Information processing system, information processing method, control program, and recording medium

Abstract

This system enables users to easily utilize the measurement results output from an odor measuring device. [Solution] The system includes an acquisition unit (11) that acquires setting information regarding processing to be performed on an object detection signal corresponding to the odor of the target, a processing unit (12) that performs processing based on the setting information, and an output control unit (14) that causes processing information including the processing results to be output to an output unit (output device 80), wherein the setting information includes at least an instruction to the processing unit (12) to perform one or more processing selected from (1) generating a graph showing the change in the object detection signal over time, and (2) extracting feature quantities of the object detection signal from the acquired object detection signal.

Description

Technical Field

[0001] The present disclosure relates to an information processing system, an information processing method, a control program, and a recording medium including an odor measurement device.

Background Art

[0002] In recent years, devices for evaluating an object based on the odor of the object have been developed. For example, Patent Document 1 describes an information processing device that identifies an object whose odor has been measured based on measured odor data and a learned model.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

[0007] An information processing method according to one aspect of the present disclosure is an information processing method performed by one or more computers, comprising: an acquisition step of acquiring setting information relating to processing performed by the computers on an object detection signal corresponding to an object odor; a processing step of performing the processing based on the setting information; and an output control step of causing the computers to output processing information including the results of the processing to an output unit, wherein the setting information includes at least an instruction to cause the computers to perform one or more processing selected from (1) generating a graph showing the change in the object detection signal over time, and (2) extracting feature quantities of the object detection signal, from the acquired object detection signal. [Effects of the Invention]

[0008] According to one aspect of this disclosure, the measurement results output from the odor measuring device can be easily utilized by the user. [Brief explanation of the drawing]

[0009] [Figure 1] This is a block diagram showing an example of the configuration of an information processing system. [Figure 2] This is a functional block diagram showing an example of the configuration of an odor measuring device. [Figure 3] This is a top view showing an example of the configuration of an odor sensor element. [Figure 4] This is a functional block diagram showing an example of the configuration of an information processing system, including an information processing device. [Figure 5] This flowchart shows an example of the process flow in which an information processing system estimates processing information. [Figure 6] This figure shows an example of the display screen of the output unit of an information processing system. [Figure 7] This figure shows an example of the display screen of the output unit of an information processing system. [Figure 8] This figure shows an example of the display screen of the output unit of an information processing system. [Figure 9]This is a functional block diagram showing an example of the configuration of an odor measuring device. [Figure 10] This is a functional block diagram showing an example of the configuration of an information processing system, including an information processing device. [Figure 11] This flowchart shows an example of the process flow in which an information processing system estimates processing information. [Modes for carrying out the invention]

[0010] One embodiment of this disclosure is described below, but this disclosure is not limited thereto. Unless otherwise specified herein, "A to B" representing a numerical range is intended to mean "A or greater and B or less".

[0011] [Embodiment 1] (Information processing system 100) First, an overview of an information processing system 100 according to one embodiment of this disclosure will be described. The information processing system 100 includes an odor measuring device 30 capable of outputting an object detection signal, which is a detection signal corresponding to the odor of a target, at regular intervals. The system extracts information from the object detection signal indicating at least one of the characteristics, intensity, and changes of the odor of the target, and provides it to the user of the information processing system 100 (hereinafter referred to as the user) in a preferred manner. The information processing system 100 can perform various processes desired by the user on the object detection signal acquired from the odor measuring device 30. Furthermore, the information processing system 100 can provide the user with the results of one or more processes in a preferred manner.

[0012] The target detection signal corresponding to the target odor acquired from the odor measurement device 30 often reflects the situation of the target. The information processing system 100 may have a function of analyzing the target detection signal acquired from the odor measurement device 30 and estimating the situation of the target. In this case, the information processing system 100 can provide and present to the user information regarding the state of the target in addition to various information regarding the odor in the target (for example, odor characteristics, odor intensity, and odor changes, etc.). Thereby, the user can maintain and manage the target based on the information regarding the state of the target obtained from the information processing system 100.

[0013] For example, when the odor measurement device 30 outputs the target detection signal in real time, the information processing system 100 can monitor the change in the target odor and can also quickly notify the user of the change that has occurred in the target odor and the change in the state of the target corresponding to the odor change.

[0014] For example, the information processing system 100 may include a plurality of odor measurement devices 30, and each of the plurality of odor measurement devices 30 may be installed at a different location from each other. In this case, the information processing system 100 can also notify the user of the odor and situation at each location where the odor measurement device 30 is installed.

[0015] In this specification, the "target" is not particularly limited as long as it can be measured for odor by an odor measurement device. The "target" may be, for example, an object such as food, cosmetics, pharmaceuticals, tobacco, chemical products, industrial products, manufactured goods, waste, and pollutants. Also, the "target" may be a living thing such as an animal, a plant, and an insect. Alternatively, the "target" may be an internal space such as a room, a corridor, a passage, a storage space, a warehouse, a bathroom, a toilet, inside a refrigerator, and a vehicle compartment. Alternatively, the "target" may be an area such as a road, a residential area, a park, a river, and a lake. In one embodiment, the "target" may be the peripheral area of an object and / or a location that can be a source of odor.

[0016] As used herein, "processing" means any processing performed on the target detection signal output from the odor measuring device. Examples of processing include (1) generation of a graph showing the change over time of the target detection signal, (2) analysis processing such as extraction of feature amounts of the target detection signal, (3) evaluation processing such as calculation of the estimation accuracy of the estimation model, (4) construction processing such as construction of the estimation model 21 using the target detection signal, (5) estimation of matters related to the target using the estimation model 21, and estimation processing such as estimation of the similarity to candidates for the estimation result of the target detection signal, etc. One or more types selected from these are included. The details of the estimation model 21 will be described later.

[0017] The information processing system 100 may execute only one type of processing, or may execute multiple types of processing simultaneously or separately. That is, the information processing system 100 may be one or more types of systems selected from (A) a system that analyzes the target detection signal, (B) a system that estimates the target based on the target detection signal, (C) a system that evaluates the estimation result of the estimation model 21, and (D) a construction system that constructs the estimation model 21.

[0018] In this specification, "processed information" means the result obtained by performing arbitrary processing on the target detection signal (i.e., the result of processing). The processed information includes the result of processing the target detection signal by the processing unit 12 of the information processing system 100. The processed information may include one or more types selected from the following: graphs generated from the target detection signal, analysis results such as the extraction results of feature quantities of the target detection signal, estimation results of matters related to the target estimated using the estimation model 21, and construction results such as the estimation results of the similarity of the estimation results of the target detection signal to candidates, the estimation accuracy of the constructed estimation model 21, and information related to the constructed estimation model 21. The estimation results of matters related to the target may include at least one type of information selected from, for example, the name of the target, the state of the target, and the classification of the target. The name of the target may be, for example, a specific name if the target is an object, or a scientific name if the target is a living organism. The state of the target may include, for example, the presence or absence of contamination, the presence or absence of odor, the presence or absence of decay, and the presence or absence of fermentation. The classification of the target may include, for example, the variety of the target, the degree of danger of the target, the intensity of the odor of the target, and the nature of the odor of the target.

[0019] (Configuration of Information Processing System 100) Next, the configuration of the information processing system 100 will be described with reference to Figure 1. Figure 1 is a block diagram showing an example of the configuration of the information processing system 100 according to one embodiment of the present disclosure. As shown in Figure 1, the information processing system 100 includes an odor measuring device 30, an information processing device 10, and a user terminal 50. The information processing system 100 processes the target detection signal output from the odor measuring device 30 based on the content input by the user via the input unit 60, and obtains the processing result. The information processing system 100 outputs the processing information, including the obtained processing result, to the output unit 70.

