JP7343290B2 - Judgment system, information processing device, server, program and judgment method - Google Patents

Description

The present invention relates to a determination system, an information processing device, a server, a program, and a determination method.

2. Description of the Related Art In recent years, detection elements that detect the types of odors related to the human sense of smell (one of the specific qualities) have been widely developed. For example, as a detection element for detecting gas, a QCM (Quartz Crystal Microbalance) sensor is known in which a film that adsorbs gas-causing substances is provided on the surface of a quartz crystal resonator. Furthermore, a technique is known that determines the type of odor based on a sensor signal detected by such a sensor.

For example, Patent Document 1 and Patent Document 2 describe odor identification devices that perform principal component analysis using sensor signals obtained from a plurality of gas sensors.

Japanese Patent Application Publication No. 2001-305088 Japanese Patent Application Publication No. 2003-232759

For example, a model (judgment information) that has learned the relationship between a sensor signal and the type of odor is generated based on pre-prepared training data, and that model is used to respond to the sensor signal detected by the sensor. A configuration that determines the type of odor is also conceivable. However, if an information processing device such as a PC (Personal Computer) owned by the user is used to generate such a model and determine the type of odor, the load on the information processing device becomes large, and it is necessary to use a computer with superior processing power. An information processing device is required.

For this reason, for example, the detected values from the sensor device may be output each time to a server with excellent processing capacity installed on the cloud, and the server may generate a model and determine the type of odor. is possible. However, if the detection values and odor information from the sensor device are uploaded to the server each time, if information leaks on the server, the timing of the detection values and the odor information may be changed to personal information (for example, when using the kitchen). timing, factory operating hours, types of smells detected, etc.) may be leaked.

The present invention has been made in view of the above, and provides a determination system, an information processing device, and a server capable of preventing leakage of personal information while suppressing an excessive processing load on an information processing device owned by a user. , the purpose is to provide a program and a determination method.

In order to solve the above-mentioned problems and achieve the purpose, a determination system according to the present invention includes an information processing device and a server, and the information processing device stores a detection value detected by a sensor device. an acquisition unit that acquires from the server judgment information that associates information indicating a specific quality with information indicating a specific quality; a reception unit that receives the detection value from the sensor device; and a reception unit that corresponds to the detection value received by the reception unit. a mode switching unit for an operator to switch the mode of the information processing device between a judgment mode that outputs information indicating the specific quality and a learning mode that generates the judgment information; and the mode switching unit. an information output unit that outputs information indicating the specific quality corresponding to the detection value received by the reception unit, based on the determination information acquired by the acquisition unit when the determination mode is switched to the determination mode; and a transmitter that transmits the detected value to the server each time to generate the determination information when the mode switching unit is switched to the learning mode, and the server transmits the determination information to the server. The information processing apparatus includes a determination information generation section that generates determination information, and a determination information transmission section that transmits the determination information generated by the determination information generation section to the information processing apparatus.

According to the present invention, it is possible to obtain information indicating a specific quality without placing an excessive load on an information processing device.

FIG. 1 is a diagram including a determination system according to an embodiment. FIG. 2 is a diagram showing the configuration of the sensor device. FIG. 3 is a diagram for explaining the odor type determination process. FIG. 4 is an explanatory diagram showing the configuration of a neural network. FIG. 5 is a block diagram showing an example of the hardware configuration of the information processing device. FIG. 6 is a block diagram showing an example of the hardware configuration of the server. FIG. 7 is a functional block diagram showing the functional configuration of the information processing device. FIG. 8 is a flowchart illustrating an example of the flow of control processing of the information processing device. FIG. 9 is a functional block diagram showing the functional configuration of the server. FIG. 10 is a flowchart illustrating an example of the flow of server control processing.

Embodiments will be described below with reference to the drawings. In the embodiment, information indicating a type of odor will be explained as an example of information indicating a specific quality. Note that the present invention is not limited to the embodiments described below.

