WO2021153566A1 - Smell decision device, smell decision method, and smell decision system - Google Patents

Abstract

A smell decision device according to an embodiment is provided with: an acquisition unit which acquires a detection value obtained from each of a plurality of detection elements; a decision unit which decides whether the detection value exceeds a preset threshold; a smell decision unit which decides on the type of smell on the basis of smell patterns obtained by patterning a plurality of the detection values acquired by the acquisition unit, when the detection value of at least one of the plurality of detection elements exceeds the threshold value; and a determination unit which determines a correspondence process corresponding to the type of the smell decided on by the smell decision unit.

Description

Smell judgment device, odor judgment method, and odor judgment system

An embodiment of the present invention relates to an odor determination device, an odor determination method, and an odor determination system.

In order to determine the odor, which is an aggregate of a plurality of gas components, a detection element having an adsorption film on which the odor-causing substance is adsorbed is arrayed, and the detection values related to the odor-causing substance detected by the detection element are patterned. An odor sensor has been developed that outputs the odor pattern. As the transducer that outputs the odor-causing substance adsorbed on the adsorption film as an electric signal, a transducer such as a piezoelectric resonator type, a semiconductor type, or an electrochemical type is used, including a QCM (Quartz Crystal Microbalance).

Then, using the odor pattern, the odor pattern is learned and the type of odor is determined by machine learning. This makes it possible to determine the type of odor by associating the odor pattern with the type of odor without having to analyze the odor pattern by a person.

JP-A-2002-298240 Japanese Unexamined Patent Publication No. 05-223720

By the way, according to the above-mentioned technique, it is possible to obtain the determination result of the type of odor (for example, the odor of oranges, the odor of apples, the odor of flowers), but it is not limited to obtaining the determination result of the type of odors. Based on the determination result of the odor type, it is required to determine the process corresponding to the odor type. For example, when a bad odor is obtained as a result of determining the type of odor, it is required to decide the processing such as spraying a deodorant, ventilating the room, stopping the device that emits the bad odor, and notifying the mobile terminal of an alarm. Has been done.

The present invention has been made in view of the above, and is an odor determination device, an odor determination method, and an odor determination method that can automatically execute a process corresponding to an odor type based on an odor type determination result. An object of the present invention is to provide an odor determination system.

The odor determination device according to the embodiment includes an acquisition unit that acquires detection values obtained from each of the plurality of detection elements, a determination unit that determines whether or not the detection value exceeds a preset threshold value, and the above-mentioned. When the detection value of at least one of the plurality of detection elements exceeds the threshold value, the type of odor is determined based on the odor pattern in which the plurality of detection values acquired by the acquisition unit are patterned. It includes an odor determination unit for determining, and a determination unit for determining a corresponding process corresponding to the type of odor determined by the odor determination unit.

According to the present invention, for example, based on the determination result of the odor type, it is possible to automatically execute the process corresponding to the odor type.

FIG. 1 is a diagram showing an example of an outline configuration of an odor determination system according to a first embodiment. FIG. 2 is a diagram showing an example of a configuration of an odor sensor included in the odor determination system according to the first embodiment. FIG. 3 is a diagram showing an example of a detection value output from an odor sensor included in the odor determination system according to the first embodiment. FIG. 4 is a diagram for explaining an example of a determination information generation process in the cloud of the odor determination system according to the first embodiment. FIG. 5 is a diagram showing an example of the hardware configuration of the SCU included in the odor determination system according to the first embodiment. FIG. 6 is a diagram showing an example of a cloud hardware configuration included in the odor determination system according to the first embodiment. FIG. 7A is a diagram showing an example of a cloud functional configuration included in the odor determination system according to the first embodiment. FIG. 7B is a diagram for explaining an example of an external device control module and an external device included in the odor determination system according to the first embodiment. FIG. 8 is a flowchart showing an example of a flow of determination processing of correspondence processing by the cloud included in the odor determination system according to the first embodiment. FIG. 9 is an explanatory diagram of an example in which the odor determination system according to the first embodiment is used for an automatic vacuum cleaner robot. FIG. 10 is an explanatory diagram of an example in which the odor determination system according to the first embodiment is used for a deodorizing system in a hotel room. FIG. 11 is an explanatory diagram of an example in which the odor determination system according to the first embodiment is used for an exhaust system of a restaurant. FIG. 12 is an explanatory diagram of an example in which the odor determination system according to the first embodiment is used as a measure against bad breath. FIG. 13 is an explanatory diagram of an example in which the odor determination system according to the first embodiment is used for risk prediction of an important facility. FIG. 14 is a flowchart showing another example of the flow of the process of determining the corresponding process by the cloud included in the odor determination system according to the second embodiment. FIG. 15 is a flowchart showing another example of the flow of the process of determining the corresponding process by the cloud included in the odor determination system according to the third embodiment. FIG. 16 is a diagram showing an example of the functional configuration of the SCU included in the odor determination system according to the fourth embodiment.

Hereinafter, the odor determination device, the odor determination method, and the odor determination system to which the odor determination system is applied will be described with reference to the attached drawings.

(First Embodiment)
FIG. 1 is a diagram showing an example of an outline configuration of an odor determination system according to a first embodiment.

First, an example of the outline configuration of the odor determination system 10 according to the present embodiment will be described with reference to FIG.

The odor determination system 10 according to the present embodiment determines the type of odor. Here, the type of odor is a type of odor existing in various environments, such as an odor existing in air, an odor existing in gas, and an odor existing in a housing. Next, the odor determination system 10 determines a process corresponding to the type of odor (hereinafter referred to as a corresponding process) based on the determination result.

As shown in FIG. 1, the odor determination system 10 includes a plurality of odor sensors 11, a SCU 12, a cloud 13, an external device control module 14, a mobile terminal 15, and an external device X.

The odor sensor 11 and the SCU 12 are connected to each other so as to be able to communicate with each other via a communication means L1 such as NFC (Near Field Communication) or Bluetooth (registered trademark). Further, the SCU 12, the cloud 13, the external device control module 14, and the mobile terminal 15 are connected to each other via a communication means L2 such as a LAN (Local Area Network), a dedicated line such as a wireless LAN, or a public line such as the Internet. , Connected to communicate with each other.

The odor sensor 11 is a sensor that detects the mass of the odor-causing substance and the like.

