest to the subject. Then, the control signal generation unit 134 calculates the wind direction from the position of the airflow generator closest to the subject toward the position of the subject, and generates a control signal for sending air in the calculated wind direction.

[0181] Also, when the control content for changing the operation mode of the airflow generator closest to the subject to the strong operation mode is determined, the control signal generation unit 134 selects the airflow generator closest to the subject from among the plurality of airflow generators. Then, the control signal generation unit 134 generates a control signal for changing the operation mode of the airflow generator closest to the subject to the strong operation mode.

[0182] Next, in step S19, the communication unit 15 transmits the control signal generated by the control signal generation unit 134 to the airflow generator 2. At this time, when there are a plurality of airflow generators in a predetermined space, the communication unit 15 transmits the control signal to the airflow generator selected when generating the control signal from among the plurality of airflow generators.

[0183] Note that the control signal may include a change duration indicating the time for changing the control content of the airflow generator 2. The change duration is the time for changing the control parameters of the airflow generator 2 according to the control signal. The same change duration may be used for all control contents, or a table associating the change duration with each control content may be prepared, and the change duration may be determined for each control content.

[0184] In addition, in the first embodiment, when a cough or a sneeze by a subject in a predetermined space is detected, the person state determination unit 133 recognizes from the image at that time whether the state of the subject's mouth is one of a state where the person's mouth is not covered, a state where the person's mouth is covered with a hand, a state where the person's mouth is covered with a handkerchief, a state where the person's mouth is covered with the sleeve of an upper garment, and a state where the person's mouth is covered with a mask. However, the present disclosure is not particularly limited to this. The person state determination unit 133 may recognize from the image at the time when a cough or a sneeze by a subject in a predetermined space is detected whether the state of the subject's mouth is one of a state where the person's mouth is not covered and a state where the person's mouth is covered with a hand.

[0185] Further, the person state determination unit 133 may recognize from the image at the time when a cough or a sneeze by a subject in a predetermined space is detected whether the state of the subject's mouth is one of a state where the person's mouth is not covered, a state where the person's mouth is covered with a hand, and a state where the person's mouth is covered with a mask. Furthermore, the person state determination unit 133 may recognize from the image at the time when a cough or a sneeze by a subject in a predetermined space is detected whether the state of the subject's mouth is one of a state where the person's mouth is not covered, a state where the person's mouth is covered with a hand, a state where the person's mouth is covered with a handkerchief, and a state where the person's mouth is covered with a mask.

[0186] Subsequently, the operation of the airflow generation device 2 in the first embodiment will be described.

[0187] FIG. 14 is a flowchart for explaining the operation of the airflow generation device in the first embodiment.

[0188] First, in step S21, the processor 22 determines whether the power supply of the airflow generation device 2 is on. Here, if it is determined that the power supply of the airflow generation device 2 is off (NO in step S21), the process ends.

[0189] On the other hand, when it is determined that the power supply of the air flow generating device 2 is turned on (YES in step S21), in step S22, the air flow control unit 221 determines whether a control signal has been received by the communication unit 21. Here, when it is determined that the control signal has not been received (NO in step S22), the process returns to step S21.

[0190] On the other hand, when it is determined that the control signal has been received (YES in step S22), in step S23, the air flow control unit 221 stores the current control parameters in the memory 23. Note that the control parameters include, for example, the operation mode, set temperature, wind direction, and air volume.

[0191] Next, in step S24, the air flow control unit 221 controls the air flow generated from the air flow generating unit 24 based on the control signal received by the communication unit 21. That is, the air flow control unit 221 instructs the air flow generating unit 24 to send air at the air volume indicated by the control signal, and also instructs the wind direction changing unit 25 to change to the wind direction indicated by the control signal.

[0192] Next, in step S25, the air flow control unit 221 determines whether the change duration included in the control signal has elapsed. Here, when it is determined that the change duration has not elapsed (NO in step S25), the determination process in step S25 is repeatedly executed.

[0193] On the other hand, when it is determined that the change duration has elapsed (YES in step S25), in step S26, the air flow control unit 221 reads out the control parameters stored in the memory 23.

[0194] Next, in step S27, the air flow control unit 221 changes to the read control parameters.

[0195] As described above, when a cough or a sneeze by a person is detected in a predetermined space, the state of the person's mouth when coughing or sneezing is recognized from the acquired image, and based on the recognized state of the person's mouth, a control signal for controlling at least one of the wind direction and the air volume of the air sent from an air flow generating device that generates an air flow in the predetermined space is generated. Therefore, by generating an air flow at the location where the droplets generated by the person's cough or sneeze are localized, the localized droplets can be diffused to make the concentration uniform, so that the risk of infection with an infectious disease in the predetermined space where a cough or a sneeze is detected can be reduced.

[0196] (Embodiment 2) In Embodiment 1, the air flow control device includes a camera and a microphone, and detects a cough or a sneeze by a subject based on an image and a sound. However, in Embodiment 2, the air flow control device does not include a microphone, includes a camera, and detects a cough or a sneeze by a subject based on an image without relying on sound.

[0197] FIG. 15 is a diagram showing the configuration of an air flow control system according to Embodiment 2 of the present disclosure. The air flow control system shown in FIG. 15 includes an air flow control device 1A and an air flow generating device 2. In this Embodiment 2, the same components as those in Embodiment 1 are denoted by the same reference numerals, and detailed descriptions thereof are omitted.

[0198] The air flow control device 1A controls the air flow within a predetermined space. The air flow control device 1A is disposed on a wall or a ceiling within the predetermined space. The air flow control device 1A is communicably connected to the air flow generating device 2 via a network.

[0199] The air flow control device 1A includes a camera 11, a processor 13A, a memory 14, and a communication unit 15.

[0200] The processor 13A includes an image processing unit 131, a cough / sneeze detection unit 132A, a person state determination unit 133, and a control signal generation unit 134. The memory 14 is, for example, a semiconductor memory, and includes an image storage unit 141, a device information storage unit 142, and an airflow control table storage unit 143.

[0201] The cough / sneeze detection unit 132A detects a cough or a sneeze by a person in a predetermined space. In the second embodiment, the cough / sneeze detection unit 132A detects at least one of a cough or a sneeze by a person in a predetermined space based on an image, not based on sound. Note that the method for detecting at least one of a cough or a sneeze by a person in a predetermined space from an image is the same as that in the first embodiment.

[0202] That is, the cough / sneeze detection unit 132A determines whether the distance between the position of the face of the person included in the image and the position of one hand of the person included in the image is less than or equal to a threshold value. When it is determined that the distance is less than or equal to the threshold value, at least one of a cough or a sneeze is detected. More specifically, the cough / sneeze detection unit 132A calculates a first distance between the center-of-gravity position of the face extracted from the image and the center-of-gravity position of the right hand, and calculates a second distance between the center-of-gravity position of the face extracted from the image and the center-of-gravity position of the left hand. The cough / sneeze detection unit 132A determines whether the shorter of the first distance and the second distance is less than or equal to the threshold value. When the cough / sneeze detection unit 132A determines that the shorter of the first distance and the second distance is less than or equal to the threshold value, it determines that a cough or a sneeze by the subject in the predetermined space has been detected. Also, when the cough / sneeze detection unit 132A determines that the shorter of the first distance and the second distance is longer than the threshold value, it determines that no cough by the subject in the predetermined space has been detected and no sneeze by the subject in the predetermined space has been detected.

[0203] Note that the cough / sneeze detection unit 132A may determine whether the area of the mouth of the person included in the image is less than or equal to a threshold value, and when it is determined that the area is less than or equal to the threshold value, detect a cough or a sneeze.

