Detection device, detection method, program

Abstract

To provide a technology for identifying or quantifying allergens such as pollen, mold, and mites.SOLUTION: This detection device uses a plurality of semiconductor sensors. With respect to the same gas component, the plurality of semiconductor sensors indicate relatively different response characteristics. The detection device acquires signal patterns detected by the plurality of semiconductor sensors, identifies or quantifies an allergen from the plurality of signal patterns, and outputs a result of identification or quantification.SELECTED DRAWING: Figure 16

Description

Technical Field

[0001] The present disclosure relates to a detection device, a detection method, and a program.

Background Art

[0002] Allergies caused by allergens floating in the air trouble many people. Representative allergens include pollen, mold (fungi), house dust (mites), etc. Among them, hay fever is a common allergy in Japan. Since the amount of pollen dispersed is correlated with the onset and severity of hay fever, the measurement of the amount of pollen dispersed has been conventionally performed. For mold (fungi) and house dust (mites) as well, measurements have been conventionally performed using morphological methods and immunological methods.

[0003] Techniques for detecting minute particles using a laser have been devised (for example, see Patent Document 1). Patent Document 1 discloses a technique for detecting particles having a desired particle diameter by detecting light diffracted by particles having a predetermined particle diameter with a simple light receiving means.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, in the conventional technology, if the particles are of a size close to that of the allergen, there is a possibility of detecting particles other than the allergen, making it difficult to identify the allergen. For this reason, it is also difficult to quantify each allergen.

[0006] The present disclosure provides a technique for identifying or quantifying allergens such as pollen, mold, and mites.

Means for Solving the Problems

[0007] The detection device according to the first aspect of the present disclosure is a detection device for identifying or quantifying allergens in a target space, wherein a control unit acquires signal patterns detected by a plurality of semiconductor sensors that exhibit relatively different response characteristics to the same gas component, identifies or quantifies allergens from the plurality of signal patterns acquired from the plurality of semiconductor sensors, and outputs the result of the identification or quantification.

[0008] According to the first aspect of the present disclosure, it is possible to identify or quantify allergens such as pollen, mold, and mites.

[0009] The detection device according to the second aspect of the present disclosure is the detection device according to the first aspect, wherein the signal pattern of the plurality of semiconductor sensors changes when a gas component is adsorbed.

[0010] The detection device according to the third aspect of the present disclosure is the detection device according to the second aspect, wherein the signal pattern includes a pattern of current, voltage, electrical conductivity, or resistance that changes when a gas component is adsorbed to the semiconductor sensor.

[0011] The detection device according to the fourth aspect of the present disclosure is the detection device according to the third aspect, wherein the signal pattern includes a pattern of current, voltage, electrical conductivity, or resistance that changes when the gas component adsorbed to the semiconductor sensor desorbs.

[0012] The detection device according to the fifth aspect of the present disclosure is the detection device according to the first to fourth aspects, wherein the gas component is introduced into the semiconductor sensor without being pressurized or liquefied.

[0013] The detection device according to the sixth aspect of the present disclosure is the detection device according to the first to fourth aspects The control unit identifies or quantifies allergens in the target space by inputting the plurality of signal patterns into a model generated by machine learning the relationship between the plurality of signal patterns of the plurality of semiconductor sensors and the type or amount of allergens.

[0014] The detection device according to the seventh aspect of the present disclosure is the detection device according to the first to sixth aspects, wherein The plurality of semiconductor sensors include two or more types of semiconductor sensors, and the two or more types of semiconductor sensors have different metal oxides as compositions.

[0015] The detection device according to the eighth aspect of the present disclosure is the detection device according to the fourth aspect, wherein The electrical conductivity repeats a decrease and a recovery as one cycle, The control unit extracts one waveform between the maximum value and the maximum value, or between the minimum value and the minimum value of the electrical conductivity as the signal pattern, and repeatedly uses the signal pattern to identify or quantify allergens.

[0016] The detection device according to the ninth aspect of the present disclosure is the detection device according to the eighth aspect, wherein When the quantified amount of allergens exceeds a threshold value, or when the slope of the amount of allergens with respect to time exceeds a threshold value, the control unit controls the environmental device so as to reduce the amount of allergens or not increase it.

[0017] The detection device according to the tenth aspect of the present disclosure is the detection device according to the first to ninth aspects, wherein the control unit displays the change in the amount of allergens with respect to time for each type of allergen.

[0018] The detection device according to the eleventh aspect of the present disclosure is the detection device according to the first to tenth aspects, wherein the allergen is pollen, mold, or mite.

[0019] The detection device according to the twelfth aspect of the present disclosure is the detection device according to the first to eleventh aspects, wherein the plurality of semiconductor sensors simultaneously output signals regarding a plurality of gas components. The control unit acquires the signal pattern including the signals simultaneously output by the plurality of semiconductor sensors.

[0020] The detection method according to the 13th aspect of the present disclosure is a detection method for a detection device to identify or quantify allergens in a target space, wherein a control unit acquires a signal pattern detected by a plurality of semiconductor sensors that exhibit relatively different response characteristics with respect to the same gas component, identifies or quantifies an allergen from the plurality of signal patterns acquired from the plurality of semiconductor sensors, and outputs the result of the identification or quantification. According to the 13th aspect of the present disclosure, allergens such as pollen, mold, and mites can be identified or quantified.

[0021] The program according to the 14th aspect of the present disclosure causes a computer to function as the detection device according to any one of the 1st to 12th aspects. According to the 14th aspect of the present disclosure, allergens such as pollen, mold, and mites can be identified or quantified.

Advantages of the Invention

[0022] The present disclosure can provide a technique for identifying or quantifying allergens such as pollen, mold, and mites.

Brief Description of the Drawings

[0023]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Figure 18

Embodiments for Carrying Out the Invention

[0024] Hereinafter, as an example of a mode for carrying out the present disclosure, an allergen detection system and an allergen detection method performed by the allergen detection system will be described.

[0025] <Supplementary Note on the Method for Measuring Allergens> Among Japanese people who feel they "have hay fever," 47.8% are affected (see Non-Patent Document 1 below). In addition to pollen, mold (fungi), house dust (mites), etc. are known as typical allergens. Evaluation methods for environmental allergen pollution are roughly classified into morphological methods and immunological methods. The Durham method (see Non-Patent Document 2) is known as a standard method for the morphological method of pollen. In the Durham method, a prepared slide coated with petroleum jelly is exposed outdoors for 24 hours, and whether the attached particles are pollen is measured while a person judges by looking at them under a microscope. The pollen dispersal amount is indicated by the number of depositions per 1 [cm 2 .

[0026] Also, a pollen collector developed by Burkard in the UK is also known. This pollen collector is based on the invention of Hirst (see Non-Patent Document 3). An adhesive tape is attached to a rotating drum in a chamber introduced into the atmosphere, and a person counts the pollen attached to the tape under a microscope.

[0027] In recent years, instead of microscopic observation, more convenient automatic analyzers have become widespread. The pollen observation system provided by the Ministry of the Environment (see Non-Patent Document 4) determines the pollen concentration (number / m 3 ) from the count of laser scattering by pollen. This pollen observation system is automated and convenient, but it has a drawback that particles with a size close to that of pollen are also measured as pollen (see Non-Patent Document 5).

[0028] Therefore, several new analytical methods have been considered. For example, Coulter counting based on the current change that occurs when particles pass between two electrodes (see Non-Patent Document 6), Fourier transform infrared absorption (see Non-Patent Document 7), or pollen identification using Raman spectroscopy (Non-Patent Document 8) has also been proposed. In addition, attempts have been made to measure the concentration of Cry j1 (ubisch body), an allergen in cedar pollen extract, by surface plasmon resonance (Non-Patent Document 9). In addition, discrimination of pollen types by the particle size estimated from the scattered light of ultraviolet irradiation and the fluorescence intensity ratio of blue / red has also been attempted (Non-Patent Document 10). Except for Cry j1, all are methods for physically detecting pollen.