The SCU (Sensor Control Unit) 12 is a single board computer, a personal computer, or the like, and controls the detection of the mass of the odor-causing substance by the odor sensor 11. Further, the SCU 12 has a communication function between the odor sensor 11 and the cloud 13 (for example, wireless communication by Wi-Fi (registered trademark), Bluetooth (registered trademark), Zigbee (registered trademark), etc.), or the cloud 13 and a mobile terminal. It has a communication function with 15 (for example, 4G line or LAN: Local Area Network).

The cloud 13 acquires the detection result such as the mass of the odor-causing substance by the odor sensor 11 via the SCU 12, determines the type of odor based on the detection result, and determines the corresponding processing corresponding to the determination result. do.

The external device control module 14 is a single board computer, an I / O expansion board, or the like, and acquires the determination result of the type of odor and the determination result of the corresponding processing from the cloud 13 and instructs the execution of the acquired corresponding processing. The control signal is transmitted to the external device X.

The mobile terminal 15 executes the user's login to the odor determination system 10, the acquisition of the odor type determination result from the cloud 13, and the determination result of the corresponding processing.

FIG. 2 is a diagram showing an example of the configuration of the odor sensor included in the odor determination system according to the first embodiment.

Next, an example of the configuration of the odor sensor 11 according to the present embodiment will be described with reference to FIG.

The odor sensor 11 has a detection element such as a QCM (Quartz Crystal Microbalance) sensor, and is a sensor capable of detecting a value related to the odor-causing substance (hereinafter referred to as a detected value) such as the mass of the odor-causing substance. .. The detection element included in the odor sensor 11 is not limited to the QCM sensor as long as it is a detection element capable of detecting the detected value related to the odor-causing substance, and is a sensor of another type such as a gas sensor using a semiconductor thin film. Is also good.

In the present embodiment, as shown in FIG. 2, the odor sensor 11 has a support portion 110, a plurality of detection elements F1 to F16, and a drive detection circuit 111. For example, 16 detection elements F are attached to the support portion 110. In the following description, when it is not necessary to distinguish the detection elements F1 to F16, it is described as the detection element F.

The plurality of detection elements F1 to F16 each detect the mass of the causative substance of a different type of gas. Specifically, the detection element F includes a crystal oscillator, two electrodes, and an adsorption film. A part of the side surface of the crystal oscillator is oscillatedly held by the support portion 110.

The two electrodes are provided on the planes on both sides of the crystal unit. Further, an AC voltage is applied to the two electrodes from the drive detection circuit 111.

The adsorption film is provided on at least one of the planes of the crystal unit. In addition, the adsorption membrane adsorbs a specific causative substance. Each of the plurality of detection elements F1 to F16 has an adsorption film that adsorbs causative substances having different chemical properties.

In the detection element F, when an AC voltage having a resonance frequency is applied to the two electrodes, the crystal oscillator vibrates due to the piezoelectric effect. The resonance frequency of the crystal unit is determined by the mass and viscoelasticity of the causative substance adhering to the adsorption film. Therefore, when the causative substance is adsorbed on the adsorption film and the mass changes, the resonance frequency of the detection element F changes according to the change in the mass of the adsorbed causative substance.

The drive detection circuit 111 applies an AC voltage to at least one detection element F to detect a change in the resonance frequency of the detection element F per unit time. As a result, the drive detection circuit 111 can detect the mass of the odor-causing substance for each detection element F.

The odor sensor 11 transmits the change in the resonance frequency detected by the drive detection circuit 111 to the SCU 12 via the communication means L1 as a detection value. In the present embodiment, the odor sensor 11 transmits the change in the resonance frequency detected by the drive detection circuit 111 to the SCU 12 as a detection value, but transmits a value related to the odor-causing substance as a detection value. If there is, the present invention is not limited to this, and for example, a change in the resistance value of the detection element F may be transmitted to the SCU 12 as a detection value.

FIG. 3 is a diagram showing an example of the detected value output from the odor sensor included in the odor determination system according to the first embodiment.

Next, an example of the detected value output from the odor sensor 11 included in the odor determination system 10 according to the present embodiment will be described with reference to FIG.

As shown in FIG. 3, the odor sensor 11 may output data (hereinafter referred to as an odor pattern) in which the detection values output from each of the detection elements F1 to F16 are patterned. The odor pattern output by the odor sensor 11 has a wide variety of odor patterns according to the detection values output from each of the detection elements F1 to F16.

In the present embodiment, an example in which the odor sensor 11 has 16 types of detection elements F is shown, but the present invention is not limited to this, and the number of detection elements F is less than 16 types or more than 16 types. May have. When a plurality of types of odors are mixed, the odor sensor 11 has more detection elements F, so that the accuracy of determining the type of odor can be improved.

The cloud 13 receives the detected value output from the odor sensor 11 via the SCU 12. The cloud 13 stores determination information indicating the type of odor indicated by the detected value in association with the detected value output from the odor sensor 11. The cloud 13 determines the type of odor corresponding to the detected value received from the odor sensor 11 based on the determination information stored in association with the received detected value. Further, the cloud 13 determines the intensity of the odor based on the rate of change of the detected value per unit time output from the detection element F. The greater the rate of change in the detected value per unit time, the stronger the odor.

In the initial state in which the determination information is not stored, the cloud 13 generates determination information indicating one type of odor indicated by the detection value based on the detection value received from the odor sensor 11. The cloud 13 performs multivariate analysis using, for example, a neural network, and generates determination information indicating one type of odor indicated by the detected value.

FIG. 4 is a diagram for explaining an example of the determination information generation process in the cloud of the odor determination system according to the first embodiment.

Next, with reference to FIG. 4, an example of the determination information generation process in the cloud 13 of the odor determination system 10 according to the present embodiment will be described.

The cloud 13 uses a neural network having an input layer N1, an intermediate layer N2, and an output layer N3 to generate determination information indicating one type of odor corresponding to the received detected value. The input layer N1 receives the detected value from the odor sensor 11. The intermediate layer N2 extracts the feature amount of the odor type from the detected values received from the input layer N1. Here, the feature amount is an amount that can distinguish the difference from other odor types. The output layer N3 outputs the type of odor indicated by the feature amount extracted in the intermediate layer N2 as determination information.