[0204] Next, the operation of the airflow control device 1A in the second embodiment will be described.

[0205] FIG. 16 is a first flowchart for explaining the operation of the airflow control device in the second embodiment, and FIG. 17 is a second flowchart for explaining the operation of the airflow control device in the second embodiment.

[0206] Since the processes of steps S31 to S34 shown in FIG. 16 are the same as the processes of steps S1 to S4 shown in FIG. 12, detailed description thereof will be omitted.

[0207] Next, in step S35, the cough / sneeze detection unit 132A determines whether or not it has detected a cough or a sneeze by a subject in a predetermined space. Here, the cough / sneeze detection unit 132A calculates a first distance between the center-of-gravity position of the face extracted from the image and the center-of-gravity position of the right hand, and calculates a second distance between the center-of-gravity position of the face extracted from the image and the center-of-gravity position of the left hand. The cough / sneeze detection unit 132A determines whether or not the shorter of the first distance and the second distance is less than or equal to a threshold value. When the cough / sneeze detection unit 132A determines that the shorter of the first distance and the second distance is less than or equal to the threshold value, it determines that it has detected a cough or a sneeze by a subject in a predetermined space. Also, when the cough / sneeze detection unit 132A determines that the shorter of the first distance and the second distance is longer than the threshold value, it determines that it has not detected a cough by a subject in a predetermined space and has not detected a sneeze by a subject in a predetermined space.

[0208] Here, when it is determined that it has not detected a cough by a subject in a predetermined space and has not detected a sneeze by a subject in a predetermined space (NO in step S35), the process returns to step S31.

[0209] On the other hand, when it is determined that a cough or a sneeze by a person in a predetermined space has been detected (YES in step S35), in step S36, the person state determination unit 133 acquires an image at the time when a cough or a sneeze by a person in the predetermined space has been detected from the image storage unit 141.

[0210] Since the processes of steps S37 to S48 shown in FIG. 17 are the same as the processes of steps S8 to S19 shown in FIG. 13, detailed descriptions thereof are omitted.

[0211] In this way, by using an image from the camera 11 that photographs a predetermined space, it is possible to detect that a person in the predetermined space has coughed or sneezed. As a result, the configuration of the airflow control device 1A can be further simplified, and the cost of the airflow control device 1A can be suppressed.

[0212] (Embodiment 3) In Embodiment 1, the airflow control device includes a camera and a microphone. However, in Embodiment 3, the airflow control device does not include a camera and a microphone, and is communicably connected to the camera and the microphone.

[0213] FIG. 18 is a diagram showing the configuration of an airflow control system according to Embodiment 3 of the present disclosure. The airflow control system shown in FIG. 18 includes an airflow control device 1B, an airflow generation device 2, a camera 3, and a microphone 4. In this Embodiment 3, the same components as those in Embodiment 1 are denoted by the same reference numerals, and detailed descriptions thereof are omitted.

[0214] The microphone 4 is installed in a predetermined space. The microphone 4 is communicably connected to the camera 3 via a network. The microphone 4 includes a sound collection unit 41, a processor 42, and a communication unit 43.

[0215] The sound collection unit 41 collects sound in a predetermined space and outputs the collected sound to the processor 42.

[0216] The processor 42 includes a cough / sneeze detection unit 421. The cough / sneeze detection unit 421 detects a cough or a sneeze by a person within a predetermined space. The cough / sneeze detection unit 421 detects that a person has coughed or sneezed in the indoor space. The cough / sneeze detection unit 421 uses the sound collected by the microphone 4 to detect a cough or a sneeze by a person within a predetermined space.

[0217] For example, the cough / sneeze detection unit 421 determines whether the volume of the sound collected by the sound collection unit 41 is equal to or greater than a threshold value. When the cough / sneeze detection unit 421 determines that the volume of the sound collected by the sound collection unit 41 is equal to or greater than the threshold value, it determines that at least one of a cough and a sneeze has been performed by a person within a predetermined space. As the threshold value, for example, 70 dB may be used.

[0218] Further, the cough / sneeze detection unit 421 may perform spectral analysis of the sound collected by the sound collection unit 41 and detect a cough or a sneeze by an algorithm such as machine learning based on the analysis result. In this case, since detection can be performed using a spectral pattern peculiar to a cough or a sneeze, the detection accuracy is improved.

[0219] When the cough / sneeze detection unit 421 detects a cough or a sneeze by a person within a predetermined space, the communication unit 43 transmits a cough / sneeze detection signal indicating that a cough or a sneeze by a person within a predetermined space has been detected to the camera 3.

[0220] The camera 3 is installed on the ceiling or wall within a predetermined space. The camera 3 is communicably connected to the airflow control device 1B, the microphone 4, and each other via a network. The camera 3 includes a photographing unit 31, a processor 32, a memory 33, and a communication unit 34.

[0221] The photographing unit 31 is, for example, an imaging device, photographs within a predetermined space, and outputs the photographed image to the memory 33.

[0222] The processor 32 includes an image processing unit 321, a cough / sneeze determination unit 322, and a person state determination unit 323.

[0223] The memory 33 is, for example, a semiconductor memory and includes an image storage unit 331. The image storage unit 331 stores the image captured by the imaging unit 31. The imaging unit 31 stores the image captured within a predetermined space in the image storage unit 331.

[0224] The image processing unit 321 acquires the image captured within a predetermined space from the image storage unit 141. The image processing unit 131 performs image processing on the acquired image and extracts human features such as the face, nose, mouth, hands, clothing, presence or absence of a mask, and the position of the person indoors. Note that the image processing unit 321 may use machine learning or deep learning for feature extraction, or may use a widely known feature extractor such as a Haar-Like extractor for face detection.

[0225] Note that the function of the image processing unit 321 is the same as the function of the image processing unit 131 in Embodiment 1.

[0226] The communication unit 34 receives the cough / sneeze detection signal transmitted by the microphone 4.

[0227] When the cough / sneeze determination unit 322 receives the cough / sneeze detection signal by the communication unit 34, it determines that a cough or sneeze by a person has been detected within a predetermined space.

[0228] When a cough or sneeze by a person is detected, the person state determination unit 323 recognizes the state of the person's mouth when the person coughs or sneezes from the image acquired at that time.

[0229] When the person state determination unit 323 detects a cough or a sneeze, it recognizes the state of the mouth area of the subject from the images of the time before and after that point. The state of the mouth area of a person can be classified into a plurality of patterns. For example, the state of the mouth area of a person includes a state where the person's mouth is not covered, a state where the person's mouth is covered with a hand, a state where the person's mouth is covered with a handkerchief, a state where the person's mouth is covered with the sleeve of a coat, and a state where the person's mouth is covered with a mask.

[0230] The person state determination unit 323 recognizes any one of a state where the person's mouth is not covered, a state where the person's mouth is covered with a hand, a state where the person's mouth is covered with a handkerchief, a state where the person's mouth is covered with the sleeve of a coat, and a state where the person's mouth is covered with a mask.

[0231] In addition, when the person state determination unit 323 detects a cough or a sneeze by a person, it recognizes the direction of the person's face when the person coughs or sneezes from the image acquired at that time.

[0232] In addition, when the person state determination unit 323 detects a cough or a sneeze by a person, it recognizes the position of the person within a predetermined space when the person coughs or sneezes from the image acquired at that time.

[0233] Note that the function of the person state determination unit 323 is the same as the function of the person state determination unit 133 in Embodiment 1.