FIG. 1 is a system diagram including a determination system 10 according to an embodiment. The determination system 10 determines the type of odor originating from the target object. The determination system 10 includes an information processing device 3 and a server 5. The information processing device 3 and the server 5 are connected through a communication line L2. The communication line L2 may be a LAN (Local Area Network), a dedicated line such as a wireless LAN, or a public line such as the Internet. Further, the determination system 10 can be connected to one or more sensor devices 1 using a communication line L1 such as NFC (Near Field Communication) or Bluetooth (registered trademark). The determination system 10 receives the detection value of the odor detected by the sensor device 1, and obtains information indicating the type of one odor indicated by the detection value. Further, the determination system 10 can be connected to the information terminal 7 via the Internet N, for example. The determination system 10 transmits information indicating the type of odor obtained to the information terminal 7.

FIG. 2 is a diagram showing the configuration of the sensor device 1. In this embodiment, the sensor device 1 is a QCM sensor that can detect the mass of minute substances (gas) contained in the air. Note that the sensor device 1 is not limited to the QCM sensor, but may be a sensor of another type such as a gas sensor using a semiconductor thin film.

In this embodiment, the sensor device 1 includes a support section 11 , at least one (16 in the embodiment) detection element F, and a drive detection circuit 12 . Each of the 16 detection elements F is attached to the support part 11.

In the example of FIG. 2, the sensor device 1 has 16 detection elements F1 to F16 of different types. For example, each of the 16 detection elements F1 to F16 detects a different type of gaseous substance.

Each of the detection elements F includes a crystal oscillator cut to be able to vibrate using a piezoelectric effect, two electrodes provided on both planes of the crystal oscillator, and a suction electrode provided on at least one of the planes of the crystal oscillator. including a membrane.

A part of the side surface of the crystal oscillator is held by the support section 11 so as to be able to vibrate. AC voltage is applied to the two electrodes from the drive detection circuit 12. The adsorption membrane adsorbs specific causative substances contained in the surrounding air. Each of the detection elements F includes an adsorption film that adsorbs different substances. Specifically, each of the detection elements F includes an adsorption film that adsorbs a causative substance to be detected by the sensor device 1 .

In such a detection element F, when an alternating current voltage at a resonant frequency is applied to the two electrodes, the crystal resonator vibrates due to the piezoelectric effect. The fundamental resonant frequency of a crystal resonator is determined by its mass and viscoelasticity. Therefore, when a causative substance is adsorbed to the adsorption film and its mass changes, the fundamental resonance frequency of the detection element F changes in accordance with the change in the adsorbed mass.

The drive detection circuit 12 applies an alternating current voltage to each of the at least one detection element F, and detects a change in the fundamental resonance frequency of each of the at least one detection element F per unit time. Thereby, the drive detection circuit 12 can detect the mass of the odor-causing substance contained in the air for each of the at least one detection element F. The sensor device 1 outputs the change in the fundamental resonance frequency of each detection element F detected by the drive detection circuit 12 as a detection value (numerical data) to the information processing device 3 using the communication line L1.

FIG. 3 shows an example of detected values output by the sensor device 1. As shown in FIG. 3, the sensor device 1 outputs a detection value in which the outputs from the detection elements F1 to F16 form one pattern. The detection values output by the sensor device 1 have a wide variety of patterns depending on the outputs from the detection elements F1 to F16.

The information processing device 3 receives the detection value output from the sensor device 1. Further, the information processing device 3 stores determination information including information indicating the type of odor indicated by the detection value associated with the detection value in the determination information storage unit 343 (storage unit) (see FIG. 5). ing. The determination information is an input/output model that outputs information indicating the type of odor corresponding to the pattern of the received detection values. For example, when a detection value related to stew is received, the determination information is outputted, and when a detection value related to curry is received, information indicating the type of smell of curry is output, and when a detection value related to curry is received, information indicating the type of curry odor is output, When the detection value related to is received, information indicating the type of smell of the soup is output.

The information processing device 3 uses the determination information to output information indicating the type of odor corresponding to the detection value of the pattern most similar to the pattern of detection values received from the sensor device 1. Note that the information processing device 3 also determines the strength of the odor for each type of odor based on the rate of change in mass per unit time output from the detection element F. The larger the rate of change in mass per unit time, the stronger the odor.