After generating the judgment information, the cloud 13 updates the judgment information with the judgment information whose accuracy is improved by the learning process. The cloud 13 may execute the learning process a plurality of times in order to improve the accuracy of the determination information.

For example, a plurality of odor-causing substances may be mixed in the odor-causing substances detected by the detection element F included in the odor sensor 11. In this case, the type of odor determined by the cloud 13 may not always match the odor actually felt by the human sense of smell. This often has a problem with the feature amount of the type of odor extracted in the intermediate layer N2. Therefore, the cloud 13 extracts the feature amount corresponding to the type of odor perceived by the human sense of smell by modifying the feature amount output from the intermediate layer N2.

In the present embodiment, the cloud 13 uses a neural network to determine the type of odor corresponding to the detected value received from the odor sensor 11, but the cloud 13 is not limited to this, and is not limited to this, for example, pattern matching. Or SVN may be used to determine the type of odor corresponding to the detected value received from the odor sensor 11.

FIG. 5 is a diagram showing an example of the hardware configuration of the SCU included in the odor determination system according to the first embodiment.

Next, an example of the hardware configuration of the SCU 12 included in the odor determination system 10 according to the present embodiment will be described with reference to FIG.

As shown in FIG. 5, the SCU 12 has a CPU (Central Processing Unit) 121, a ROM (Read Only Memory) 122, a RAM (Random Access Memory) 123, and a memory unit 124.

The CPU 121 controls the entire SCU 12. The ROM 122 and the memory unit 124 store various programs. The RAM 123 temporarily stores various data. The CPU 121, ROM 122, RAM 123, and memory unit 124 are connected to each other via the data bus 125.

Then, the CPU 121 expands various programs stored in the ROM 122 and the memory unit 124 into the RAM 123, and executes the expanded various programs to control the entire SCU 12.

Further, as shown in FIG. 5, the CPU 121 is connected to the operation unit 127 and the display unit 128 via the data bus 125 and the controller 126. The operation unit 127 is a keyboard for the operator to operate and input data. The display unit 128 is composed of, for example, a liquid crystal display, and displays information to the operator of the SCU 12.

Further, as shown in FIG. 5, the CPU 121 is connected to the communication I / F 129 via the data bus 125. The communication I / F 129 is connected to the communication means L1 and the communication means L2. The communication I / F 129 can communicate with the odor sensor 11 via the communication means L1, and receives various information such as a detected value from the odor sensor 11. Further, the communication I / F 129 can communicate with the cloud 13 via the communication means L2, and receives various information from the cloud 13 such as teacher data and corrected determination information. Here, the communication I / F 129 also transmits various information such as a detection value of the detection element F to the cloud 13 via the communication means L2. Further, the communication I / F 129 can communicate with the mobile terminal 15.

FIG. 6 is a diagram showing an example of a cloud hardware configuration of the odor determination system according to the first embodiment.

Next, an example of the hardware configuration of the cloud 13 included in the odor determination system 10 according to the present embodiment will be described with reference to FIG.

As shown in FIG. 6, the cloud 13 has a CPU 131, a ROM 132, a RAM 133, and a memory unit 134.

The CPU 131 controls the entire cloud 13. The ROM 132 and the memory unit 134 store various programs. The RAM 133 temporarily stores various data. The CPU 131, ROM 132, RAM 133, and memory unit 134 are connected to each other via the data bus 135.

Then, the CPU 131 expands various programs stored in the ROM 132 and the memory unit 134 into the RAM 133, and executes the expanded various programs to control the entire cloud 13.

Further, as shown in FIG. 6, the CPU 131 is connected to the operation unit 137 and the display unit 138 via the data bus 135 and the controller 136. The operation unit 137 is a keyboard for the operator to operate and input data. Further, the display unit 138 is composed of, for example, a liquid crystal display, and displays information to the operator of the cloud 13.

Further, as shown in FIG. 6, the CPU 131 is connected to the communication I / F 139 via the data bus 135. The communication I / F 139 is connected to the communication means L2. The communication I / F 139 can communicate with the SCU 12 via the communication means L2, and receives information (for example, a detection value of the detection element F) from the SCU 12. Further, the communication I / F 139 transmits information to the SCU 12 via the communication means L2.

FIG. 7A is a diagram showing an example of a cloud functional configuration included in the odor determination system according to the first embodiment.

Next, an example of the functional configuration of the cloud 13 included in the odor determination system 10 according to the present embodiment will be described with reference to FIG. 7A.

In the present embodiment, the CPU 131 expands various programs stored in the ROM 132 or the memory unit 134 into the RAM 133, and executes the expanded various programs to execute the acquisition unit 701, the determination unit 702, the odor determination unit 703, and the odor determination unit 703. It functions as a determination unit 704. In this embodiment, the CPU 131 is an example of an odor determination device.

In the present embodiment, the acquisition unit 701, the determination unit 702, the odor determination unit 703, and the determination unit 704 are realized in the cloud 13, but the acquisition unit 701, the determination unit 702, the odor determination unit 703, and the determination unit 704 It is also possible to realize a part or all of the above in an external device (for example, SCU 12) of the cloud 13.

The acquisition unit 701 acquires the detection values obtained from each of the plurality of detection elements F from the plurality of odor sensors 11. In the present embodiment, the acquisition unit 701 acquires the odor pattern of the detection value of the plurality of detection elements F possessed by each of the plurality of odor sensors 11 from the plurality of odor sensors 11 via the SCU 12.

The determination unit 702 determines whether or not the detection value acquired by the acquisition unit 701 exceeds a predetermined threshold value. Here, the predetermined threshold value is a preset threshold value. Specifically, the predetermined threshold value is the threshold value of the detection value for determining the presence of the odor-causing substance.

When the odor determination unit 703 determines by the determination unit 702 that at least one of the plurality of detected values exceeds a predetermined threshold value, the odor determination unit 703 determines that the plurality of detected values exceed a predetermined threshold value, and the odor determination unit 703 is based on an odor pattern in which the plurality of detected values are patterned. Judge the type of. In the present embodiment, the odor determination unit 703 determines the type of odor based on the odor pattern, but if the type of odor is determined based on the detection values of the plurality of detection elements F, the odor determination unit 703 determines the type of odor. It is not limited to this. For example, the odor determination unit 703 extracts the feature amount of the odor type from the plurality of detected values acquired by the acquisition unit 701, and determines the odor type based on the feature amount.