[0029] As an immunological method, quantification of a single allergen (major allergen) by ELISA (Enzyme-linked Immunosorbent assay) has been performed.

[0030] However, the standard methods of the morphological method (Durham method, rotary drum method) require microscopic observation and are not suitable for automation. An automated analyzer that improves the standard method measures particles of similar size as allergens and requires periodic removal of the accumulated allergens from the measuring device, so continuous measurement is not possible, and furthermore, the specificity is low.

[0031] Quantification of a single allergen by ELISA, an immunological method, has high specificity but cannot perform continuous measurement. In the gas analysis method, a mechanism for preventing new contamination by the generated gas is required, and it is not suitable for miniaturization. In particular, for mites, unlike pollen, morphological methods cannot be used and no automated analysis technology is known.

[0032] <<Non-Patent Documents>> · Non-Patent Document 1 Novartis Pharma Co., Ltd. "Occupation-specific actual situation survey on pollinosis" (Survey period: March - April 2020). · Non-Patent Document 2: O.C. Durham, "The volumetric incidence of atmospheric allergens; a proposed standard method of gravity sampling, counting, and volumetric interpolation of results", J. Allergy, vol 79, p79, 1946 · Non-Patent Document 3: J.M. Hirst, "AN AUTOMATIC VOLUMETRIC SPORE TRAP", Annals of Applied Biology, vol 39, p257, 1952 · Non-Patent Document 4: http: / / kafun.taiki.go.jp / · Non-Patent Document 5: Toshitaka Watada, "On the amount of cedar pollen invading each place indoors", Acta Otolaryngologica Japonica, vol 108, p801, 2005 · Non-Patent Document 6: Z. Zhang et al., "An electronic pollen detection method using Coulter counting principle", Atmospheric Environment, vol 39, p5446, 2005 · Non-Patent Document 7: C.S. Pappas et al., "New Method for Pollen Identification by FT-IR Spectroscopy", Applied Spectroscopy, vol 57, p23, 2003 · Non-Patent Document 8: F. Schulte et al., "Chemical Characterization and Classification of Pollen", Analytical Chemistry, vol 80, p9551, 2008 ·Non-Patent Document 9: Q. Wang et al., "Diurnal and Nocturnal Behaviour of Airborne Cryptomeria japonica Pollen Grains and the Allergenic Species in Urban Atmosphere of Saitama, Japan", Asian Journal of Atmospheric Environment, vol.7, p.65, 2013 ·Non-Patent Document 10: Mitsumoto et al., "Development of a novel real-time pollen-sorting counter using species-specific pollen autofluorescence", Aerobiologia, vol.26, p.99, 2010 <Identification and Quantification of Allergens Using the Semiconductor Sensor of the Present Disclosure> Therefore, one of the objectives of the present disclosure is to continuously identify or quantify allergens such as pollen, mold, and mites floating in the air. For this purpose, in the present disclosure, allergens are detected by two or more types of semiconductor sensors 11 having different metal oxide compositions. The semiconductor sensor 11 reacts to low-concentration VOCs (Volatile Organic Compounds) contained in non-pressurized or non-liquefied gases, and the electrical conductivity (reciprocal of the resistance value) changes. Therefore, the detection device can be made small enough to be used at home or the like. In addition, since the measurement cycle of VOCs by the semiconductor sensor 11 is about several minutes and no cleaning is required, allergens can be continuously measured. Measurement can be performed automatically without the need for human intervention. In addition, in the present disclosure, a model generated by learning the signal pattern of the semiconductor sensor 11 identifies and quantifies allergens, so pollen, mold, and mites can be identified and quantified with high specificity.

[0033] <Regarding Terms> The target space is a space in which there is at least enough air for humans to survive, for example, an indoor living space. The target space may also be outdoors.

[0034] The gas components are nitrogen, oxygen, water vapor, and trace gases that make up air. Trace gases include VOCs. Although pollen and the like are not gases, in this embodiment, allergens may be described as being included in one of the gas components. This is because some VOCs are derived from allergens.

[0035] An allergen refers to a substance that floats in the target space and has the potential to cause an allergic reaction. On the premise that the composition of the allergen includes VOCs, the semiconductor sensor detects VOCs.

[0036] Mites contain substances derived from mites, such as mite corpses, feces, and molted exoskeletons. In addition, mold may include yeast and mushrooms. Also, although the detected mold is mainly hyphae, spores may also be detected.

[0037] <Overview of the allergen detection method> FIG. 1 is a diagram for explaining an example of the system configuration of the allergen detection system 100 and an overview of the allergen detection method. The environmental device 10, the sensor unit 8, the user terminal 70, and the information processing device 60 are communicably connected via the network N.

[0038] The sensor unit 8 is preferably installed in each room of the building where the inhabitant 9 lives. The sensor unit 8 may be installed only once in the building. The sensor unit 8 preferably has an air intake mechanism and incorporates a plurality of semiconductor sensors 11 in the air flow path. This semiconductor sensor 11 reacts to the allergen in the target space 7 where the inhabitant 9 lives, and the electrical conductivity changes.

[0039] The environmental device 10 is a device that controls the environment related to air quality, such as an air conditioner, a ventilation device, or an air purifier. The environmental device 10 may have a plurality of functions such as an air conditioner, a ventilation device, or an air purifier, or there may be environmental devices 10 for each function.

[0040] The user terminal 70 is a terminal device used by the resident 9. In the user terminal 70, a web browser or a native app is executed, and information for display on the display is received from the information processing device 60 via the network N. The resident 9 currently checks the type and amount of the detected allergen and operates the environmental device 10 so as to reduce or not increase the amount of the allergen. The user terminal 70 can be carried by the resident 9 and does not have to be installed in the same space as the space where the sensor unit 8 is installed.

[0041] The information processing device 60 (an example of a detection device) is a server device that performs various information processes in the present disclosure. The information processing device 60 generates an allergen quantification model and an allergen identification model described later, and identifies and quantifies the allergen by inputting the signal pattern detected by the semiconductor sensor 11 into the allergen quantification model and the allergen identification model.

[0042] Assuming that the learning phase for generating the allergen quantification model and the allergen identification model has ended, the flow of identifying and quantifying the allergen will be described. As described later, the allergen quantification model and the allergen identification model output the type and amount of the allergen from the signal pattern detected by the semiconductor sensor 11.

[0043] (1) The sensor unit 8 transmits the signal data (instantaneous value) detected by the semiconductor sensor 11 to the information processing device 60.

[0044] (2) The information processing device 60 accumulates the signal data, and when a signal pattern for one waveform is obtained, inputs it into the generated allergen quantification model and allergen identification model, thereby continuously and automatically identifying and quantifying the allergen.

[0045] (3) The information processing device 60 transmits the type and amount of the obtained allergen with respect to the signal pattern to the user terminal 70. The information processing device 60 transmits a recommendation to operate the environmental device 10 so as to reduce or not increase the amount of the allergen according to the amount of the allergen.

[0046] (4) The user terminal 70 displays the type and amount of allergens and a recommendation to operate the environmental device 10. By inputting an operation to operate the environmental device 10, the user terminal 70 transmits a control request for the environmental device 10 to the information processing device 60.

[0047] (5) The information processing device 60 converts the control request for the environmental device 10 into control information for the environmental device 10 and transmits it to the environmental device 10. Thereby, the environmental device 10 can be controlled so as to reduce or not increase the amount of allergens.