[0020] In the information processing system 100, as shown in Figure 1, the odor measuring device 30, the information processing device 10, and the user terminal 50 equipped with an input unit 60 and an output unit 70 may be connected via a wide-area communication network 40. The wide-area communication network 40 is not particularly limited and may be a network capable of long-distance communication such as the Internet, a telephone network, a mobile communication network, a CATV communication network, and a satellite communication network. The wide-area communication network 40 may be a local area network (LAN) connection without going through an ISP, a telephone network, etc., or it may be a serial communication, a mobile phone network including a 5G communication network, LPWA (Low Power Wide Area-network), Wi-Fi (registered trademark), PAN (Personal Area Network), Bluetooth (registered trademark), etc.

[0021] In this configuration, the information processing device 10 can acquire the detection signal output by the odor measuring device 30 via the wide-area communication network 40. Furthermore, the user terminal 50 can acquire processing information from the information processing device 10 via the wide-area communication network 40.

[0022] The number of odor measuring devices 30 provided in the information processing system 100 is not particularly limited and may be one or more, three or more, five or more, or ten or more. If the information processing system 100 is equipped with multiple odor measuring devices 30, the location in which each odor measuring device 30 is installed is not particularly limited. For example, each odor measuring device 30 may be installed in the same location or space. The odor measuring devices 30 may be installed inside a moving object such as a vehicle, railway car, or aircraft, or they may be installed outside of such a moving object.

[0023] Furthermore, each odor measuring device 30 may be installed in different locations or positions within the same area. For example, each odor measuring device 30 may be installed at the same position on a plane but at different heights. Each of the multiple odor measuring devices 30 may be configured to measure the odor of a different object. Alternatively, some or all of the multiple odor measuring devices 30 may be configured to measure the odor of the same object.

[0024] The number of user terminals 50 provided by the information processing system 100 is not particularly limited and may be one or more, three or more, five or more, or ten or more. If the information processing system 100 is equipped with multiple user terminals 50, each user terminal 50 may be linked to a different odor measuring device 30, or they may be linked to the same odor measuring device 30. The linking of user terminals 50 to odor measuring devices 30 may be performed based on user information stored in the information processing device 10.

[0025] The information processing system 100 may also include measuring devices other than the odor measuring device 30 (not shown). While not particularly limited, these measuring devices could include cameras, sound sensors, motion sensors, temperature sensors, humidity sensors, wind direction sensors, wind speed sensors, pressure sensors, position sensors, etc.

[0026] Here, the position sensor may be used together with the odor measuring device 30 to acquire position information corresponding to the location of the odor measuring device 30 in the target space where the odor measuring device 30 is installed. Alternatively, the odor measuring device 30 may also function as a position sensor, and the odor measuring device 30 may transmit position information along with the target detection signal to the information processing device 10. The position sensor may be at least one of the following (a) to (d).

[0027] (a) A GPS receiver that receives signals from multiple GPS (Global Positioning System) satellites.

[0028] (b) A GLONASS receiver that receives signals from GLONASS (Global Navigation Satellite System) satellites.

[0029] (c) Galileo receiver that receives signals from Galileo satellites.

[0030] (d) Beidou navigation positioning module.

[0031] [User terminal 50] The user terminal 50 is a terminal equipped with an input unit 60 and an output unit 70. The input unit 60 may be a device that accepts input operations from the user. The input unit 60 may be, for example, a keyboard, a touch panel, etc. In one embodiment, the functions of the input unit 60 may be provided by a separate device (input device) that can communicate with the user terminal 50 and is not connected to the user terminal. On the other hand, the output unit 70 may be a device that presents processed information in a manner that the user can confirm. The output unit 70 may be, for example, a display, a monitor, etc. In one embodiment, the functions of the output unit 70 may be provided by a separate device (output device) that can communicate with the user terminal 50 and is not connected to the user terminal.

[0032] The user terminal 50 is not particularly limited as long as it is a device that can receive input operations from the user, transmit the information entered by said input operations to the information processing device 10, and receive processing information from the information processing device 10 and allow the user to confirm said processing information. Examples of user terminals 50 include smartphones, tablets, and personal computers. The user terminal 50 is used by the user to determine the processing to be performed by the information processing device 10 and the processing information to be output by the information processing device 10. The user terminal 50 is also used by the user to confirm the processing information output by the information processing device 10.

[0033] The user terminal 50 may be a portable device for the user. Preferably, the user terminal 50 is a device that can check the processing information at any location where it can communicate with the information processing device 10. With the above configuration, the user can check the processing information more easily.

[0034] [Odor measuring device 30] The odor measuring device 30 is equipped with an odor sensor element 31 and outputs a detection signal corresponding to the measured odor at regular intervals. The odor measuring device 30 may output a target detection signal, for example, every hour, every 30 minutes, every 10 minutes, every 5 minutes, every minute, every 30 seconds, or every second. In addition to the detection signal, the odor measuring device 30 may also output information related to the odor measuring device 30 itself (for example, device number, installation location, operating time, etc.).

[0035] The location where the odor measuring device 30 is installed is not particularly limited and can be installed in any location indoors or outdoors. In one embodiment, the odor measuring device 30 may be a portable device. The odor measuring device 30 may be able to continuously (or at regular intervals) draw in (sample) the gas to be measured (a gas containing odor substances) at the installed location and measure the odor. In this case, the odor measuring device 30 may transmit the measurement results to the information processing device 10 at regular intervals.

[0036] In one embodiment, the odor measuring device 30 may further include a temperature control function for adjusting the temperature of the gas to be measured, and / or a humidity control function for adjusting the humidity of the gas to be measured. If the odor measuring device 30 has the above functions, it will be possible to measure the odor of the target without being affected by changes in the environment in which it is installed.

[0037] The configuration of the odor measuring device 30 to which the odor sensor element 31 is applied will be described below with reference to Figure 2. Figure 2 is a functional block diagram showing an example of the configuration of the odor measuring device 30. The odor measuring device 30 includes an odor sensor element 31 for detecting odor substances, a power supply 32 (power supply), a clock 33 (timer), a control unit 34, and a communication unit 35. As described above, the odor measuring device 30 may be connected to a wide-area communication network 40.

[0038] The power supply 32 is a power source for supplying power to the odor sensor element 31. The power supply 32 may be a constant voltage power supply, a constant current power supply, or an AC power supply. In one embodiment, the power supply 32 may be a battery. If the power supply 32 is a constant voltage power supply, it supplies current (for example, a DC current of 1 μA to 10 mA) to the odor sensor element 31 via lead wires. The voltage value supplied by the power supply 32 is, for example, 0.01 V to 10 V, and more specifically, 0.1 V to 5.0 V.

[0039] Clock 33 measures the time. Clock 33 transmits the measured time to the control unit 34. Clock 33 may be a clock whose time is set by the user, or it may be a radio-controlled clock. Clock 33 may correct its own time using the time obtained from the communication unit 35. Furthermore, Clock 33 can measure the time even when the power to the odor measuring device 30 is turned off.

[0040] The control unit 34 controls all parts of the odor measuring device 30. The control unit 34 also outputs the odor detected by the odor sensor element 31 as a detection signal. The control unit 34 may also output the odor detection signal according to the time measured by the clock 33.