The determination unit 704 determines the corresponding processing corresponding to the type of odor determined by the odor determination unit 703. As a result, when it is determined that an odor is present, the corresponding processing corresponding to the odor type can be automatically executed based on the determination result of the odor type.

For example, the determination unit 704 determines spraying of a deodorant, ventilation, generation of ozone, operation of an air purifier, etc. as a response process corresponding to an odor determined as a type of odor by the odor determination unit 703.

In addition, the determination unit 704 publishes the determination result of the type of odor and the determination result of the corresponding processing to the external device control module 14 and the mobile terminal 15 by the Web API (Application Programming Interface) or the like.

As a result, the external device control module 14 and the mobile terminal 15 can acquire the determination result of the type of odor and the determination result of the corresponding processing. For example, the external device control module 14 acquires the determination result of the corresponding process published by the determination unit 704 at a preset cycle.

Then, the external device control module 14 functions as an example of a control unit that outputs the acquired control information instructing the execution of the corresponding processing to the external device X. For example, the external device control module 14 has a control program that turns on a relay that can instruct the external device X to execute the determined corresponding processing among the relays of a plurality of channels (for example, four channels) of the relay output board. Execute.

FIG. 7B is a diagram for explaining an example of an external device control module and an external device included in the odor determination system according to the first embodiment.

Next, an example of the external device control module 14 and the external device X included in the odor determination system 10 according to the present embodiment will be described with reference to FIG. 7B.

In this embodiment, the external device control module 14 has a single board computer, a relay output board, and the like. Then, as shown in FIG. 7B, the external device control module 14 acquires the determination result of the corresponding processing by the determination unit 704 of the cloud 13 via the SCU 12. Next, the external device control module 14 turns on the relay capable of instructing the external device X to execute the determined response process among the relays of the plurality of channels of the relay output board based on the acquired determination result of the response process. do. As shown in FIG. 7B, the external device X executes a corresponding process (for example, spraying a deodorant) corresponding to the relay turned on by the external device control module 14.

FIG. 8 is a flowchart showing an example of a flow of determination processing of correspondence processing by the cloud included in the odor determination system according to the first embodiment.

Next, an example of the flow of the determination processing of the corresponding processing by the cloud 13 will be described with reference to FIG.

First, the acquisition unit 701 acquires the detection values of the plurality of detection elements F from the plurality of odor sensors 11 via the SCU 12 (step S801). In the present embodiment, the acquisition unit 701 acquires the detection values of the plurality of detection elements F from the plurality of odor sensors 11 at a preset cycle.

Next, the determination unit 702 determines whether or not the detection value of the detection element F exceeds a predetermined threshold value each time the detection value is acquired by the acquisition unit 701 (step S802).

When none of the detection values of the plurality of detection elements F exceeds a predetermined threshold value (step S802: No), the determination unit 702 determines that the odor does not exist, and ends the determination process of the corresponding process.

On the other hand, when the detection value of at least one detection element F among the plurality of detection elements F exceeds a predetermined threshold value (step S802: Yes), the odor determination unit 703 is based on the detection values of the plurality of detection elements F. , The type of odor is determined (step S803).

Next, the determination unit 704 determines the corresponding process corresponding to the determined odor type based on the determination result of the odor type by the odor determination unit 703 (step S804).

Next, with reference to FIGS. 9 to 13, an example of various situations to which the odor determination system 10 according to the present embodiment can be applied will be described. FIG. 9 is an explanatory diagram of an example in which the odor determination system according to the first embodiment is used for an automatic vacuum cleaner robot. FIG. 10 is an explanatory diagram of an example in which the odor determination system according to the first embodiment is used for a deodorizing system in a hotel room. FIG. 11 is an explanatory diagram of an example in which the odor determination system according to the first embodiment is used for an exhaust system of a restaurant. FIG. 12 is an explanatory diagram of an example in which the odor determination system according to the first embodiment is used as a measure against bad breath. FIG. 13 is an explanatory diagram of an example in which the odor determination system according to the first embodiment is used for risk prediction of an important facility.

First, an example of applying the odor determination system 10 according to the present embodiment to deodorization and cleaning will be described.

For example, when the odor determination system 10 according to the present embodiment is used as a deodorizing measure for the odor discharged from the factory, the odor sensor 11 is installed in the exhaust duct of the factory. Then, when the detection value of the detection element F included in the odor sensor 11 exceeds a predetermined threshold value, the odor determination unit 703 of the cloud 13 determines the type of odor based on the plurality of detection values. Next, the determination unit 704 of the cloud 13 determines the process of spraying the deodorant corresponding to the determined odor type as the corresponding process.

For example, when the odor determination system 10 according to the present embodiment is used for controlling the automatic vacuum cleaner robot 900, the odor sensor 11 is mounted on the automatic vacuum cleaner robot 900 as shown in FIG. Then, when the detection value of the detection element F of the odor sensor 11 exceeds a predetermined threshold value while the automatic vacuum cleaner robot 900 is cleaning, the odor determination unit 703 of the cloud 13 determines the odor based on a plurality of detection values. Judge the type of. Next, the determination unit 704 of the cloud 13 determines the corresponding process for spraying the deodorant corresponding to the determined odor type, and causes the automatic vacuum cleaner robot 900 to execute the corresponding process. When the detection element F of the odor sensor 11 mounted on the automatic vacuum cleaner robot 900 can detect the detected value of the odor-causing substance in the entire room, the determination unit 704 of the cloud 13 creates an air flow by blowing air. Ventilation can also be determined as a corresponding process.

For example, when the odor determination system 10 according to the present embodiment is used as a deodorizing system in a hotel room, an odor sensor 11 is installed in the hotel room as shown in FIG. Then, when the detection value of the detection element F of the odor sensor 11 exceeds a predetermined threshold value after the customer checks out the hotel, the odor determination unit 703 of the cloud 13 determines the odor based on the plurality of detection values. Judge the type of. Next, the determination unit 704 of the cloud 13 determines the spraying of the deodorant corresponding to the determined odor type or the generation of ozone as the corresponding process. As a result, it is not necessary for the hotel employee to confirm the odor of the hotel guest room and perform the processing corresponding to the confirmed odor, so that the labor saving of the hotel employee can be achieved.

