Indoor abnormality detection method, system thereof, and program

Abstract

To provide an indoor abnormality detection method capable of remotely determining a physical condition of a resident while protecting privacy of the resident or the like.SOLUTION: An indoor abnormality detection method in which a computer executes a first step of receiving a carbon dioxide concentration detected by a concentration sensor in a room and a second step of determining a state of a person in the room on the basis of the carbon dioxide concentration in the room received in the first step, the second step determining that an abnormality has occurred in the person when a first condition that the carbon dioxide concentration changes from a survival concentration to a non-survival concentration is satisfied in a first state in which a person is present in the room and ventilation is not performed on the basis of the carbon dioxide concentration.SELECTED DRAWING: Figure 6

Description

[Technical Field]

[0001] The present invention relates to a method for detecting an abnormality in an indoor space, a system therefor, and a program therefor. [Background technology]

[0002] There is a system in place that installs cameras in the living spaces of elderly people to check whether they are alive or not. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-131832 Summary of the Invention [Problem to be solved by the invention]

[0004] However, as mentioned above, the use of cameras raises concerns about the infringement of residents' privacy. Residents have the right to live independently, and constant surveillance could violate that right. Additionally, if the camera breaks down or is hacked, there is a risk that personal information and information about your daily life will be leaked to third parties. Furthermore, since the space should be one in which elderly people can move around freely, installing cameras may restrict the residents' movements. Given these circumstances, there is a need for a method to ensure the safety of the elderly while protecting their individual privacy and dignity.

[0005] The present invention has been made in consideration of the above circumstances, and its purpose is to provide an indoor abnormality detection method, system, and program that can remotely determine the physical condition of occupants while protecting the privacy of the occupants, etc. [Means for solving the problem]

[0006] The present invention is an indoor abnormality detection method in which a computer executes a first step of receiving a carbon dioxide concentration detected by an indoor concentration sensor, and a second step of determining the status of a person in the room based on the indoor carbon dioxide concentration received in the first step, wherein the second step determines that an abnormality has occurred in the person based on the carbon dioxide concentration when a first condition is met that the carbon dioxide concentration changes from a survival concentration to a non-survival concentration in a first state in which a person is present in the room and ventilation is not being performed.

[0007] Preferably, the method further includes a third step of determining in advance a first state determination criterion based on the carbon dioxide concentration in a first state in which people are present in the room and ventilation is not being performed, and the second step determines whether or not the room is in the first state using the first state determination criterion determined in the third step.

[0008] Preferably, the third step determines a second state judgment criterion in advance based on the carbon dioxide concentration in a second state in which a person is present in the room and ventilation is being performed, and the second step uses the second state judgment criterion determined in the third step to judge whether or not the room is in the second state, and if, in the second state, the detected carbon dioxide concentration changes from a state in which it is fluctuating within a predetermined range to a state in which it is not fluctuating within the predetermined range, it is determined that an abnormality has occurred in the person.

[0009] Preferably, the third step determines the first state judgment criterion using a first trained model based on the carbon dioxide concentration, and determines the second state judgment criterion using a second trained model based on the carbon dioxide concentration.

[0010] Preferably, the first trained model is a trained model generated by machine learning with the carbon dioxide concentration as an explanatory variable and the first state judgment criterion for that carbon dioxide concentration as an objective variable, and the second trained model is a trained model generated by machine learning with the carbon dioxide concentration as an explanatory variable and the second state judgment criterion for that carbon dioxide concentration as an objective variable.

[0011] Preferably, it is determined whether or not a person is present in the room based on the carbon dioxide concentration detected in each of a plurality of rooms in the room.

[0012] Preferably, the method includes a fourth step of receiving a human presence detection result from a human presence sensor in the room, and a fifth step of detecting whether or not there is a person in the room based on the human presence detection result received in the fourth step.

[0013] Preferably, the method includes a seventh step of identifying in advance the behavioral patterns of people in the room based on changes in concentration over a predetermined period of time, and further using the detection results of the seventh step to determine whether or not there is a person in the room.

[0014] Preferably, the change in the carbon dioxide concentration is detected for a certain period of time for each of a plurality of rooms in the room, and based on the detected change, it is determined whether the room is in the first state or the second state.