Note that the information processing device 3 transmits the detected values of representative gases to the server 5 in an initial state where the determination information indicating the type of odor is not yet stored in the determination information storage unit 343. Based on the detected value received from the information processing device 3, the server 5 generates information indicating one type of odor indicated by the detected value. The server 5 performs multivariate analysis using, for example, a neural network, and generates information indicating the type of odor indicated by the detected value. Note that in the embodiment, the server 5 is installed on the cloud. Therefore, the server 5 is composed of one or more server devices.

FIG. 4 is a diagram for generating information indicating a type of odor from received detection values using a neural network. The neural network uses an input layer N1, an intermediate layer N2, and an output layer N3 to output information indicating one odor type corresponding to the received detection value. Specifically, the input layer N1 receives the odor detection value output by the sensor device 1. The intermediate layer N2 extracts feature amounts that are characteristics of the odor type (that is, the difference from other odor types) from among the detection values received by the input layer N1. The output layer N3 outputs information indicating the type of odor of the feature indicated by the odor feature extracted by the intermediate layer.

The server 5 extracts a feature amount based on the first received representative detection value of the gas, and determines information indicating the type of odor indicated by the feature amount. The server 5 generates the first determination information in this way. After generating the determination information, the server 5 updates the determination information to determination information whose accuracy has been increased through learning processing. This learning process may be performed multiple times to improve accuracy.

Here, the learning process of the determination information will be briefly explained. For example, when many odors are mixed, the information indicating the type of odor output using the determination information may not necessarily match the odor that a person's sense of smell actually perceives. For example, in the case of a mixed smell of curry and stew, even though the information indicating the type of odor output using the judgment information is the smell of stew, the smell perceived by the human sense of smell is curry. If the odor is perceived to be similar, the output of the judgment information is corrected to bring it closer to the odor perceived by the human sense of smell, and the judgment information related to the odor is learned.

In this case, there are often problems with the feature amounts output by the intermediate layer N2 based on the detected values received by the input layer N1. Therefore, in the server 5, by modifying the feature amount output by the intermediate layer N2, it is possible to output a feature amount that is close to the smell that the human sense of smell senses. Specifically, the information processing device 3 transmits the detected value and information indicating the type of odor to be corrected to the server 5, and the server 5 combines the received detected value and the feature amount indicating the stew extracted by the middle layer N2. The feature quantity indicating curry is corrected based on the information indicating the type of odor to be corrected. Then, the neural network outputs information indicating the type of odor representing the characteristics of curry from the output layer N3 based on the detected value received at the input layer N1. The server 5 makes a correction to add this corrected teacher data to the judgment information. Then, the server 5 transmits the corrected determination information to the information processing device 3, so that the information processing device 3 can make a determination with improved accuracy.

Note that, as a specific method, the server 5 may use other methods (for example, pattern matching or SVN) to improve the odor accuracy instead of using the above-described neural network.

Note that the example in FIG. 3 shows an example in which the sensor device 1 outputs detection values of 16 types of detection elements F. However, the sensor device 1 may output detection values of fewer than 16 types or more than 16 types of detection elements. When multiple types of odors coexist, it is possible to identify the odors with high accuracy by using detection elements of more than 16 types (for example, 32 types).

From here on, the hardware of the information processing device 3 will be explained. FIG. 5 is a block diagram showing the hardware configuration of the information processing device 3. As shown in FIG. As shown in FIG. 5, the information processing device 3 includes a CPU (Central Processing Unit) 31, a ROM (Read Only Memory) 32, a RAM (Random Access Memory) 33, a memory section 34, and the like. The CPU 31 is the main control body. The ROM 32 stores various programs. The RAM 33 expands various data. The memory unit 34 stores various programs. The CPU 31, ROM 32, RAM 33, and memory section 34 are connected to each other via a data bus 35. The CPU 31, ROM 32, and RAM 33 constitute a control unit 300. That is, the control unit 300 executes control processing of the information processing device 3, which will be described later, by the CPU 31 operating according to a control program stored in the ROM 32 or the memory unit 34 and developed in the RAM 33.