Next, an example of applying the odor determination system 10 according to the present embodiment to food-related items will be described.

For example, as shown in FIG. 11, in the building 1100 containing a plurality of restaurants 1101-1109, the exhaust from each restaurant 1101-1109 is often exhausted to the outside at once. Therefore, when the filter of the exhaust equipment of a certain restaurant (for example, restaurant 1101) deteriorates or breaks down and the exhaust of that restaurant is exhausted to the outside, the exhaust equipment of any restaurant deteriorates or breaks down. It is difficult to identify what is happening, and it takes time to improve it.

Therefore, when the odor determination system 10 according to the present embodiment is used as a countermeasure against odors exhausted from the building 1100 containing a plurality of restaurants 1101 to 1109, as shown in FIG. 11, a duct that exhausts air to the outside of the building 1100. The odor sensor 11 is installed in 1110. Then, when the detection value of the detection element F included in the odor sensor 11 exceeds a predetermined threshold value, the odor determination unit 703 of the cloud 13 determines the type of odor based on the plurality of detection values. Next, the determination unit 704 of the cloud 13 identifies the restaurant (for example, restaurant 1101) that is generating the odor based on the determined type of odor, and notifies the restaurant 1101 to improve the odor. The process to be performed is determined as the corresponding process. As a result, the restaurant 1101 can immediately repair the exhaust equipment, and the time required for improving the odor exhausted from the building 1100 can be shortened. At that time, the determination unit 704 of the cloud 13 may acquire the information of the smart meters of each restaurant 1101 to 1109 and identify the restaurant generating the odor from the operating restaurants. ..

For example, when the odor determination system 10 according to the present embodiment is used for process control of a food factory that manufactures food, an odor sensor 11 is installed on the line of the food factory. Then, when the detection value of the detection element F included in the odor sensor 11 exceeds a predetermined threshold value, the odor determination unit 703 of the cloud 13 determines the type of odor based on the plurality of detection values. Next, the determination unit 704 of the cloud 13 determines the corresponding processing corresponding to the determined odor type.

Specifically, the determination unit 704 of the cloud 13 stops the device that generates the burnt odor among the devices of the food factory when the burnt odor generated during cooking of the food is determined to be the type of odor. Is determined as the corresponding process. Further, the determination unit 704 of the cloud 13 determines in the corresponding process an alert notifying that the odor generated by the spoilage of the food is generated by the spoilage of the food when the odor generated by the spoilage of the food is determined by the type of the odor. .. Further, when the scent of the beast is determined to be the type of scent, the determination unit 704 of the cloud 13 determines an alert notifying that the beast is occurring in the corresponding process.

Next, an example of applying the odor determination system 10 according to the present embodiment to the etiquette relationship will be described.

For example, when the odor determination system 10 according to the present embodiment is used as a measure against bad breath, an odor sensor 11 is installed in an office or hotel in the hospitality industry as shown in FIG. Then, when the detection value of the detection element F possessed by the odor sensor 11 when the odor sensor 11 is blown with exhaled air, the odor determination unit 703 of the cloud 13 exceeds a predetermined threshold value, the odor determination unit 703 is based on the plurality of detection values. Judge the type of. At that time, the odor determination unit 703 is made to input the food eaten by the subject, the presence or absence of alcohol intake, the body odor of the subject, the photograph of the mouth of the subject, etc., and adds the input information to the type of odor. May be determined. Next, the determination unit 704 of the cloud 13 determines the corresponding processing corresponding to the determined odor type.

Specifically, when the odor of dumplings is determined to be the type of odor, the determination unit 704 of the cloud 13 determines the notification process for urging the use of mouthwash for garlic as the corresponding process. Further, when the odor of periodontal disease is determined to be the type of odor, the determination unit 704 of the cloud 13 determines the notification process for encouraging the use of the mouthwash 1203 for treating the periodontal disease as the corresponding process. Further, when the bad breath due to indigestion is determined to be the type of odor, the determination unit 704 of the cloud 13 determines the notification process for encouraging the use of a stomach medicine or an intestinal regulator as a corresponding process. Further, as shown in FIG. 12, the determination unit 704 of the cloud 13 determines the process of displaying the degree of inconvenience caused by the determined odor type to the other party on the display device 1202 as the corresponding process. Further, in the determination unit 704 of the cloud 13, when the determined odor type is the mouthwash 1203 or the odor type that cannot be deodorized by the prescription of the medicine, the distance at which the bad breath does not affect the other party, the mouthwash 1203, or the like. The process of displaying the time when the effect of prescribing the drug disappears on the display device 1202 may be determined as the corresponding process.

For example, when the odor determination system 10 according to the present embodiment is also used as a measure against body odor, the odor sensor 11 is installed in a closed space (for example, a room) installed in an office in the hospitality industry, a hotel, a running station, or the like. .. Then, when the detection value of the detection element F possessed by the odor sensor 11 when the subject enters the closed space, the odor determination unit 703 of the cloud 13 exceeds a predetermined threshold value, the odor determination unit 703 is based on a plurality of detection values. Judge the type of. Next, the determination unit 704 of the cloud 13 determines the corresponding processing corresponding to the determined odor type.

Specifically, when the odor of sweat is determined to be the type of odor, the determination unit 704 of the cloud 13 determines the spraying of the deodorant spray as the corresponding process. Further, the determination unit 704 of the cloud 13 determines the spraying of the antibacterial spray as the corresponding treatment when the odor due to the dryness of the clothes is determined to be the type of odor. Further, when the odor of the axillary odor is determined to be the type of odor, the determination unit 704 of the cloud 13 determines the spraying of the deodorant spray centering on the axilla as the corresponding process. Further, when the odor of the foot is determined to be the type of odor, the determination unit 704 of the cloud 13 determines the spraying of the deodorant spray centering on the foot as the corresponding process. Further, when the odor of the scalp is determined to be the type of odor, the determination unit 704 of the cloud 13 determines the spraying of the fragrance for hair as a corresponding process.

Next, an example of applying the odor determination system 10 according to the present embodiment to risk prediction of important facilities (for example, data centers, shrines and temples, power plants, substations) will be described.

