JP7491467B2 - MEASUREMENT APPARATUS, MEASUREMENT METHOD, MEASUREMENT PROGRAM, AND JUDGMENT SYSTEM - Google Patents

Description

The present disclosure relates to a measuring device, a measuring method, a measuring program, and a determination system for measuring carbon dioxide concentration.

In recent years, it has been suggested to avoid crowding in closed environments in order to prevent the spread of viral infections. In addition, techniques for determining carbon dioxide concentration to evaluate the degree of crowding are known. For example, JP 2020-166709 A (Patent Document 1) discloses an estimation device that estimates the number of people in a room based on the change in carbon dioxide concentration over time in an indoor space and the breathing volume per person.

JP 2020-166709 A

According to the estimation device disclosed in Patent Document 1, the number of people present in a room can be estimated by determining the carbon dioxide concentration in the indoor space. Depending on the environment, carbon dioxide may be emitted into the atmosphere not only from people but also from carbon dioxide emission sources other than humans, but the estimation device disclosed in Patent Document 1 does not take into account carbon dioxide emitted from carbon dioxide emission sources other than humans. For this reason, the estimation device disclosed in Patent Document 1 has difficulty in accurately determining the carbon dioxide concentration originating from people, and there was a risk that it would not be possible to accurately determine the density of people.

The present disclosure has been made to solve these problems, and its purpose is to provide technology that can accurately determine the density of people in an environment where there are sources of carbon dioxide emissions other than humans.

A measurement device according to an aspect of the present disclosure includes a storage device that stores first time series data of a carbon dioxide concentration in a first environment in which there are no carbon dioxide emission sources other than humans that emit carbon dioxide into the atmosphere, a data acquisition device that acquires second time series data of a carbon dioxide concentration in a second environment in which there are carbon dioxide emission sources other than humans, and a control device. The control device calculates a reference value for determining the carbon dioxide concentration in the second environment based on the difference between the first time series data and the second time series data.

A measurement method according to another aspect of the present disclosure includes: (a) storing first time series data of carbon dioxide concentration in a first environment in which there are no carbon dioxide emission sources other than humans that emit carbon dioxide into the atmosphere; (b) acquiring second time series data of carbon dioxide concentration in a second environment in which there are carbon dioxide emission sources other than humans; and (c) calculating a reference value for determining the carbon dioxide concentration in the second environment based on the difference between the first time series data and the second time series data.

A measurement program according to another aspect of the present disclosure causes a computer to execute the steps of (a) storing first time series data of carbon dioxide concentration in a first environment in which there are no carbon dioxide emission sources other than humans that emit carbon dioxide into the atmosphere, (b) acquiring second time series data of carbon dioxide concentration in a second environment in which there are carbon dioxide emission sources other than humans, and (c) calculating a reference value for determining the carbon dioxide concentration in the second environment based on the difference between the first time series data and the second time series data.

According to the present disclosure, a reference value for determining the carbon dioxide concentration in a second environment is generated based on the difference between first time-series data of the carbon dioxide concentration in a first environment in which there are no carbon dioxide emission sources other than humans, and second time-series data of the carbon dioxide concentration in a second environment in which there are carbon dioxide emission sources other than humans. This makes it possible to determine the carbon dioxide concentration in an environment in which there are carbon dioxide emission sources other than humans, and therefore to accurately determine the density of people in an environment in which there are carbon dioxide emission sources other than humans.

1 is a diagram for explaining an application example of the determination system according to the first embodiment; FIG. 13 is a diagram showing an example of a reference value of human density relative to the concentration of carbon dioxide emitted in each of a first environment and a second environment. FIG. 1 is a diagram showing a configuration of a determination system according to a first embodiment; FIG. 11 is a diagram illustrating an example of a change in time-series data. 5 is a diagram for explaining the timing of processing of the measurement device and the determination device according to the first embodiment. FIG. FIG. 4 is a diagram showing a display mode of a display. 10A and 10B are diagrams illustrating an example of calculation of a difference between first time-series data and second time-series data by the measurement device according to the first embodiment; 11 is a flowchart illustrating a reference value calculation process executed by the measurement device according to the first embodiment. 11 is a diagram for explaining generation of first feature data based on time-series data in a first environment. FIG. FIG. 11 is a diagram for explaining an example of calculation of a feature value. 11 is a diagram for explaining generation of first feature data based on time-series data in a second environment. FIG. 13A and 13B are diagrams illustrating an example of calculation of a difference between first feature data and second feature data by the measurement device according to the second embodiment. 13 is a flowchart illustrating a reference value calculation process executed by a measurement device according to a second embodiment. 13 is a flowchart illustrating a difference calculation process executed by a measurement device according to a second embodiment. 13A and 13B are diagrams illustrating an example of calculation of a difference between first feature data and second feature data by the measurement device according to the third embodiment. 13A and 13B are diagrams illustrating an example of calculation of a difference between first feature data and second feature data by the measurement device according to the third embodiment. 13A and 13B are diagrams illustrating an example of calculation of a difference between first feature data and second feature data by the measurement device according to the third embodiment. 13 is a flowchart illustrating a difference calculation process executed by a measurement apparatus according to a third embodiment. 13A and 13B are diagrams illustrating an example of calculation of a difference between first feature data and second feature data by the measurement device according to the fourth embodiment. 13 is a flowchart illustrating a difference calculation process executed by a measurement apparatus according to a fourth embodiment. FIG. 13 is a diagram showing a configuration of a determination system according to a fifth embodiment. 23 is a flowchart of a determination process executed by a measurement device according to a sixth embodiment.

Hereinafter, the embodiments of the present disclosure will be described in detail with reference to the drawings. Note that the same or corresponding parts in the drawings are designated by the same reference numerals and their description will not be repeated.

<First embodiment>
A measurement device 1 according to a first embodiment and a determination system 100 including the measurement device 1 will be described with reference to FIGS. 1 to 8. FIG.

[Application example]
FIG. 1 is a diagram for explaining an application example of a determination system 100 according to the first embodiment.

As shown in Figure 1, in restaurants, an increase in the number of customers or staff can lead to crowded conditions. In recent years, however, in order to prevent the spread of viral infections, it has been suggested to avoid crowding in closed environments such as restaurants.

Therefore, in the first embodiment, the concentration of carbon dioxide (hereinafter also referred to as "CO2") in an indoor space, which changes over time, is measured by the sensor 25 of the sensor module 2. The determination system 100 then predicts future changes in the CO2 concentration by analyzing the time-series data of the CO2 concentration acquired from the sensor module 2. Furthermore, the determination system 100 compares the predicted value of the CO2 concentration with a reference value for determining the density of people, and if the predicted value of the CO2 concentration exceeds the reference value or is likely to exceed the reference value, it determines that the density of people is increasing, and drives the ozonizer 26 to prevent the spread of infection by the virus, or uses the display 31 or speaker 32 included in the alarm device 3 to encourage the user to ventilate the room, or issues a warning to prevent further increases in the number of people.

Here, the environments in which CO2 is emitted include an environment where there are no CO2 emission sources other than humans that emit CO2 into the atmosphere, such as a conference room (hereinafter also referred to as the "first environment"), and an environment where there are CO2 emission sources other than humans, such as a restaurant and a factory (hereinafter also referred to as the "second environment"). For example, in a restaurant, CO2 is emitted by people such as customers and staff, cooking ingredients such as grilling, and operating cooking utensils. In a manufacturing site such as a factory, CO2 is emitted by people such as workers, and the operation of manufacturing equipment. Thus, in the second environment, the CO2 concentration tends to be higher than in the first environment because CO2 is emitted from sources other than humans. For this reason, in the second environment, it is necessary to determine the CO2 concentration taking into account the CO2 emitted from CO2 emission sources other than humans.

Figure 2 is a diagram showing an example of a reference value of human density relative to the concentration of carbon dioxide emitted in each of the first and second environments. As shown in Figure 2, in the first environment, CO2 emitted by people is added to the CO2 originally contained in the atmosphere.

For example, if the CO2 emitted by people is added to the approximately 400 ppm of CO2 originally contained in the atmosphere, and the result is less than 1000 ppm, it can be said that people are not crowded. If the result is 1000 ppm or more and less than 1500 ppm, it can be said that people are likely to be crowded, so caution is required. If the result is 1500 ppm or more, it can be said that people are crowded. These standards are based on figures released by the Ministry of Health, Labor and Welfare, and for more information, please refer to the web address below.
https://www.mhlw.go.jp/content/10900000/000616069.pdf

On the other hand, in the second environment, the CO2 emitted by humans is added to the CO2 originally contained in the atmosphere, and CO2 emitted from sources other than humans is also added. That is, in the second environment, the sum result is greater than the CO2 concentration in the first environment by the amount of the CO2 concentration emitted from CO2 emission sources other than humans. Therefore, in the second environment, the standard value used in the first environment cannot be used as is, and it is necessary to determine the CO2 concentration taking into account the CO2 emitted from CO2 emission sources other than humans.