[0234] The communication unit 34 transmits state information indicating the state of the mouth area of the person, the direction of the person's face, and the position of the person within a predetermined space, which are recognized by the person state determination unit 323, to the airflow control device 1B.

[0235] The airflow control device 1B controls the airflow within a predetermined space. The place where the airflow control device 1B is arranged is not particularly limited. The airflow control device 1B may be, for example, a server. The airflow control device 1B is communicably connected to the airflow generator 2 and the camera 3 via a network.

[0236] The airflow control device 1B includes a processor 13B, a memory 14B, and a communication unit 15B.

[0237] The processor 13B includes a control signal generation unit 134. The memory 14B is, for example, a semiconductor memory and includes a device information storage unit 142 and an airflow control table storage unit 143.

[0238] The communication unit 15B receives the status information transmitted by the camera 3. The communication unit 15B transmits a control signal to the airflow generation device 2.

[0239] The control signal generation unit 134 generates a control signal for controlling at least one of the wind direction and the air volume of the air sent from the airflow generation device 2 that generates an airflow within a predetermined space based on the state of the mouth of the person included in the status information received by the communication unit 15B. Also, the control signal generation unit 134 makes the wind direction of the air sent from the airflow generation device 2 different when the person's face is facing forward and when the person's face is facing downward. Further, the control signal generation unit 134 generates a control signal based on the state of the mouth of the person included in the status information received by the communication unit 15B and the position coordinates included in the status information received by the communication unit 15B.

[0240] Also, the control signal generation unit 134 acquires the control content corresponding to the state of the mouth of the person and the orientation of the person's face included in the status information received by the communication unit 15B from the airflow control table stored in the airflow control table storage unit 143, and generates a control signal for controlling the airflow generation device 2 with the acquired control content.

[0241] The control signal generation unit 134 outputs the generated control signal to the communication unit 15B. The communication unit 15B transmits the control signal generated by the control signal generation unit 134 to the airflow generation device 2.

[0242] Subsequently, the operations of the airflow control device 1B and the camera 3 in the third embodiment will be described.

[0243] FIG. 19 is a flowchart for explaining the operation of the camera in the third embodiment.

[0244] First, in step S51, the processor 32 determines whether the power of the camera 3 is on. Here, if it is determined that the power of the camera 3 is off (NO in step S51), the process ends.

[0245] On the other hand, if it is determined that the power of the camera 3 is on (YES in step S51), in step S52, the imaging unit 31 captures an image within a predetermined space. The imaging unit 31 stores the captured image in the image storage unit 331. Note that the imaging unit 31 stores a moving image in the image storage unit 331.

[0246] Next, in step S53, the cough / sneeze determination unit 322 determines whether a cough / sneeze detection signal has been received by the communication unit 34. The cough / sneeze detection signal is transmitted by the microphone 4. Here, if it is determined that the cough / sneeze detection signal has not been received (NO in step S53), the process returns to step S51.

[0247] On the other hand, if it is determined that the cough / sneeze detection signal has been received (YES in step S53), in step S54, the person state determination unit 323 acquires, from the image storage unit 331, an image at the time when a cough or sneeze by the target person in the predetermined space is detected. Note that the cough / sneeze detection signal includes the time when a cough or sneeze by a person in the predetermined space is detected. Also, the image includes the time when it was captured. The person state determination unit 323 acquires, from the image storage unit 331, the image captured at the time included in the cough / sneeze detection signal.

[0248] Next, in step S55, the person state determination unit 323 recognizes the state of the target person's mouth when the target person coughs or sneezes. Note that the process of step S55 shown in FIG. 19 is the same as the process of step S8 shown in FIG. 13.

[0249] Next, in step S56, when a cough or a sneeze by a target person in a predetermined space is detected, the person state determination unit 323 recognizes the direction of the face of the target person when the target person coughs or sneezes from the image at that time. Note that the process of step S56 shown in FIG. 19 is the same as the process of step S9 shown in FIG. 13.

[0250] Next, in step S57, when a cough or a sneeze by a target person in a predetermined space is detected, the person state determination unit 323 recognizes the position of the target person in the predetermined space when the target person coughs or sneezes from the image at that time. Note that the process of step S57 shown in FIG. 19 is the same as the process of step S10 shown in FIG. 13.

[0251] Next, in step S58, the communication unit 34 transmits state information indicating the state of the mouth area of the target person, the direction of the face of the target person, and the position of the target person in a predetermined space, which are recognized by the person state determination unit 323, to the airflow control device 1B.

[0252] FIG. 20 is a flowchart for explaining the operation of the airflow control device according to the third embodiment.

[0253] First, in step S71, the processor 13B determines whether the power supply of the airflow control device 1B is on. Here, if it is determined that the power supply of the airflow control device 1B is off (NO in step S71), the process ends.

[0254] On the other hand, if it is determined that the power supply of the airflow control device 1B is on (YES in step S71), in step S72, the control signal generation unit 134 determines whether state information has been received by the communication unit 15B. The state information is transmitted by the camera 3. Here, if it is determined that the state information has not been received (NO in step S72), the process returns to step S71.

[0255] On the other hand, when it is determined that the status information has been received (YES in step S72), in step S73, the control signal generation unit 134 reads out the device information from the device information storage unit 142.

[0256] Note that the processes of steps S74 to S81 shown in FIG. 20 are the same as the processes of steps S12 to S19 shown in FIG. 13.

[0257] In this way, the microphone 4 detects that a person in a predetermined space has coughed or sneezed, the camera 3 recognizes the state of the mouth, the face orientation, and the position in the predetermined space of the subject when the subject coughs or sneezes, and the airflow control device 1B generates a control signal for controlling the airflow in the predetermined space. Therefore, the configuration of the airflow control device 1B can be further simplified, and the processing load of the airflow control device 1B can be suppressed.

[0258] Note that in the third embodiment, the cough / sneeze determination unit 322 determines that a cough or sneeze by a person in a predetermined space has been detected when the cough / sneeze detection signal is received by the communication unit 34. However, the present disclosure is not particularly limited thereto. The cough / sneeze determination unit 322 may determine whether a cough or sneeze by a person in a predetermined space has been detected from the image and the cough / sneeze detection signal. For example, when the cough / sneeze determination unit 322 receives the cough / sneeze detection signal by the communication unit 34 and determines that the distance between the position of the face of the person included in the image taken by the imaging unit 31 and the position of one hand of the person included in the image is equal to or less than the threshold value, it may be determined that the subject has coughed or sneezed.

[0259] (Embodiment 4) In the third embodiment, the airflow control system includes a microphone and detects a cough or sneeze by the subject based on sound. However, in the fourth embodiment, the airflow control system does not include a microphone and detects a cough or sneeze by the subject based on an image.

[0260] FIG. 21 is a diagram showing the configuration of the airflow control system according to Embodiment 4 of the present disclosure. The airflow control system shown in FIG. 21 includes an airflow control device 1B, an airflow generation device 2, and a camera 3A. In Embodiment 4, the same components as those in Embodiment 3 are denoted by the same reference numerals, and detailed descriptions thereof are omitted.

[0261] The camera 3A is installed on the ceiling or wall within a predetermined space. The camera 3A is communicably connected to the airflow control device 1B via a network. The camera 3A includes a photographing unit 31, a processor 32A, a memory 33, and a communication unit 34A.

[0262] The processor 32A includes an image processing unit 321, a person state determination unit 323, and a cough / sneeze detection unit 324.

[0263] The cough / sneeze detection unit 324 detects a cough or a sneeze by a person in a predetermined space. In Embodiment 4, the cough / sneeze detection unit 324 detects a cough or a sneeze by a person in a predetermined space based on an image. Note that the method of detecting a cough or a sneeze by a person in a predetermined space from an image is the same as that in Embodiment 1.