[0015] Preferably, the method has an eighth step of detecting the temperature inside the room, and further uses the temperature detected in the eighth step to determine whether or not there is a person in the room.

[0016] Preferably, the predetermined range is a range that is determined in advance based on the amount of change in carbon dioxide concentration when someone is present in the room while ventilation is being performed by a ventilation fan.

[0017] The present invention is an indoor abnormality detection system that comprises a first means for receiving a carbon dioxide concentration detected by a concentration sensor in a room, and a second means for determining the state of a person in the room based on the carbon dioxide concentration in the room received by the first means, and the second means determines that an abnormality has occurred in the person based on the carbon dioxide concentration when a first condition is met that the carbon dioxide concentration changes from a survival concentration to a non-survival concentration in a first state in which a person is present in the room and ventilation is not being performed.

[0018] The present invention is a program that causes a computer to execute a first step of receiving a carbon dioxide concentration detected by a concentration sensor in a room, and a second step of determining the condition of a person in the room based on the carbon dioxide concentration in the room received in the first step, and the second step determines that an abnormality has occurred in the person based on the carbon dioxide concentration when a first condition is met in which the carbon dioxide concentration changes from a survival concentration to a non-survival concentration in a first state in which a person is present in the room and ventilation is not being performed. [Effects of the Invention]

[0019] According to the present invention, it is possible to provide an indoor abnormality detection method, system and program that can remotely determine the physical condition of a resident while protecting the privacy of the resident or the like. [Brief explanation of the drawings]

[0020] [Figure 1] FIG. 1 is a system configuration diagram for explaining indoor abnormality detection according to an embodiment of the present invention. [Figure 2] FIG. 2 is a functional block diagram of the indoor abnormality detection device 11 shown in FIG. [Figure 3] FIG. 3 is a diagram showing the detection results of carbon dioxide concentration over a predetermined period of time, including a state in which a person is present and a window is open and a state in which a window is closed. [Figure 4] FIG. 4 is a diagram illustrating a concentration sensor 13 placed in a room 12 of a house to be monitored. [Figure 5] FIG. 5 is a flowchart for explaining a method for setting the first to third state determination criteria in this embodiment. [Figure 6] FIG. 6 is a flowchart for explaining the abnormal state detection operation of the indoor abnormality detection device 11 in the first state of this embodiment. [Figure 7] FIG. 7 is a flowchart for explaining the abnormal state detection operation of the indoor abnormality detection device 11 in the second state of this embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0021] Hereinafter, an indoor abnormality detection method according to an embodiment of the present invention will be described. First Embodiment FIG. 1 is a system configuration diagram for explaining indoor abnormality detection according to an embodiment of the present invention. As shown in FIG. 1, in this embodiment, concentration sensors 13 (13_1 to 13_4, etc.) are arranged in rooms 12 (12_1 to 12_4, etc.) of a residential space or a business. The indoor abnormality detection device 11 receives the carbon dioxide concentration detected by the concentration sensor 13, performs a determination process described below, and transmits a message to the person involved terminal device 21 as necessary.

[0022] FIG. 2 is a functional block diagram of the indoor abnormality detection device 11 shown in FIG. As shown in FIG. 2, the indoor abnormality detection device 11 includes, for example, an operation unit 53, a communication unit 55, a memory 59, and a processing unit 61.

[0023] The operation unit 53 is an operation means such as a touch panel, a keyboard, or a mouse. The communication unit 55 communicates with the concentration sensor 13 and the related person terminal device 21. The input unit 57 is a terminal or the like for inputting data from the outside. The memory 59 stores the program executed by the processing unit 61 . The processing unit 61 executes the program PRG stored in the memory 59 to perform the processing of the indoor abnormality detection device 11 defined in this embodiment.

[0024] The indoor abnormality detection device 11 receives carbon dioxide concentration data indicating the carbon dioxide concentration detected by the concentration sensor 13 from the concentration sensor 13 in the living space.

[0025] The indoor abnormality detection device 11 determines the condition of the person in the living space based on the detected carbon dioxide concentration. Specifically, it determines whether the condition of the person in the living space is abnormal. The above determination may also be made based on the amount of change in carbon dioxide concentration. The amount of change may be expressed as a percentage change in carbon dioxide concentration. By using the amount of change in this way, it is possible to identify changes in the resident's condition with high accuracy.