[0048] Thus, according to the present disclosure, by using the semiconductor sensor 11, it is possible to continuously and automatically identify and quantify allergens such as pollen, mold, and mites without increasing the size of the environmental device 10.

[0049] <<Modification Example of System Configuration>> Instead of the sensor unit 8 existing independently, as shown in FIG. 2, the semiconductor sensor 11 may be built into the indoor unit 10b. FIG. 2 shows a modification example of the system configuration of the allergen detection system 100. The allergen detection system 100 mainly includes one outdoor unit 10a as a heat source unit, one or more indoor units 10b as utilization units, and a remote control device (hereinafter referred to as "remote control 15") as an input device for inputting commands related to various settings.

[0050] The outdoor unit 10a and the indoor unit 10b are referred to as air conditioners. The outdoor unit 10a and the indoor unit 10b are connected by a refrigerant connection pipe (gas connection pipe GP) to form a refrigerant circuit. In the allergen detection system 100, a plurality of communication networks (network NW1, network NW2) that function as signal transmission paths between the indoor unit and the outdoor unit are constructed. The network NW2 may be wired or wireless.

[0051] The remote control 15 is a user interface that accepts settings such as temperature and humidity. The function of the information processing device 60 may be the same as that in FIG. 1. (1) The indoor unit 10b incorporates a built-in semiconductor sensor 11 at the air intake or the like. The indoor unit 10b transmits signal data to the outdoor unit 10a. (2) The outdoor unit 10a transmits signal data to the information processing device 60. (3) The information processing device 60 accumulates the signal data, and when a signal pattern for one waveform is obtained, inputs it into the generated allergen quantification model and allergen identification model, thereby continuously and automatically identifying and quantifying allergens. (4) The information processing device 60 transmits the type and amount of the allergen obtained for the signal pattern to the remote controller 15 via the outdoor unit 10a and the indoor unit 10b. (5) The remote controller 15 displays the type and amount of the allergen. The remote controller 15 displays a recommendation to reduce or not increase the amount of the allergen according to the amount of the allergen, and recommends operating the environmental device 10 accordingly. When the user inputs an operation to operate the environmental device 10, the remote controller 15 transmits setting information to the indoor unit 10b. (6) The indoor unit 10b controls itself based on the setting information. Thereby, the environmental device 10 can be controlled to reduce or not increase the amount of the allergen.

[0052] <System configuration of the allergen detection system> Next, with reference to FIG. 3, the system configuration of the allergen detection system 100 will be described. FIG. 3 is a diagram showing an example of the system configuration of the allergen detection system 100.

[0053] The allergen detection system 100 provides various services utilizing IoT from administrators to general users by communicating various environmental devices 10 such as air conditioners, ventilators, and cleaners with the information processing device 60 on the cloud side via the network N. The edge device 80, the environmental device 10, the sensor switches 53, and the user terminal 70 are installed on the customer side, and the information processing device 60 is installed in the cloud such as a data center or the Internet. Note that since the edge device 80 is a device that centrally manages the environmental device 10 and the sensor switches 53, the edge device 80 may not be provided.

[0054] As described above, the environmental device 10 is preferably a device that comes into contact with the air in the living space, such as an air conditioner, a ventilation device, a cleaner, etc. The living space may be outdoors as well as indoors. Generally, the edge device 80 may be connected to security equipment, heat source equipment, a fire alarm, an AHU (Air Handling Unit), a power meter, lighting, etc.

[0055] The environmental device 10 and the sensor switches 53 are controlled by the edge device 80. In other words, the edge device 80 performs necessary operations on the environmental device 10 and the sensor switches 53 so as to be suitable for the purposes of the environmental device 10 and the sensor switches 53. Although the content of the control varies depending on the types of the environmental device 10 and the sensor switches 53, for example, when the environmental device 10 is an air conditioner, all controls related to the functions of the air conditioner, such as the cooling / heating mode, set temperature, air volume, humidity, air direction, etc., that can generally be set on the air conditioner may be included. The sensor switches 53 may include a semiconductor sensor 11.

[0056] The environmental device 10 collects operation data corresponding to the environmental device 10 and mainly transmits it to the edge device 80 periodically. Periodically means, for example, once per minute, once per ten minutes, once per sixty minutes, etc., but it may be set by the user or the information processing device 60. The operation data varies depending on the environmental device 10. For example, in the case of an air conditioner, it may be various data such as the high pressure of the refrigerant, the low pressure of the refrigerant, the refrigerant temperature, the rotation speed of the fan, and the CPU temperature of the microcomputer.

[0057] The edge device 80 is a controller that controls the environmental device 10 and the sensor switches 53. In the case where there is no edge device 80, the information processing device 60 controls the environmental device 10 and the sensor switches 53.

[0058] The information processing device 60 may be one or more server devices. Although one information processing device 60 is shown in FIG. 3, the information processing device 60 may be divided and installed into several parts according to functions. Also, the functions of the information processing device 60 may be aggregated by one server device. Further, a plurality of information processing devices 60 with the same functions may be prepared, and a plurality of information processing devices 60 may process while communicating like a server cluster.

[0059] The information processing device 60 inputs a signal pattern into an allergen quantification model and an allergen identification model to identify and quantify allergens, and provides them to the user terminal 70 or the like. The information processing device 60 can identify and quantify allergens not only for individual facilities such as houses and buildings, but also for each region, and these may be shared with public broadcasts and the like.

[0060] Although not shown in FIG. 3, an information processing device that generates an allergen quantification model and an allergen identification model may exist separately from the information processing device 60. In this case, the allergen quantification model and the allergen identification model generated by another information processing device are introduced into the information processing device 60. In the present disclosure, for convenience of explanation, it is assumed that the information processing device 60 generates an allergen quantification model and an allergen identification model.

[0061] The information processing device 60 may also have the function of a Web server. The Web server responds to requests from client software (Web client) such as a Web browser operated by the user, and provides screen information described in HTML files, XML, CSS files, JavaScript (registered trademark), etc. to the client. An application that uses such a Web mechanism is called a Web application.

[0062] Note that the information processing device 60 preferably supports cloud computing. Cloud computing refers to a usage form in which resources on a network are used without being aware of specific hardware resources.

[0063] The user terminal 70 is a client terminal that displays various screens provided by the information processing device 60. The user terminal 70 may be used by an administrator or a general user (resident 9 in the present disclosure). When the environmental device 10 is in a general household, the administrator may be a family member of the resident, or the resident 9 may also serve as the administrator. When the environmental device 10 is in a building or the like managed by a company, the administrator is, for example, a facility administrator or the like.

[0064] The user terminal 70 is, for example, a PC (Personal Computer), a smartphone, a tablet terminal, a PDA (Personal Digital Assistant), a wearable PC (such as a sunglass type or a wristwatch type), etc. However, it is only necessary to have a communication function and for the web browser to operate. Also, instead of a web browser, a native app dedicated to the allergen detection system 100 may operate on the user terminal 70.

[0065] <Hardware Configuration of Information Processing Device> With reference to FIG. 4, the hardware configuration of the information processing device 60 will be described. FIG. 4 is a diagram showing an example of the hardware configuration of the information processing device 60. As shown in FIG. 4, the information processing device 60 includes a processor 221, a memory 222, an auxiliary storage device 223, an I / F (Interface) device 224, a communication device 225, and a drive device 226. Each hardware of the information processing device 60 is interconnected via a bus 207.

[0066] The processor 221 includes various arithmetic devices such as a CPU (Central Processing Unit). The processor 221 reads out and executes various programs on the memory 222. The processor 211 controls the entire information processing device 60.

[0067] The memory 222 has a main memory device such as a ROM (Read Only Memory) or a RAM (Random Access Memory). The processor 221 and the memory 222 form a so-called computer, and the processor 221 executes various programs read onto the memory 222.