For example, when the odor determination system 10 according to the present embodiment is used for risk prediction of a data center 1301, a power plant, or a substation 1302, as shown in FIG. 13, an information processing device 1301a installed in the data center 1301 or , The odor sensor 11 is installed on the distribution board 1302a, the distribution board 1302b, and the control board 1302c of the power plant or the substation 1302. Then, when the detection value of the detection element F included in the odor sensor 11 exceeds a predetermined threshold value, the odor determination unit 703 of the cloud 13 determines the type of odor based on the plurality of detection values. Next, the determination unit 704 of the cloud 13 determines in the response process an alert notifying that a fire may occur when the odor of burning wiring is determined as the type of odor.

Conventionally, when smoke is detected by a smoke detector installed in the data center 1301, it is necessary for a person to enter the data center 1301 in order to identify the place where the smoke is emitted in the data center 1301. .. On the other hand, according to the odor determination system 10 according to the present embodiment, if the location of the detection element F that detects the detected value of the determined odor type is specified, the location where smoke is generated in the data center 1301 can be determined. It can be easily identified.

In addition, since it is difficult for smoke to be emitted from the wiring existing in the power plant or substation 1302, depending on the smoke detector, it may not be possible to detect smoke from the wiring until the damage becomes large. On the other hand, according to the odor determination system 10 according to the present embodiment, if the odor sensor 11 is installed in the power plant or the substation 1302, it is possible to execute the processing for dealing with the scorching of the wiring before the damage becomes large. .. Further, in addition to the detection value of the detection element F possessed by the odor sensor 11, a dust sensor that measures particles in the air with light is used to detect the generation of smoke, so that the accuracy of the processing for dealing with the scorching of the wiring can be determined. And the time until the corresponding process is executed can be shortened.

As described above, according to the odor determination system 10 according to the first embodiment, it is possible to automatically execute the corresponding processing corresponding to the odor type based on the determination result of the odor type.

(Second Embodiment)
In this embodiment, an example in which a corresponding process is determined based on the degree of similarity between an odor pattern in which a plurality of detected values are patterned and a reference pattern which is a reference odor pattern set for each odor type candidate. Is. In the following description, description of the same configuration as that of the first embodiment will be omitted.

In the present embodiment, the determination unit 704 of the cloud 13 obtains the degree of similarity between the odor pattern in which a plurality of detected values are patterned and the reference pattern. Here, the reference pattern is a pattern that is preset for each candidate for the type of odor to be determined and serves as a reference for the odor pattern.

Then, the determination unit 704 determines the corresponding processing when the obtained similarity is equal to or higher than the predetermined similarity. Here, the predetermined similarity is a preset similarity, which is a lower limit value (for example, 50%) of the similarity for executing the corresponding process. As a result, it is possible to prevent an erroneous response process from being determined due to fluctuations such as a measurement error of the detected value by the detection element F. As a result, it is possible to prevent the odor from being exacerbated by executing an erroneous response process.

On the other hand, the determination unit 704 does not determine the corresponding processing when the obtained similarity is less than the predetermined similarity. For example, when the response process differs depending on the cause of the fire that is causing the odor, if the wrong response process is executed, the fire may be exacerbated. Therefore, as described above, the determination unit 704 determines the corresponding process when the obtained similarity is equal to or higher than the predetermined similarity.

For example, when the similarity between the odor pattern and the reference pattern A is 34%, the similarity between the odor pattern and the reference pattern B is 33%, and the similarity between the odor pattern and the reference pattern C is 33%. , The type of odor is likely to be the type of odor of reference pattern A, but is also close to the type of odor of reference patterns B and C.

Therefore, in this case, the determination unit 704 does not determine the corresponding processing because the similarity between the odor pattern and each of the reference patterns A to C is less than the predetermined similarity. Then, the acquisition unit 701 described above reacquires the detection values of the plurality of detection elements F. Further, when the degree of similarity is less than a predetermined degree of similarity, the odor determination unit 703 redetermines the type of odor based on a plurality of newly acquired detected values. As a result, when the similarity between the odor pattern and the reference patterns A to C is low and the reliability of the odor type determination result is low, the odor type is re-determined and the odor type determination result with high reliability is obtained. Based on this, the corresponding processing can be determined. As a result, it becomes possible to execute a corresponding process that is more suitable for the determination result of the type of odor.

Further, the odor determination unit 703 determines the odor type candidate corresponding to the reference pattern having the highest degree of similarity consecutively a preset number of times among the plurality of reference patterns A to C as the odor type. Is also possible. That is, among the plurality of reference patterns A to C, the odor type candidate corresponding to the reference pattern having the highest similarity consecutively a preset number of times is the odor type determination result by the odor determination unit 703. .. For example, when the similarity between the odor pattern and the reference pattern A is the highest among the similarity between the odor pattern and the reference patterns A to C for a preset number of times in a row, the odor determination unit 703 may perform the odor determination unit 703. , The candidate of the odor type corresponding to the reference pattern A is determined as the odor type. As a result, the corresponding processing can be determined based on the determination result of the more reliable odor type based on the similarity between the odor pattern and each of the reference patterns A to C. As a result, it becomes possible to execute a corresponding process that is more suitable for the determination result of the type of odor. In the present embodiment, when the degree of similarity between the odor pattern and each of the reference patterns A to C is less than the predetermined degree of similarity, the odor determination unit 703 determines the degree of similarity among the plurality of reference patterns A to C. The odor type candidate corresponding to the highest reference pattern in succession for a preset number of times shall be determined as the odor type.

Further, in the present embodiment, the determination unit 704 can change the corresponding processing according to the obtained similarity. For example, when the corresponding treatment is spraying a deodorant, the determination unit 704 changes to a corresponding treatment in which the amount of the deodorant to be sprayed increases as the obtained similarity increases. Further, when the corresponding treatment is the generation of ozone, the determination unit 704 changes to the corresponding treatment in which the amount of ozone generated is large as the obtained similarity becomes large. Further, when the corresponding process is the operation of the air purifier, the determination unit 704 changes the operating time of the air purifier to the longer corresponding process as the obtained similarity increases.

Further, in the present embodiment, when a plurality of odor types are determined by the odor determination unit 703 and the corresponding processing corresponding to each of the plurality of odor types is determined, the determination unit 704 is determined by the plurality of determined odor types. It is also possible to change the determined correspondence process based on the relationship between the correspondence processes of. As a result, when a plurality of odor types are determined by the odor determination unit 703 and corresponding processes corresponding to each of the plurality of odor types are determined, if they are executed at the same time, the odors and the like are deteriorated. It is possible to prevent the processes from being executed at the same time.