The memory section 14 includes a control program section 341, a gas data storage section 342, a determination information storage section 343, and a correction data storage section 344. The control program unit 341 stores a program for controlling the information processing device 3 . The odor data storage unit 342 stores the gas detection values received from the sensor device 1 . The determination information storage unit 343 stores information related to a plurality of odors, which is generated using a neural network, and which indicates the detection value output by the sensor device 1 for each gas and the type of odor associated with the detection value. , or judgment information that is judgment data obtained by improving accuracy of the teacher data using a neural network. The correction data storage unit 344 stores gas detection values for correcting information indicating the type of odor output from the determination information. Note that the detected value of the gas to be corrected may be stored in the gas data storage unit 342 instead of the correction data storage unit 344. In this case, the modified data storage section 344 is not required.

Further, the control section 300 is connected to an operation section 37 and a display section 38 via a data bus 35 and a controller 36. The operation unit 37 is a keyboard operated by an operator to input data and give instructions. The operation unit 37 is a switch that switches the mode of the information processing device 3 between a determination mode in which information indicating the type of odor corresponding to the received detection value is output and a learning mode in which determination information is generated or modified. A certain mode switching section 371 is provided. When the mode switching unit 371 is switched to the determination mode, the information processing device 3 outputs information indicating the type of odor corresponding to the received detection value. When the mode switching unit 371 is switched to the learning mode, the information processing device 3 transmits the detected value to the server 5 in order for the server 5 to generate or modify determination information. Further, the display section 38 is composed of, for example, a liquid crystal display, and displays information to the operator of the information processing device.

Further, the control unit 300 is connected to the communication I/F 39 via the data bus 35. The communication I/F 35 is connected to the communication line L1 and the communication line L2. The communication I/F 39 is capable of communicating with the sensor device 1 via the communication line L1, and receives information (for example, a detected value) from the sensor device 1. Further, the communication I/F 39 is capable of communicating with the server 5 via the communication line L2, and receives information (for example, teacher data and corrected determination information) from the server 5. Further, the communication I/F 39 transmits information (for example, the odor detection value to be corrected) to the server 5 via the communication line L2. The communication I/F 39 is capable of communicating with the information terminal 7 via the Internet N, and provides information to the information terminal 7 (for example, information indicating the type of odor output by the output layer N3 (for example, the smell of curry). information indicating the type of data)) sent.

From here on, the hardware of the server 5 will be explained. FIG. 6 is a block diagram showing the hardware configuration of the server 5. As shown in FIG. As shown in FIG. 6, the server 5 includes a CPU 51, a ROM 52, a RAM 53, a memory section 54, and the like. The CPU 51 is the main body of control. The ROM 52 stores various programs. The RAM 53 expands various data. The memory unit 54 stores various programs. The CPU 51, ROM 52, RAM 53, and memory section 54 are connected to each other via a data bus 55. The CPU 51, ROM 52, and RAM 53 constitute a control unit 500. That is, the control unit 500 executes control processing for the server 5, which will be described later, by the CPU 51 operating according to a control program stored in the ROM 52 or the memory unit 54 and developed in the RAM 53. Note that the above-described neural network processing is executed by the control unit 500.

The memory section 14 includes a control program section 541. The control program unit 541 stores a program for controlling the server 5 .

Further, the control section 500 is connected to an operation section 57 and a display section 58 via a data bus 55 and a controller 56. The operation unit 57 is a keyboard operated by an operator to input data and give instructions. Further, the display section 58 is composed of, for example, a liquid crystal display, and displays information to the operator of the information processing device.

Further, the control unit 500 is connected to a communication I/F 59 via a data bus 55. Communication I/F 55 is connected to communication line L2. The communication I/F 59 is capable of communicating with the information processing device 3 via the communication line L2, and receives information (for example, detected value of odor to be corrected) from the information processing device 3. Further, the communication I/F 59 transmits information to the information processing device 3 via the communication line L2.

From here, the functional configuration of the information processing device 3 will be explained. FIG. 7 is a functional block diagram showing the functional configuration of the information processing device 3. As shown in FIG. As shown in FIG. 7, the control unit 300 of the information processing device 3 controls the acquisition unit 301, the reception unit 302, the information acquisition unit 303, and the information acquisition unit 301, the reception unit 302, the information acquisition unit 303, and It functions as an output section 304, a transmission section 305, and a data update section 306.