[0026] Based on the carbon dioxide concentration in the room, the indoor abnormality detection device 11 determines that an abnormality has occurred in the person when a first condition is met, that is, when the carbon dioxide concentration changes from a survival concentration to a non-survival concentration in a first state in which a person is present in the room and ventilation is not being performed. The survival concentration is a concentration specified in advance as the carbon dioxide concentration when a person is normally active in the room. The non-survival concentration is a concentration of carbon dioxide that has been specified in advance as the concentration at which a person in the room would develop physical abnormalities.

[0027] The indoor abnormality detection device 11 determines in advance a first state judgment criterion based on the carbon dioxide concentration in a first state in which people are present in the room and ventilation is not being performed. The indoor abnormality detection device 11 uses the first state determination criterion to determine whether the indoor environment is in the first state.

[0028] In a second state in which there is a person in the room and ventilation is being performed, the indoor abnormality detection device 11 determines that an abnormality has occurred with the person in the room when the detected carbon dioxide concentration changes from a state in which it fluctuates within a predetermined range to a state in which it does not fluctuate within the predetermined range. As an example, the predetermined range is a range that is determined in advance based on the amount of change in carbon dioxide concentration when someone is present in the room while ventilation is being performed by a ventilation fan.

[0029] Indoor abnormality detection device 11 determines in advance a second state judgment criterion based on the carbon dioxide concentration in a second state in which people are present in the room and ventilation is being performed. The indoor abnormality detection device 11 uses the second state determination criterion to determine whether the indoor environment is in the second state.

[0030] FIG. 3 is a diagram showing the detection results of carbon dioxide concentration over a predetermined period of time, including a state in which a person is present and a window is open and a state in which a window is closed. In FIG. 3, the horizontal axis represents time and the vertical axis represents carbon dioxide concentration. In this example, a carbon dioxide concentration sensor, a motion sensor, and a temperature sensor are installed in the living room. Conditions: The living room window is open from 10:00, the air conditioner is on, and the test is conducted while the person is at home. The window is closed before going to bed and after waking up. The verification results are as follows: As fresh air enters through the window, it cannot offset the carbon dioxide concentration contained in people's breath, and the carbon dioxide concentration in the living room decreases. The motion sensor does not react in areas where it cannot detect (toilet, bathroom, washroom, kitchen, etc.), but since people generally touch the motion sensor, it can be determined that someone is at home. Also, by checking the temperature sensor, it is possible to confirm the presence or absence of someone by manually turning the air conditioner on and off. As will be described in the embodiment below, by using these three types of sensors, it is possible to confirm presence or absence in real time even when the window is open.

[0031] The above-described processing is based on the premise that there is only one room in the room, and that the concentration sensor is installed in that room. There may be a case where a room (house) has multiple rooms and concentration sensors are arranged in multiple rooms.

[0032] FIG. 4 is a diagram illustrating concentration sensors 13 arranged in a plurality of rooms in a room to be monitored. The concentration sensors 13_1 to 13_4 are installed in a plurality of predetermined rooms 12_1 to 12_4, respectively. In this case, the indoor abnormality detection device 11 identifies where in the room a person is located based on the carbon dioxide concentrations detected by the concentration sensors 13_1 to 13_4, and determines the state of the person in the room as described above. That is, as shown in FIG. 4, the indoor abnormality detection device 11 may detect changes in carbon dioxide concentration for a certain period of time for each of a plurality of rooms in the room, and determine whether the room is in the first state, second state, or third state based on the detected changes.

[0033] An example of the operation of the indoor abnormality detection device 11 will now be described. <Setting the first to third state judgment criteria> FIG. 5 is a flowchart for explaining a method for setting the first to third state determination criteria in this embodiment. Each step will be explained. Step ST11: The indoor abnormality detection device 11 determines in advance a first state judgment criterion based on the carbon dioxide concentration in a first state in which people are present in the room and ventilation is not being performed. The first state determination criterion is the carbon dioxide concentration measured in the first state and its change pattern, and indicates a threshold value of the carbon dioxide concentration and the similarity of the change pattern. The first state determination criterion is determined, for example, based on the carbon dioxide concentration obtained over a certain period (e.g., one month) during which the indoor abnormality detection device 11 is in full operation. The indoor abnormality detection device 11 uses the first state determination criterion to determine whether the indoor environment is in the first state.