Therefore, the determination system 100 of embodiment 1 is configured to determine the CO2 concentration taking into account CO2 emitted from CO2 emission sources other than humans, as described below.

[Configuration of the Determination System]
3 is a diagram showing a configuration of a determination system 100 according to embodiment 1. As shown in FIG. 3, the determination system 100 includes a measurement device 1 and a determination device 4.

The measuring device 1 is a device that calculates a reference value for determining the CO2 concentration in the environment in which the sensor module 2 is installed based on time series data of CO2 concentration acquired from the sensor module 2, and is equipped with a control device 11, a memory device 12, and a data acquisition device 13.

The control device 11 is an example of a computer such as a processor, and is a computing entity that executes various processes according to various programs. The processor is composed of, for example, a microcontroller, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or an MPU (Multi Processing Unit). The processor has a function of executing various processes by executing a program, but some or all of these functions may be implemented using a dedicated hardware circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field-Programmable Gate Array). The term "processor" is not limited to a processor in the narrow sense that executes processes using a stored program method such as a CPU or an MPU, but may also include hardwired circuits such as an ASIC or an FPGA. For this reason, the processor can also be read as a processing circuitry in which processing is defined in advance by computer-readable code and/or hardwired circuits. The control device 11 may be composed of one chip or multiple chips. Furthermore, the control device 11 includes volatile memories such as a dynamic random access memory (DRAM) and a static random access memory (SRAM), and non-volatile memories such as a read only memory (ROM) and a flash memory.

The storage device 12 includes a non-volatile memory such as a hard disk drive (HDD) and a solid state drive (SSD). The storage device 12 stores various programs and data, such as a measurement program 121 executed by the control device 11, calculation data 122 referenced by the control device 11, and time series data 123 acquired from the sensor module 2.

The measurement program 121 includes a program that specifies the processing procedures of the control device 11 (processing flows shown in Figures 8, 13, 14, 18, 20, and 22). The calculation data 122 is data used when executing processing according to the measurement program 121, and includes data for calculating a reference value for determining the CO2 concentration.

The measuring device 1 may store the measurement program 121 and the calculation data 122 in advance in the storage device 12, or may acquire the measurement program 121 and the calculation data 122 from an external device (not shown) via communication. Furthermore, the measuring device 1 may further include a media reading device (not shown), and may acquire the measurement program 121 and the calculation data 122 from a removable disk, which is a storage medium, by the media reading device.

The data acquisition device 13 receives data from the sensor module 2 by performing wired or wireless communication with the sensor module 2 via the network 50. For example, the data acquisition device 13 acquires time series data of CO2 concentration from the sensor module 2 by communicating with the sensor module 2.

The sensor module 2 is a device that acquires time series data of CO2 concentration in the environment in which the sensor module 2 is installed, and is equipped with a control device 21, a communication device 23, and a sensor 25.

The control device 21 is an example of a computer such as a processor, and is a computing entity that executes various processes according to various programs. The processor is composed of, for example, a microcontroller, a CPU, a GPU, or an MPU. The processor has the function of executing various processes by executing a program, but some or all of these functions may be implemented using a dedicated hardware circuit such as an ASIC or an FPGA. The "processor" is not limited to a processor in the narrow sense that executes processes using a stored program method such as a CPU or an MPU, but may include a hardwired circuit such as an ASIC or an FPGA. For this reason, the processor can also be read as a processing circuitry in which processing is defined in advance by computer-readable code and/or a hardwired circuit. The control device 11 may be composed of one chip or multiple chips. Furthermore, the control device 21 includes volatile memories such as DRAM and SRAM, and non-volatile memories such as ROM and flash memory.

The communication device 23 transmits and receives data to and from the measurement device 1 by performing wired or wireless communication with the measurement device 1 via the network 50. For example, the communication device 23 transmits time series data of the CO2 concentration to the measurement device 1 by communicating with the measurement device 1.

The sensor 25 periodically (e.g., every minute) measures the CO2 concentration in the environment in which the sensor module 2 is installed. The time series data of the CO2 concentration obtained by the measurement of the sensor 25 is transmitted to the measurement device 1 by the communication device 23.

The determination device 4 is a device that determines the CO2 concentration in the environment in which the sensor module 2 is installed based on the reference value of CO2 concentration calculated by the measuring device 1 from the time series data of CO2 concentration acquired by the sensor module 2, and is equipped with a control device 41, a memory device 42, a data acquisition device 43, and a data output device 44.

The control device 41 is an example of a computer such as a processor, and is a computing entity that executes various processes according to various programs. The processor is composed of, for example, a microcontroller, a CPU, an FPGA, a GPU, or an MPU. The processor has a function of executing various processes by executing a program, but some or all of these functions may be implemented using a dedicated hardware circuit such as an ASIC or an FPGA. The "processor" is not limited to a processor in the narrow sense that executes processes using a stored program method such as a CPU or an MPU, but may include a hardwired circuit such as an ASIC or an FPGA. For this reason, the processor can also be read as a processing circuitry in which processing is defined in advance by computer-readable code and/or a hardwired circuit. The control device 41 may be composed of one chip or multiple chips. Furthermore, the control device 41 has volatile memories such as DRAM and SRAM, and non-volatile memories such as ROM and flash memory.

The storage device 42 includes a non-volatile memory such as an HDD and an SSD. The storage device 42 stores various programs and data, such as a judgment program 421 executed by the control device 41 and reference value data 422 referenced by the control device 41.

The judgment program 421 includes a program in which the processing procedure of the control device 41 is defined. Specifically, the judgment program 421 defines a processing procedure for determining the CO2 concentration in the environment in which the sensor module 2 is installed. The reference value data 422 is data indicating a reference value for determining the CO2 concentration in the environment in which the sensor module 2 is installed, and is acquired from the measurement device 1.

The determination device 4 may store the determination program 421 in advance in the storage device 42, or may acquire the determination program 421 from an external device (not shown) via communication. Furthermore, the determination device 4 may further include a media reading device (not shown), and may acquire the determination program 421 from a removable disk, which is a storage medium, via the media reading device.

The data acquisition device 43 receives data from the measurement device 1 by performing wired or wireless communication with the measurement device 1 via the network 50. For example, the data acquisition device 43 acquires reference value data 422 indicating a reference value for determining the CO2 concentration from the measurement device 1.

The data output device 44 transmits data to each of the alarm device 3 and the ozonizer 26 by performing wired or wireless communication with each of the alarm device 3 and the ozonizer 26 via the network 50. For example, the data output device 44 transmits a control signal for controlling each of the alarm device 3 and the ozonizer 26 to each of the alarm device 3 and the ozonizer 26.

In the judgment system 100 configured in this manner, the measuring device 1 calculates a reference value of CO2 concentration for determining the density of people in the environment in which the sensor module 2 is installed.

The determination device 4 analyzes the time series data of the CO2 concentration acquired by the sensor module 2, and determines the CO2 concentration in the environment in which the sensor module 2 is installed using the reference value calculated by the measurement device 1, thereby determining the density of people in the environment in which the sensor module 2 is installed. In addition to determining the density of people from the obtained CO2 concentration, the determination device 4 can also determine the density of people from the CO2 concentration that will be reached if the current state continues. A prediction model is used to predict future changes in the time series data. Using a prediction model makes it possible to predict changes in the time series data, and further makes it possible to determine the CO2 concentration by comparing the predicted value of the CO2 concentration with the reference value.

A prediction model is defined by a function (mathematical formula) that represents the relationship between elapsed time and data that changes over time. For example, a prediction model is defined by a function (mathematical formula) expressed by the following equation (1).

In formula (1), C _∞ is expressed by the following formula (2).

In formula (1), t represents a certain timing (time). C is a parameter representing the CO2 concentration ([ppm]) occurring in the closed environment (indoor space) at timing t. V is a parameter representing the volume ([m ³ ]) of the closed environment (indoor space). Q is a parameter representing the ventilation volume ([m ³ /h]) in the closed environment (indoor space). In formula (2), G is a parameter representing the amount of CO2 concentration discharged ([ppm*m ³ /h]) from the closed environment (indoor space). _{C out} is a parameter representing the CO2 concentration ([ppm]) of the outside air (CO2 concentration originally contained in the atmosphere), and is about 400 ppm.

[Example of predicting changes in time series data]
Prediction of changes in time-series data will be described with reference to Figures 4 and 5. Figure 4 is a diagram showing an example of changes in time-series data.