[0264] That is, the cough / sneeze detection unit 324 determines whether the distance between the position of the face of the person included in the image and the position of one hand of the person included in the image is equal to or less than a threshold value. When it is determined that the distance is equal to or less than the threshold value, a cough or a sneeze is detected. More specifically, the cough / sneeze detection unit 324 calculates a first distance between the center-of-gravity position of the face extracted from the image and the center-of-gravity position of the right hand, and calculates a second distance between the center-of-gravity position of the face extracted from the image and the center-of-gravity position of the left hand. The cough / sneeze detection unit 324 determines whether the shorter of the first distance and the second distance is equal to or less than the threshold value. When the cough / sneeze detection unit 324 determines that the shorter of the first distance and the second distance is equal to or less than the threshold value, it determines that a cough or a sneeze by the subject in a predetermined space has been detected. Further, when the cough / sneeze detection unit 324 determines that the shorter of the first distance and the second distance is longer than the threshold value, it determines that no cough by the subject in the predetermined space has been detected and no sneeze by the subject in the predetermined space has been detected.

[0265] Note that the cough / sneeze detection unit 324 may determine whether the area of the mouth of the person included in the image is equal to or less than a threshold value, and when it is determined that the area is equal to or less than the threshold value, a cough or a sneeze may be detected.

[0266] The communication unit 34A transmits state information indicating the state of the mouth area of the person recognized by the person state determination unit 323, the orientation of the face of the person, and the position of the person in a predetermined space to the airflow control device 1B.

[0267] Subsequently, the operation of the camera 3A in the fourth embodiment will be described.

[0268] FIG. 22 is a flowchart for explaining the operation of the camera in the fourth embodiment.

[0269] First, in step S91, the processor 32A determines whether the power of the camera 3A is on. Here, when it is determined that the power of the camera 3A is off (NO in step S91), the process ends.

[0270] On the other hand, when it is determined that the power of the camera 3A is turned on (YES in step S91), in step S92, the imaging unit 31 captures an image within a predetermined space. The imaging unit 31 stores the captured image in the image storage unit 331. Note that the imaging unit 31 stores a moving image in the image storage unit 331.

[0271] Next, in step S93, the image processing unit 321 acquires an image from the image storage unit 331.

[0272] Next, in step S94, the image processing unit 321 extracts the features of the subject from the image. Here, the features of the subject are, for example, the face, eyes, mouth, right hand, left hand, clothing, and mask of the subject. The image processing unit 321 also detects the centroid position of each feature.

[0273] Next, in step S95, the cough / sneeze detection unit 324 determines whether a cough or sneeze by the subject in the predetermined space is detected. Here, the cough / sneeze detection unit 324 calculates a first distance between the centroid position of the face extracted from the image and the centroid position of the right hand, and calculates a second distance between the centroid position of the face extracted from the image and the centroid position of the left hand. The cough / sneeze detection unit 324 determines whether the shorter of the first distance and the second distance is less than or equal to a threshold value. When the cough / sneeze detection unit 324 determines that the shorter of the first distance and the second distance is less than or equal to the threshold value, it determines that a cough or sneeze by the subject in the predetermined space is detected. Also, when the cough / sneeze detection unit 324 determines that the shorter of the first distance and the second distance is longer than the threshold value, it determines that no cough by the subject in the predetermined space is detected and no sneeze by the subject in the predetermined space is detected.

[0274] Here, when it is determined that no cough or sneeze by the subject in the predetermined space is detected (NO in step S95), the process returns to step S91.

[0275] On the other hand, when it is determined that a cough or a sneeze by a person in a predetermined space has been detected (YES in step S95), in step S96, the person state determination unit 323 acquires, from the image storage unit 331, an image at the time when a cough or a sneeze by a person in the predetermined space has been detected.

[0276] Since the processes of steps S97 to S100 shown in FIG. 22 are the same as the processes of steps S55 to S58 shown in FIG. 19, detailed description thereof will be omitted.

[0277] In this way, it is detected by the camera 3A that a person in a predetermined space has coughed or sneezed, and the state of the mouth area, the face orientation, and the position in the predetermined space of the person when the person has coughed or sneezed are recognized. A control signal for controlling the air flow in the predetermined space is generated by the air flow control device 1B. As a result, the configuration of the air flow control system can be further simplified, and the cost of the air flow control system can be suppressed.

[0278] (Infection risk assessment system) The present disclosure includes an infection risk assessment system described below. In the description of the infection risk assessment system, the same components as those of the air flow control system described above are denoted by the same reference numerals, and detailed description thereof will be omitted.

[0279] FIG. 23 is a diagram showing the configuration of the infection risk assessment system of the present disclosure. The infection risk assessment system shown in FIG. 23 is an example of an information processing system, and includes an infection risk assessment device 1C and a terminal device 5.

[0280] The infection risk assessment device 1C is an example of an information processing device, and assesses the risk of infection (infection risk) with an infectious disease. The infection risk assessment device 1C is arranged on a wall or a ceiling in a predetermined space.

[0281] The infection risk assessment device 1C is communicably connected to the terminal device 5 via a network.

[0282] The terminal device 5 is, for example, a personal computer, a smartphone, or a tablet computer. The terminal device 5 is used, for example, by the administrator or staff of the facility where the subject person is located.

[0283] The infection risk assessment device 1C includes a camera 11, a microphone 12, a processor 13, a memory 14, and a communication unit 15. When detecting a cough or a sneeze based on an image without relying on sound, the infection risk assessment device 1C may not include a microphone.

[0284] The infection risk assessment device 1C does not determine whether the subject person is infected with an infectious disease, and treats a subject person who has coughed or sneezed as an infected person.

[0285] The camera 11 and the microphone 12 may be provided inside the infection risk assessment device 1C, or may be provided outside the infection risk assessment device 1C. When the camera 11 and the microphone 12 are provided outside the infection risk assessment device 1C, the infection risk assessment device 1C is communicably connected to the camera 11 and the microphone 12 by wire or wirelessly.

[0286] The processor 13 includes an image processing unit 131, a cough / sneeze detection unit 132, a person status determination unit 133, an infection risk assessment unit 135, and an assessment result notification unit 136. The memory 14 is, for example, a semiconductor memory, and includes an image storage unit 141 and an infection risk assessment table storage unit 144.

[0287] The infection risk assessment device 1C may include a plurality of cameras. Thereby, not only can a wide range be photographed without sweeping one camera, but also camera calibration becomes easier.

[0288] When a person coughs or sneezes, they reflexively perform various actions. For example, a person may cough or sneeze with their hand covering a part of their face such as the nose and mouth, cough or sneeze with nothing covering their mouth, cough or sneeze with a handkerchief covering a part of their face such as the nose and mouth, cough or sneeze with a part of their face such as the nose and mouth covered by the sleeve of their upper garment, or cough or sneeze with a mask covering their mouth. It is considered that the subsequent infection risk in the space varies depending on the state of the subject when coughing or sneezing. For example, when coughing or sneezing with nothing covering the mouth, droplets or droplet nuclei fly several meters in front of the subject. That is, when coughing or sneezing with nothing covering the mouth, the infection risk in the subsequent space becomes extremely high due to droplet infection or airborne infection. Also, after the droplets or droplet nuclei scatter into the space, it is considered that they may adhere or deposit on surrounding furniture, etc., and the infection risk due to contact infection is not low either.