[0068] The auxiliary storage device 223 stores various programs and various data used when the various programs are executed by the processor 221.

[0069] The I / F device 224 is a connection device that connects a display device 230, which is an example of an external device, an operation device 240, and the information processing device 60. The display device 230 displays the internal state of the information processing device 60. The operation device 240 is used when an administrator of the information processing device 60 inputs various instructions to the information processing device 60.

[0070] The communication device 225 is a communication device for communicating with the edge device 80 and the user terminal 70 via the network N.

[0071] The drive device 226 is a device for setting the recording medium 250. The recording medium 250 here includes media that optically, electrically, or magnetically record information, such as a CD-ROM, a flexible disk, or a magneto-optical disk. Further, the recording medium 250 may include semiconductor memories that electrically record information, such as a ROM or a flash memory.

[0072] Note that the various programs installed in the auxiliary storage device 223 are installed, for example, when the distributed recording medium 250 is set in the drive device 226 and the various programs recorded on the recording medium 250 are read by the drive device 226. Alternatively, the various programs installed in the auxiliary storage device 223 may be installed by being downloaded from the network N via the communication device 225.

[0073] <Regarding Functions> Next, with reference to FIG. 5, the functional configuration of the allergen detection system 100 will be described in detail. FIG. 5 is an example of a functional block diagram that separately explains the functions of the information processing device 60 and the environmental device 10 (or the sensor unit 8) in blocks. Note that FIG. 5 shows both the functions in the learning phase and the functions in the inference phase for convenience of explanation.

[0074] The environmental device 10 or the sensor unit 8 includes a plurality of semiconductor sensors 11, a sensor control unit 12, and a transmission unit 13. A plurality of semiconductor sensors 11 are arranged at the air intake of the environmental device 10 or the sensor unit 8. Since the semiconductor material used for the semiconductor sensor 11 for gas is often used in a situation where it is kept at a high temperature in the air, a thermally and chemically stable metal oxide is used. The semiconductor sensor 11 changes its electrical conductivity (i.e., resistance value) according to the adsorption and desorption of VOCs in the air. A plurality of semiconductor sensors 11 are arranged so as to be suitable for detecting different VOCs, and the composition of the metal oxides of the plurality of semiconductor sensors 11 varies depending on the semiconductor sensor 11. The plurality of semiconductor sensors 11 have different characteristics regarding how the electrical conductivity and the like change with respect to the same gas component.

[0075] An example of the composition of the metal oxide included in the semiconductor sensor 11 is shown below. The metal oxide includes, for example, zinc oxide (ZnO), stannic oxide (SnO2), ferric oxide (Fe2O3), tungsten oxide (WO3), indium oxide (In2O3), etc., but is not limited thereto.

[0076] The sensor control unit 12 controls these semiconductor sensors 11. The sensor control unit 12, for example, generates a driving voltage and supplies it to the semiconductor sensor 11, and performs detection instructions of VOCs to the semiconductor sensor 11, signal capture from the semiconductor sensor 11, noise removal, filtering, and removal of abnormal values.

[0077] The transmission unit 13 transmits the signal data detected by the semiconductor sensor 11 to the information processing device 60 in real time or every time a certain amount of data is accumulated via the network N. Since the information processing device 60 receives the signal data in time series, the signal pattern of each semiconductor sensor 11 can be reproduced.

[0078] The information processing device 60 includes an acquisition unit 21, a data unit 22, a model generation unit 23, an analysis unit 24, an output unit 25, and an environmental device control unit 26. These units of the information processing device 60 are collectively referred to as a control unit 20, and the control unit 20 is a function or means realized by the processor 221 of the information processing device 60 executing the instructions of the program developed in the memory 222.

[0079] The acquisition unit 21 acquires the signal data detected by the semiconductor sensor 11 from the environmental device 10. The acquisition unit 21 may request the environmental device 10 for the signal data and receive the signal data as a response, or may receive it without a request. Further, the acquisition unit 21 may accumulate the signal data in the data unit 22. If there is separately prepared teacher data, the model generation unit 23 can reconstruct the model based on the signal data accumulated in the data unit 22 using the environmental device 10 and the sensor unit 8 operating in the market.

[0080] In the learning phase, training data is stored in the data unit 22. The training data of this embodiment is, for example, "signal pattern and type of allergen", "signal pattern and amount of allergen". The details of the training data will be described later with reference to FIG. 13.

[0081] The model generation unit 23 learns the training data, generates an allergen identification model from "signal pattern and type of allergen", and generates an allergen quantification model from "signal pattern and amount of allergen". The generated allergen identification model and allergen quantification model are set in the analysis unit 24.

[0082] In the inference phase, the analysis unit 24 accumulates the signal data detected by the semiconductor sensor 11 in real time to generate one signal pattern, and inputs it into the allergen identification model and the allergen quantification model. The allergen identification model outputs the amount of allergen, and the allergen quantification model outputs the type of allergen. The analysis unit 24 passes the amount of allergen and the type of allergen to the output unit 25 and the environmental device control unit 26.

[0083] The output unit 25 transmits the detected type and amount of allergen to the user terminal 70 and the remote control 15. The output unit 25 may generate screen information such as HTML displayed by a web application or a web page. Since the user terminal 70 and the remote control 15 display the type and amount of allergen, the user can operate the environmental device 10 to activate, for example, the air purification function.

[0084] When the amount of allergen exceeds a threshold or the rate of increase in the amount of allergen exceeds a threshold, the environmental device control unit 26 transmits control information for activating the air purification function of the environmental device 10 to the environmental device 10. Thereby, the environmental device 10 can start operating so as to reduce the amount of allergen or not increase it.

[0085] In FIG. 5, the semiconductor sensor 11 and the sensor control unit 12 are on the environmental device 10 side, and the control unit 20 is on the information processing device 60 side, but the semiconductor sensor 11 and the control unit 20 may be arranged in one device. For example, in a household air conditioner, air purifier, ventilation device, etc., one device may have the semiconductor sensor 11, the sensor control unit 12, and the control unit 20. Also, in the case of an air conditioner with an indoor unit and an outdoor unit, the indoor unit may have the semiconductor sensor 11 and the sensor control unit 12, and the outdoor unit may have the control unit 20, or the indoor unit or the outdoor unit may have the semiconductor sensor 11, the sensor control unit 12, and the control unit 20. Also, in the case of a ventilation type air conditioner, it is preferable that the semiconductor sensor 11 can detect allergens on both the indoor side and the outdoor side. Furthermore, if the semiconductor sensor 11 is used for both the indoor side and the outdoor side, the cost increase can be suppressed.

[0086] <Method for Detecting Allergens Used for Identification and Quantification> Referring to FIG. 6, the disadvantages in the conventional GC-MS (Gas Chromatography-Mass Spectrometry) are explained. FIG. 6 shows a TIC (Total Ion Chromatogram) chromatogram of volatile compounds obtained from 10 mg of pollen of Cryptomeria japonica, Chamaecyparis obtusa, Pinus densiflora, and Quercus serrata. As shown in FIG. 6, in the method of identifying the type of pollen from VOCs using GC-MS, the type is determined from the difference in the retention time until a peak appears after injecting the sample. For this reason, the maximum retention time when the VOC peak appears is required, and it is not suitable for continuous measurement. Also, since a mechanism for heating the gas and a mechanism for exhausting the heated gas are required, it is difficult to reduce the cost or miniaturize the device.

[0087] Therefore, as shown in FIG. 7, in the present embodiment, allergens are detected by the semiconductor sensor 11. FIG. 7 is an image diagram of the detection principle of the semiconductor sensor 11. As shown in FIG. 7, the semiconductor sensor 11 detects the components of a gas by utilizing the reaction between oxygen adsorbed on the surface of the metal oxide and a reducing gas (CH3, H2, CO, CO2, H2O, etc.). That is, the reducing gas corresponds to the VOC contained in the allergen, and the electrical conductivity changes due to the adsorption and desorption of the reducing gas. Although there are a plurality of semiconductor sensors 11, each outputs signals regarding a plurality of gas components simultaneously.