[0041] The communication unit 35 transmits the detection signal output by the control unit 34. The communication unit 35 transmits the detection signal to the wide-area communication network 40, and the transmitted detection signal is acquired by the information processing device 10.

[0042] The odor measuring device 30 may also include a housing, although this is not a mandatory component. The housing is a container capable of enclosing the components of the odor measuring device 30. If the odor measuring device 30 includes a housing, the odor sensor element 31 is installed inside the housing. The odor sensor element 31 is an element that can adsorb / desorb odor substances when exposed to air containing such substances. With the above configuration, the odor sensor element 31, control unit 34, communication unit 35, etc., can be protected from wind, rain, sunlight, dust, etc. The housing may also include a configuration or mechanism for fixing the odor measuring device 30 to the installation location.

[0043] The odor measuring device 30 outputs a detection signal that shows the change in the electrical conductivity of the odor sensor element 31 over time, before and after odor substances are adsorbed onto the odor sensor element 31. By equipping the odor measuring device 30 with multiple types of odor sensor elements capable of adsorbing and desorbing various odor substances, it is possible to detect and identify a wide variety of odors.

[0044] In one embodiment, the odor measuring device 30 may further include a containment section 36 capable of accommodating an object (for example, a solid sample or a liquid sample), as shown in Figure 9, and may be capable of measuring the odor originating from the object in the containment section 36. If the odor measuring device 30 further includes a containment section 36, the odor measuring device 30 may be capable of adjusting the temperature inside the containment section 36 to adjust the concentration of odor substances originating from the object inside the containment section 36.

[0045] The odor measuring device 30 may be configured to use the detection signal obtained when measuring dry air or nitrogen that does not contain odor substances as a baseline before and after measuring the odor originating from the target in the containment section 36. With this configuration, when the odor measuring device 30 measures the odor originating from the target in the containment section 36, it can output an accurate signal intensity by comparing it with the baseline.

[0046] <Odor sensor element 31> The odor measuring device 30 is equipped with a plurality of odor sensor elements 31 capable of outputting detection signals, and each of the plurality of odor sensor elements 31 is equipped with an odor substance receiving layer 315 in which interactable odor substances are different from each other.

[0047] Figure 3 is a top view showing an example of the configuration of the odor sensor element 31. The odor sensor element 31 comprises an odor substance receiving layer 315 containing the resin composition described above, a first metal wiring 313A, and a second metal wiring 313B. In the following, when the first metal wiring 313A and the second metal wiring 313B are not distinguished, they may be referred to simply as metal wiring 313.

[0048] The first metal wiring 313A and the second metal wiring 313B are metal wirings that function as electrodes for measuring changes in the electrical conductivity of the odor substance receiving layer 315 (i.e., the resin composition). That is, the first metal wiring 313A and the second metal wiring 313B are spaced apart from each other, and the odor substance receiving layer 315 is in contact with at least a portion of the first metal wiring and at least a portion of the second metal wiring. In one example, the first metal wiring 313A and the second metal wiring 313B are metal wirings that are not in direct contact with each other, and may be substantially parallel to each other, as shown in Figure 2.

[0049] As shown in Figure 3, the metal wiring 313, including the first metal wiring 313A and the second metal wiring 313B, may be arranged on a substrate 311. The substrate 311 may be a substrate such as glass epoxy, which is commonly used in electronic circuits. The metal wiring 313 may be made of copper or gold. The thickness of the first metal wiring 313A and the second metal wiring 313B, as viewed from a direction perpendicular to the surface of the substrate, may be, for example, 10 μm to 2 mm.

[0050] The odor substance receiving layer 315 may be in contact with at least a portion of the first metal wiring 313A and at least a portion of the second metal wiring 313B. The odor substance receiving layer 315 may be arranged to fill the region sandwiched between the first metal wiring 313A and the second metal wiring 313B, for example, as shown in Figures 2 and 3.

[0051] If the electrical conductivity of the odor substance receiving layer 315 (i.e., the electrical conductivity of the odor sensor element 31) is low, it is desirable that the distance between the first metal wiring 313A and the second metal wiring 313B be less than or equal to a predetermined distance (for example, 500 μm).

[0052] The odor substance receiving layer 315 may contain a resin composition. The resin composition may contain a resin and further contain one or more selected from a surfactant and a filler (e.g., a conductive carbon material). In this specification, "odor substance receiving layer" means a layer that adsorbs odor substances to be identified. The odor substance receiving layer 315 is formed from the above-described resin composition. The odor substance receiving layer 315 may be provided as part of an odor sensor element 31. The electrical resistance of this odor substance receiving layer 315 changes in response to the adsorption of odor substances, etc. That is, the odor sensor element 31 is an odor detection device equipped with such an odor substance receiving layer 315, and the odor measurement method of the odor sensor element 31 may be a chemiresistor type.

[0053] When the odor sensor element 31 is a chemisistor type containing a resin composition, the change in electrical conductivity over time differs depending on whether odor substance A is adsorbed or odor substance B, which is different from odor substance A, is adsorbed. Therefore, it is possible to detect and identify various odor substances. In the odor measuring device 30 described later, multiple odor sensor elements 31 are arranged, each having a substrate 311 equipped with a configuration for detecting odor substances (metal wiring 313 and odor substance receiving layer 315). Each substrate 311 has multiple sets of odor substance receiving layers 315, each containing odor substances that can be measured differently from each other. Each of the multiple odor sensor elements 31 may also be equipped with a constant voltage power supply and a voltmeter. In the odor measuring device 30, one configuration for detecting odor substances (metal wiring 313 and odor substance receiving layer 315) may be arranged on each substrate 311. Alternatively, in the odor measuring device 30, multiple sets of configurations for detecting odor substances (metal wiring 313 and odor substance receiving layer 315) may be arranged on a single substrate 311. In the latter case, a constant voltage power supply and a voltmeter are connected to each of the sets provided on the circuit board 311.

[0054] The resin compositions contained in the odor substance receiving layers 315 of the multiple odor sensor elements 31 in the odor measuring device 30 may be the same or different. If the odor substance receiving layers 315 contained in the multiple odor sensor elements 31 have the same composition, each of the multiple odor substance receiving layers 315 can detect the same odor substance. If the multiple odor sensor elements 31 each contain odor substance receiving layers 315 with different compositions, each of the multiple odor substance receiving layers 315 will respond differently to the odor substance. In this way, by providing multiple sets of configurations for detecting odor substances, the accuracy of odor substance identification in the odor measuring device 30 can be improved.

[0055] The odor measuring device 30 described above can output the change in the electrical conductivity of the odor sensor element 31 over time for each odor substance when various odor substances are adsorbed onto the odor sensor element 31. By applying this odor measuring device 30, it is possible to compare the change in the electrical conductivity of the odor sensor element 31 over time when odor substance A is adsorbed onto the odor sensor element 31 with the change in the electrical conductivity of the odor sensor element 31 over time when odor substance B is adsorbed onto the odor sensor element 31.

[0056] [Information processing device 10] The configuration of the information processing device 10 will be described below. The information processing device 10 is a device that processes the target detection signal output from the odor measuring device 30 described above, based on the content input by the user.

[0057] Figure 4 is a functional block diagram showing an example of the configuration of an information processing system 100 including an information processing device 10. The information processing device 10 includes a control unit 1 that controls all parts of the information processing device 10, and a storage unit 2 that stores various data used by the information processing device 10.