[0034] Step ST12: Indoor abnormality detection device 11 determines in advance a second state judgment criterion based on the carbon dioxide concentration in a second state in which people are present in the room and ventilation is being performed. The second state determination criterion is the carbon dioxide concentration measured in the second state and its change pattern, and indicates a threshold value for the carbon dioxide concentration and the similarity of the change pattern. The second state determination criterion is determined, for example, based on the carbon dioxide concentration obtained over a certain period (e.g., one month) during which the indoor abnormality detection device 11 is in full operation. For example, the carbon dioxide concentration is measured in preset states such as a state where all windows are fully open, a state where all windows are closed and only the ventilation fan is running, etc. The indoor abnormality detection device 11 uses the second state determination criterion to determine whether the indoor environment is in the second state.

[0035] Step ST13: Indoor abnormality detection device 11 determines in advance a third state judgment criterion based on the carbon dioxide concentration in a third state in which no one is in the room. The third state determination criterion is the carbon dioxide concentration measured in the second state and its change pattern, and indicates a threshold value of the carbon dioxide concentration and the similarity of the change pattern. The first state determination criterion is determined, for example, based on the carbon dioxide concentration obtained over a certain period (e.g., one month) during which the indoor abnormality detection device 11 is in full operation. The indoor abnormality detection device 11 uses the third state determination criterion to determine whether the room is in the third state or not. The above steps ST11 to ST13 may be performed in any order.

[0036] <Abnormal state detection operation in the first state> FIG. 6 is a flowchart for explaining the abnormal state detection operation of the indoor abnormality detection device 11 in the first state of this embodiment. Step ST21: The indoor abnormality detection device 11 receives carbon dioxide concentration data indicating the carbon dioxide concentrations detected by the concentration sensors 13_1 to 13_4 from the concentration sensors 13_1 to 13_4 in the living space.

[0037] Step ST22: The indoor abnormality detection device 11 uses the first state determination criterion to determine whether the room is in the first state (there is someone in the room and ventilation is not being performed). If the indoor abnormality detection device 11 determines that the result is positive, the process proceeds to step ST23, and if not, the process ends.

[0038] Step ST23: The indoor abnormality detection device 11 determines whether the detected carbon dioxide concentration has changed from a survival concentration to a non-survival concentration, and if the determination is affirmative, the process proceeds to step ST24, and if not, the process ends.

[0039] Step ST24: The indoor abnormality detection device 11 determines that an abnormality has occurred in a person in the room and performs abnormality processing, such as sending a call or message to relatives, an emergency center, or the like.

[0040] <Abnormal state detection operation in the second state> FIG. 7 is a flowchart for explaining the abnormal state detection operation of the indoor abnormality detection device 11 in the second state of this embodiment. Step ST31: The indoor abnormality detection device 11 receives carbon dioxide concentration data indicating the carbon dioxide concentrations detected by the concentration sensors 13_1 to 13_4 from the concentration sensors 13_1 to 13_4 in the living space.

[0041] Step ST32: The indoor abnormality detection device 11 uses the first state determination criterion to determine whether the room is in the second state (there is someone in the room and ventilation is being performed) or not. If the indoor abnormality detection device 11 determines that the result is positive, the process proceeds to step ST33, and if not, the process ends.

[0042] Step ST33: The indoor abnormality detection device 11 determines whether the detected carbon dioxide concentration has changed from a state in which it is fluctuating within a predetermined range to a state in which it is not fluctuating within the predetermined range, and if the determination is positive, proceeds to step ST34, and if not, terminates the processing.

[0043] Step ST34: The indoor abnormality detection device 11 determines that an abnormality has occurred in a person in the room and performs abnormality processing, such as sending a call or message to relatives, an emergency center, or the like.