[0088] FIG. 8 shows an example of the signal pattern 110 detected by the semiconductor sensor 11. The vertical axis in FIG. 8 is the resistance value, and the horizontal axis is time. The semiconductor sensor 11 sets the reference value RD of the resistance value in the state where no VOC is adsorbed (initial state). The resistance value decreases due to the consumption of the adsorbed oxygen in the sensor electron depletion layer (adsorption of the reducing gas) and repeats a cycle of recovery by the supply of oxygen from the air. The length of one cycle varies depending on the type of the semiconductor sensor 11 and the VOC, but is, for example, several minutes. The semiconductor sensor 11 can measure a sufficient number of resistance values to reproduce the waveform during one cycle.

[0089] In this way, since the resistance value can be continuously measured, it becomes possible to continuously measure the VOC derived from allergens. Further, the semiconductor sensor 11 has high sensitivity at low concentrations and can detect the VOC derived from allergens without pressurizing or liquefying the air. Also, the semiconductor sensor 11 has a high cost reduction effect during mass production and is characterized by good responsiveness. Therefore, the environmental device 10 can be miniaturized. By using the semiconductor sensor 11, an inexpensive and small environmental device 10 and sensor unit 8 can be realized as compared with GC-MS.

[0090] In FIG. 8, the signal pattern of the resistance value is shown, but the signal pattern may be current, voltage, electrical conductivity, or resistance (electrical resistance). The control unit 20 identifies or quantifies the allergen from the signal pattern of current, voltage, electrical conductivity, or resistance (electrical resistance).

[0091] <An example of an allergen> As described above, when the VOC derived from an allergen adsorbs to the semiconductor sensor 11, the resistance value changes according to the material of the semiconductor sensor 11 and the type (VOC) of the allergen. That is, each semiconductor sensor 11 detects a different signal pattern according to the type of allergen. Also, the signal pattern changes depending on the amount of the allergen. Therefore, by machine learning the signal patterns of the plurality of semiconductor sensors 11, it becomes possible to identify and quantify the allergen.

[0092] As examples of allergens, pollen, mites, and mold are known. Also, the information processing device 60 can discriminate the pollen of Cryptomeria japonica, Chamaecyparis obtusa, Oryza sativa, Miscanthus sinensis, Hordeum vulgare, Odorrana schmackeri, Halla gigantea, Rana chensinensis, Pinus densiflora, Pinus thunbergii, Artemisia princeps, Solidago virgaurea, Papaver rhoeas, Setaria viridis, Betula platyphylla, Ginkgo biloba if it is pollen. The information processing device 60 of the present embodiment can also discriminate the types of pollen, mites, and mold.

[0093] <Identification and quantification of allergens using a neural network> In this embodiment, an allergen identification model and an allergen quantification model are generated by machine learning. Machine learning is a technology that enables a computer to acquire learning capabilities similar to those of humans. It refers to a technology in which a computer autonomously generates algorithms necessary for judgments such as data identification from pre-imported training data and applies this to new data for prediction. The learning method for machine learning may be any one of supervised learning, unsupervised learning, semi-supervised learning, reinforcement learning, and deep learning. Furthermore, a learning method that combines these learning methods may also be used, and the learning method for machine learning is not limited. As an example, an allergen identification model and an allergen quantification model using a neural network will be described.

[0094] Referring to FIG. 9, an example of a method for creating an allergen quantification model will be described. FIG. 9 shows an example of a neural network used by the model generation unit 23 for learning. The neural network in FIG. 9 is a regression neural network (for predicting continuous values) that outputs one output value for a plurality of data input to the input layer 41.

[0095] FIG. 9 is a neural network in which L layers (the number of weighted intermediate layers 42 and output layer 43 = 2 layers) are fully connected from the input layer 41 to the output layer 43. A neural network with a deep hierarchy is called a DNN (Deep Neural Network). The layer between the input layer 41 and the output layer 43 is called an intermediate layer 42 (or hidden layer). The number of intermediate layers 42 and the number of nodes 35a to 35c in each layer are simplified for the purpose of explanation and are merely examples. The number of nodes 35a in the input layer 41 may be the number of elements of the vector that is the input data. In the case of predicting continuous values, the number of nodes 35c in the output layer 43 is often one. Therefore, an allergen quantification model is created for each type of allergen.

[0096] In the neural network of Fig. 9, all the nodes 35a of the input layer 41 are connected to one node 35b of the intermediate layer 42, and all the nodes 35b of the intermediate layer 42 are connected to one node 35c of the output layer 43 (fully connected). The product of the output z of the node 35a of the input layer 41 and the connection weight w is input to the node 35b of the intermediate layer 42, and the product of the output z of the node 35b of the intermediate layer 42 and the connection weight w is input to the node 35c of the output layer 43. Equation (1) shows the calculation method of the output signal of the node 35b.

[0097] [Number] In Equation (1), w ji (l,l-1) is the weight between the j-th node of the l-th layer and the i-th node of the (l-1)-th layer, and b j is the bias component in the network. u j (l) is the input to the j-th node of the l-th layer, and z i (l-1) is the output of the i-th node of the (l-1)-th layer. I is the number of nodes in the (l-1)-th layer.

[0098] [Number] Also, as shown in Equation (2), the input u j (l) to the node is activated by the activation function f. f means the activation function of the node. As the activation function, ReLU, tanh, sigmoid, etc. are known. Note that the nodes 35a of the input layer 41 only need to transmit the input data to the second layer and are not activated. The nodes 35 of the l-th layer non-linearly transform the input with the activation function and output it to the nodes 35 of the (l+1)-th layer. In the neural network, this process is repeated from the input layer 41 to the output layer 43.

[0099] For the node 35c of the output layer 43, an activation function for the output layer is used. As the activation function of the output layer 43 of the regression model, the identity function (y = x) is generally used.

[0100] Figure 10 is a diagram for explaining the learning of a neural network. The neural network processes the data input to the input layer 41 and outputs an output value from the output layer 43. For example, for input data such as "0.1" and "0.3", the node 35c of the output layer 43 outputs "5". Suppose that teacher data of "7" corresponding to "0.1" and "0.3" is preset in the training data. The teacher data of the allergen quantification model is, for example, the amount of allergen counted by some method such as the above non-patent literature (per unit area or volume, and the number per unit time).

[0101] In the learning phase, the loss function is used to evaluate the error between the teacher data and the output value, and the weights w and b are adjusted so that the output value is close to the teacher data. The loss function of the regression model may be a function that calculates the mean squared error. The value of the loss function is propagated to the nodes of the input layer 41 by a calculation method called the error backpropagation method. During the propagation process, the weights w and b between the nodes are learned.

[0102] Next, with reference to Figure 11, a neural network for identifying allergens will be described. Figure 11 shows an example of a neural network used by the model generation unit 23 for learning the allergen identification model. In the description of Figure 11, the differences from Figure 9 will be mainly described. The neural network in Figure 11 is a classification neural network that outputs, from the output layer 43, the probability that the input plurality of data is for each allergen.

[0103] The configurations of the input layer 41 and the intermediate layer 42 may be the same as those in Figures 9 and 10. In the case of classification, the softmax function is often used as the activation function for classification at the node 35c of the output layer 43. By the softmax function, the input to each node 35c of the output layer 43 is converted into a probability between 0 and 1.