[0058] <Storage section 2> First, let's explain the memory unit 2. The memory unit 2 stores the estimation model 21, the target detection signal 22, the setting information 23, the processing information 24, and the user information 25.

[0059] The estimation model 21 is trained by machine learning using training data. The training data may include a sample detection signal corresponding to the odor of the sample as an explanatory variable, and sample information relating to at least one of the cause of the odor of the sample and the state of the object corresponding to the sample detection signal as an objective variable. Only one type of estimation model 21 may be stored in the storage unit 2, or multiple types may be stored.

[0060] In this specification, the term "specimen" is not particularly limited to any object that can be selected as an object as described above. The specimen may be the same as or different from the object. In one embodiment, the specimen is preferably similar to the object, and more preferably of the same kind as the object, such as an object, organism, space, or region.

[0061] In this specification, "sample information" means any information relating to a sample. The sample information is not particularly limited, as long as it is information about a sample that can be selected as the processing information described above. The desired sample information can be selected according to the processing information to be estimated.

[0062] In the machine learning process for the estimation model 21, further data preprocessing and feature extraction may be performed. Additionally, machine learning algorithms may be used to generate the estimation model 21.

[0063] (Feature extraction) The training data for generating the estimation model 21 by machine learning may be the measured values ​​themselves or features extracted from the measured values. Features may be, for example, statistics, differential and integral values, peak detection values, or autocorrelation values. Examples of statistics include the mean, variance, maximum value, minimum value, the difference between the maximum and minimum values, and the standard deviation. Examples of differential and integral values ​​include the derivative (the slope of a graph showing the change in measured values ​​over time) and the integral (the area of ​​the region defined by the curve showing the change in measured values ​​in a graph showing the change in measured values ​​over time and the horizontal axis (e.g., the time axis)). Examples of peak detection values ​​include the number and height of peaks in the change in measured values ​​(e.g., change over time). Examples of autocorrelation values ​​include the difference in the change in measured values ​​(e.g., change over time). Extraction of these features from measured values ​​can be carried out based on known methods.

[0064] (Pre-treatment method) The training data for generating the estimation model 21 by machine learning may be used for machine learning without preprocessing, or it may be used after predetermined preprocessing as necessary. Furthermore, if preprocessing is performed, it may be performed before feature extraction, after feature extraction, or both before and after feature extraction. Preprocessing may be performed by known methods. Known methods include correction, denoising, standardization, data transformation, smoothing, and data augmentation. Examples of correction include integration, addition, subtraction, and division based on the output ratio, independent component analysis (ICA), or statistics, based on the measurement results of a standard gas by multiple sensor elements or commercially available sensors (e.g., temperature sensors or humidity sensors). Examples of denoising include removal of outliers or white noise. Examples of standardization include normalization and regularization of features. Examples of data transformation include trend removal, frequency transformation, and logarithmic transformation. Examples of smoothing include obtaining the moving average of the data and obtaining the difference. Data augmentation methods include, for example, adding the same sample data (e.g., adding data assuming a normal distribution) or adding new sample data (e.g., adding data related to the mixing ratio of vectors).

[0065] (Machine learning algorithms) Machine learning algorithms that can be used to create the estimated model 21 include regression analysis, classification, trees, time series analysis, neural networks, and clustering. Examples of regression analysis include logistic regression, Lasso regression, elastic network regression, support vector regression (SVR), linear regression, Ridge regression, and ensemble regression. Examples of classification include k-nearest neighbor method, support vector classification (SVC), Naibe Bayes classifier, stochastic gradient descent (SGD), and kernel approximation. Examples of trees include decision trees, regression trees, random forests, boosting (lightGBM, XGboost), and stacking. Examples of time series include AR, MA, ARIMA, and state space. Examples of neural networks include multilayer perceptrons (MLPs), convolutional neural networks (CNNs), recurrent neural networks (RNNs), residual neural networks (ResNets), transformers, and graph neural networks (GNNs). Examples of clustering methods include Gaussian mixture models (GMMs), k-means algorithms, mini k-means algorithms, variational Gaussian mixture models (VBGMMs), and kernel approximations.

[0066] The target detection signal 22 includes a detection signal output from the odor measuring device 30. In one embodiment, the target detection signal 22 may be associated with other data that the acquisition unit 11 described above can acquire.

[0067] The setting information 23 is information relating to the processing that the processing unit 12 will perform on the target detection signal. The setting information 23 may also be information that is input by the user from the input unit 60, indicating the type of processing that the processing unit 12 will perform and the type of information that the output control unit 14 will output. Based on the setting information 23, the processing unit 12 will execute the processing and the output control unit 14 will output the information. If the odor measuring device 30 does not output data such as the device number and device location information, such data may be included in the setting information 23.

[0068] The setting information 23 may include at least an instruction to the processing unit 12 to output target estimation information relating to at least one of the cause of the odor of the target and the state of the target, using an estimation model based on the acquired target detection signal. In one embodiment, the setting information 23 may further include the following instructions to be executed by the processing unit 12.

[0069] (1) An instruction to plot the detected target signal on a graph of a specific type (bar graph, line graph, scatter plot, histogram, etc.), (2) If multiple estimation models 21 exist, an instruction to perform estimation using a specific estimation model 21. (3) Instructions to construct the estimation model 21 using specific training data.

[0070] Furthermore, the configuration information 23 may include information other than instructions to be executed by the processing unit 12, such as the following:

[0071] (4) Information concerning the type, name and condition of specimens and subjects, (5) The types of information acquired by the acquisition unit 11 other than the target detection signal.

[0072] The processing information 24 is information obtained by the processing unit 12, including the results of the processing. The processing information 24 may consist of only one type of information or may contain multiple types of information. Examples of the processing information 24 include one or more types selected from a table of detected values ​​of the target detection signal, a graph generated based on the target detection signal, feature quantities extracted from the target detection signal, values ​​obtained from a camera, sound sensor, motion sensor, temperature sensor, humidity sensor, wind direction sensor, wind speed sensor, barometric pressure sensor, position sensor, etc., and the device ID of the odor measuring device 30.

[0073] User information 25 is data used to link the odor measuring device 30 with the user terminal 50. The user information 25 allows the information processing system 100 to transmit results output from a specific odor measuring device 30 to a specific user terminal 50, even if the system has multiple odor measuring devices 30 and multiple user terminals 50. Specifically, user information 25 may be information linked to an ID input from the user terminal 50 and the device ID of the odor measuring device 30.

[0074] <Control Unit 1> Next, the control unit 1 will be described. The control unit 1 includes an acquisition unit 11, a processing unit 12, an estimation unit 13, and an output control unit 14. Furthermore, some of the blocks included in the control unit 1 may be assigned to other devices that can communicate with the information processing device 10, and those blocks may be omitted from the control unit 1. For example, the functions of the output control unit 14 may be assigned to other devices. In this case, the information processing device 10 may output the results estimated by the estimation unit 13 using the other device. An example of another device that can communicate with the information processing device 10 is an odor measuring device 30.

[0075] The acquisition unit 11 acquires the target detection signal output from the odor measuring device 30 and the setting information input by the user. In one embodiment, the acquisition unit 11 may acquire the target detection signal output from the odor measuring device 30 at regular intervals, or it may acquire it each time the target detection signal is output. The acquisition unit 11 may acquire the target detection signal, for example, every hour, every 30 minutes, every 10 minutes, every 5 minutes, every minute, every 30 seconds, or every second. The acquisition unit 11 may be configured to acquire detection signals stored on the wide-area communication network 40 at regular intervals. The acquisition unit 11 may store the acquired target detection signal and the setting information input by the user in the storage unit 2.