4 shows a graph of time series data with the CO2 concentration on the vertical axis and the time on the horizontal axis. The measured values of the CO2 concentration actually obtained by the sensor 25 after _t0 are represented by line A. Furthermore, assuming that the time point at which the change in the time series data is predicted is _t0 , the result of predicting the change in the time series data at time _t0 using the prediction model expressed by the above-mentioned formulas (1) and (2) is represented by line G.

4, the predicted value line G is approximate to and generally coincides with the actual measured value line A. In other words, by using the prediction model represented by the above-mentioned equations (1) and (2), it is possible to predict changes in the time series data so as to generally coincide with the actual measured value of the CO2 concentration actually obtained by the sensor 25.

Figure 5 is a diagram for explaining the timing of processing by the measurement device 1 and the determination device 4 according to embodiment 1. In Figure 5, the timing of processing performed by the sensor module 2, the timing of processing performed by the measurement device 1, and the timing of processing performed by the determination device 4 are shown.

As shown in FIG. 5, when the sensor module 2 acquires the time series data of the CO2 concentration from _t10 to _t11 , the measuring device 1 calculates a reference value for judging the CO2 concentration based on the time series data (time series data from _t10 to _t11 ) from _t11 onwards. The judging device 4 judges the CO2 concentration using the reference value calculated by the measuring device 1 from _t12 onwards. The period in which the sensor module 2 acquires the time series data (for example, the data acquisition period in the period from _t10 to _t11 or _t11 to _t12 ) is, for example, 1 minute, 5 minutes, or 10 minutes. The period in which the measuring device 1 calculates the reference value (for example, the period from _t11 to _t15 ) is, for example, 1 week or 10 days. The period (for example, the period from _t12 to _t13 or _t13 to _t14 ) in which the determination device 4 determines the CO2 concentration using the reference value calculated by the measurement device 1 is, for example, 1 minute intervals, 5 minute intervals, or 10 minute intervals, similar to the period in which the sensor module 2 acquires the time series data. In Fig. 5, the time series data used for calculating the reference value and the time series data used for determining the CO2 concentration are separated, but both may be used in common.

In this way, the measuring device 1 calculates the reference value based on the time series data acquired by the sensor module 2 periodically for each predetermined time interval (for example, one week or ten days).

[Display Mode]
Fig. 6 is a diagram showing a display mode of the display 31. As shown in Fig. 6, the screen displayed on the display 31 includes an icon 311 indicating the current CO2 concentration in the environment (e.g., a restaurant) in which the sensor module 2 is installed, a graph 312 indicating the change in the CO2 concentration, an icon 313 indicating the remaining time (predicted arrival time) until ventilation becomes necessary, and an icon 314 for enabling audio notification of the determination result by the speaker 32.

The user may enable or disable the audio notification by touching icon 314, or may enable or disable the audio notification by manipulating icon 314 using a tool such as a mouse (not shown).

A predictive model is used to predict changes in CO2 concentration, and the predicted value is compared with a reference value to calculate the remaining time until ventilation is required. The display 31 notifies the user of the calculated remaining time by icon 313.

[Calculation of reference value]
Calculation of the reference value by the measurement device 1 will be described with reference to Fig. 7 and Fig. 8. In Fig. 7 and Fig. 8, an example will be described in which the measurement device 1 calculates a reference value of the CO2 concentration in a second environment such as a restaurant shown in Fig. 1.

Figure 7 is a diagram showing an example of calculation of the difference between the first time series data and the second time series data by the measuring device 1 according to embodiment 1. In preparation for calculating the reference value in the second environment, the measuring device 1 acquires in advance time series data of the CO2 concentration in a first environment, such as a conference room (hereinafter also referred to as "first time series data").

For example, FIG. 7(A) shows a graph of first time series data with CO2 concentration on the vertical axis and time on the horizontal axis. As shown in FIG. 7(A), the measuring device 1 acquires first time series data of CO2 concentration measured periodically (e.g., every minute) in the first environment. Note that in the graph of FIG. 7(A), it is assumed that the part with a large amount of change in CO2 concentration is, for example, a meeting taking place in a conference room. In other words, it is assumed that CO2 is being generated due to people present in the first environment.

The measuring device 1 stores first time series data in a first environment, such as that shown in Figure 7 (A), in the memory device 12, and then acquires time series data in the second environment (hereinafter also referred to as "second time series data") from a sensor 25 installed in the second environment.

For example, FIG. 7(B) shows a graph of the second time series data with the CO2 concentration on the vertical axis and the time on the horizontal axis. As shown in FIG. 7(B), the measuring device 1 acquires second time series data of the CO2 concentration measured periodically (for example, every minute) in the second environment. Note that in the graph of FIG. 7(B), it is assumed that the part with a large amount of change in the CO2 concentration is, for example, an increase in the number of customers at a restaurant or cooking of ingredients such as grilling. In other words, in addition to the CO2 being generated due to people in the second environment, it is assumed that CO2 is also being generated due to causes other than people in the second environment.

The measuring device 1 calculates the difference between the first time series data and the second time series data. Specifically, the measuring device 1 calculates a first calculated value based on the first time series data, calculates a second calculated value based on the second time series data, and calculates the difference by subtracting the first calculated value from the second calculated value.

For example, the measuring device 1 calculates, as the first calculated value, an average value (e.g., 636.08) of multiple CO2 concentrations acquired in a time series in a first environment included in the first time series data. The measuring device 1 also calculates, as the second calculated value, an average value (e.g., 942.48) of multiple CO2 concentrations acquired in a time series in a second environment included in the second time series data. The measuring device 1 then calculates a difference (e.g., 306.4) by subtracting the first calculated value (e.g., 636.08) from the second calculated value (e.g., 942.48).

The above-mentioned difference arises from the difference in the environments between the first environment and the second environment. In other words, the above-mentioned difference is a value caused by CO2 emitted from CO2 emission sources other than humans in the second environment. Therefore, the measuring device 1 calculates a reference value for determining the CO2 concentration in the second environment by taking into account the calculated difference, using the reference value of the CO2 concentration used in the first environment as a reference.

Specifically, the measuring device 1 calculates the reference value of the CO2 concentration in the second environment (hereinafter also referred to as the "second reference value") by adding the difference to the reference value of the CO2 concentration in the first environment (hereinafter also referred to as the "first reference value"). For example, if the first reference value of the CO2 concentration in the first environment is 1000 ppm, the measuring device 1 calculates 1306.4 as the second reference value by adding 306.4 ppm (the difference) to 1000 ppm. In other words, the fact that the CO2 concentration in the second environment exceeds the second reference value of 1306.4 ppm means that the density of people in the second environment is increasing and caution is required.

Alternatively, the determination device 4 may remove the CO2 concentration emitted from CO2 emission sources other than humans from the second time series data by subtracting the difference from the second time series data of the CO2 concentration in the second environment. That is, the measurement device 1 may convert the second time series data of the CO2 concentration in the second environment to the time series data of the CO2 concentration in the first environment without changing the reference value of the CO2 concentration for determining the density of people. In this way, the determination device 4 can compare the converted time series data in the second environment with the first reference value in the first environment.

[Processing by measuring device]
Fig. 8 is a flowchart relating to the processing executed by the measurement device 1 according to the first embodiment. The control device 11 of the measurement device 1 periodically executes the processing of the flowchart shown in Fig. 8 by executing the measurement program 121 stored in the storage device 12. In the figure, "S" is used as an abbreviation for "STEP."

As shown in Fig. 8, the control device 11 determines whether or not the second time series data for a predetermined time period (e.g., one day's worth) has been acquired (S1). If the control device 11 has not acquired the second time series data for the predetermined time period (NO in S1), the control device 11 ends this process.

On the other hand, when the control device 11 acquires the second time series data for a predetermined time period (YES in S1), it calculates a first calculated value based on the first time series data (S2). For example, as shown in FIG. 7(A), the control device 11 calculates the average value of the first time series data based on the first time series data in the first environment as the first calculated value. Furthermore, the control device 11 calculates a second calculated value based on the second time series data (S3). For example, as shown in FIG. 7(B), the control device 11 calculates the average value of the second time series data based on the second time series data in the second environment as the second calculated value. Then, the control device 11 calculates the difference by subtracting the first calculated value from the second calculated value (S4).

The control device 11 calculates a second reference value of the CO2 concentration in the second environment based on the difference (S5). For example, the control device 11 calculates the second reference value of the CO2 concentration in the second environment by adding the difference to a first reference value of the CO2 concentration in the first environment that is determined in advance. The control device 11 then ends this process.