[0104] For example, for input data such as "0.1" and "0.3", each node 35 in the output layer 43 outputs "0.15", "0.80", and "0.05". Assume that teacher data "0 1 0" corresponding to "0.1" and "0.3" is preset in the training data. The teacher data in the case of classification may be a one-hot vector. "0 1 0" corresponds to "pollen, mite, mold" in order. When the input data detects pollen, the teacher data is "1 0 0"; when it detects mites, the teacher data is "0 1 0"; when it detects mold, the teacher data is "0 0 1". Therefore, "0 1 0" in FIG. 11 indicates that the teacher data is mites.

[0105] In the learning phase, the loss function evaluates the error between the teacher data and the output value, and adjusts the weights w and b so that the output value approaches the teacher data. The loss function of the classification model may be a function that calculates cross-entropy. The value of the loss function is propagated to the nodes in the input layer 41 by a calculation method called the error backpropagation method. The weights w and b between the nodes are learned during the propagation process.

[0106] <Preprocessing of waveform data> In the present embodiment, the input data input to the input layer 41 is waveform data detected by the semiconductor sensor 11. FIG. 12(a) shows an example of a signal pattern 110 detected by a certain semiconductor sensor 11. As described above, the signal pattern 110 repeats the cycle of decrease and recovery. It is considered that the waveform of one cycle includes the characteristics of how the semiconductor sensor 11 reacts to allergens. Therefore, the analysis unit 24 uses this one cycle (one signal pattern 110) as one input data for the identification and quantification of allergens. However, a half cycle of the signal pattern 110 may be used. The identification and quantification of allergens can be achieved in a shorter time.

[0107] As shown in FIG. 8, the analysis unit 24 extracts the signal pattern 110 between the maximum values from the waveforms of the continuously obtained signals. The signal pattern between the minimum values of the waveform may be extracted. Alternatively, the signal pattern between the maximum value and the minimum value of the waveform may be extracted. Then, as shown in FIG. 12(b), the analysis unit 24 samples P values from the signal pattern 110 using the sampling window 120. The sampling window 120 is a range (time length) for sampling signal data from the signal pattern 110. One sampling window 120 obtains, for example, P resistance values. In order to obtain the waveform of the signal pattern 110 without omission, the analysis unit 24 moves the sampling window 120 so as to overlap with respect to time. If the number of sampling windows 120 covering one signal pattern 110 is Q, the number of data N input for one signal pattern 110 is as follows. N = P×Q The training data is a set of this input data and teacher data. As described above, the teacher data is a one-hot vector indicating the amount of allergen in regression and the type of allergen in classification.

[0108] FIG. 13 schematically shows the training data. One row (one record) shown in FIG. 13 is one training data. The training data is the input data and the amount of allergen, or the input data and the type of allergen. The input data is preferably normalized and standardized to 0 to 1. The person in charge prepares a large number of input data, the amount of allergen, and the type of allergen in advance.

[0109] The model generation unit 23 acquires the training data of the batch size from the data unit 22, and generates an allergen identification model and an allergen quantification model by repeating a predetermined number of epochs for each batch.

[0110] If the number of data input for one signal pattern 110 is N and the number of semiconductor sensors 11 is M, the number of nodes 35a in the input layer 41 is N×M.

[0111] <<Method for Converting Waveform Data into Image Data>> In FIGS. 12 and 13, it was described that the numerical values constituting the signal pattern 110 are used as input data, but the input data may also be an image.

[0112] FIG. 14 is a diagram for explaining the conversion of the signal pattern 110 into image data. As a method for converting into image data, when performing preprocessing, the information processing apparatus 60 draws a time-series signal as shown in FIG. 14(a) on a graph or the like. The information processing apparatus 60 may maintain the interval between data points. Further, as shown in FIG. 14(b), the information processing apparatus 60 cuts out the circumscribed rectangle of the signal pattern 110 between the maximum values (or between the minimum values). The analysis unit 24 preferably shapes the image data into square screen data with determined numbers of vertical and horizontal pixels. Also, in this embodiment, since the color of the image data does not carry information on the amount or type of allergen, the analysis unit 24 binarizes the image data.

[0113] For a neural network that takes image data as input, convolution and pooling are possible. The convolutional layer has a function equivalent to a filter and can extract various features and patterns in the image, such as the shape of a line. Also, through pooling, the amount of data can be reduced without losing too much information, and a certain degree of invariance to positional displacement can be achieved.

[0114] FIG. 15 shows a configuration example of a model when using a neural network corresponding to image data. The neural network 30 in FIG. 15 is a neural network called a CNN (Convolutional Neural Network). Screen data 31 of the signal pattern 110 for each semiconductor sensor 11 is input to the neural network 30, and the neural network 30 outputs the type 32 or amount 33 of the allergen. In FIG. 15, for the sake of explanation, one neural network 30 outputs the type 32 or amount 33 of the allergen, but neural networks 30 for outputting the type 32 or amount 33 of the allergen are separately constructed. Further, for the amount 33 of the allergen, neural networks 30 may be separately constructed for each type of allergen.

[0115] The neural network 30 has convolutional layers 1, 2, pooling layers 1, 2, activation functions 1 to 3, and fully connected layers 1, 2. The convolutional layers 1, 2 refer to a process of converting into one numerical value by calculating the sum of products for each element of the grid-like numerical data called a kernel (or filter) and the numerical data of a partial image (called a window) having the same size as the kernel. The convolutional layers 1, 2 perform this conversion process by shifting the window little by little to convert it into small grid-like numerical data (i.e., a tensor).

[0116] The pooling layers 1 and 2 are processes that create one numerical value from the numerical data of the window. For example, there are max pooling that selects the maximum value in the window, average pooling that selects the average value in the window, and so on. The convolutional layers 1 and 2 extract the features of the captured image, and the pooling layers 1 and 2 blur the accuracy of the position of the object. The activation functions 1 to 3 are functions that non-linearly transform (activate) the input (for example, there are ReLU, tanh, sigmoid, etc.). The fully connected layer 1 corresponds to the input layer 41 that aggregates the output of the activation function 2, and the fully connected layer 2 corresponds to the output layer 43. The numerical values aggregated in the fully connected layer 1 are transmitted to the fully connected layer 2 through the activation function 3. The fully connected layer 2 has one (quantification) or multiple (identification) output nodes, and these output nodes output the type of allergen or the amount of allergen.

[0117] Note that the numbers of the illustrated convolutional layers 1 and 2, pooling layers 1 and 2, activation functions 1 to 3, and fully connected layers 1 and 2 are just examples, and the order of the processes is also just an example.

[0118] In the case of the neural network 30 in FIG. 15, the training data is obtained by replacing the N×M input data in FIG. 13 with M image data. If the resolution of the image data converted from one signal pattern 110 is, for example, 100 pixels×100 pixels and the number of semiconductor sensors 11 is M, the number of nodes 35 in the input layer 41 is 100×100×M. In the case of the neural network 30 in FIG. 15, through learning, the content of the filter and the coefficients between the nodes in the fully connected layers 1 and 2 are adjusted.

[0119] <<Other machine learning methods>> Machine learning techniques include, in addition to neural networks (perceptrons, deep learning), support vector machines, logistic regression, decision trees, random forests, etc., and are not limited to the techniques described in this embodiment. For example, support vector machines are mainly used for classification models. A support vector machine is a technique that maximizes the margin plane between the vectors of positive and negative examples included in the training data. Non-linear data can also be classified by the kernel method that maps data onto a high-dimensional feature space.

[0120] The boosting decision tree is a technique that independently trains a plurality of weak discriminators such as decision trees, integrates the prediction results by the plurality of weak discriminators using majority voting or the like, and outputs them as the prediction results of the whole (strong discriminator). The boosting decision tree is for regression, but it can also be applied to regression by using the boosting regression tree, which is a similar technique.