The acquisition unit 301 (first step) acquires from the server 5 determination information that associates the detection value of the gas detected by the sensor device 1 with information indicating the type of odor corresponding to the detection value.

The receiving unit 302 (second step) receives the detected value from the sensor device 1. Specifically, the receiving unit 302 receives a detection value transmitted by the sensor device 1, which is a change in the fundamental resonance frequency related to a specific odor detected by the plurality of detection elements F of the sensor device 1.

The information acquisition unit 303 outputs information indicating the type of odor corresponding to the detection value received by the reception unit 302, based on the determination information acquired by the acquisition unit 301. Specifically, the information acquisition unit 303 acquires information indicating the type of odor corresponding to the detection value received by the reception unit 302, based on the determination information acquired by the acquisition unit 301 and stored in the determination information storage unit 343. get.

The information output unit 304 (third step) outputs information indicating the type of odor corresponding to the detection value received by the reception unit 302, based on the determination information acquired by the acquisition unit 301. Specifically, in the determination mode for identifying the type of odor, the information output unit 304 determines the type of odor based on the detection value received by the receiving unit 302 and based on the determination information stored in the determination information storage unit 343. Outputs information indicating.

The transmitter 305 transmits information indicating the detected value and the type of odor to the server 5 in the learning mode for generating determination information. Specifically, in the learning mode, the transmitting unit 305 transmits to the server 5 the detected value received by the receiving unit 302 and information indicating the type of odor to be modified corresponding to the detected value.

The data updating unit 306 receives the determination information transmitted by the determination information transmitting unit 502 (described later) and stores it in the determination information storage unit 343. Specifically, the data update unit 306 stores the corrected determination information received from the server 5 in the determination information storage unit 343.

From here on, control of the information processing device 3 will be explained. FIG. 8 is a flowchart showing an example of the flow of control processing of the information processing device 3. As shown in FIG. 8, the control unit 300 of the information processing device 3 determines whether the mode switching unit 371 is in the determination mode (S11). If the mode switching unit 371 determines that the mode is the determination mode (Yes in S11), the receiving unit 302 receives the detection value of the gas detected by the sensor device 1 (S12). Next, the control unit 300 stores the received gas detection value in the odor data storage unit 342 (S13). Next, the information acquisition unit 303 uses the determination information stored in the determination information storage unit 343 to acquire information indicating the type of odor associated with the gas detection value received by the reception unit 302 ( S14). The information output unit 304 then outputs information indicating the type of the acquired odor to the information terminal 7 (S15). The control unit 300 then returns to S11.

Further, if the mode switching unit 371 determines that the mode is not the determination mode (No in S11), the control unit 300 determines whether the mode switching unit 371 is in the learning mode (S21). If the mode switching unit 371 determines that the learning mode is selected (Yes in S21), the receiving unit 302 receives information from the sensor device 1 in the learning mode to generate odor type determination information or The gas detection value for correcting the determination information is received (S22). Next, the control unit 300 stores the input gas detection value in the gas data storage unit 342 (S23). In addition, when modifying the determination information, information indicating the type of odor corresponding to the detected value is stored in the gas data storage unit 342 (S23). Information indicating the type of odor corresponding to the detected value is input by a person from the information processing device 3.

Next, the transmitter 305 transmits the stored detected value (or information indicating the stored detected value and the type of odor corresponding to the detected value) to the server 5 (S24). Then, the control unit 300 receives from the server 5 the determination information generated based on the information indicating the type of odor based on the detected value transmitted in S24, or the detected value transmitted in S24 and the type of odor corresponding to the detected value. The determination information corrected based on the information shown is received and acquired (S25). Next, the data update unit 306 stores the generated or modified determination information acquired from the server 5 in the determination information storage unit 343 (S26). The control unit 300 then returns to S11. Note that if the mode switching unit 371 determines that the mode is not the learning mode (No in S21), the control unit 300 returns to S11.

From here on, the functional configuration of the server 5 will be explained. FIG. 9 is a functional block diagram showing the functional configuration of the server 5. As shown in FIG. As shown in FIG. 9, the control unit 500 of the server 5 functions as a determination information generation unit 501 and a determination information transmission unit 502 by following a control program stored in the ROM 52 or the memory unit 54 and developed in the RAM 53.