[0044] In addition, the indoor abnormality detection device 11 may identify in advance the behavior patterns of people in the room based on the carbon dioxide concentration over a predetermined period of time and its changes, and further use the identified behavior patterns to determine whether or not there is anyone in the room. In addition, the indoor abnormality detection device 11 may detect changes in carbon dioxide concentration for a certain period of time in each of multiple rooms in the room, and determine whether the room is in the first state, second state, or third state based on the detected changes.

[0045] As described above, according to the indoor abnormality detection device 11, it is possible to determine the condition of the occupants in the room 12 by installing a concentration sensor 13 without installing a camera in the room 12 and using the carbon dioxide concentration detected by the concentration sensor 13. Therefore, the privacy of the residents can be protected.

[0046] The temperature and humidity of the room 12 are also affected by whether or not there is a person in the room 12. It is also possible to determine whether or not the occupant has intentionally turned on the air conditioning, which serves as vital monitoring. In addition, as the number of people increases, humidity also increases, and there are also changes due to seasonal factors, and by detecting these, the condition of the room 12 can be understood. The indoor abnormality detection device 11 can ultimately utilize the above information comprehensively, convert it into individual data, detect whether people are at home or not, and read their behavioral patterns.

[0047] For example, the behavioral patterns of an elderly person living alone in an apartment are the bedroom, living room, or going out (excluding the toilet and bathroom). By installing the concentration sensor 13 in the living room and bedroom, it is possible to check the safety and lifestyle patterns of the elderly person without the camera observing their private life.

[0048] Second Embodiment In this embodiment, in addition to the concentration sensors 13_1 to 13_4 used in the first embodiment, a human presence sensor is installed in the room, and based on the human presence detection result of this human presence sensor, it is determined whether or not there is a person in the room.

[0049] In this embodiment, the presence / absence determination is performed using both the presence / absence determination based on the carbon dioxide concentration as in the first embodiment and the presence / absence determination based on the human detection result. For example, if either of the presence / absence determinations determines that a person is present, it is determined that a person is present.

[0050] Alternatively, for example, a thermometer may be installed in the room, and the temperature measured by the thermometer may be used to determine whether or not someone is in the room. For example, if the temperature in the room changes from high to low in summer, it is highly likely that the air conditioner has been turned on, indicating that someone is in the room. The indoor abnormality detection device 11 may identify the ventilation state based on detection information from open / close sensors of the windows and entrances of the rooms 12_1 to 12_4 and on / off information of the ventilation device.

[0051] By further using a human presence sensor as in the second embodiment, the indoor state (first to third states) and the state of a person can be determined with higher accuracy than in the first embodiment.

[0052] <Third embodiment> In this embodiment, a case will be illustrated in which the first to third state determination criteria shown in FIG. 5 are determined using a trained model. In step ST11 shown in FIG. 5, the indoor abnormality detection device 11 determines the first state judgment criterion using the first trained model based on the detected carbon dioxide concentration. The first trained model is a trained model generated by machine learning using the detected carbon dioxide concentration as an explanatory variable and the first state judgment criterion for the carbon dioxide concentration as a target variable. The objective variable may include a state such as the first state.

[0053] In step ST12 shown in FIG. 5, the indoor abnormality detection device 11 determines the second state judgment criterion using the second trained model based on the detected carbon dioxide concentration. The second trained model is a trained model generated by machine learning using the detected carbon dioxide concentration as an explanatory variable and the second state judgment criterion for that carbon dioxide concentration as a target variable. The objective variable may include a state such as the first state.

[0054] In step ST13 shown in FIG. 5, the indoor abnormality detection device 11 determines the third state judgment criterion using the third trained model based on the detected carbon dioxide concentration. The third trained model is a trained model generated by machine learning using the detected carbon dioxide concentration as an explanatory variable and the third state judgment criterion for that carbon dioxide concentration as a target variable. The objective variable may include a state such as the first state.

[0055] By using a trained model as in the third embodiment, the indoor condition can be determined with higher accuracy.

[0056] The present invention is not limited to the above-described embodiments. That is, those skilled in the art may make various modifications, combinations, subcombinations, and substitutions of the components of the above-described embodiments within the technical scope of the present invention or its equivalents.