As described above, the measuring device 1 according to the first embodiment calculates the difference between the first time series data of the CO2 concentration in the first environment where there are no CO2 emission sources other than humans and the second time series data of the CO2 concentration in the second environment where there are CO2 emission sources other than humans, and calculates a reference value (in this example, the second reference value) for determining the CO2 concentration in the second environment based on the calculated difference. As a result, the determining device 4 can use the reference value calculated by the measuring device 1 to determine the CO2 concentration in the second environment taking into account the CO2 emitted from the CO2 emission sources other than humans, so that the CO2 concentration can be accurately determined even in the second environment where there are CO2 emission sources other than humans. In other words, the determining device 4 can use the reference value calculated by the measuring device 1 to accurately determine the density of people in the second environment where there are CO2 emission sources other than humans.

8 may be a step of reading out the first calculated value from the storage device 12. That is, the control device 11 may calculate the first time series data or the first calculated value related to the first environment in advance and store it in the storage device 12, and when calculating the second reference value from the second time series data, it may read out the stored first calculated value, thereby calculating the difference with the second calculated value.

The second time-series data in the second environment acquired by the sensor module 2 differs depending on the second environment in which the sensor module 2 is installed. For example, in a restaurant, the concentration of CO2 emitted from CO2 emission sources other than humans differs depending on whether or not food is cooked, such as by grilling, the cooking time, the number of cooking utensils, and the size of the restaurant. Or, in a manufacturing site such as a factory, the concentration of CO2 emitted from CO2 emission sources other than humans differs depending on the number of manufacturing devices, the operating time of the manufacturing devices, and the size of the factory. For this reason, it is preferable that the reference value for determining the CO2 concentration is also set depending on the second environment in which the sensor module 2 is installed.

In this regard, the measuring device 1 acquires second time-series data of the CO2 concentration for each second environment in which the sensor module 2 is installed, and calculates the difference between the acquired second time-series data and the first time-series data, thereby being able to set a reference value according to the second environment in which the sensor module 2 is installed. This allows the determining device 4 to use the reference value calculated by the measuring device 1 to appropriately determine the CO2 concentration according to the second environment in which the sensor module 2 is installed.

Although it is possible in some cases to measure only the concentration of CO2 emitted from sources other than humans, it can be difficult to measure CO2 concentrations other than those originating from humans, particularly in restaurants, because they may need to stop business and cook in order to measure the CO2 concentration, or because it may not be possible to eliminate the influence of the person cooking. In this regard, the measuring device 1 can set a reference value for measuring the CO2 concentration while actual business is being conducted, minimizing the impact on business and production, and the concentration of CO2 emitted from sources other than humans during actual cooking and operation can be used to determine the concentration.

<Embodiment 2>
A measurement device according to the second embodiment will be described with reference to Fig. 9 to Fig. 14. Only the parts of the measurement device according to the second embodiment that are different from the measurement device 1 according to the first embodiment will be described below.

[Calculating the difference]
9A and 9B are diagrams for explaining generation of first feature data based on time series data in a first environment. Fig. 9A shows a graph of the first time series data with the CO2 concentration on the vertical axis and the time on the horizontal axis. As shown in Fig. 9A, the measurement device 1 acquires first time series data of the CO2 concentration measured periodically (for example, every minute) in the first environment.

Next, the measurement device 1 generates first feature data based on the first time series data in the first environment, and stores the generated first feature data in the memory device 12 as calculation data 122.

Specifically, the measurement device 1 generates a histogram from the first time series data as the first feature data. For example, in Fig. 9(B) and Fig. 9(C), histograms are shown with the number on the vertical axis and G/Q on the horizontal axis. As shown in Fig. 9(B) and Fig. 9(C), the measurement device 1 generates first feature data representing the features of the first time series data by expressing the number of each value of G/Q in a histogram. Note that the measurement device 1 may use Q/V or G/V as well as G/Q on the horizontal axis in the histogram corresponding to the first feature data.

As explained using equations (1) and (2), G/Q is a parameter representing the CO2 concentration per unit ventilation volume. Q/V is a parameter representing the ventilation volume per unit volume. G/V is a parameter representing the CO2 concentration emission amount per unit volume. When generating the first feature data (histogram), the measuring device 1 may calculate any of the feature values G/Q, Q/V, and G/V, instead of C (CO2 concentration) itself.

Here, the calculation of the characteristic value will be described with reference to FIG. 10. FIG. 10 is a diagram for explaining an example of the calculation of the characteristic value. FIG. 10 shows a graph of time series data of CO2 concentration with the CO2 concentration on the vertical axis and time on the horizontal axis. The measuring device 1 calculates the characteristic value from equations (1) and (2) by performing simultaneous equation calculations.

Specifically, as shown in Fig. 10, the measuring device 1 extracts a specific number of data from the first time-series data. For example, the measuring device 1 extracts a CO2 concentration C( _t0 ) at _t0 , a CO2 concentration C( _t1 ) at _t1 , and a CO2 concentration C( _t2 ) at _t2 .

The measurement apparatus 1 calculates the following simultaneous equations (3) from equation (1) and the extracted C(t ₀ ), C(t ₁ ), and C(t ₂ ).

The measuring device 1 calculates the following equation (4) from the simultaneous equations (3).

The measuring device 1 calculates the following equation (5) from equation (4).

The measuring device 1 can calculate the following equation (6) from equations (2) and (5).

In addition, the measuring device 1 can calculate the following equation (7) from equations (3) and (5).

In this way, the measuring device 1 can calculate G/Q (equation (6)) and Q/V (equation (7)) from the first time series data. Furthermore, the measuring device 1 can calculate G/V from G/Q (equation (6)) and Q/V (equation (7)).

In the example of Fig. 10, the measuring device 1 calculates the feature value using the CO2 concentration (C(t)) at three extraction timings such as _t0 , _t1 , and _t2 , but by changing these extraction timings, it is possible to calculate a plurality of feature values. In the example of Fig. 9(A), since the CO2 concentration is acquired every minute, for example, if _t0 is 15:00, the measuring device 1 may set _t1 to 15:01 and _t2 to 15:02. Furthermore, the measuring device 1 may update t every minute, and if _t0 is 15:01, _t1 to 15:02 and _t2 to 15:03.

Returning to Fig. 9, the measuring device 1 generates a histogram based on a plurality of feature values calculated from the first time series data. Here, the measuring device 1 may calculate the feature value (G/Q in this example) using all data included in the first time series data shown in Fig. 9(A) or may calculate the feature value (G/Q in this example) using data selected according to a predetermined rule from among all data included in the first time series data shown in Fig. 9(A).

For example, the measuring device 1 may calculate the feature value using the CO2 concentration in a period in which the change in CO2 concentration in the first time-series data exceeds a threshold value (e.g., 200 ppm). Specifically, when the CO2 concentration that changes over time in the first time-series data changes from a minimum value to a maximum value, the measuring device 1 may identify a period in which the difference between the minimum value and the maximum value (i.e., the change in CO2 concentration) exceeds a threshold value (200 ppm), and calculate the feature value using the CO2 concentration obtained within that period.

As an example, in FIG. 9A, the CO2 concentration acquired at timing _t21 is a minimum value, the CO2 concentration acquired at timing _t22 is a maximum value, and the difference between the minimum value and the maximum value exceeds 200 ppm. Therefore, the measuring device 1 calculates the feature value using the CO2 concentrations acquired in the period from timing _t21 to timing _t22 .

When the measuring device 1 calculates a plurality of feature values using all data included in the first time series data shown in Fig. 9(A), the histogram corresponding to the calculated feature values is shown in Fig. 9(B). On the other hand, when the measuring device 1 calculates a plurality of feature values using data selected according to the above-mentioned predetermined rule from among all data included in the first time series data shown in Fig. 9(A), the histogram corresponding to the calculated plurality of feature values is shown in Fig. 9(C).

In the histogram of FIG. 9(B), the feature values are calculated using all the data included in the first time series data shown in FIG. 9(A), so when the frequency of occurrence of an event is low as in FIG. 9(A), the histogram features related to the event are less likely to appear. In contrast, in the histogram of FIG. 9(C), the feature values are calculated using data from the period in which the change in CO2 concentration is large, out of all the data included in the first time series data shown in FIG. 9(A), so the histogram features are more likely to appear. Note that in the first time series data, when the frequency of occurrence of an event is high, that is, when there are many peaks that are selected according to the above-mentioned predetermined rules, the data can be used as is without extracting specific data.

Figure 11 is a diagram for explaining the generation of second feature data based on time series data in a second environment. The measurement device 1 stores the first feature data of the first time series data in the first environment as shown in Figure 9 (B) or Figure 9 (C) in the storage device 12, and then generates the second feature data of the second time series data in the second environment.