[0076] In one embodiment, the acquisition unit 11 may further acquire data other than the target detection signal. This other data may include, for example, data related to the odor measuring device 30, such as the device number and location information (device location information) indicating the installation location of the device, or time information such as the measurement start time and measurement end time by the odor measuring device 30.

[0077] The processing unit 12 processes the target detection signal acquired by the acquisition unit 11 based on the setting information input by the user. In one embodiment, the processing unit 12 may read the target detection signal 22 already stored in the storage unit 2 and perform the processing described later. The processing unit 12 may also include an analysis unit 15.

[0078] The analysis unit 15 performs analysis of the target detection signal. Examples of analysis performed by the analysis unit 15 include one or more methods selected from plotting the target detection signal on a graph, extracting feature quantities from the target detection signal, and detecting outliers. The analysis unit 15 may perform only one type of analysis of the target detection signal, or it may perform multiple types. After performing the analysis on the target detection signal, the obtained analysis results are transmitted to the output control unit 14. The analysis unit 15 may also store the analysis results in the storage unit 2.

[0079] The analysis unit 15 may further perform tasks such as detecting whether or not the odor sensor element 31 is damaged based on the analysis results of the target detection signal, plotting weather information at the location where the odor measuring device 30 is installed, measured by sensors other than the odor measuring device 30 (e.g., humidity sensor, wind direction sensor, wind speed sensor, pressure sensor, etc.), on a map, and plotting the location information of the odor measuring device 30 measured by the location sensor on a map.

[0080] The output control unit 14 transmits (outputs) the processing information output by the processing unit 12 to the user terminal 50. The user terminal 50, upon receiving the processing information, causes the output unit 70 to output the processing information. In other words, the output control unit 14 causes the output unit 70 to output the processing information. The output control unit 14 may further transmit the target detection signal acquired by the acquisition unit 11 and / or data related to the odor measuring device 30 to the user terminal 50. The information output by the output control unit 14 is determined based on the setting information 23. The output control unit 14 may further transmit the estimation result estimated by the estimation unit 13 to the user terminal 50. The output control unit 14 may transmit the processing information directly to the user terminal 50, or it may transmit the processing information to a web page or web service on the wide-area communication network 40 that is accessible to the user terminal 50.

[0081] In one embodiment, the output control unit 14 may transmit the processing information along with alert information to the user terminal 50 when the processing information meets certain conditions. The conditions under which the output control unit 14 outputs alert information may be set by the user via the input unit 60.

[0082] When the information processing device 10 performs processing based on the setting information input by the user, multiple types of processing information may be output. In this case, all of the multiple types of processing information may be sent to the user terminal 50, or some of the multiple types of processing information may be sent to a device other than the user terminal 50.

[0083] The output mode of the output control unit 14 is not particularly limited. The processing information output by the output control unit 14 may be displayed on a web page or the like that can be accessed by any terminal. The output control unit 14 may also issue a dedicated address to a user who has requested the processing information and provide access information to the web page or the like. The output control unit 14 may also transmit the processing information and estimation results, etc., to an output device on which dedicated software is installed, via said dedicated software.

[0084] The information processing device 10 shown in Figure 4 is not limited to the configuration described above. For example, the storage unit 2 may be a data management device that is communicatively connected to the information processing device 10, or it may be a detachable storage device separate from the information processing device 10.

[0085] [Display screen 1] Figure 6 shows an example of the display screen of the output unit 70 of the information processing system 100. As shown in Figure 6, multiple types of information may be output to the output unit 70.

[0086] The output unit 70 may output, for example, a graph 71 plotting the detection signals from the odor measuring device 30. Graph 71 is a graph obtained by the analysis unit 15 performing an analysis on the target detection signals acquired by the acquisition unit 11. Graph 71 may be a graph based only on the detection signals from a specific odor measuring device 30, or it may be a graph plotting the detection signals from multiple odor measuring devices 30. Graph 71 may be a graph plotting the detection signals measured by the odor measuring device 30 within a certain period of time, or it may be a graph that continuously plots the detection signals over time. Examples of graph 71 include, but are not limited to, a graph plotting the detection signals as they are, a graph showing the intensity of the detection signals, a graph showing the feature quantities of the detection signals, and a graph showing the detection signals after arbitrary numerical processing. Examples of arbitrary numerical processing include calculating the average value at arbitrary time intervals and correcting for drift with respect to temperature or humidity. The type of graph 71 can be determined based on user input.

[0087] In one embodiment, the horizontal axis of graph 71 represents time. In one embodiment, the vertical axis of graph 71 represents the electrical resistance (Ω) output by the odor measuring device 30, the voltage value (V) based on the electrical resistance, or the rate of change (%) relative to the electrical resistance or voltage value at a specific point in time.

[0088] The output unit 70 may output, for example, an annotation 72 of the odor measuring device 30. The annotation 72 of the odor measuring device 30 refers to information related to the odor measuring device 30 that has been pre-input by the user. In one embodiment, the annotation 72 may be information acquired from the odor measuring device 30 by the acquisition unit 11. Examples of information output as annotation 72 include a time range indicating the start and end times of the event being measured, an odor type which is a classification of the odor of the item being measured based on human olfaction, and the serial number of the odor measuring device 30. Here, the event being measured may be any event that has the potential to change the odor of the item.

[0089] For example, the output unit 70 may output one or more time ranges as annotations 72, indicating the start and end times of the event being measured. If a user selects one of the one or more time ranges output, the output unit 70 may also output the target detection signal output from the odor measuring device 30 and / or information related to the target detection signal within that selected time range.

[0090] For example, the output unit 70 may output one or more odor types as annotations 72, which are classifications of the odor to be measured based on human olfaction. If the user selects one or more of the output odor types, the output unit 70 may output a target detection signal and / or information related to the target detection signal corresponding to the selected odor type.

[0091] For example, the output unit 70 may output the serial number of one or more odor measuring devices 30 as annotation 72. If one or more of the outputted serial numbers are selected by the user, the output unit 70 may output the target detection signal from the odor measuring device 30 and / or information related to the target detection signal corresponding to the selected serial number. With the above configuration, only the measurement result from a specific odor measuring device 30 can be output from the measurement results from multiple odor measuring devices 30.

[0092] In one embodiment, the output unit 70 may display location information 73 of the odor measuring device 30. The location information 73 may be information acquired from the odor measuring device 30 by the acquisition unit 11. The location information 73 may be displayed together with the annotation 72. In order to provide the user with easily understandable information, the output unit 70 may also display a map (see Figure 6) showing the location corresponding to each of the location pieces of location information 73, separately from the annotation 72, along with the annotation 72.

[0093] (Processing performed by the information processing system 100) An information processing method according to one embodiment of this disclosure will be described with reference to Figure 5. Figure 5 is a flowchart showing an example of the processing flow in which the information processing system 100 estimates processing information. Note that the information processing system 100 may include one or more computers, and each of the one or more computers may be capable of executing some or all of the functions of the information processing device 10. That is, the processing shown in Figure 5 can be executed by one or more computers.

[0094] In step S1, the input unit 60 receives input from the user (input reception step). In step S1, the user may input information they want to output to the output unit 70, or they may input information necessary to construct the estimation model 21. In step S1, the user may also input further information related to the odor measuring device 30.