[0057] In the above-described embodiment, a residential space is exemplified, but the present invention may also be applied to other spaces such as a workplace in a company, a hospital ward, or a facility. [Industrial Applicability]

[0058] The present invention is applicable to an indoor anomaly detection system. [Explanation of symbols]

[0059] 11...Indoor abnormality detection device 12…Indoor 13...Carbon dioxide concentration sensor 21...Stakeholder terminal device

Claims

1. a first step of receiving a carbon dioxide concentration detected by a concentration sensor in a room; a second step of determining the state of a person in the room based on the carbon dioxide concentration in the room received in the first step; An indoor anomaly detection method executed by a computer, comprising: The second step includes: Based on the carbon dioxide concentration, if a first condition is satisfied in which the carbon dioxide concentration changes from a survival concentration to a non-survival concentration in a first state in which a person is present in the room and ventilation is not being performed, it is determined that an abnormality has occurred in the person. Indoor anomaly detection method.

2. a third step of determining in advance a first state criterion based on the carbon dioxide concentration in the first state in which a person is present in the room and ventilation is not being performed; and The second step determines whether the device is in the first state using the first state determination criterion determined in the third step. The indoor abnormality detection method according to claim 1 .

3. the third step includes determining a second state determination criterion in advance based on the carbon dioxide concentration in a second state in which a person is present in the room and ventilation is being performed; The second step includes: determining whether or not the second state is present using the second state determination criterion determined in the third step; In the second state, when the detected carbon dioxide concentration changes from a state in which it fluctuates within a predetermined range to a state in which it does not fluctuate within the predetermined range, it is determined that an abnormality has occurred in the person. The indoor abnormality detection method according to claim 2.

4. The third step includes: determining the first state judgment criterion using a first trained model based on the carbon dioxide concentration; The second state determination criterion is determined using a second trained model based on the carbon dioxide concentration. The indoor abnormality detection method according to claim 3.

5. the first trained model is a trained model generated by machine learning using the carbon dioxide concentration as an explanatory variable and the first state judgment criterion for the carbon dioxide concentration as a target variable, The second trained model is a trained model generated by machine learning using the carbon dioxide concentration as an explanatory variable and the second state determination criterion for the carbon dioxide concentration as a target variable. The indoor abnormality detection method according to claim 4.

6. Based on the carbon dioxide concentration detected in each of a plurality of rooms in the room, it is determined whether or not there is a person in the room. The indoor abnormality detection method according to claim 3.

7. a fourth step of receiving a human presence detection result from a human presence sensor in the room; a fifth step of detecting whether or not there is a person in the room based on the human presence detection result received in the fourth step; The indoor abnormality detection method according to claim 6, further comprising:

8. a seventh step of identifying in advance the behavioral patterns of people in the room based on the concentration change over a predetermined period of time; and The detection result of the seventh step is further used to determine whether or not there is a person in the room.

9. A change in the carbon dioxide concentration is detected for each of the plurality of rooms in the room for a certain period of time, and based on the detected change, it is determined whether the room is in the first state or the second state. The indoor abnormality detection method according to claim 6.

10. an eighth step of detecting the temperature inside the room; and The temperature detected in the eighth step is further used to determine whether or not there is a person in the room. The indoor abnormality detection method according to claim 9.

11. The predetermined range is a range that is determined in advance based on the amount of change in carbon dioxide concentration when someone is present in the room while ventilation is being performed by a ventilation fan. The indoor abnormality detection method according to claim 3.

12. a first process for receiving a carbon dioxide concentration detected by a concentration sensor in the room; a second means for determining the state of a person in the room based on the carbon dioxide concentration in the room received by the first means; and The second means includes: Based on the carbon dioxide concentration, if a first condition is satisfied in which the carbon dioxide concentration changes from a survival concentration to a non-survival concentration in a first state in which a person is present in the room and ventilation is not being performed, it is determined that an abnormality has occurred in the person. Indoor anomaly detection system.

13. a first step of receiving a carbon dioxide concentration detected by a concentration sensor in a room; a second step of determining the state of a person in the room based on the carbon dioxide concentration in the room received in the first step; A program that causes a computer to execute the The second step includes: Based on the carbon dioxide concentration, if a first condition is satisfied in which the carbon dioxide concentration changes from a survival concentration to a non-survival concentration in a first state in which a person is present in the room and ventilation is not being performed, it is determined that an abnormality has occurred in the person. program.

Images