For example, Fig. 11(A) shows a graph of the second time series data with the CO2 concentration on the vertical axis and the time on the horizontal axis. As shown in Fig. 11(A), the measuring device 1 acquires the second time series data of the CO2 concentration measured periodically (for example, every minute) in the second environment.

Next, the measurement device 1 generates second feature data based on the second time series data in the second environment, and stores the generated second feature data in the memory device 12 as calculation data 122.

Specifically, the measurement device 1 generates a histogram from the second time series data as the second feature data. For example, in FIG. 11(B) and FIG. 11(C), a histogram is shown with the number on the vertical axis and G/Q on the horizontal axis. As shown in FIG. 11(B) and FIG. 11(C), the measurement device 1 generates second feature data representing the features of the second time series data by expressing the number of each value of G/Q in a histogram. Note that the measurement device 1 may take Q/V or G/V on the horizontal axis in addition to G/Q in the histogram corresponding to the second feature data. However, the measurement device 1 uses the same type of feature value (for example, G/Q) in the first feature data and the second feature data. The calculation method of these feature values is the same as the calculation method of the first feature data in the first environment described using FIG. 9 and FIG. 10.

Here, the measuring device 1 may calculate the feature value (in this example, G/Q) using all the data included in the time series data shown in FIG. 11 (A), or may calculate the feature value (in this example, G/Q) using data selected according to a predetermined rule from among all the data included in the time series data shown in FIG. 11 (A).

For example, the measuring device 1 may calculate the feature value using the CO2 concentration in a period in which the change in CO2 concentration in the second time-series data exceeds a threshold value (e.g., 200 ppm). Specifically, when the CO2 concentration that changes over time in the second time-series data changes from a minimum value to a maximum value, the measuring device 1 may identify a period in which the difference between the minimum value and the maximum value (i.e., the change in CO2 concentration) exceeds a threshold value (200 ppm), and calculate the feature value using the CO2 concentration obtained within that period.

As an example, in FIG. 11A, the CO2 concentration acquired at timing _t31 is a minimum value, the CO2 concentration acquired at timing _t32 is a maximum value, and the difference between the minimum value and the maximum value exceeds 200 ppm. Therefore, the measuring device 1 calculates the feature value using the CO2 concentrations acquired in the period from timing _t31 to timing _t32 .

When the measuring device 1 calculates a plurality of feature values using all data included in the second time series data shown in Fig. 11(A), the histogram corresponding to the calculated feature values is shown in Fig. 11(B). On the other hand, when the measuring device 1 calculates a plurality of feature values using data selected according to the above-mentioned predetermined rule from among all data included in the second time series data shown in Fig. 11(A), the histogram corresponding to the calculated plurality of feature values is shown in Fig. 11(C).

In the histogram of FIG. 11(B), the feature values are calculated using all the data included in the second time series data shown in FIG. 11(A), so when the frequency of occurrence of an event is low as in FIG. 11(A), the histogram features related to the event are less likely to appear. In contrast, in the histogram of FIG. 11(C), the feature values are calculated using the data of the period in which the change in the CO2 concentration is large, among all the data included in the second time series data shown in FIG. 11(A), so the histogram features are more likely to appear. Note that in the second time series data, when the frequency of occurrence of an event is high, that is, when there are many peaks that are selected according to the above-mentioned predetermined rule, the data may be used as is without extracting specific data. It is preferable to perform the same process on the data measured in each of the first and second environments to determine whether to extract specific data or use the data as is.

Figure 12 is a diagram showing an example of calculation of the difference between the first feature data and the second feature data by the measuring device 1 of embodiment 2. Figure 12 (A) shows a histogram of the first feature data in the first environment. That is, the histogram of Figure 12 (A) corresponds to the histogram of the first feature data shown in Figure 9 (C). Figure 12 (B) shows a histogram of the second feature data in the second environment. That is, the histogram of Figure 12 (B) corresponds to the histogram of the second feature data shown in Figure 11 (C).

12, after generating the second feature data, the measurement device 1 calculates the difference between the first feature data previously stored in the storage device 12 and the generated second feature data. Specifically, the measurement device 1 calculates the difference by calculating a first calculated value from the first feature data, calculating a second calculated value from the second feature data, and subtracting the first calculated value from the second calculated value.

For example, as shown in FIG. 12(A), the measurement device 1 calculates the average value of the feature value (G/Q in this example) as the first calculated value based on the histogram in the first environment. Also, as shown in FIG. 12(B), the measurement device 1 calculates the average value of the feature value (G/Q in this example) as the second calculated value based on the histogram in the second environment. Then, the measurement device 1 calculates the difference by subtracting the first calculated value from the second calculated value.

The above-mentioned difference arises from the difference in the environments between the first environment and the second environment. In other words, the above-mentioned difference is a value caused by CO2 emitted from CO2 emission sources other than humans in the second environment. Therefore, the measuring device 1 calculates data for determining the CO2 concentration in the second environment by taking into account the calculated difference, using the reference value of the CO2 concentration used in the first environment as a reference.

Specifically, the determination device 4 calculates the second reference value of the CO2 concentration in the second environment by adding the difference to the first reference value of the CO2 concentration in the first environment. For example, if the first reference value of the CO2 concentration in the first environment is 1000 ppm, the measurement device 1 calculates the second reference value of 1306.4 by adding the difference (e.g., 306.4 ppm) to 1000 ppm. In other words, the fact that the CO2 concentration in the second environment exceeds the second reference value of 1306.4 ppm means that the density of people in the second environment is increasing and caution is required.

Alternatively, the determination device 4 may remove the CO2 concentration emitted from CO2 emission sources other than humans from the second time series data in advance by adding a difference from the second time series data of the CO2 concentration in the second environment. That is, the measurement device 1 may convert the second time series data of the CO2 concentration in the second environment to the time series data of the CO2 concentration in the first environment without changing the reference value of the CO2 concentration for determining the density of people. In this way, the determination device 4 can compare the converted time series data in the second environment with the first reference value in the first environment.

In the example of FIG. 12, the measurement device 1 calculates the average value of the feature values as the calculated value, but the measurement device 1 may calculate the variance value of the feature values as the calculated value. That is, the measurement device 1 may calculate the variance value of the feature values (G/Q in this example) as the first calculated value based on the histogram in the first environment. The measurement device 1 may also calculate the variance value of the feature values (G/Q in this example) as the second calculated value based on the histogram in the second environment. Furthermore, the measurement device 1 may calculate both the average value and the variance value of the feature values as the calculated value. That is, the measurement device 1 may calculate at least one of the average value and the variance value of the feature values as the calculated value.

As shown in Fig. 12(A), the measuring device 1 calculates the first calculated value using the histogram of the first feature data shown in Fig. 9(C), but may also calculate the first calculated value using the histogram of the first feature data shown in Fig. 9(B). As shown in Fig. 12(B), the measuring device 1 calculates the second calculated value using the histogram of the second feature data shown in Fig. 11(C), but may also calculate the second calculated value using the histogram of the second feature data shown in Fig. 11(B).

[Processing by measuring device]
The processing executed by the measuring device 1 according to the second embodiment will be described with reference to Figs. 13 and 14. Fig. 13 is a flowchart of the reference value calculation processing executed by the measuring device 1 according to the second embodiment. Fig. 14 is a flowchart of the difference calculation processing executed by the measuring device according to the second embodiment. The control device 11 of the measuring device 1 periodically executes the processing of the flowcharts shown in Figs. 13 and 14 by executing the measurement program 121 stored in the storage device 12. Note that in the figures, "S" is used as an abbreviation for "STEP".

13, the control device 11 determines whether or not the second time series data for a predetermined time period (e.g., one day) has been acquired (S11). If the control device 11 has not acquired the second time series data for the predetermined time period (NO in S11), the control device 11 ends this process.

On the other hand, when the control device 11 acquires the second time series data for a predetermined time (YES in S11), it extracts the CO2 concentration from the second time series data for a period in which the change in the CO2 concentration exceeds a threshold value (for example, 200 ppm) (S12). When the control device 11 handles time series data that does not require the extraction of the CO2 concentration, it may skip the process of S12 and proceed to the process of S13. The control device 11 generates a histogram (first feature data) as shown in FIG. 9 (C) from the first time series data (S13). In addition, the control device 11 generates a histogram (second feature data) as shown in FIG. 11 (C) from the extracted second time series data of the CO2 concentration (S14).

Next, the control device 11 executes a difference calculation process to calculate the difference between the first feature data and the second feature data (S15).

As shown in Fig. 14, in the difference calculation process, the control device 11 calculates a first calculated value from the first feature data (S111). For example, as shown in Fig. 12(A), the control device 11 calculates a statistic of the feature value (G/Q in this example) as the first calculated value based on the histogram (first feature data) in the first environment. Examples of the statistic include the mean, variance, minimum, median, first quartile, third quartile, skewness, and kurtosis.