[0095] In step S2, the acquisition unit 11 acquires the target detection signal output from the odor measuring device 30 and the setting information input by the user, which is input to the input unit 60, when the target odor is measured using the odor measuring device 30 (acquisition step). In step S2, the target detection signal is output by one or more odor measuring devices 30 at regular intervals. In step S2, the acquisition unit 11 may acquire information related to the odor measuring device 30 in addition to the target detection signal and the setting information input by the user.

[0096] In step S3, the processing unit 12 processes the target detection signal based on the setting information 23 input by the user (processing step). In step S3, the estimation unit 13 may further perform estimation using the estimation model 21 from the processing results output from the processing unit 12.

[0097] In step S4, the output control unit 14 transmits (outputs) processing information, including the processing results, to the user terminal 50. At this time, the output control unit 14 may also transmit processing information, including a target detection signal, to the user terminal 50. Upon receiving this processing information, the user terminal 50 displays the processing information on the output unit 70. In addition to the processing results, the output control unit 14 may further output the estimation results from the estimation unit 13.

[0098] According to this information processing method, the information processing device 10 can output desired information related to the measurement results from the odor measuring device 30 based on user input. With the above configuration, the information processing system 100 can provide the user with processing information that has been performed on the target detection signal output from the odor measuring device 30 as desired by the user. Therefore, the user can easily utilize the measurement results from the odor measuring device 30.

[0099] [Embodiment 2] Other embodiments of this disclosure are described below. For the sake of clarity, components having the same function as those described in the above embodiments are denoted by the same reference numerals, and their descriptions are not repeated.

[0100] In Embodiment 2, the processing unit 12 includes an estimation unit 13. The processing unit 12 may include both an analysis unit 15 and an estimation unit 13, or it may include only an estimation unit 13. When the processing unit 12 includes an estimation unit 13, the processing information includes the estimation result (target estimation information) from the estimation unit 13.

[0101] The estimation unit 13 estimates target estimation information relating to at least one of the cause of the target's odor and the state of the target from the processed target detection signal and outputs it to the output control unit 14. The estimation unit 13 performs estimation using an estimation model 21. The estimation unit 13 may perform estimation using only one type of estimation model 21, or it may perform estimation using multiple types of estimation models 21. The estimation unit 13 may perform estimation from the target detection signal before processing. The estimation unit 13 may estimate matters relating to a specific type of target based on the user's input. The estimation unit 13 may further output details of the estimation model 21 used for estimation. The estimation unit 13 may store the estimation results in the storage unit 2.

[0102] The estimation unit 13 may also perform similarity estimation of the target detection signal to candidate estimation results. The similarity estimated by the estimation unit 13 is a value estimated based on the target detection signal and the sample detection signal used by the estimation model 21 for machine learning. For example, if there are three candidate odors, 1 to 3, as candidates for the estimation result, the estimation unit 13 estimates which of odors 1 to 3 the odor emitted by the target is based on the target detection signal. At this time, the estimation unit 13 may output similarity values ​​as results, such as a similarity of 75% to odor 1, a similarity of 20% to odor 2, and a similarity of 5% to odor 3 of the target detection signal, rather than the estimated result of which of odors 1 to 3 the odor emitted by the target is.

[0103] The estimation unit 13 may perform estimation based on the target detection signal acquired by the acquisition unit 11. Alternatively, the estimation may be performed based on the target detection signal after analysis such as feature extraction by the analysis unit 15.

[0104] In one embodiment, the processing unit 12 may further include a determination unit that determines the similarity value estimated by the estimation unit 13. The determination unit may output a determination that the similarity value is a pass if it is equal to or greater than a predetermined value, and a fail if it is less than the predetermined value. The determination by the determination unit may be output together with the estimation result by the estimation unit 13.

[0105] [Display screen 2] Figure 7 shows another example of the display screen of the output unit 70 of the information processing system 100. Figure 7 shows the display screen when the target detection signal is measured over time. As shown in Figure 7, the type of information output to the output unit 70 is not particularly limited.

[0106] As an example, the output unit 70 outputs a similarity score 74 to the candidate estimated results of the detection signal estimated by the estimation unit 13. The similarity score 74 is a value estimated by the estimation unit 13 that indicates how similar the detection signal output by the odor measuring device 30 is to the candidate odors (e.g., odors 1 to 3). The similarity score 74 may be estimated over time based on the acquired detection signal.

[0107] The output unit 70 may output, for example, an alert setting 75. The alert setting 75 is an alert condition determined by the user. If the detection signal meets the conditions set in the alert setting 75, the user is notified of an alert. The alert setting 75 is not particularly limited, but for example, it may be a setting that notifies the user of an alert when the value of graph 71 and the similarity value 74, as shown in Figure 7, meet specific conditions. The alert setting 75 may be acquired by the acquisition unit 11.

[0108] [Embodiment 3] Other embodiments of this disclosure are described below. For the sake of clarity, components having the same function as those described in the above embodiments are denoted by the same reference numerals, and their descriptions are not repeated.

[0109] In Embodiment 3, the processing unit 12 may include an evaluation unit 16 in addition to the estimation unit 13. The processing unit 12 may further include an analysis unit 15.

[0110] The evaluation unit 16 evaluates the estimation accuracy of the estimation results estimated by the estimation unit 13. The evaluation of estimation accuracy by the evaluation unit 16 may be performed by measuring the agreement rate when comparing the values ​​given as annotations with the estimation results. If the information processing device 10 has multiple estimation models, the evaluation unit 16 can check the estimation accuracy of each estimation model, thereby obtaining more accurate estimation results. The evaluation unit 16 may store the estimation accuracy of the estimation models in the storage unit 2.

[0111] [Display screen 3] Figure 8 shows another example of the display screen of the output unit 70 of the information processing system 100. As shown in Figure 8, multiple pieces of information can be output to the output unit 70. For example, the estimated model accuracy 76 shown in Figure 8 may be output to the output unit 70.

[0112] The estimated model accuracy 76 is a value calculated by the evaluation unit 16 evaluating the estimation results of the estimated model 21. If the information processing system 100 has multiple estimated models 21, the user can decide which estimated model 21 to use to estimate the target detection signal based on the estimated model accuracy 76. Here, each of the multiple estimated models 21 may be a model created from the same measurement data using different methods, or a model created from different data using the same method. When the estimated model accuracy 76 is output to the output unit 70, a graph 71 of the feature quantities of each estimated model may also be output for the purpose of qualitatively evaluating the validity of the accuracy of each estimated model 21. In addition to the estimated model number and the accuracy rate, the estimated model accuracy 76 may also display the construction method of the estimated model, the type of data used to construct the estimated model, etc. The estimated model accuracy 76 may be the accuracy of an estimated model constructed by the user, or it may be the accuracy of a pre-constructed estimated model.

[0113] [Embodiment 4] Other embodiments of this disclosure are described below. For the sake of clarity, components having the same function as those described in the above embodiments are denoted by the same reference numerals, and their descriptions are not repeated.

[0114] In Embodiment 4, the processing unit 12 includes a model building unit 17. The processing unit 12 may further include one or more units selected from an analysis unit 15, an estimation unit 13, and an evaluation unit 16.