[0289] Next, when coughing or sneezing with the nose and mouth covered by the hand, mainly the virus will adhere to the hand. If a person touches a surrounding person or object with the hand to which the virus has adhered, the person who is touched may be infected with the virus, or a person who further touches the object that has been touched may be infected with the virus. Therefore, when coughing or sneezing with the mouth covered by the hand, the infection risk due to contact infection becomes high. Also, the initial velocity at the time of coughing or sneezing is generally 10 [m / s] or more, that is, the virus scatters at high speed. Therefore, even when the mouth is covered by the hand, if there is a gap in the hand, droplets or droplet nuclei will leak out from that gap. Therefore, when coughing or sneezing with the mouth covered by the hand, the infection risks due to airborne infection and droplet infection are not low either.

[0290] Furthermore, when coughing or sneezing with the mouth covered by a handkerchief or the sleeve of an outer garment, the probability of the virus adhering to the hand is considerably lower and gaps are less likely to form compared to covering the mouth with the hand. Therefore, the risk of infection when covering the mouth with a handkerchief or the sleeve of an outer garment is lower than when covering the mouth with the hand. However, when covering the mouth with the sleeve of an outer garment, the virus adhering to the sleeve may re-disperse over time as a result of the subject's movements. Therefore, it can be said that the risk of airborne infection when covering the mouth with the sleeve of an outer garment is higher than when covering the mouth with a handkerchief.

[0291] Also, when coughing or sneezing with the mouth covered by a mask, if the mask is worn correctly, most droplets or droplet nuclei will be trapped by the mask filter. Therefore, it can be said that the risk of infection when covering the mouth with a mask is low.

[0292] Also, a person may cough or sneeze with their face down. In this way, when coughing or sneezing with the face down, the droplets or droplet nuclei will spread downward in the space, so the risk of droplet infection generally decreases.

[0293] Thus, the risk of contracting an infectious disease varies depending on the state of the subject's mouth when coughing or sneezing. Also, which route of infection has a high risk of infection also varies depending on the state of the subject's mouth.

[0294] The person state determination unit 133 recognizes the state of the subject's mouth from images of the time before and after the detection of coughing or sneezing. The state of the subject's mouth can be classified into a plurality of patterns. For example, the state of the subject's mouth includes a state where the subject's mouth is not covered, a state where the subject's mouth is covered with the hand, a state where the subject's mouth is covered with a handkerchief, a state where the subject's mouth is covered with clothing (e.g., the sleeve of an outer garment), and a state where the subject's mouth is covered with a mask.

[0295] The human state determination unit 133 recognizes any one of the states where the person's mouth is uncovered, the state where the person's mouth is covered with a hand, the state where the person's mouth is covered with a handkerchief, the state where the person's mouth is covered with clothing (e.g., the sleeve of an upper garment), and the state where the person's mouth is covered with a mask.

[0296] The infection risk evaluation table storage unit 144 stores an infection risk evaluation table that associates the state of the area around the person's mouth with an evaluation value obtained by quantifying the risk of contracting an infectious disease through each of droplet infection, contact infection, and airborne infection.

[0297] FIG. 24 is a diagram showing an example of the infection risk evaluation table stored in the infection risk evaluation table storage unit 144.

[0298] As shown in FIG. 24, for the state where the mouth is uncovered, an evaluation value indicating the risk of contracting an infectious disease through droplet infection is associated with "3", an evaluation value indicating the risk of contracting an infectious disease through contact infection is associated with "2", and an evaluation value indicating the risk of contracting an infectious disease through airborne infection is associated with "3". Note that the evaluation values are represented by numerical values from "1" to "3", and the larger the numerical value, the higher the risk of infection.

[0299] Also, for the state where the mouth is covered with a hand, an evaluation value indicating the risk of contracting an infectious disease through droplet infection is associated with "2", an evaluation value indicating the risk of contracting an infectious disease through contact infection is associated with "3", and an evaluation value indicating the risk of contracting an infectious disease through airborne infection is associated with "2".

[0300] Also, for the state where the mouth is covered with a handkerchief, an evaluation value indicating the risk of contracting an infectious disease through droplet infection is associated with "1", an evaluation value indicating the risk of contracting an infectious disease through contact infection is associated with "1", and an evaluation value indicating the risk of contracting an infectious disease through airborne infection is associated with "1".

[0301] In addition, for the state where the mouth is covered by the sleeve of the upper garment, an evaluation value indicating the risk of contracting an infectious disease through droplet infection is associated with "1", an evaluation value indicating the risk of contracting an infectious disease through contact infection is associated with "1", and an evaluation value indicating the risk of contracting an infectious disease through airborne infection is associated with "2".

[0302] In addition, for the state where the mouth is covered by a mask, an evaluation value indicating the risk of contracting an infectious disease through droplet infection is associated with "1", an evaluation value indicating the risk of contracting an infectious disease through contact infection is associated with "1", and an evaluation value indicating the risk of contracting an infectious disease through airborne infection is associated with "1".

[0303] The infection risk evaluation unit 135 evaluates the risk of contracting an infectious disease in a predetermined space based on the state of the mouth of the person recognized by the person state determination unit 133. The infection risk evaluation unit 135 evaluates the risk of contracting an infectious disease through each of droplet infection, contact infection, and airborne infection. The infection risk evaluation unit 135 extracts, from the infection risk evaluation table, the evaluation values corresponding to the state of the mouth of the person recognized by the person state determination unit 133 for each of droplet infection, contact infection, and airborne infection, and accumulates each of the extracted evaluation values within a predetermined time.

[0304] The evaluation result notification unit 136 outputs the evaluation result by the infection risk evaluation unit 135 to the communication unit 15. When the cumulative value is equal to or greater than the threshold value, the evaluation result notification unit 136 outputs to the communication unit 15 an evaluation result indicating that the risk of contracting an infectious disease in a predetermined space is high.

[0305] The communication unit 15 transmits to the terminal device 5 an evaluation result indicating that the risk of contracting an infectious disease in a predetermined space is high.

[0306] The terminal device 5 receives the evaluation result transmitted by the communication unit 15. The terminal device 5 displays the received evaluation result.

[0307] Next, the operation of the infection risk assessment device 1C in this embodiment will be described.

[0308] FIG. 25 is a first flowchart for explaining the operation of the infection risk assessment device, and FIG. 26 is a second flowchart for explaining the operation of the infection risk assessment device in this embodiment.

[0309] First, in step S101, the processor 13 determines whether the power of the infection risk assessment device 1C is on. Here, if it is determined that the power of the infection risk assessment device 1C is off (NO in step S101), the process ends.

[0310] On the other hand, if it is determined that the power of the infection risk assessment device 1C is on (YES in step S101), in step S102, the camera 11 captures an image within a predetermined space. The camera 11 stores the captured image in the image storage unit 141. Note that the camera 11 stores a moving image in the image storage unit 141.

[0311] Next, in step S103, the processor 13 determines whether a predetermined time has elapsed. Here, the predetermined time is, for example, 30 minutes. In this embodiment, it is determined whether to notify the evaluation result of the risk of contracting an infectious disease at predetermined time intervals. Note that if the evaluation results are notified frequently, for example, at one-minute intervals, the person being notified may feel bothered, so it is preferable to notify at, for example, 30-minute intervals. Thereby, the risk of contracting an infectious disease within a predetermined space within a predetermined time can be evaluated. Note that the predetermined time may be settable by, for example, an administrator.

[0312] Here, if it is determined that the predetermined time has not elapsed (NO in step S103), in step S104, the image processing unit 131 acquires an image from the image storage unit 141.