The control device 11 calculates a second calculated value from the second feature data (S112). For example, as shown in FIG. 12(B), the control device 11 calculates a statistic of the feature value (G/Q in this example) as the second calculated value based on the histogram (second feature data) in the second environment. Examples of the statistic include the mean, variance, minimum, median, first quartile, third quartile, skewness, and kurtosis.

Then, the control device 11 calculates the difference by subtracting the first calculated value calculated from the first feature data from the second calculated value calculated from the second feature data (S113).

Returning to FIG. 13, the control device 11 calculates a second reference value of the CO2 concentration in the second environment based on the difference (S16). For example, the control device 11 calculates the second reference value of the CO2 concentration in the second environment by adding the difference to a first reference value of the CO2 concentration in the first environment that is determined in advance. Thereafter, the control device 11 ends this process.

As described above, the measuring device 1 according to the second embodiment calculates the difference between the first feature data generated based on the first time series data of the CO2 concentration in the first environment where there are no CO2 emission sources other than humans, and the second feature data generated based on the second time series data of the CO2 concentration in the second environment where there are CO2 emission sources other than humans, and calculates a reference value (in this example, the second reference value) for determining the CO2 concentration in the second environment based on the calculated difference. As a result, the determining device 4 can use the reference value calculated by the measuring device 1 to determine the CO2 concentration in the second environment taking into account the CO2 emitted from the CO2 emission sources other than humans, and can accurately determine the CO2 concentration even in the second environment where there are CO2 emission sources other than humans.

The measuring device 1 calculates the difference between the first feature data and the second feature data by subtracting the first calculated value calculated from the first feature data from the second calculated value calculated from the second feature data, so that the difference can be calculated relatively easily without performing complex processing such as generating new feature data to calculate the difference.

In S13 of the flow in FIG. 13, the control device 11 may read out the first feature data. That is, the measurement device 1 can calculate the first feature data in advance from the first time series data and store it in the storage device 12, and can shorten the processing time by reading out the stored first feature data. Similarly, in S111 of FIG. 14, the measurement device 1 may read out the first calculated value. That is, the measurement device 1 can calculate the first calculated value in advance from the first feature data and store it in the storage device 12, and can respond by simply reading out the first calculated value from the storage device 12 at the time of judgment.

<Third embodiment>
15 to 18, the measurement device 1 according to the third embodiment will be described. In the following, only the parts of the measurement device 1 according to the third embodiment that are different from the measurement device 1 according to the second embodiment will be described.

[Calculating the difference]
15 to 17 are diagrams showing an example of calculation of the difference between the first feature data and the second feature data by the measurement device 1 according to the third embodiment. FIG. 15(A) shows a histogram of the first feature data in the first environment. That is, the histogram in FIG. 15(A) corresponds to the histogram of the first feature data shown in FIG. 9(C). FIG. 15(B) shows a histogram of the second feature data in the second environment. That is, the histogram in FIG. 15(B) corresponds to the histogram of the second feature data shown in FIG. 11(C).

15, after generating the second feature data, the measurement device 1 according to the third embodiment calculates the difference between the first feature data previously stored in the storage device 12 and the generated second feature data. Specifically, the measurement device 1 generates new feature data (hereinafter also referred to as "third feature data") by subtracting the first feature data from the second feature data.

For example, the measurement device 1 generates a histogram of the third feature data as shown in Fig. 15(C) by subtracting the frequency of each class of the histogram of the first feature data shown in Fig. 15(A) from the frequency of each class of the histogram of the second feature data shown in Fig. 15(B). For this reason, it is desirable that the histogram of the first environment and the histogram of the second environment are created with the same class width.

Here, the measuring device 1 cannot properly generate the third feature data if the number of data included in the first feature data is smaller than the number of data included in the second feature data, and therefore generates the third feature data when any of the following conditions are satisfied.

For example, the measuring device 1 generates the third feature data when the acquisition time of the CO2 concentration in the first time series data is equal to or longer than the acquisition time of the CO2 concentration in the second time series data. Alternatively, the measuring device 1 generates the third feature data when the amount of data in the first feature data (the number of feature values G/Q) is equal to or greater than the amount of data in the second feature data (the number of feature values G/Q).

Furthermore, when the number of data items in the first feature data is smaller than the number of data items in the second feature data, the measurement device 1 may generate the third feature data by multiplying the number of data items in the first feature data by a predetermined number to make the number of data items in the first feature data equal to or greater than the number of data items in the second feature data. The predetermined number to be multiplied may be, for example, a number (e.g., D1/D2) obtained by dividing the number of data items in the first feature data (e.g., D1) by the number of data items in the second feature data (e.g., D2).

After generating the third feature data, the measuring device 1 calculates the average value (for example, 394.63) of the feature value (G/Q in this example) as the difference based on the histogram of the third feature data. The measuring device 1 may calculate a statistical quantity of the feature value as the difference based on the histogram of the third feature data. In addition to the average value, examples of the statistical quantity include the variance value, minimum value, median, first quartile, third quartile, skewness, and kurtosis. The measuring device 1 may calculate at least one of the above-mentioned statistical quantities. For example, the measuring device 1 may calculate the variance value of the feature value as the difference based on the histogram of the third feature data. Furthermore, the measuring device 1 may calculate both the average value and the variance value of the feature value as the difference based on the histogram of the third feature data. Here, when calculating the difference, the measuring device 1 changes the multiple feature values included in the histogram of the third feature data so that the minimum value becomes 0.

For example, as shown in FIG. 16 (A), the measuring device 1 targets all of the multiple feature values included in the third feature data as change targets, and, as shown in FIG. 16 (B), arranges the feature values to be changed in order starting from 0 so that the lowest value among the feature values to be changed is 0.

Alternatively, as shown in Figures 17 (A) and 17 (B), the measuring device 1 changes a portion of the multiple feature values included in the third feature data that includes a feature value that corresponds to the maximum value among the feature values included in the first feature data, and, as shown in Figure 17 (C), arranges the feature values to be changed in order starting from 0 so that the minimum value among the feature values to be changed is 0.

This enables the measuring device 1 to calculate characteristic values caused by CO2 emitted from CO2 emission sources other than humans in the second environment, and to calculate the difference based on such characteristic values.

As shown in Fig. 15(A), the measurement device 1 generates the third feature data using the histogram of the first feature data shown in Fig. 9(C), but may also generate the third feature data using the histogram of the first feature data shown in Fig. 9(B). As shown in Fig. 15(B), the measurement device 1 generates the third feature data using the histogram of the second feature data shown in Fig. 11(C), but may also generate the third feature data using the histogram of the second feature data shown in Fig. 11(B).

[Processing by measuring device]
Fig. 18 is a flowchart relating to the difference calculation process (S15 in Fig. 13) executed by the measurement device 1 according to embodiment 3. The control device 11 of the measurement device 1 according to embodiment 3 periodically executes the process of the flowchart shown in Fig. 18 by executing the measurement program 121 stored in the storage device 12.

As shown in FIG. 13, the control device 11 generates a histogram (first feature data) as shown in FIG. 9 (C) and a histogram (second feature data) as shown in FIG. 11 (C) through processing of S11 to S14, and then performs the difference calculation processing shown in FIG. 18.

As shown in FIG. 18, the control device 11 generates a histogram of the third feature data as shown in FIG. 15 (C) by subtracting the first feature data from the second feature data (S121).

As shown in Figures 16(B) and 17(C), the control device 11 rearranges the histogram of the third feature data by changing the feature values so that the minimum value in the histogram of the third feature data becomes 0 (S122). The control device 11 calculates the difference by calculating the average value of the feature values based on the histogram of the three feature data after rearrangement (S123).

Then, as shown in FIG. 13, the control device 11 calculates a second reference value based on the difference by processing S16.

As described above, the measurement device 1 according to the third embodiment generates the third feature data by subtracting the first feature data from the second feature data, and calculates the difference based on the third feature data. This allows the difference to be calculated with high accuracy by using the new third feature data to calculate the difference.

<Fourth embodiment>
19 and 20, the measurement device 1 according to the fourth embodiment will be described. In the following, only the parts of the measurement device 1 according to the fourth embodiment that are different from the measurement device 1 according to the second embodiment will be described.

[Calculating the difference]
19A and 19B are diagrams illustrating an example of calculation of the difference between the first feature data and the second feature data by the measurement device 1 according to the fourth embodiment. A histogram of the second feature data in the second environment is illustrated in Fig. 19A. That is, the histogram in Fig. 19A corresponds to the histogram of the second feature data illustrated in Fig. 11C.