[0121] In addition, there are various techniques suitable for regression and classification, and any technique may be used to generate the allergy identification model and allergy quantification model of this embodiment.

[0122] <Example display of allergy identification and quantification> FIG. 16 shows an allergen detection result screen 300 displayed on the user terminal 70 or the remote controller 15. In the allergen detection result screen 300, the horizontal axis represents the current time, and the vertical axis represents the amount of allergen. The temporal changes in the amount of allergen are represented by line graphs 301-303. In FIG. 16, pollen, mold, and mites are shown as allergens as an example, but the allergen detection result screen 300 may display the number of other types of allergens. The resident 9 can operate the user terminal 70 or the remote controller 15 to give an instruction on which allergen to display. If the user designates pollen as the allergen on the allergen detection result screen 300, the number of pollen by type can be displayed. If mites are designated, the number of mites by type can be displayed. If mold is designated, the number of mold by type can be displayed. Also, the resident 9 may specify the time range for displaying the line graphs 301-303. The allergen detection result screen 300 may display the maximum and minimum values of each allergen over a certain period in the past.

[0123] In the allergen detection result screen 300 of FIG. 16, after 12:45, the amount of pollen has increased rapidly. In such a case, it is preferable for the output unit 25 to warn the resident 9. In FIG. 16, a message 304 saying "The amount of pollen is increasing. Do you want to turn on the air purification function?", a yes button 305, and a no button 306 are displayed. When the resident 9 presses the yes button 305, the information processing device 60 transmits control information for activating, for example, the air purification function to the environmental device 10. Note that the environmental device control unit 26 may perform appropriate control on the environmental device 10 according to the allergen detection result without the output unit 25 asking the user.

[0124] Also, the output unit 25 may emphasize (such as blinking, thick line, etc.) the line graph with an increasing trend. Also, when the amount of allergen decreases due to the control of the environmental device 10, the output unit 25 may display to that effect on the allergen detection result screen 300. The resident 9 can confirm that the allergen has decreased due to the control of the environmental device 10.

[0125] As described above, the information processing apparatus 60 according to this embodiment can continuously detect allergens, thereby alerting the occupant 9 in real time and controlling the environmental device 10 without delay. Even when the allergens are reduced by the control of the environmental device 10, it can be detected in real time, and the occupant 9 can be notified of the effect of the air cleaning function.

[0126] In addition, when the environmental device 10 is installed outdoors or can take in outdoor air, the information processing apparatus 60 may provide a map showing the distribution of pollen based on the detection result of allergens (mainly pollen) and the position information of the environmental device 10. The position information of the environmental device 10 may be identified by, for example, an IP address, or the environmental device 10 may transmit its postal code or address to the information processing apparatus 60.

[0127] FIG. 17 shows a detection result screen 320 of pollen outdoors displayed on the user terminal 70. The information processing apparatus 60 can receive the amount of pollen in each place from the environmental device 10. The information processing apparatus 60 divides the map into meshes and obtains the average amount of pollen in the meshes. The information processing apparatus 60 can visually display the amount of pollen for each place, for example, by color-coding the meshes according to the amount of pollen. The occupant 9 can check the amount of pollen scattering when going out to a distant place, for example. Note that the information processing apparatus 60 may provide the amount of pollen in each place to the weather information service.

[0128] <Overall processing flow> Subsequently, referring to FIG. 18, the overall processing flow of the allergen detection system 100 will be described. FIG. 18 is a sequence diagram for explaining the process in which the allergen detection system 100 displays an allergen detection result screen and controls the environmental device 10.

[0129] S101: The acquisition unit 21 of the information processing apparatus 60 repeatedly acquires the signal data measured by the semiconductor sensor 11 from the environmental device 10 or the sensor unit 8, for example, at regular intervals or for a fixed amount.

[0130] S102: The analysis unit 24 of the information processing apparatus 60 extracts a signal pattern 110 for one waveform from the time-series signal data, inputs the signal pattern 110 into the allergen identification model and the allergen quantification model, and identifies and quantifies the allergen.

[0131] S103: The output unit 25 compares the measured amount for each type of allergen with a threshold value to determine whether to recommend the operation of the environmental device 10. Further, the output unit 25 calculates the slope of the amount of allergen with respect to time from the past measured allergen quantification results, compares the slope with a threshold value, and determines whether to recommend the operation of the environmental device 10.

[0132] S104, S105: When the resident 9 inputs an operation to display the allergen detection result screen 300 on the user terminal 70, the user terminal 70 transmits a request for the allergen detection result screen 300 to the information processing apparatus 60. S106: In response to a request from the user terminal 70, the output unit 25 of the information processing apparatus 60 creates the allergen detection result screen 300. The output unit 25 transmits the screen information of the allergen detection result screen 300 to the user terminal 70. Note that instead of the user terminal 70, the remote controller 15 may display the allergen detection result screen 300. In this case, even if the resident 9 does not perform an operation to display the allergen detection result screen 300, the allergen detection result screen 300 may be displayed on the remote controller 15.

[0133] S107: The user terminal 70 receives the screen information of the allergen detection result screen 300 and displays the allergen detection result screen 300.

[0134] S108, S109: When the resident 9 inputs an operation to select the "Yes" button 305 on the allergen detection result screen 300, the user terminal 70 transmits a control request for the environmental device 10 to the information processing apparatus 60. When the remote controller 15 instead of the user terminal 70 displays the allergen detection result screen 300, the setting information may be transmitted to the environmental device 10.

[0135] S110: In response to a control request for the environmental device 10 from the user terminal 70, the environmental device control unit 26 of the information processing apparatus 60 creates control information. For example, the environmental device control unit 26 creates control information such as activating the air purification function or starting the environmental device 10 if it is stopped. The environmental device control unit 26 may start the environmental device 10 and further activate the air purification function.

[0136] S111: The environmental device control unit 26 transmits the control information to the environmental device 10. Since the environmental device 10 converts the control information into setting information to control itself, it can be controlled so as to reduce or not increase the amount of allergens in the space where the inhabitant 9 lives.

[0137] Note that in the process of FIG. 18, when the inhabitant 9 presses the enter button 305, the environmental device 10 is controlled. However, depending on the determination result of step S103, the environmental device 10 may be controlled by the environmental device control unit 26 without inquiring the inhabitant 9.

[0138] <Main effects> As described above, in the present disclosure, two or more types of semiconductor sensors 11 having different compositions of metal oxides are used to detect VOCs contained in allergens. The semiconductor sensor 11 reacts to low-concentration VOCs contained in a gas that is not pressurized or liquefied, and the electrical conductivity changes. Therefore, the detection device can be used at home and is small in size. Also, since the measurement cycle of VOCs by the semiconductor sensor 11 is about several minutes, allergens can be continuously measured. Measurement can be automatically performed without the need for human intervention. Further, in the present disclosure, since the model generated by machine learning the signal pattern of the semiconductor sensor 11 identifies allergens, pollen, mold, and mites can be identified and quantified with high specificity.

[0139] <Other application examples> As described above, the best mode for carrying out the present disclosure has been described using examples. However, the present disclosure is not limited to such examples, and various modifications and substitutions can be made without departing from the gist of the present disclosure.

[0140] For example, in this embodiment, an allergen is mainly detected using the semiconductor sensor 11, but an allergen may also be detected using other gas sensors. For example, there are an optical (NDIR type) gas sensor that utilizes the infrared absorption characteristics of gas molecules, a fuel cell type gas sensor that utilizes the oxidation reaction occurring at the sensing electrode, or a catalytic combustion type gas sensor that utilizes the combustion heat on the surface of the sensing element, etc.