The determination information generation unit 501 generates determination information. Specifically, the determination information generation unit 501 generates determination information using a neural network based on the detection value received from the information processing device 3 in the learning mode. More specifically, the determination information generation unit 501 inputs the detected value received in the learning mode to the input layer N1, and determines the type of odor indicated by the detected value that is associated with the detected value from the output layer N3. Generate judgment information that outputs the information shown.

Further, the determination information generation unit 501 modifies the determination information based on the detection value and information indicating the type of odor transmitted by the transmission unit 305. Specifically, the determination information generation unit 501 modifies the feature amount modified from the intermediate layer N2 based on the received detection value and information indicating the type of odor corresponding to the detection value. The feature amount is modified as follows, for example. For example, when the intermediate layer N2 extracts the feature amount of stew from a detected value that is considered to be the smell of curry according to the human olfactory sense, based on the information indicating the smell of curry input from the information processing device 3, Then, the feature amount output from the intermediate layer N2 is corrected to the feature amount of curry. This process performed by the determination information generation unit 501 is a learning process.

The determination information transmitting unit 502 transmits the determination information generated by the determination information generating unit 501 to the information processing device 3. Further, the determination information transmitting unit 502 transmits the determination information modified by the determination information generating unit 501 to the information processing device 3.

Note that the process performed by the determination information generation unit 501 is to determine information indicating one odor type based on detection values based on information on gases detected by the 16 types of detection elements F, so the control unit 500 is under heavy load. Therefore, generation of the determination information and correction of the determination information are performed by the server 5 having high processing capacity.

From here on, control of the server 5 will be explained. FIG. 10 is a flowchart showing an example of the flow of control processing of the server 5. As shown in FIG. As shown in FIG. 10, the control unit 500 of the server 5 determines whether a detected value has been received from the information processing device 3 (S31). If it is determined that a detection value has been received from the information processing device 3 (Yes in S31), it is determined whether new determination information is generated (S32). In S31, if only the detected value is received, the control unit 300 determines that the determination information is newly generated. On the other hand, in S31, if information indicating the type of odor is received together with the detected value, the control unit 300 determines that the determination information is to be corrected. If it is determined that new determination information is to be generated (Yes in S32), the determination information generation unit 501 uses a neural network to generate the odor corresponding to the detected value based on the received detected value. Determination information including information indicating the type is generated (S33). Then, the determination information transmitting unit 502 transmits the determination information generated by the determination information generating unit 501 to the information processing device 3 (S34). The control unit 500 then returns to S31.

If it is determined that the determination information is to be modified (No in S32), the determination information generation unit 501 extracts the detected value based on the received detected value and the information indicating the type of odor. Determination information is generated in which one model is added in which the feature amount is corrected and the information indicating the type of odor associated with the detected value is corrected (S35). Then, the determination information transmitting unit 502 transmits the modified determination information to the information processing device 3 (S36). The control unit 500 then returns to S31. Further, if it is determined that the detection value related to odor has not been received from the information processing device 3 (No in S31), the control unit 500 returns to S31.

In such a determination system 10, in a state where determination information is not yet stored in the information processing device 3, the information processing device 3 first inputs a detection value related to the odor detected by the sensor device 1. The information processing device 3 then transmits the detected value to the server 5. Based on the input detection value, the server 5 uses a neural network to generate determination information including information indicating the type of odor associated with the detection value. The server 5 transmits the generated determination information to the information processing device 3. The information processing device 3 stores the received determination information in the determination information storage unit 343 (first step). The information processing device 3 thereafter receives a detection value from the sensor device 1 based on the stored determination information (second step). The information processing device 3 then acquires information indicating the type of odor corresponding to the received detection value and transmits it to the information terminal 7 (third step).

On the other hand, the information processing device 3 receives the detection value related to the odor to be corrected from the sensor device 1 . The information processing device 3 transmits the received detection value to the server 5. The server 5 modifies the information indicating the type of odor corresponding to the received detection value. Then, the server 5 transmits determination information including information indicating the corrected odor type to the information processing device 3. The information processing device 3 stores the received corrected determination information in the determination information storage unit 343 and updates the determination information.