19, after generating the second feature data, the measurement device 1 according to the fourth embodiment calculates the difference between the first feature data previously stored in the storage device 12 and the generated second feature data. Specifically, the measurement device 1 generates new feature data (hereinafter also referred to as "fourth feature data") by subtracting data having a feature value equivalent to the first calculated value of the first feature data from the second feature data.

For example, the measuring device 1 separates the histogram of the second feature data shown in Fig. 19(A) into the histogram shown in Fig. 19(B) and the histogram shown in Fig. 19(C). The average value of the feature values (G/Q in this example) included in the histogram in Fig. 19(B) corresponds to the average value of the feature values (G/Q in this example) included in the histogram in the first environment shown in Fig. 12(A). In other words, the average value of the feature values included in the histogram in Fig. 19(B) is the same or approximately the same as the first calculated value of the first feature data.

The measuring device 1 subtracts data having a feature value corresponding to the average value of the first feature data from the second feature data shown in Figure 19 (A) to generate a histogram including the remaining feature values as the fourth feature data, as shown in Figure 19 (C).

The measuring device 1 may calculate a statistical quantity other than the average value of the feature values included in the histogram in the first environment as the first calculated value. Examples of statistical quantities other than the average value include the variance value, minimum value, median, first quartile, third quartile, skewness, and kurtosis. The measuring device 1 may generate the fourth feature data by subtracting data having a feature value equivalent to the variance value of the first feature data from the second feature data.

After generating the fourth feature data, the measuring device 1 calculates the average value (for example, 464.7) of the feature value (G/Q in this example) based on the histogram of the fourth feature data. The measuring device 1 may calculate a statistical quantity of the feature value as a difference based on the histogram of the fourth feature data. Examples of the statistical quantity include the average value, variance value, minimum value, median, first quartile, third quartile, skewness, and kurtosis. The measuring device 1 may calculate at least one of the above-mentioned statistical quantities. For example, the measuring device 1 may calculate a variance value of the feature value as a difference based on the histogram of the fourth feature data. Furthermore, the measuring device 1 may calculate both the average value and the variance value of the feature value as a difference based on the histogram of the fourth feature data. Here, when calculating the difference, the measuring device 1 changes the multiple feature values included in the histogram of the fourth feature data so that the minimum value becomes 0.

For example, the measuring device 1 targets all of the multiple feature values included in the fourth feature data as change targets, and arranges the feature values to be changed in order starting from 0 so that the lowest value among the feature values to be changed is 0.

This enables the measuring device 1 to calculate characteristic values caused by CO2 emitted from CO2 emission sources other than humans in the second environment, and to calculate the difference based on such characteristic values.

As shown in FIG. 19 (A), the measuring device 1 generates the fourth feature data using the histogram of the second feature data shown in FIG. 11 (C), but it may also generate the fourth feature data using the histogram of the second feature data shown in FIG. 11 (B).

[Processing by measuring device]
Fig. 20 is a flowchart relating to processing executed by the measurement device 1 according to embodiment 4. The control device 11 of the measurement device 1 according to embodiment 4 periodically executes the processing of the flowchart shown in Fig. 20 by executing the measurement program 121 stored in the storage device 12.

As shown in FIG. 13, the control device 11 generates a histogram (first feature data) as shown in FIG. 9 (C) and a histogram (second feature data) as shown in FIG. 11 (C) through processing of S11 to S14, and then performs the difference calculation processing shown in FIG. 20.

20, the control device 11 calculates a first calculated value from the first feature data (S131). For example, the control device 11 calculates an average value of the feature value (G/Q in this example) as the first calculated value based on the histogram (first feature data) in the first environment.

The control device 11 generates a histogram of the fourth feature data as shown in FIG. 19 (C) by subtracting data having a feature value corresponding to the first calculated value of the first feature data from the second feature data (S132).

The control device 11 rearranges the histogram of the fourth feature data by changing the feature values so that the minimum value in the histogram of the fourth feature data becomes 0 (S133). The control device 11 calculates the difference by calculating the average value of the feature values based on the histogram of the four feature data after rearrangement (S134).

13, the control device 11 calculates a second reference value based on the difference by processing in S16. The control device 11 may calculate the first calculated value in advance from the first feature data and store it in the storage device 12, and read out the stored first calculated value. That is, the control device 11 may read out the first calculated value in S131.

As described above, the measurement device 1 according to the fourth embodiment generates the fourth feature data by subtracting data having a feature value equivalent to the first calculated value of the first feature data from the second feature data, and calculates the difference based on the fourth feature data. This allows the difference to be calculated with high accuracy by using new fourth feature data to calculate the difference. Furthermore, the measurement device 1 does not directly subtract the first feature data from the second feature data, but generates the fourth feature data by subtracting data having a feature value equivalent to the first calculated value of the first feature data from the second feature data, so that the difference can be calculated with higher accuracy.

<Fifth embodiment>
A determination system 100 according to the fifth embodiment will be described with reference to Fig. 21. Only the parts of the determination system 100 according to the fifth embodiment that are different from the determination system 100 according to the first embodiment will be described below.

21, the determination system 100 further includes an alarm device 3 in addition to the measurement device 1 and the sensor module 2. The sensor module 2 further includes an ozonizer 26.

The determination device 4 predicts future changes in the CO2 concentration by analyzing the second time-series data of the CO2 concentration acquired from the sensor module 2. Furthermore, the determination device 4 compares the predicted value of the CO2 concentration with the second reference value acquired from the measurement device 1, and if the predicted value of the CO2 concentration exceeds the second reference value or is likely to exceed the second reference value, the determination device 4 activates the ozonizer 26 or urges the user to ventilate the room using the display 31 or speaker 32 included in the alarm device 3 to prevent the spread of infection by the virus.

The data output device 44 of the judgment device 4 outputs a control signal for controlling the ozonizer 26 to the sensor module 2, and outputs a control signal for controlling the alarm device 3 to the alarm device 3 in accordance with the instructions of the control device 41.

The ozonizer 26 of the sensor module 2 generates ozone and discharges the generated ozone into the second environment in which the sensor module 2 is installed. The control device 21 controls the ozonizer 26 in accordance with a control signal from the determination device 4, thereby causing the ozonizer 26 to generate ozone.

The alarm device 3 includes a display 31 and a speaker 32. The display 31 displays various images, such as an image based on the determination result of the CO2 concentration calculated by the control device 41, in accordance with a control signal from the determination device 4. For example, the display 31 displays an image to encourage the user to ventilate in accordance with a control signal from the determination device 4. The speaker 32 outputs various sounds, such as a sound based on the determination result of the CO2 concentration calculated by the control device 41, in accordance with a control signal from the determination device 4. For example, the speaker 32 outputs a sound to encourage the user to ventilate in accordance with a control signal from the determination device 4.

The alarm device 3 is not limited to being configured separately from the determination device 4. The determination device 4 may include at least one of a display 31 and a speaker 32. Furthermore, the alarm device 3 may be a mobile terminal or a PC (Personal Computer) owned by a user of the measurement device 1 or the determination device 4. For example, the determination device 4 may output a control signal to a mobile terminal or PC owned by the user via short-range wireless communication or the like, and the mobile terminal or PC (alarm device 3) may display an image on the display 31 or output a sound from the speaker 32 based on the control signal from the determination device 4.

In the determination system 100 configured in this manner, the determination device 4 predicts future changes in the CO2 concentration by analyzing the time-series data of the CO2 concentration acquired by the sensor module 2. The determination device 4 then compares the predicted value of the CO2 concentration with the second reference value acquired from the measurement device 1, and if the predicted value of the CO2 concentration exceeds the second reference value or is about to exceed the second reference value, it outputs a control signal to the sensor module 2 to drive the ozonizer 26, or outputs a control signal to the alarm device 3 to control the display 31 or speaker 32.

<Sixth embodiment>
The measurement device 1 according to the sixth embodiment will be described with reference to Fig. 22. Only the differences between the measurement device 1 according to the sixth embodiment and the measurement devices 1 according to the first to fourth embodiments will be described below.

The measuring device 1 according to the first to fourth embodiments is configured to calculate a second reference value for determining the CO2 concentration in the second environment, but the measuring device 1 according to the sixth embodiment may further determine the CO2 concentration in the second environment using the calculated second reference value. That is, the measuring device 1 may have the function of the determination device 4, or may be a device integrated with the determination device 4. Specifically, the measuring device 1 according to the sixth embodiment may predict the attainment value of the CO2 concentration in the second environment acquired from the sensor module 2 by the data acquisition device 13 using a prediction model, and may determine the CO2 concentration in the second environment based on the predicted attainment value and the second reference value.