For example, if the odor or the like deteriorates when a plurality of determined corresponding processes are executed at the same time, the determination unit 704 executes one of the determined plurality of corresponding processes. At that time, the determination unit 704 selects the corresponding process corresponding to the type of odor of the reference pattern having the highest degree of similarity to the odor pattern among the plurality of determined corresponding processes. Alternatively, if the odor or the like deteriorates when a plurality of determined corresponding processes are executed at the same time, the determination unit 704 can discard the determined result of the corresponding process.

Further, in the present embodiment, the determination unit 704 can change the determined response process based on at least one of the temperature and humidity of the installation location of the detection element F. For example, the determination unit 704 acquires the temperature and humidity of the location where the detection element F is installed from the sensor installed near the detection element F. Then, when the acquired temperature or humidity belongs to a predetermined temperature or humidity range, the determination unit 704 changes the corresponding process (for example, discards the corresponding process). Here, the predetermined temperature or humidity range is a preset temperature or humidity range.

FIG. 14 is a flowchart showing another example of the flow of the process of determining the corresponding process by the cloud included in the odor determination system according to the second embodiment.

Next, another example of the flow of the determination processing of the corresponding processing by the cloud 13 will be described with reference to FIG. Since steps S801 to S803 shown in FIG. 14 are the same as those in FIG. 8, the description thereof will be omitted.

The determination unit 704 determines the degree of similarity between the odor pattern and each of the plurality of reference patterns (for example, the three reference patterns A to C) (step S1401). Here, the determination unit 704 obtains the similarity between each of the three reference patterns A to C and the odor pattern, but may obtain the similarity between the plurality of reference patterns and the odor pattern. For example, it is not limited to this.

Next, the determination unit 704 determines whether or not the obtained similarity is equal to or higher than the predetermined similarity for each type of odor corresponding to each of the plurality of reference patterns (step S1402). Then, the determination unit 704 determines the corresponding processing corresponding to the type of odor for the type of odor determined that the obtained similarity is equal to or higher than the predetermined degree of similarity (step S1402: Yes) (step S1403). .. On the other hand, the determination unit 704 does not determine the corresponding processing corresponding to the type of odor for the type of odor determined that the obtained similarity is less than the predetermined degree of similarity (step S1402: No).

As described above, according to the odor determination system 10 according to the second embodiment, it is possible to prevent the erroneous response process from being determined due to fluctuations in the measurement error of the detected value by the detection element F, and thus the erroneous response process. Is performed to prevent the odor from getting worse.

(Third Embodiment)
This embodiment is an example of determining the corresponding processing based on the number of times that the same odor type is determined. In the following description, description of the same configuration as that of the first embodiment will be omitted.

In the present embodiment, the determination unit 704 of the cloud 13 continuously determines the same odor type by the odor determination unit 703 for a predetermined number of times n (n is an integer of 1 or more. For example, n = 3) or more. If so, determine the corresponding process. Here, the predetermined number of times is a preset number of times, and is a number of times for which the odor determination unit 703 determines with high reliability the determination result of the type of odor.

This makes it possible to prevent the corresponding process from being determined based on the determination result of the wrong odor type. As a result, it is possible to increase the possibility of executing an appropriate response process for the odor. In addition, the response process is not executed for the temporarily generated odor, and the response process (for example, spraying of deodorant) is executed when the odor is continuously generated for a certain period of time. It is possible to reduce the load on the external device X (for example, the deodorant sprayer) due to the execution of the corresponding processing for the temporarily generated odor.

In the present embodiment, the determination unit 704 determines the corresponding processing based on the number of times that the same odor type is determined, but the present invention is not limited to this. For example, the determination unit 704 may determine the corresponding process based on the time during which the same odor type continues to be determined.

Specifically, the determination unit 704 determines the corresponding processing corresponding to the type of odor when the same type of odor continues to be determined for a predetermined time. On the other hand, the determination unit 704 does not determine the corresponding process when the time during which the same odor type continues to be determined is less than a predetermined time. As a result, the response process is not executed for the temporarily generated odor, and the response process is executed when the odor is continuously generated for a certain period of time, so that the response process is temporarily generated. It is possible to reduce the load on the external device X due to the execution of the corresponding processing for the odor.

FIG. 15 is a flowchart showing another example of the flow of the process of determining the corresponding process by the cloud included in the odor determination system according to the third embodiment.

Next, another example of the flow of the determination processing of the corresponding processing by the cloud 13 will be described with reference to FIG. Since steps S801 to S803 shown in FIG. 15 are the same as those in FIG. 8, the description thereof will be omitted.

The determination unit 704 determines whether or not the same odor type has been determined consecutively for a predetermined number of times n (for example, three times) or more for each odor type determined by the odor determination unit 703 (step S1501). ).

When it is determined that the same odor type is determined by the odor determination unit 703 (step S1501: Yes) in succession for a predetermined number of times n or more, the determination unit 704 corresponds to the odor type determined by the odor determination unit 703. The corresponding processing to be performed is determined (step S1502).

On the other hand, when it is determined that the same odor type is not determined by the odor determination unit 703 for a predetermined number of times n or more (step S1501: No), the determination unit 704 determines the odor by the odor determination unit 703. Do not determine the corresponding processing corresponding to the type of.

As described above, according to the odor determination system 10 according to the third embodiment, it is possible to prevent the response process from being determined based on the determination result of the wrong odor type, so that an appropriate response process for the odor can be suppressed. Can be more likely to be executed. In addition, the response process is not executed for the temporarily generated odor, and the response process is executed when the odor is continuously generated for a certain period of time, so that the temporarily generated odor is generated. It is possible to reduce the load on the external device X due to the corresponding processing being executed.

(Fourth Embodiment)
This embodiment is an example of determining a corresponding process corresponding to the type of odor in SCU. In the following description, the description of the same parts as those in the first to third embodiments will be omitted.

FIG. 16 is a diagram showing an example of the functional configuration of the SCU included in the odor determination system according to the fourth embodiment.