[0313] Next, in step S105, the image processing unit 131 extracts the features of the subject from the image. Here, the features of the subject are, for example, the face, eyes, mouth, right hand, left hand, clothing, and mask of the subject. Also, the image processing unit 131 detects the centroid position of each feature.

[0314] Next, in step S106, the cough / sneeze detection unit 132 acquires the sound from the microphone 12.

[0315] Next, in step S107, the cough / sneeze detection unit 132 determines whether a cough or a sneeze by the subject in a predetermined space has been detected. Here, the cough / sneeze detection unit 132 calculates a first distance between the centroid position of the face extracted from the image and the centroid position of the right hand, and calculates a second distance between the centroid position of the face extracted from the image and the centroid position of the left hand. The cough / sneeze detection unit 132 determines whether the shorter of the first distance and the second distance is less than or equal to a threshold value. When the cough / sneeze detection unit 132 determines that the shorter of the first distance and the second distance is less than or equal to the threshold value, the cough / sneeze detection unit 132 determines whether the volume of the sound acquired from the microphone 12 is greater than or equal to the threshold value. When the cough / sneeze detection unit 132 determines that the shorter of the first distance and the second distance is less than or equal to the threshold value and the volume of the sound is greater than or equal to the threshold value, the cough / sneeze detection unit 132 determines that a cough or a sneeze by the subject in the predetermined space has been detected. Also, when the cough / sneeze detection unit 132 determines that the shorter of the first distance and the second distance is longer than the threshold value, or when the cough / sneeze detection unit 132 determines that the volume of the sound information is smaller than the threshold value, the cough / sneeze detection unit 132 determines that no cough by the subject in the predetermined space has been detected and no sneeze by the subject in the predetermined space has been detected.

[0316] Here, when it is determined that no cough or sneeze by the subject in the predetermined space has been detected (NO in step S107), the process returns to step S101.

[0317] When it is determined that a cough or a sneeze by a target person in a predetermined space has been detected (YES in step S107), in step S108, the person state determination unit 133 acquires an image at the time when a cough or a sneeze by the target person in the predetermined space has been detected from the image storage unit 141.

[0318] Next, in step S109, the person state determination unit 133 recognizes the state of the mouth of the target person when the target person coughs or sneezes. Here, the person state determination unit 133 recognizes from the image at the time when a cough or a sneeze by the target person in the predetermined space has been detected whether the state of the mouth of the target person is a state where the person's mouth is not covered, a state where the person's mouth is covered with a hand, a state where the person's mouth is covered with a handkerchief, a state where the person's mouth is covered with the sleeve of an upper garment, or a state where the person's mouth is covered with a mask.

[0319] Note that the person state determination unit 133 may recognize the state of the mouth of the target person not only from the image at the time when a cough or a sneeze has been detected but also from the images of the time before and after the time when a cough or a sneeze has been detected.

[0320] Next, in step S110, the infection risk evaluation unit 135 acquires the cumulative value of the evaluation values stored in the memory 14. The memory 14 stores the cumulative value obtained by accumulating the evaluation values of the infection risks due to droplet infection, contact infection, and airborne infection in a predetermined space. The infection risk evaluation unit 135 acquires from the memory 14 the cumulative values of the evaluation values of the infection risks due to droplet infection, contact infection, and airborne infection in a predetermined space.

[0321] Next, in step S111, the infection risk evaluation unit 135 reads out the infection risk evaluation table from the infection risk evaluation table storage unit 144.

[0322] Next, in step S112, the infection risk evaluation unit 135 refers to the infection risk evaluation table and determines the evaluation values of the infection risks due to droplet infection, contact infection, and airborne infection corresponding to the state of the mouth of the target person recognized by the person state determination unit 133.

[0323] Next, in step S113, the infection risk evaluation unit 135 adds the evaluation values of the infection risks caused by the determined droplet infection, contact infection, and airborne infection to the acquired cumulative values, and stores the cumulative values of the evaluation values of the infection risks caused by droplet infection, contact infection, and airborne infection in the memory 14. As a result, the cumulative value in the memory 14 is updated. Thereafter, the process returns to step S101, and the processes after step S101 are performed.

[0324] On the other hand, when it is determined in step S103 that a predetermined time has elapsed (YES in step S103), in step S114, the infection risk evaluation unit 135 determines whether the total value of the cumulative values of each infection route is equal to or greater than a threshold value. That is, the infection risk evaluation unit 135 sums up the cumulative values of the evaluation values of the infection risks caused by droplet infection, contact infection, and airborne infection stored in the memory 14, and determines whether the total value is equal to or greater than the threshold value. Here, when it is determined that the total value of the cumulative values is not equal to or greater than the threshold value (NO in step S114), the process proceeds to step S117.

[0325] On the other hand, when it is determined that the total value of the cumulative values is equal to or greater than the threshold value (YES in step S114), in step S115, the evaluation result notification unit 136 outputs an evaluation result indicating a high risk of contracting an infectious disease in a predetermined space to the communication unit 15.

[0326] Next, in step S116, the communication unit 15 transmits an evaluation result indicating a high risk of contracting an infectious disease in a predetermined space to the terminal device 5. The terminal device 5 receives the evaluation result transmitted by the infection risk evaluation device 1C and displays the received evaluation result. The administrator who has confirmed the evaluation result displayed on the terminal device 5, since the risk of contracting an infectious disease in the predetermined space has become high, ventilates the predetermined space, turns on the power of the air purifier arranged in the predetermined space, or moves the people in the predetermined space to another place.

[0327] Next, in step S117, the infection risk evaluation unit 135 initializes the cumulative value of the evaluation value of each infection route stored in the memory 14 and a predetermined time. Thereafter, the process returns to step S101, and the processes after step S101 are performed.

[0328] Note that in step S114, the infection risk evaluation unit 135 determines whether the total value of the cumulative values of each infection route is equal to or greater than a threshold value. However, the present disclosure is not particularly limited to this, and it may be determined whether at least one of the cumulative values of each infection route is equal to or greater than the threshold value. That is, the infection risk evaluation unit 135 may determine whether at least one of the cumulative value of the evaluation value of the infection risk due to droplet infection, the cumulative value of the evaluation value of the infection risk due to contact infection, and the cumulative value of the evaluation value of the infection risk due to airborne infection is equal to or greater than the threshold value.

[0329] Further, the evaluation result notification unit 136 outputs an evaluation result indicating a high risk of infection with an infectious disease in a predetermined space to the communication unit 15. However, the present disclosure is not particularly limited to this, and the cumulative values of droplet infection, contact infection, and airborne infection may be output to the communication unit 15 as evaluation results. At this time, when it is determined that the total value of the cumulative values is equal to or greater than the threshold value, the evaluation result notification unit 136 may output the cumulative values of droplet infection, contact infection, and airborne infection to the communication unit 15 as evaluation results. Further, when a predetermined time has elapsed, the evaluation result notification unit 136 may output the cumulative values of droplet infection, contact infection, and airborne infection to the communication unit 15 as evaluation results without determining whether the total value of the cumulative values is equal to or greater than the threshold value.

[0330] In the present disclosure, when a predetermined time has elapsed and it is determined that the total value of the cumulative values is equal to or greater than the threshold value, the evaluation result is transmitted to the terminal device 5. However, the present disclosure is not particularly limited to this, and each time the cumulative values of droplet infection, contact infection, and airborne infection are stored in step S113, the cumulative values of droplet infection, contact infection, and airborne infection may be transmitted to the terminal device 5. In this case, the terminal device 5 can display the cumulative values of droplet infection, contact infection, and airborne infection in real time.