For example, Figure 22 is a flowchart relating to the determination process executed by the measurement device 1 according to embodiment 6. The control device 11 of the measurement device 1 periodically executes the process of the flowchart shown in Figure 22 by executing the measurement program 121 stored in the storage device 12. Note that in the figure, "S" is used as an abbreviation for "STEP."

22, the control device 11 determines whether or not second time series data for a predetermined time period has been acquired (S51). Note that in S51, the control device 11 may determine whether or not second time series data with an amount of data that allows a prediction model to predict future changes in CO2 concentration has been acquired. If the control device 11 has not acquired second time series data for a predetermined time period (NO in S51), it terminates this process.

On the other hand, when the control device 11 acquires the second time series data for a predetermined time (YES in S51), it calculates a predicted value (attainment value) of the CO2 concentration in the second environment by predicting the change in the second time series data using the prediction model (S52). The control device 11 judges the CO2 concentration in the second environment by comparing the predicted value with the second reference value (S53) and outputs the judgment result (S54). For example, when the predicted value exceeds the second reference value or when the predicted value is likely to exceed the second reference value, the control device 11 outputs a control signal for controlling the ozonizer 26 to the sensor module 2, or outputs a control signal for controlling the alarm device 3 to the alarm device 3. The control device 11 then ends this process.

As described above, the measuring device 1 according to the sixth embodiment calculates the difference between the first time series data of the CO2 concentration in a first environment where there are no CO2 emission sources other than humans and the second time series data of the CO2 concentration in a second environment where there are CO2 emission sources other than humans, and determines the CO2 concentration in the second environment based on the calculated difference and the second time series data. This allows the measuring device 1 to determine the CO2 concentration in the second environment taking into account the CO2 emitted from CO2 emission sources other than humans, and therefore allows the CO2 concentration to be determined with high accuracy even in the second environment where there are CO2 emission sources other than humans.

<Modification>
In the processing of S52 in FIG. 22, the control device 11 may calculate a subtraction value by subtracting a difference from the CO2 concentration in the second environment acquired from the sensor module 2 by the data acquisition device 13, and determine the CO2 concentration in the second environment based on the subtraction value and a first standard value of the CO2 concentration in the first environment.

Furthermore, the control device 11 may predict the target value of the CO2 concentration in the second environment acquired from the sensor module 2 by the data acquisition device 13 using a prediction model, and calculate the above-mentioned subtraction value by subtracting the difference from the predicted target value.

In the above-described embodiment, the measuring device 1 is separate from the sensor module 2, but the measuring device 1 may include each of the components included in the sensor module 2. That is, the measuring device 1 according to the modified example may include a sensor 25 and an ozonizer 26, and the control device 11 may control the sensor 25 and the ozonizer 26. Furthermore, the measuring device 1 may not be a single device that integrally includes a communication unit (data acquisition device 13), a control unit (control device 11), and a memory unit (memory device 12), but may be composed of multiple devices, such as a device specialized for a communication unit having a function corresponding to the data acquisition device 13, a device having a control unit having a function corresponding to the control device 11, and a device having a memory unit having a function corresponding to the memory device 12.

Furthermore, the measuring device 1 may include each component included in the alarm device 3. That is, the measuring device 1 according to the modified example may include a display 31 and a speaker 32, and the control device 11 may control the display 31 and the speaker 32.

Although several embodiments and variants have been described above, the features of each of these embodiments and variants can be combined as appropriate to the extent that no contradictions arise.

The embodiments disclosed herein should be considered to be illustrative and not restrictive in all respects. The scope of the present disclosure is indicated by the claims, not by the description of the embodiments above, and is intended to include all modifications within the meaning and scope of the claims.

1 Measuring device, 2 Sensor module, 3 Alarm device, 4 Determination device, 11, 21, 41 Control device, 12, 42 Storage device, 13, 43 Data acquisition device, 23 Communication device, 25 Sensor, 26 Ozonizer, 31 Display, 32 Speaker, 44 Data output device, 50 Network, 100 Determination system, 121 Measurement program, 122 Calculation data, 123 Time series data, 311, 313, 314 Icon, 421 Determination program, 422 Reference value data.

Claims (17)

A measuring device for measuring a carbon dioxide concentration,
a storage device that stores first time series data of carbon dioxide concentration in a first environment in which there are no carbon dioxide emission sources other than humans that emit carbon dioxide into the atmosphere;
a data acquisition device that acquires second time series data of a carbon dioxide concentration in a second environment where the carbon dioxide emission source other than the human is present;
a control device;
The control device calculates a reference value for determining a carbon dioxide concentration in the second environment based on a difference between the first time series data and the second time series data. The control device includes:
Calculating a first calculated value based on the first time-series data;
Calculating a second calculated value based on the second time series data;
The measurement apparatus according to claim 1 , wherein the difference is calculated by subtracting the first calculated value from the second calculated value. the first calculated value includes an average value of the first time series data,
The measurement apparatus according to claim 2 , wherein the second calculated value includes an average value of the second time-series data. The control device includes:
generating first feature data based on the first time-series data;
generating second feature data based on the second time series data;
Calculating a first calculated value based on the first characteristic data;
Calculating a second calculated value based on the second feature data;
The measurement apparatus according to claim 1 , wherein the difference is calculated by subtracting the first calculated value from the second calculated value. The control device includes:
generating first feature data based on the first time-series data;
generating second feature data based on the second time series data;
generating third feature data by subtracting the first feature data from the second feature data;
The measurement apparatus according to claim 1 , wherein the difference is calculated by calculating at least one of an average value and a variance value of the third feature data. The control device includes:
generating first feature data based on the first time-series data;
generating second feature data based on the second time series data;
Calculating a first calculated value based on the first characteristic data;
generating fourth feature data by subtracting data corresponding to the first calculated value from the second feature data;
The measurement apparatus according to claim 1 , wherein the difference is calculated by calculating at least one of an average value and a variance value of the fourth feature data. The measurement device of claim 6, wherein the first calculated value includes at least one of the average value and the variance value of the first feature data. The control device includes:
generating the first characteristic data based on a carbon dioxide concentration during a period in which a change in the carbon dioxide concentration in the first time-series data exceeds a threshold;
The measurement device according to any one of claims 4 to 7, wherein the first characteristic data is generated based on the carbon dioxide concentration during a period in which an amount of change in the carbon dioxide concentration in the second time-series data exceeds the threshold value. The measurement device according to claim 8, wherein the amount of change includes the difference between the minimum value and the maximum value when the carbon dioxide concentration that changes over time changes from the minimum value to the maximum value. The measurement device according to any one of claims 1 to 7, wherein the control device calculates the reference value for determining the carbon dioxide concentration in the second environment by adding the difference to a first reference value for determining the carbon dioxide concentration in the first environment. The measuring device according to any one of claims 1 to 7 ;
A determination device,
The determination device determines the carbon dioxide concentration in the second environment based on the reference value calculated by the measuring device. The determination device includes:
predicting an ultimate value of the carbon dioxide concentration in the second environment;
The determination system according to claim 11 , which determines the carbon dioxide concentration in the second environment based on the predicted reached value and the reference value. The determination device includes:
Calculating a subtraction value by subtracting the difference calculated by the measuring device from the carbon dioxide concentration in the second environment;
The determination system according to claim 11, further comprising a step of determining the carbon dioxide concentration in the second environment based on the subtraction value and a first reference value for determining the carbon dioxide concentration in the first environment. The determination device includes:
predicting an ultimate value of the carbon dioxide concentration in the second environment;
The determination system according to claim 13 , wherein the subtraction value is calculated by subtracting the difference calculated by the measurement device from the predicted reached value. The determination system according to claim 11 , wherein the determination device transmits a signal for controlling an ozonizer disposed in the second environment to the ozonizer based on a result of the determination of the carbon dioxide concentration in the second environment. A method for measuring a carbon dioxide concentration by a computer, comprising:
Storing first time series data of carbon dioxide concentration in a first environment in which there are no carbon dioxide emission sources other than humans that emit carbon dioxide into the atmosphere;
acquiring second time series data of a carbon dioxide concentration in a second environment where the carbon dioxide emission source other than the human is present;
and calculating a reference value for determining a carbon dioxide concentration in the second environment based on a difference between the first time series data and the second time series data. A measurement program for measuring a carbon dioxide concentration,
On the computer,
Storing first time series data of carbon dioxide concentration in a first environment in which there are no carbon dioxide emission sources other than humans that emit carbon dioxide into the atmosphere;
acquiring second time series data of a carbon dioxide concentration in a second environment where the carbon dioxide emission source other than the human is present;
and calculating a reference value for determining a carbon dioxide concentration in the second environment based on a difference between the first time series data and the second time series data.

Images