In the present embodiment, the CPU 121 expands various programs stored in the ROM 122 or the memory unit 124 into the RAM 123, and executes the expanded various programs to execute the acquisition unit 701, the determination unit 702, the odor determination unit 703, and the odor determination unit 703. It functions as a determination unit 704. In this embodiment, the CPU 121 is an example of an odor determination device.

As a result, even in a situation where the SCU 12 is not connected to the network and cannot communicate with the cloud 13 (for example, when the SCU 12 is mounted on a car or a ship), the type of odor is determined and the determination is made. Corresponding processing corresponding to the type of odor can be executed.

In the present embodiment, the odor determination unit 703 shall download in advance the determination information generated by the learning process in the cloud 13 from the cloud 13. Then, the odor determination unit 703 determines the type of odor based on the detection values of the plurality of detection elements F by using the downloaded determination information.

Also in this embodiment, the determination unit 704 shall disclose the determination result of the type of odor and the determination result of the corresponding processing to the external device control module 14 and the mobile terminal 15 by the Web API or the like.

In the present embodiment, the SCU 12 and the external device control module 14 are realized by separate devices, but when the SCU 12 is connected to an I / O expansion board or a relay output board connected to the external device X. Can realize the function of the external device control module 14 in the SCU 12.

However, if the SCU 12 is mounted in a dedicated housing like a commercially available gateway and it is difficult to connect to the I / O expansion board or relay output board, the SCU 12 and the external device control module 14 are separated devices. Need to be realized by.

As described above, according to the odor determination system 10 according to the fourth embodiment, the SCU 12 is not connected to the network and cannot communicate with the cloud 13 (for example, the SCU 12 is mounted on a car or a ship. In this case as well, the type of odor can be determined, and the corresponding processing corresponding to the determined type of odor can be executed.

As described above, according to the first to fourth embodiments, it is possible to automatically execute the corresponding processing corresponding to the odor type based on the determination result of the odor type.

The program executed by the odor determination system 10 of the present embodiment is provided by being incorporated in a ROM or the like in advance. The program executed by the odor determination system 10 of the present embodiment is a computer in an installable format or an executable format, such as a CD-ROM, a flexible disk (FD), a CD-R, or a DVD (Digital Versatile Disk). It may be configured to be recorded and provided on a recording medium that can be read by.

Further, the program executed by the odor determination system 10 of the present embodiment may be stored on a computer connected to a network such as the Internet and provided by downloading via the network. Further, the program executed by the odor determination system 10 of the present embodiment may be configured to be provided or distributed via a network such as the Internet.

The program executed by the odor determination system 10 of the present embodiment has a modular configuration including the above-mentioned parts (acquisition unit 701, determination unit 702, odor determination unit 703, determination unit 704), and is used as actual hardware. When the CPU reads the program from the ROM and executes the program, each of the above units is loaded on the main storage device, and the acquisition unit 701, the determination unit 702, the odor determination unit 703, and the determination unit 704 are generated on the main storage device. It has become like.

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

10 Smell judgment system 11 Smell sensor 12 SCU
13 Cloud 14 External device control module 15 Mobile terminal 121,131 CPU
122,132 ROM
123,133 RAM
124,134 Memory unit 125,135 Data bus 126,136 Controller 127,137 Operation unit 128,138 Display unit 129,139 Communication I / F
701 Acquisition unit 702 Judgment unit 703 Smell judgment unit 704 Determining unit F Detection element X External device

Claims (11)

1. An acquisition unit that acquires detection values obtained from each of a plurality of detection elements,
   A determination unit that determines whether or not the detected value exceeds a preset threshold value, and
   When the detection value of at least one of the plurality of detection elements exceeds the threshold value, the type of odor is based on the odor pattern in which the plurality of detection values acquired by the acquisition unit are patterned. The odor judgment unit that determines
   A determination unit that determines a corresponding process corresponding to the type of odor determined by the odor determination unit, and a determination unit.
   An odor determination device equipped with.
2. The odor determination according to claim 1, wherein the odor determination unit extracts a feature amount of an odor type from a plurality of the detected values acquired by the acquisition unit, and determines the type of odor based on the feature amount. Device.
3. The determination unit determines the corresponding processing when the similarity between the odor pattern and the reference pattern set for each odor type candidate is equal to or higher than a predetermined similarity, claim 1 or 2. The odor determination device described in 1.
4. The odor determination device according to claim 3, wherein the odor determination unit redetermines the type of odor when the similarity is less than the predetermined similarity.
5. Among the plurality of reference patterns, the odor type candidate corresponding to the reference pattern having the highest similarity a predetermined number of times in a row is the odor type determination result of the odor determination unit according to claim 3 or The odor determination device according to 4.
6. The odor determination device according to any one of claims 1 to 4, wherein the determination unit determines the corresponding processing when the same odor type is determined consecutively a predetermined number of times.
7. The odor determination device according to any one of claims 3 to 5, wherein the determination unit further changes the corresponding processing according to the similarity.
8. The odor according to any one of claims 1 to 7, wherein the determination unit further changes the correspondence process based on the relationship between the plurality of correspondence processes when a plurality of the correspondence processes are determined. Judgment device.
9. The odor determination device according to any one of claims 1 to 8, wherein the determination unit changes the corresponding processing based on at least one of the temperature and humidity of the place where the detection element is installed.
10. Obtain the detection values obtained from each of the multiple detection elements,
    It is determined whether or not the detected value exceeds a preset threshold value, and it is determined.
    When the detection value of at least one of the plurality of detection elements exceeds the threshold value, the type of odor is determined based on the odor pattern obtained by patterning the plurality of acquired detection values.
    Determine the corresponding processing corresponding to the determined odor type,
    Smell judgment method including that.
11. An odor determination system having a plurality of detection elements and an external device.
    An acquisition unit that acquires detection values obtained from each of the plurality of detection elements, and an acquisition unit.
    A determination unit that determines whether or not the detected value exceeds a preset threshold value, and
    When the detection value of at least one of the plurality of detection elements exceeds the threshold value, the type of odor is based on the odor pattern in which the plurality of detection values acquired by the acquisition unit are patterned. The odor judgment unit that determines
    A determination unit that determines a corresponding process corresponding to the type of odor determined by the odor determination unit, and a determination unit.
    A control unit that outputs control information instructing execution of the corresponding process determined by the determination unit to the external device, and a control unit.
    Smell judgment system equipped with.

Images