[0141] Also, the configuration examples such as in FIG. 5 are divided according to the main functions in order to facilitate the understanding of the processing by the information processing apparatus 60. The present disclosure is not limited by the way of division of the processing units or their names. The processing of the information processing apparatus 60 can be further divided into more processing units according to the processing content. Also, it can be divided such that one processing unit includes more processes.

[0142] Also, the device group described in the examples only shows one of a plurality of computing environments for implementing the embodiments disclosed in this specification. In an embodiment, the information processing apparatus 60 includes a plurality of computing devices such as a server cluster. The plurality of computing devices are configured to communicate with each other via an arbitrary type of communication link including a network or a shared memory, and implement the processing disclosed in this specification.

[0143] Each function of the present disclosure described above can be realized not only by software processing by executing a program but also by one or a plurality of processing circuits. Here, the "processing circuit" in this specification includes a processor programmed to execute each function by software like a processor implemented by an electronic circuit, an ASIC (Application Specific Integrated Circuit) designed to execute each function described above, a DSP (Digital Signal Processor), an FPGA (Field Programmable Gate Array), and devices such as conventional circuit modules.

[0144] <Reason for the effect> · Since the first aspect of the present disclosure is to "obtain signal patterns detected by a plurality of semiconductor sensors that exhibit different response characteristics relative to the same gas component, and identify or quantify an allergen from the plurality of signal patterns obtained from the plurality of semiconductor sensors", different signal patterns can be obtained for the same gas component, and a lot of information about the allergen is included in the different signal patterns. Since the detection device analyzes this, identification or quantification of the allergen becomes possible. Since the semiconductor sensor does not require cleaning, it can be continuously identified or quantified. It can be automatically identified or quantified without the need for human intervention in the analysis of the signal pattern.

[0145] · Since the second aspect of the present disclosure is that "the signal pattern changes when a gas component is adsorbed by the plurality of semiconductor sensors", a signal pattern reflecting the adsorption of VOC derived from the allergen contained in the gas component can be obtained.

[0146] · Since the third aspect of the present disclosure is that "the signal pattern includes a pattern of current, voltage, electrical conductivity, or resistance that changes when a gas component is adsorbed by the semiconductor sensor", a signal pattern showing changes in current, voltage, electrical conductivity, or resistance, which reflects the adsorption of VOC derived from the allergen, can be obtained.

[0147] · Since the fourth aspect of the present disclosure is that "it includes a pattern of current, voltage, electrical conductivity, or resistance that changes when the gas component adsorbed on the semiconductor sensor desorbs", a signal pattern showing changes in current, voltage, electrical conductivity, or resistance, which reflects the desorption of VOC derived from the allergen, can be obtained.

[0148] · Since the fifth aspect of the present disclosure is that "the gas component is introduced into the semiconductor sensor without being pressurized or liquefied", it is possible to provide a small-sized detection device that does not require pressurization or liquefaction equipment and can be used at home or the like.

[0149] · The sixth aspect of the present disclosure is "identifying or quantifying allergens in the target space by inputting the plurality of signal patterns into a model generated by machine learning the relationship between the plurality of signal patterns of the plurality of semiconductor sensors and the type or amount of allergens". Therefore, pollen, mold, and mites can be identified and quantified with high specificity.

[0150] · The seventh aspect of the present disclosure is "the plurality of semiconductor sensors include two or more types of semiconductor sensors, and the two or more types of semiconductor sensors have different metal oxides as compositions". Therefore, the plurality of semiconductor sensors can exhibit relatively different response characteristics to the same gas component.

[0151] · The eighth aspect of the present disclosure is "the electric conductivity repeats a decrease and a recovery as one cycle, and the control unit extracts one waveform between the maximum value and the maximum value, or between the minimum value and the minimum value of the electric conductivity as the signal pattern, and repeatedly uses the signal pattern to identify or quantify allergens". Therefore, if there is a time for one cycle of the signal pattern, the allergens in the target space can be identified or quantified. Also, since the signal pattern repeats cycles, allergens can be measured continuously.

[0152] · The ninth aspect of the present disclosure is "when the quantified amount of allergens exceeds a threshold value, or when the slope of the amount of allergens with respect to time exceeds a threshold value, controlling the environmental equipment so as to reduce the amount of allergens or not increase it". Therefore, the environmental equipment can be automatically controlled according to the amount of allergens and the way it increases.

[0153] · The tenth aspect of the present disclosure is "displaying the change in the amount of allergens with respect to time for each type of allergen". Therefore, the amount of allergens and the way it increases can be visualized for the user, and the user can be prompted to activate the environmental equipment.

[0154] · The eleventh aspect of the present disclosure is "the allergens to be identified or quantified are pollen, mold, or mites". Therefore, pollen, mold, or mites can be identified.

[0155] · In the 12th aspect of the present disclosure, since "a plurality of semiconductor sensors output signals regarding a plurality of gas components" to be identified or quantified, allergens can be identified or quantified without waiting for the time until separation like chromatography.

Explanation of Signs

[0156] 10 Environmental equipment 11 Semiconductor sensor 60 Information processing device 70 User terminal 100 Allergen detection system

Claims

1. A detection device for identifying or quantifying allergens in a target space, comprising: A control unit that acquires signal patterns detected by a plurality of semiconductor sensors that exhibit relatively different response characteristics to the same gas component, identifies or quantifies the allergen, which is pollen, mold, or mite, from the plurality of signal patterns acquired from the plurality of semiconductor sensors, and outputs the result of the identification or quantification.

2. The detection device according to claim 1, wherein the signal pattern of the plurality of semiconductor sensors changes when a gas component is adsorbed.

3. The detection device according to claim 2, wherein the signal pattern includes a pattern of current, voltage, electrical conductivity, or resistance that changes when a gas component is adsorbed to the semiconductor sensor.

4. The detection device according to claim 3, wherein the signal pattern includes a pattern of current, voltage, electrical conductivity, or resistance that changes when the gas component adsorbed to the semiconductor sensor is desorbed.

5. The detection device according to any one of claims 1 to 4, wherein the gas component is introduced into the semiconductor sensor without being pressurized or liquefied.

6. The control unit inputs the plurality of signal patterns into a model generated by machine learning the relationship between the plurality of signal patterns of the plurality of semiconductor sensors and the type or amount of the allergen, thereby identifying or quantifying the allergen in the target space. The detection device according to any one of claims 1 to 4.

7. The detection device according to claim 1, wherein the plurality of semiconductor sensors include two or more types of semiconductor sensors, and the two or more types of semiconductor sensors have different metal oxides as compositions.

8. The electrical conductivity repeats a decrease and a recovery as one cycle, and the control unit extracts one waveform between the maximum value and the maximum value, or between the minimum value and the minimum value of the electrical conductivity as the signal pattern, and repeatedly uses the signal pattern to identify or quantify the allergen. The detection device according to claim 4.

9. When the amount of the quantified allergen exceeds a threshold value, or when the slope of the amount of the allergen with respect to time exceeds a threshold value, the control unit controls the environmental device so as to reduce the amount of the allergen or not to increase it. The detection device according to claim 8.

10. The detection device according to claim 1, wherein the control unit displays the change in the amount of the allergen with respect to time for each type of the allergen.

11. The plurality of semiconductor sensors output signals regarding a plurality of gas components simultaneously, The detection device according to claim 1, wherein the control unit acquires the signal pattern including the signals simultaneously output by the plurality of semiconductor sensors.

12. A detection method for a detection device to identify or quantify allergens in a target space, wherein a control unit acquires signal patterns detected by a plurality of semiconductor sensors that exhibit relatively different response characteristics to the same gas component, identifies or quantifies the allergen, which is pollen, mold, or mite, from the plurality of signal patterns acquired from the plurality of semiconductor sensors, and outputs the result of the identification or quantification.

13. A program for causing a computer to function as the detection device according to claim 1.

Images