(Effects of embodiment)
The determination system 10 according to this embodiment has been described above. The determination system 10 according to this embodiment has the following effects, for example.

The determination system 10 according to the present embodiment includes a determination information generation unit 501 in the server 5 that generates and corrects determination information based on the detected value received from the sensor device 1, and corresponds to the detected value received from the sensor device 1. The information processing device 3 is provided with an information output unit 304 that outputs information indicating the type of smell. Therefore, the information processing device 3 outputs information indicating the type of odor associated with the detected value, but does not generate or modify the judgment information, so it is possible to suppress the load from becoming excessive. Become. Further, the server 5 only generates and modifies determination information. The information processing device 3 transmits the detection value received from the sensor device 1 to the server 5 while switching from the determination mode to the learning mode. That is, since the information processing device 3 does not transmit the determination of the type of odor based on the detected value to the server 5 each time, it is possible to prevent leakage of personal information from the server 5.

Further, the information processing device 3 outputs information indicating the type of odor associated with the detected value, but does not generate or modify judgment information, so it is possible to suppress excessive load. Become. Further, since the information processing device 3 can output the information indicating the type of odor by itself, the time required to output the information indicating the type of odor can be shortened.

Furthermore, since the server 5 only generates and corrects the judgment information, it does not send detection values to the server 5 each time to obtain information indicating the type of odor, so leakage of personal information from the server 5 can be prevented. becomes possible. Additionally, the server 5 can reduce its burden.

Although the embodiments of the present invention have been described above, these embodiments are presented as examples and are not intended to limit the scope of the invention. Embodiments are capable of various modifications.

For example, in the embodiment, information indicating the type of odor has been described as an example of information indicating a specific quality. However, the information is not limited to this, and the information indicating the specific quality may be, for example, information indicating the type of sound, information indicating the type of vibration, or information indicating the type of taste. Further, the information indicating a specific quality may be information indicating a specific quality other than a person's five senses. For example, the information may be information indicating the quality of the environment (for example, the rank of the environment) that is output as a result of measuring the environment of a room in a building or the like by an environment measuring device.

Furthermore, in the embodiment, the information processing device 3 and the server 5 modify the determination information in the learning mode. However, the present invention is not limited to this, and the determination information may be modified in the determination mode or other modes.

Note that since there are a wide variety of odors, many detection elements F are required in the sensor device 1 to obtain a pattern of detection values indicating the characteristics of the gas. Therefore, creating or modifying odor determination information requires more effort than other specific qualities (type of sound, type of vibration, type of taste, etc.). Therefore, it can be said that it is suitable to use the present invention, in which the load is distributed between the information processing device 3 and the server 5, for generating and modifying the judgment information related to odor. Furthermore, as the number of detection elements F of the sensor device 1 increases, the privacy related to smells becomes clearer from the output from the sensor device 1. Therefore, from the perspective of privacy protection, the present invention It can be said that it is suitable to use it for generating and modifying judgment information.

Note that the program executed by the information processing device 3 of the embodiment is a file in an installable format or an executable format, and is stored on a CD-ROM, a flexible disk (FD), a CD-R, a DVD (Digital Versatile Disc), etc. Provided recorded on a computer-readable recording medium.

Further, the program executed by the information processing device 3 of the embodiment may be stored on a computer connected to a network such as the Internet, and may be provided by being downloaded via the network. Further, the program executed by the information processing device 3 of the embodiment may be provided or distributed via a network such as the Internet.

Further, the program to be executed by the information processing device 3 of the embodiment may be configured to be provided by being incorporated in a ROM or the like in advance.