[0115] The model building unit 17 constructs an estimation model by machine learning using training data that includes a sample detection signal corresponding to the odor of the sample as an explanatory variable and sample information relating to the sample corresponding to the sample detection signal as an objective variable. In one embodiment, the model building unit 17 may construct the estimation model using an object detection signal and object information instead of a sample detection signal and sample information. When constructing a model, the model building unit 17 may construct the estimation model using only the sample detection signal and sample information selected by the user from among the sample detection signal and sample information as training data. The model building unit 17 may use training data that includes object detection signals acquired by the acquisition unit 11 to construct the estimation model, or it may use training data that includes analysis results output by the analysis unit 15.

[0116] In one embodiment, the model building unit 17 may automatically build an estimation model if the estimation accuracy output from the evaluation unit 16 is less than a predetermined value, or it may build an estimation model based on user input. Model building may be performed, for example, by performing machine learning again using training data input by the user, or the estimation model newly built by the user may be stored in the storage unit 2.

[0117] [Embodiment 5] Other embodiments of this disclosure are described below. For the sake of clarity, components having the same function as those described in the above embodiments are denoted by the same reference numerals, and their descriptions are not repeated.

[0118] The information processing system 100a according to Embodiment 5 includes an acquisition unit 11 that acquires setting information regarding processing to be performed on an object detection signal corresponding to the odor of the object, a processing unit 12 that performs processing based on the setting information, and an output control unit 14 that causes an output device 80 (output unit) to output processing information including the processing results. In the following description, the case in which the information processing system 100a analyzes an object detection signal output from an odor measuring device 30a, which includes an object-containing unit 36 ​​capable of accommodating an object and a plurality of odor sensor elements 31 capable of outputting detection signals, as shown in Figure 9, will be explained as an example. In this case, the object detection signal may include, for example, a series of detection signals such as a detection signal (baseline) when measuring dry air or nitrogen, a detection signal when measuring the odor of the object, and a detection signal when measuring dry air or nitrogen again.

[0119] In one example, the information processing system 100a includes an information processing device 10a that is communicatively connected to the odor measuring device 30a. Figure 10 is a functional block diagram showing an example of the configuration of the information processing system 100a including the information processing device 10a. The information processing device 10a includes a control unit 1a that controls all parts of the information processing device 10a, and a storage unit 2a that stores various data used by the information processing device 10a.

[0120] [Information processing device 10a] The configuration of the information processing device 10a will be described below. The information processing device 10a is a device that processes the target detection signal output from the odor measuring device 30a based on the content input by the user. As shown in Figure 10, the information processing device 10a comprises a control unit 1a, a storage unit 2a, and an input unit 18.

[0121] <Input section 18> The input unit 18 accepts input operations from the user. The input unit 18 may be, for example, a keyboard and touch panel provided by the information processing device 10a.

[0122] <Storage section 2a> As shown in Figure 10, the memory unit 2a stores the estimated model 21, the target detection signal 22, the setting information 23, and the processing information 24.

[0123] <Control Unit 1a> As shown in Figure 10, the control unit 1a includes an acquisition unit 11, a processing unit 12 that processes based on the setting information, and an output control unit 14.

[0124] The acquisition unit 11 acquires setting information related to the processing to be performed on the target detection signal corresponding to the target odor. Specifically, the acquisition unit 11 acquires setting information input by the user from the input unit 18. The acquisition unit 11 may also store the setting information input by the user in the storage unit 2a.

[0125] The acquisition unit 11 acquires the target detection signal output from the odor measuring device 30a. If the information processing device 10a and the odor measuring device 30a are connected via the wide-area communication network 40, the acquisition unit 11 may acquire the target detection signal output from the odor measuring device 30a while measuring the target odor (i.e., in real time), or when the measurement is completed. The acquisition unit 11 may store the acquired target detection signal in the storage unit 2a.

[0126] The output control unit 14 transmits (outputs) the processing information output by the processing unit 12 to the output device 80. The output device 80, upon receiving the processing information, causes the processing information to be output. In other words, the output control unit 14 causes the output device 80 to output the processing information. The output control unit 14 may further transmit the target detection signal acquired by the acquisition unit 11 to the output device 80. The information output by the output control unit 14 is determined based on the setting information 23. The output control unit 14 may further transmit the estimation result estimated by the estimation unit 13 to the output device 80.

[0127] In the information processing system 100a, the information processing device 10a may also have the functions of an odor measuring device 30a. In other words, a single odor measuring device 30a that has the functions of the information processing device 10a may function as the information processing device 100a.

[0128] (Processing performed by information processing system 100a) An information processing method according to one embodiment of this disclosure will be described with reference to Figure 11. Figure 11 is a flowchart showing an example of the processing flow in which the information processing system 100a estimates processing information. The processing shown in Figure 11 can be performed by one or more computers.

[0129] In step S11, the acquisition unit 11 acquires the setting information (acquisition step). In step S12, the processing unit 12 processes the target detection signal based on the setting information 23 (processing step). The processing in step S12 may be one or more processes selected from (1) and (2) below.

[0130] (1) A process to generate a graph showing the time-dependent changes in the detected signal.

[0131] (2) Processing to extract feature quantities from the target detection signal. Alternatively, in step S12, the estimation unit 13 may perform estimation using the estimation model 21 from the processing results output from the processing unit 12.

[0132] In step S13, the output control unit 14 causes the output device 80 to display the processing information, including the processing results. Here, the output device 80 may be a display device that is communicatively connected to the information processing device 10a, or it may be a personal computer used by the user. Alternatively, the output device 80 may be a display unit provided by the information processing device 10a. In addition to the processing results, the output control unit 14 may further output the estimation results from the estimation unit 13.

[0133] According to this information processing method, the information processing device 10a can output desired information related to the measurement results from the odor measuring device 30a based on user input. With the above configuration, the information processing system 100a can provide the user with processing information that has been performed on the target detection signal output from the odor measuring device 30a as desired by the user. Therefore, the user can easily utilize the measurement results from the odor measuring device 30a.

[0134] [Examples of implementation using software] The functions of the information processing devices 10 and 10a (hereinafter referred to as "devices") are programs that cause the devices to function as computers, and these programs can be realized by programs that cause each control block of the devices (especially each part included in the control unit 1) to function as a computer.

[0135] In this case, the device includes a computer having at least one control device (e.g., a processor) and at least one storage device (e.g., memory) as hardware for executing the program. By executing the program using this control device and storage device, the functions described in each of the embodiments are realized.

[0136] The above program may be recorded on one or more computer-readable recording media, not temporary ones. These recording media may or may not be provided by the above device. In the latter case, the program may be supplied to the above device via any wired or wireless transmission medium.

[0137] Furthermore, some or all of the functions of each of the above control blocks can also be implemented by logic circuits. For example, an integrated circuit in which logic circuits functioning as each of the above control blocks are formed is also included in the scope of this disclosure. In addition, it is also possible to implement the functions of each of the above control blocks by, for example, a quantum computer.

[0138] Furthermore, each process described in the above embodiments may be performed by AI (Artificial Intelligence). In this case, the AI ​​may operate on the control device described above, or it may operate on other devices (for example, an edge computer or a cloud server).

[0139] This disclosure is not limited to the embodiments described above, and various modifications are possible within the scope of the claims. Embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of this disclosure.

[0140] [Summary 1] An information processing system according to aspect 1A of the present disclosure comprises one or more odor measuring devices that output an object detection signal corresponding to an object odor at regular intervals; an acquisition unit that acquires the object detection signals output from each of the one or more odor measuring devices and setting information relating to processing to be performed on the object detection signals, which is input by a user; a processing unit that performs the processing based on the setting information; and an output control unit that causes an output unit to output processing information including the results of the processing.