[0331] Also, the number of subjects in a predetermined space is not necessarily one, and there may be a plurality of subjects. When there are a plurality of subjects in a predetermined space, coughing or sneezing by each of the plurality of subjects is detected, the state of the mouth of each of the plurality of subjects is recognized, and an evaluation value of the infection risk due to each of droplet infection, contact infection, and airborne infection corresponding to the recognized state of the mouth of each of the plurality of subjects is determined, and the cumulative value of the evaluation values of the infection risk due to each of droplet infection, contact infection, and airborne infection may be stored.

[0332] Further, the memory 14 may store in advance infected person information in which a face image of a subject is associated with information indicating whether the subject is infected with an infectious disease. In this case, the infection risk evaluation unit 135 may determine whether the subject is infected with an infectious disease from the face image of the subject included in the image information. And when it is determined that the subject is infected with an infectious disease, the infection risk evaluation unit 135 may weight the determined evaluation value. Also, when it is determined that the subject is not infected with an infectious disease, the infection risk evaluation unit 135 may determine the evaluation value to be 0. Note that the infection risk evaluation device 1C may capture a face image of the subject in advance, acquire the biological information of the subject from the biological sensor, and determine whether the subject is infected with an infectious disease from the acquired biological information. Also, the infection risk evaluation device 1C may receive an input of information indicating whether the subject is infected with an infectious disease from a doctor or an administrator.

[0333] The infection risk evaluation system described above is an example of the following information processing system.

[0334] A camera that images a predetermined space, An information processing device, and is provided with, The information processing device, detects coughing or sneezing by a person in the predetermined space, acquires an image of the predetermined space taken by the camera when the coughing or the sneezing is detected, Detect the state of the mouth of the person from the image, Based on the state of the mouth, evaluate the risk of contracting an infectious disease in the predetermined space, Output the evaluation result, An information processing system.

[0335] In addition, the following information processing method can be realized by the above information processing system.

[0336] Detect a cough or a sneeze by a person in a predetermined space, Obtain an image of the predetermined space captured when the cough or the sneeze is detected, Detect the state of the mouth of the person from the image, Based on the state of the mouth, evaluate the risk of contracting an infectious disease in the predetermined space, Output the evaluation result, An information processing method.

[0337] According to the configuration of this information processing method, the state of the mouth of the person is detected from an image of a predetermined space captured when a cough or a sneeze is detected, and based on the state of the mouth of the person, the risk of contracting an infectious disease in the predetermined space is evaluated. Therefore, the risk of contracting an infectious disease in the predetermined space where a cough or a sneeze is detected can be estimated. And when it is estimated that the risk of contracting an infectious disease in the predetermined space is high, appropriate countermeasures can be promoted to reduce the risk of contracting an infectious disease.

[0338] In addition, in the above information processing method, the recognition of the state of the mouth of the person may recognize either a state where the mouth of the person is not covered or a state where the mouth of the person is covered with a hand.

[0339] According to this configuration, the risk of contracting an infectious disease is different between a state where a person's mouth is uncovered and a state where a person's mouth is covered with a hand. Therefore, based on whether the state of the area around a person's mouth is either a state where the person's mouth is uncovered or a state where the person's mouth is covered with a hand, it is possible to more accurately evaluate the risk of contracting an infectious disease within a predetermined space.

[0340] Also, in the above information processing method, the recognition of the state of the area around the person's mouth may recognize any one of a state where the person's mouth is uncovered, a state where the person's mouth is covered with a hand, and a state where the person's mouth is covered with a mask.

[0341] According to this configuration, the risk of contracting an infectious disease is different between a state where a person's mouth is uncovered, a state where the person's mouth is covered with a hand, and a state where the person's mouth is covered with a mask. Therefore, based on whether the state of the area around a person's mouth is either a state where the person's mouth is uncovered, a state where the person's mouth is covered with a hand, or a state where the person's mouth is covered with a mask, it is possible to more accurately evaluate the risk of contracting an infectious disease within a predetermined space.

[0342] Also, in the above information processing method, the recognition of the state of the area around the person's mouth may recognize any one of a state where the person's mouth is uncovered, a state where the person's mouth is covered with a hand, a state where the person's mouth is covered with a handkerchief, and a state where the person's mouth is covered with a mask.

[0343] According to this configuration, the risk of contracting an infectious disease is different between a state where a person's mouth is uncovered, a state where the person's mouth is covered with a hand, a state where the person's mouth is covered with a handkerchief, and a state where the person's mouth is covered with a mask. Therefore, based on whether the state of the area around a person's mouth is either a state where the person's mouth is uncovered, a state where the person's mouth is covered with a hand, a state where the person's mouth is covered with a handkerchief, or a state where the person's mouth is covered with a mask, it is possible to more accurately evaluate the risk of contracting an infectious disease within a predetermined space.

[0344] In addition, in the above information processing method, the recognition of the state of the person's mouth area may recognize any one of the state where the person's mouth is not covered, the state where the person's mouth is covered with a hand, the state where the person's mouth is covered with a handkerchief, the state where the person's mouth is covered with clothing, and the state where the person's mouth is covered with a mask.

[0345] According to this configuration, the risk of contracting an infectious disease is different between the state where the person's mouth is not covered, the state where the person's mouth is covered with a hand, the state where the person's mouth is covered with a handkerchief, the state where the person's mouth is covered with clothing, and the state where the person's mouth is covered with a mask. Therefore, based on whether the state of the person's mouth area is any one of the state where the person's mouth is not covered, the state where the person's mouth is covered with a hand, the state where the person's mouth is covered with a handkerchief, the state where the person's mouth is covered with clothing, and the state where the person's mouth is covered with a mask, the risk of contracting an infectious disease in a predetermined space can be evaluated more accurately.

[0346] In addition, in the above information processing method, the detection of the cough or sneeze may detect a cough or sneeze by a person in the predetermined space from the image.

[0347] According to this configuration, a cough or sneeze by a person in a predetermined space can be detected using an image.

[0348] In addition, in the above information processing method, the detection of the cough or sneeze determines whether the distance between the position of the person's face included in the image and the position of one of the person's hands included in the image is less than or equal to a threshold value, and when it is determined that the distance is less than or equal to the threshold value, the cough or sneeze may be detected.

[0349] Generally, when a person coughs or sneezes, they perform the action of putting their hand to their mouth. Therefore, by determining whether the distance between the position of the face of the person included in the image and the position of one hand of the person included in the image is less than or equal to a threshold value, it is possible to easily detect that the person has coughed or sneezed.

[0350] Also, in the above information processing method, the detection of the cough or sneeze may be performed by determining whether the area of the mouth of the person included in the image is less than or equal to a threshold value, and when it is determined that the area is less than or equal to the threshold value, the cough or sneeze may be detected.

[0351] Generally, when a person coughs or sneezes, they perform the action of putting their hand to their mouth. Therefore, by determining whether the area of the mouth of the person included in the image is less than or equal to a threshold value, it is possible to easily detect that the person has coughed or sneezed.

[0352] Also, in the above information processing method, further, voice collected from the microphone installed in the predetermined space is obtained, and the detection of the cough or sneeze may be performed by detecting a cough or sneeze by a person in the predetermined space from the image and the voice.

[0353] According to this configuration, voice collected from the microphone installed in the predetermined space is obtained. The detection of the cough or sneeze is performed by detecting a cough or sneeze by a person in the predetermined space from the image and the voice.

[0354] Therefore, by using not only the image but also the voice, a cough or sneeze by a person in the predetermined space can be detected, so that a cough or sneeze by a person in the predetermined space can be detected more accurately.