1 Sensor device 3 Information processing device 5 Server 7 Information terminal N1 Input layer N2 Intermediate layer N3 Output layer 10 Judgment system 14 Memory section 31 CPU
32 ROM
33 RAM
34 Memory section 51 CPU
52 ROM
53 RAM
54 Memory section 300 Control section 301 Acquisition section 302 Receiving section 303 Information acquisition section 304 Information output section 305 Transmission section 306 Data updating section 342 Gas data storage section 343 Judgment information storage section 344 Modified data storage section 371 Mode switching section 500 Control section 501 Judgment information generation section 502 Judgment information transmission section

Claims (8)

A determination system comprising an information processing device and a server,
The information processing device includes:
an acquisition unit that acquires from the server judgment information that associates a detection value detected by the sensor device with information indicating a specific quality;
a receiving unit that receives the detected value from the sensor device;
A determination mode in which information indicating the specific quality corresponding to the detection value received by the receiving unit is output, and a learning mode in which the determination information is generated are determined by an operator operating the mode of the information processing device. A mode switching section for switching,
When the mode switching unit is switched to the determination mode, outputting information indicating the specific quality corresponding to the detection value received by the receiving unit based on the determination information acquired by the acquisition unit. an information output section for
a transmitting unit that transmits the detected value to the server each time to generate the determination information when the mode switching unit is switched to the learning mode,
The server is
a determination information generation unit that generates the determination information;
a determination information transmitter that transmits the determination information generated by the determination information generator to the information processing device ;
Judgment system. The determination information generation unit generates the determination information based on the detection value received from the information processing device.
The determination system according to claim 1. When the mode switching unit is switched to the learning mode, the information processing device receives input of information indicating the detected value related to the correction of the determination information and the specific quality corresponding to the detected value, transmitting the received detected value and information indicating the specific quality to the server by the transmitting unit;
In the server , the determination information generation unit corrects the determination information based on the detected value and information indicating the specific quality transmitted from the transmission unit.
The determination system according to claim 2. The information indicating the specific quality is information indicating the type of odor,
The determination system according to any one of claims 1 to 3. An information processing device in a determination system including an information processing device and a server,
an acquisition unit that acquires from the server judgment information that associates a detection value detected by the sensor device with information indicating a specific quality;
a receiving unit that receives the detected value from the sensor device;
A determination mode in which information indicating the specific quality corresponding to the detection value received by the receiving unit is output, and a learning mode in which the determination information is generated are determined by an operator operating the mode of the information processing device. A mode switching section for switching,
When the mode switching unit is switched to the determination mode, outputting information indicating the specific quality corresponding to the detection value received by the receiving unit based on the determination information acquired by the acquisition unit. an information output section for
a transmitting unit that transmits the detected value to the server each time to generate the determination information when the mode switching unit is switched to the learning mode;
Information processing device. A server in a determination system including an information processing device and a server,
A mode in which an operator operates and switches the mode of the information processing device between a determination mode in which information indicating a specific quality corresponding to a detection value detected by the sensor device is output and a learning mode in which determination information is generated. Judgment information generation that generates the judgment information that associates the detected value with information indicating a specific quality, which is transmitted from the information processing device when the switching unit switches to the learning mode in the information processing device. Department and
a determination information transmitter that transmits the determination information generated by the determination information generator to the information processing device ;
server. A computer as an information processing device in a determination system equipped with an information processing device and a server,
an acquisition unit that acquires from the server judgment information that associates a detection value detected by the sensor device with information indicating a specific quality;
a receiving unit that receives the detected value from the sensor device;
A determination mode in which information indicating the specific quality corresponding to the detection value received by the receiving unit is output, and a learning mode in which the determination information is generated are determined by an operator operating the mode of the information processing device. A mode switching section for switching,
When the mode switching unit is switched to the determination mode, outputting information indicating the specific quality corresponding to the detection value received by the receiving unit based on the determination information acquired by the acquisition unit. an information output section for
a transmitting unit that transmits the detected value to the server each time to generate the determination information when the mode switching unit is switched to the learning mode;
A program to function as A determination method in an information processing device in a determination system including an information processing device and a server, the method comprising:
a first step of acquiring from the server judgment information that associates the detection value detected by the sensor device with information indicating a specific quality;
a second step of receiving the detected value from the sensor device;
a third step of accepting an operation by an operator to switch the mode of the information processing device between a determination mode that outputs information indicating the specific quality corresponding to the detected value and a learning mode that generates the determination information;
When switched to the determination mode in the third step, information indicating the specific quality corresponding to the detected value received by the second step based on the determination information acquired in the first step. a fourth step of outputting
a fifth step of transmitting the detected value to the server each time to generate the determination information when the learning mode is switched in the third step;
Judgment method.

Images