[0141] The information processing system according to aspect 2A of the present disclosure, in aspect 1A, includes at least an instruction to the processing unit to output target estimation information relating to at least one of the cause of the odor of the target and the state of the target, using an estimation model from the acquired target detection signal, the processing unit further comprises an estimation unit that estimates target estimation information relating to at least one of the cause of the odor of the target and the state of the target, using an estimation model from the acquired target detection signal, the processing information includes the target estimation information, and the estimation model may be generated by machine learning using training data that includes a sample detection signal corresponding to the odor of the sample as an explanatory variable and sample information relating to at least one of the cause of the odor of the sample and the state of the target corresponding to the sample detection signal as an objective variable.

[0142] In the information processing system according to aspect 3A of the present disclosure, the setting information may include at least an instruction to cause the processing unit to perform one or more processes selected from (1) calculating the estimation accuracy of the estimation model and (2) constructing the estimation model.

[0143] The information processing system according to aspect 4A of the present disclosure, in any of aspects 1A to 3A, comprises a plurality of odor sensor elements capable of outputting a detection signal, and each of the plurality of odor sensor elements may have an odor substance receiving layer in which interactable odor substances are different from each other.

[0144] In any of the embodiments 1A to 4A of the Information Processing System, the setting information may include at least an instruction to the processing unit to perform one or more processes selected from (1) generating a graph showing the change in the target detection signal over time, and (2) extracting feature quantities of the target detection signal, based on the acquired target detection signal.

[0145] In the information processing system according to embodiment 6A of the present disclosure, in any of embodiments 1A to 5A, the acquisition unit may further acquire location information indicating the installation location of the odor measuring device, and the output control unit may output the location information in addition to the processing information.

[0146] An information processing method according to aspect 7A of the present disclosure is an information processing method performed by one or more computers, comprising: an acquisition step of acquiring a target detection signal corresponding to a target odor output from each of one or more odor measuring devices at regular intervals, and setting information relating to processing to be performed on the target detection signal input by a user; a processing step of performing the processing based on the setting information; and an output control step of causing an output unit to output processing information including the result of the processing.

[0147] The control program according to aspect 8A of this disclosure is a control program for causing a computer to function as an information processing system as described in aspects 1A to 6A, and is a control program for causing the computer to function as the acquisition unit, the processing unit, and the output control unit.

[0148] The recording medium according to aspect 9A of this disclosure is a computer-readable recording medium on which the control program described in aspect 8A is recorded.

[0149] [Summary 2] An information processing system according to Embodiment 1B of the present disclosure includes: an acquisition unit that acquires setting information relating to processing to be performed on an object detection signal corresponding to an object odor; a processing unit that performs the processing based on the setting information; and an output control unit that causes an output unit to output processing information including the result of the processing. The configuration information includes at least an instruction to the processing unit to perform one or more processes selected from (1) generating a graph showing the change in the target detection signal over time, and (2) extracting feature quantities from the target detection signal, based on the acquired target detection signal.

[0150] The information processing system according to aspect 2B of the present disclosure, in aspect 1B, includes at least an instruction to the processing unit to output an estimated information relating to at least one of the cause of the odor of the object and the state of the object, using an estimation model based on the acquired object detection signal, wherein the estimation model may be generated by machine learning using training data that includes a sample detection signal corresponding to the odor of the sample as an explanatory variable and sample information relating to at least one of the cause of the odor of the sample and the state of the object corresponding to the sample detection signal as an objective variable.

[0151] In the information processing system according to embodiment 3B of the present disclosure, the setting information may include at least an instruction to cause the processing unit to perform one or more processes selected from (1) calculating the estimation accuracy of the estimation model and (2) constructing the estimation model.

[0152] The information processing system according to aspect 4B of the present disclosure, in any of aspects 1B to 3B, wherein the target detection signal is a detection signal output from an odor measuring device that measures the odor of the target, the odor measuring device comprises a housing unit capable of housing the target and a plurality of odor sensor elements capable of outputting a detection signal, and each of the plurality of odor sensor elements may have an odor substance receiving layer in which interactable odor substances are different from each other.

[0153] An information processing method according to aspect 5B of the present disclosure is an information processing method performed by one or more computers, comprising: an acquisition step of acquiring setting information relating to processing performed by the computers on an object detection signal corresponding to an object odor; a processing step of the computers performing the processing based on the setting information; and an output control step of causing the computers to output processing information including the results of the processing to an output unit, wherein the setting information includes at least an instruction to cause the computers to perform one or more processing selected from (1) generating a graph showing the change in the object detection signal over time, and (2) extracting feature quantities of the object detection signal, from the acquired object detection signal.

[0154] The control program according to aspect 6B of this disclosure is a control program for causing a computer to function as an information processing system as described in aspects 1B to 4B, and is a control program for causing the computer to function as the acquisition unit, the processing unit, and the output control unit.

[0155] The recording medium according to aspect 7B of this disclosure is a computer-readable recording medium on which the control program described in aspect 6B is recorded. [Explanation of Symbols]

[0156] 10, 10a Information Processing Device 11 Acquisition Department 14 Output Control Unit 30, 30a Odor measuring device 36 Storage Unit 40 Wide-area telecommunications network 50 User Terminals 18, 60 Input section 70 Output section 80 Output device (output section) 100, 100a Information Processing System

Claims

1. An acquisition unit that acquires setting information regarding the processing to be performed on the target detection signal corresponding to the target odor, A processing unit that performs the above processing based on the above setting information, An output control unit that causes an output unit to output processing information including the results of the above processing, Equipped with, The setting information includes at least an instruction to the processing unit to perform one or more processes selected from (1) generating a graph showing the change in the target detection signal over time, and (2) extracting feature quantities from the target detection signal, based on the acquired target detection signal. Information processing system.

2. The setting information includes at least an instruction to the processing unit to output target estimation information relating to at least one of the cause of the odor of the target and the state of the target, using an estimation model based on the acquired target detection signal. The estimation model is generated by machine learning using training data that includes a sample detection signal corresponding to the odor of the sample as an explanatory variable, and sample information relating to at least one of the cause of the odor of the sample corresponding to the sample detection signal and the state of the object as an objective variable. The information processing system according to claim 1.

3. The setting information includes at least an instruction to the processing unit to perform one or more processes selected from (1) calculating the estimation accuracy of the estimation model, and (2) constructing the estimation model. The information processing system according to claim 2.

4. The aforementioned target detection signal is a detection signal output from an odor measuring device that measures the odor of the target. The odor measuring device is A housing section capable of accommodating the aforementioned object, It comprises multiple odor sensor elements capable of outputting detection signals, Each of the multiple odor sensor elements is Interactable odor molecules have different odor molecule receiving layers. The information processing system according to claim 1.

5. An information processing method performed by one or more computers, An acquisition step to obtain setting information regarding the processing that the computer performs on the target detection signal corresponding to the target odor, A processing step in which a computer performs the processing based on the setting information, The output control step includes causing the computer to output processing information including the results of the processing to an output unit, The setting information includes at least an instruction to cause the computer to perform one or more processes selected from (1) generating a graph showing the change in the target detection signal over time, and (2) extracting feature quantities from the target detection signal, based on the acquired target detection signal. Information processing methods.

6. A control program for causing a computer to function as an information processing system according to claim 1, wherein the computer functions as the acquisition unit, the processing unit, and the output control unit.

7. A computer-readable recording medium that stores the control program described in claim 6.

Images