[0355] Also, in the above information processing method, the assessment of the risk of infection with the infectious disease may be performed by assessing the risk of infection with the infectious disease due to each of droplet infection, contact infection, and airborne infection.

[0356] According to this configuration, since the risk of contracting an infectious disease is evaluated for each of droplet infection, contact infection, and airborne infection, the risk of contracting an infectious disease can be estimated for each infection route of droplet infection, contact infection, and airborne infection. In addition, infection prevention measures for infectious diseases can be implemented according to the infection routes of droplet infection, contact infection, and airborne infection.

[0357] In addition, in the above information processing method, the evaluation of the risk of contracting the infectious disease is to extract, from an evaluation table in which the state of the person's mouth is associated with an evaluation value obtained by quantifying the risk of contracting the infectious disease by each of the droplet infection, the contact infection, and the airborne infection, the evaluation values of the droplet infection, the contact infection, and the airborne infection respectively associated with the recognized state of the person's mouth, accumulate the extracted evaluation values respectively, and the output of the evaluation result may output the cumulative values of the droplet infection, the contact infection, and the airborne infection respectively as the evaluation result.

[0358] According to this configuration, in the evaluation table, the state of the person's mouth is associated with an evaluation value obtained by quantifying the risk of contracting an infectious disease by each of droplet infection, contact infection, and airborne infection. The evaluation values of droplet infection, contact infection, and airborne infection respectively associated with the recognized state of the person's mouth are extracted from the evaluation table. The extracted evaluation values are accumulated respectively. The cumulative values of droplet infection, contact infection, and airborne infection are output as the evaluation result.

[0359] Therefore, using the cumulative values of droplet infection, contact infection, and airborne infection respectively, the risk of contracting an infectious disease by each of droplet infection, contact infection, and airborne infection can be easily estimated.

[0360] Also, in the above information processing method, the evaluation of the risk of contracting the infectious disease involves associating the state of the person's mouth with an evaluation table that correlates the risk of contracting the infectious disease through each of the droplet infection, contact infection, and airborne infection with a quantified evaluation value. From the evaluation table, the evaluation values for each of the droplet infection, contact infection, and airborne infection associated with the recognized state of the person's mouth are extracted. Each of the extracted evaluation values is accumulated within a predetermined time. The output of the evaluation result may be to output the evaluation result indicating that the risk of contracting the infectious disease is high within the predetermined space when the accumulated value is equal to or greater than a threshold value.

[0361] According to this configuration, in the evaluation table, the state of the person's mouth is associated with an evaluation value that quantifies the risk of contracting an infectious disease through each of droplet infection, contact infection, and airborne infection. The evaluation values for each of the droplet infection, contact infection, and airborne infection associated with the recognized state of the person's mouth are extracted from the evaluation table. Each of the extracted evaluation values is accumulated within a predetermined time. When the accumulated value is equal to or greater than a threshold value, the evaluation result indicating that the risk of contracting an infectious disease is high within the predetermined space is output.

[0362] Therefore, by using the accumulated values for each of the droplet infection, contact infection, and airborne infection within a predetermined time, it is possible to easily estimate the risk of contracting an infectious disease through each of the droplet infection, contact infection, and airborne infection.

[0363] As described above, the device of the present disclosure has been described based on the embodiments. However, the present disclosure is not limited to these embodiments. As long as the gist of the present disclosure is not deviated from, various modifications conceived by those skilled in the art applied to these embodiments or forms constructed by combining components in different embodiments may also be included within the scope of one or more aspects of the present disclosure.

[0364] In each of the above embodiments, each component may be implemented by dedicated hardware or by executing a software program suitable for each component. Each component may also be implemented by a program execution unit such as a CPU or a processor reading and executing a software program recorded on a recording medium such as a hard disk or a semiconductor memory.

[0365] Part or all of the functions of the device according to the embodiments of the present disclosure are typically realized as an LSI (Large Scale Integration), which is an integrated circuit. These may be individually formed into one chip, or may be formed into one chip so as to include part or all of them. Further, the integration is not limited to LSI, and it may be realized by a dedicated circuit or a general-purpose processor. An FPGA (Field Programmable Gate Array) that can be programmed after manufacturing the LSI, or a reconfigurable processor that can reconfigure the connection and setting of circuit cells inside the LSI may also be used.

[0366] Also, part or all of the functions of the device according to the embodiments of the present disclosure may be realized by a processor such as a CPU executing a program.

[0367] Also, all the numbers used above are for exemplification in order to specifically explain the present disclosure, and the present disclosure is not limited to the exemplified numbers.

[0368] Also, the order in which each step shown in the above flowchart is executed is for exemplification in order to specifically explain the present disclosure, and other orders may be used as long as the same effects can be obtained. Also, some of the above steps may be executed simultaneously (in parallel) with other steps.

[0369] Furthermore, various modifications obtained by making changes within the scope conceivable to those skilled in the art to each embodiment of the present disclosure are also included in the present disclosure as long as they do not depart from the gist of the present disclosure.

Industrial Applicability

[0370] The information processing method, information processing program, and information processing system according to the present disclosure can reduce the risk of infection with an infectious disease in a predetermined space where a cough or a sneeze is detected, and are useful as an information processing method, information processing program, and information processing system for controlling the airflow in the predetermined space where a cough or a sneeze is detected.

Explanation of Signs

[0371] 1, 1A, 1B Airflow control device 1C Infection risk assessment device 2 Airflow generation device 3, 3A Camera 4 Microphone 5 Terminal device 11 Camera 12 Microphone 13, 13A, 13B Processor 14, 14B Memory 15, 15B Communication unit 21 Communication unit 22 Processor 23 Memory 24 Airflow generation unit 25 Wind direction change unit 31 Photographing unit 32, 32A Processor 33 Memory 34, 34A Communication unit 41 Sound collection unit 42 Processor 43 Communication unit 131 Image processing unit 132, 132A Cough / sneeze detection unit 133 Person state determination unit 134 Control signal generation unit 135 Infection risk assessment unit 136 Evaluation result notification unit 141 Image storage unit 142 Equipment information storage unit 143 Airflow control table storage unit 144 Infection risk assessment table storage unit 201 Air conditioning equipment 202 Air purifier 221 Airflow control unit 321 Image processing unit 322 Cough / sneeze judgment unit 323 Person status determination unit 324 Cough / sneeze detection unit 331 Image memory unit 421 Cough / sneeze detection unit

Claims

1. The computer Detecting a cough or sneeze by a person within a given space; acquiring an image of the predetermined space captured when the cough or sneeze is detected; detecting a state of the person's mouth from the image; A step of evaluating a risk of infection with an infectious disease in the specified space based on the state of the mouth; outputting the evaluation result; Including, the state of the person's mouth is any one of a state in which the person's mouth is not covered, a state in which the person's mouth is covered by a hand, a state in which the person's mouth is covered by a handkerchief or clothing, and a state in which the person's mouth is covered by a mask; The evaluation varies depending on the state of the person's mouth. Information processing methods.

2. A camera that captures an image of a predetermined space; An information processing device; Equipped with The information processing device includes: Detecting a cough or sneeze by a person within the predetermined space; Acquiring an image of the predetermined space captured when the cough or sneeze is detected; Detecting the state of the person's mouth from the image; Evaluating the risk of infection in the specified space based on the state of the mouth; Output the evaluation result, the state of the person's mouth is any one of a state in which the person's mouth is not covered, a state in which the person's mouth is covered by a hand, a state in which the person's mouth is covered by a handkerchief or clothing, and a state in which the person's mouth is covered by a mask; The evaluation varies depending on the state of the person's mouth. Information processing system.

Images