A gas identification method, device, equipment and medium suitable for a home environment

Abstract

The application relates to the technical field of odor recognition, and discloses a gas recognition method, device, equipment and medium suitable for a home environment, the method comprising the following steps: acquiring an odor real-time measurement value collected by a multi-factor gas-sensitive sensor, and constructing a real-time measurement value curve based on the odor real-time measurement value; performing legality verification on the real-time measurement value curve, and generating a virtual measurement value sequence based on a legality verification result; configuring a kernel function on the virtual measurement value sequence, and generating a kernel space distribution; and generating a home environment gas recognition result by using a kernel linear discriminant analysis method based on the kernel space distribution. The application realizes accurate recognition of gases in a home environment.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of odor recognition, in particular to a gas recognition method, device, equipment and medium suitable for a home environment. BACKGROUND

[0002] An electronic nose is an electronic instrument that uses an array of gas sensors to measure data and then identifies the type of odor by pattern matching in an odor database.

[0003] The electronic nose was initially used in the fields of beverages, meat products, aquatic products, dairy products, tobacco, grain storage, food processing, chemical industry, etc. Now, some manufacturers have also tried to introduce the electronic nose into the toC (Total Organic Carbon) home health service field, trying to solve the problem of olfactory quantification and create a new industry format.

[0004] However, the application of the electronic nose in the home environment has a high cost, and the gas recognition in the home environment is not accurate. SUMMARY

[0005] Therefore, the present application provides a gas recognition method, device, equipment and medium suitable for a home environment to solve the problem of inaccurate gas recognition in the home environment by the electronic nose.

[0006] In a first aspect, the present application provides a gas recognition method suitable for a home environment, comprising:

[0007] Obtaining real-time measurement values of odors collected by a multi-factor gas-sensitive sensor, and constructing a real-time measurement value curve based on the real-time measurement values of odors;

[0008] Performing legality verification on the real-time measurement value curve, and generating a virtual measurement value sequence based on the legality verification result;

[0009] Configuring a kernel function for the virtual measurement value sequence to generate a kernel space distribution;

[0010] Generating a gas recognition result in the home environment based on the kernel space distribution using kernel linear discriminant analysis.

[0011] The gas recognition method suitable for a home environment provided in this embodiment uses low-cost sensors and improves the recognition degree of common gases in the bedroom by the electronic nose. The effectiveness of the real-time measurement values is ensured by performing legality verification on the real-time measurement value curve. Furthermore, the gas recognition result in the home environment is generated based on the kernel space distribution using kernel linear discriminant analysis, which greatly reduces the calculation amount of odor recognition in the home environment and improves the accuracy of gas recognition in the home environment.

[0012] In an optional implementation, the real-time measurement value curve is subjected to legality verification, and a virtual measurement value sequence is generated based on the legality verification result, including:

[0013] The real-time measurement value curve is subjected to legality verification, and when the legality verification result is that there is an illegal measurement value, the real-time measurement value curve is subjected to weighted dimensionality increasing processing to generate an extended value curve;

[0014] The extended value curve is cleaned to generate the virtual measurement value sequence.

[0015] In an optional implementation, the real-time measurement value curve is subjected to legality verification, and a virtual measurement value sequence is generated based on the legality verification result, further including:

[0016] When the legality verification result is that the real-time measurement value has legality, the real-time measurement value curve is cleaned to generate the virtual measurement value sequence.

[0017] In an optional implementation, a kernel function is configured for the virtual measurement value sequence to generate a kernel space distribution, including:

[0018] The virtual measurement value sequence is subjected to Laplace transformation to generate a measurement value linear space;

[0019] The measurement value linear space is mapped to a Gaussian transformation kernel space by using a Gaussian kernel function to generate the kernel space distribution.

[0020] In an optional implementation, based on the kernel space distribution, a kernel linear discriminant analysis method is used to generate a home environment gas recognition result, including:

[0021] The kernel linear discriminant analysis method is used to perform nonlinear feature extraction on the kernel space distribution to generate a gas feature;

[0022] The gas feature is input into a classifier to determine a gas category to generate the home environment gas recognition result.

[0023] In an optional implementation, further including:

[0024] The home environment gas recognition result is subjected to report quality scoring to generate a home environment gas quality, and the current home environment is adjusted based on the home environment gas quality.

[0025] In an optional implementation, the home environment gas recognition result is subjected to report quality scoring to generate a home environment gas quality, and the current home environment is adjusted based on the home environment gas quality, including:

[0026] When the home environment gas quality is unqualified, the home environment gas quality is sent to a user end, so that the user analyzes the breath state report, and adjusts the current home environment based on the analysis result.

[0027] Or, when the home environment gas quality is qualified, a breath state report is generated and stored.

[0028] In a second aspect, the present application provides a gas identification device suitable for a home environment, comprising:

[0029] An acquisition module is configured to acquire a smell real-time measurement value collected by a multi-factor gas sensitive sensor, and construct a real-time measurement value curve based on the smell real-time measurement value;

[0030] A legality verification module is configured to perform legality verification on the real-time measurement value curve, and generate a virtual measurement value sequence based on a legality verification result;

[0031] A configuration module is configured to configure a kernel function on the virtual measurement value sequence, and generate a kernel space distribution;

[0032] A generation module is configured to generate a home environment gas identification result by using a kernel linear discriminant analysis method based on the kernel space distribution.

[0033] In a third aspect, the present application provides a computer device, comprising a memory and a processor, which are communicatively connected with each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the gas identification method suitable for a home environment according to the first aspect or any one of the corresponding embodiments thereof.

[0034] In a fourth aspect, the present application provides a computer readable storage medium, which stores computer instructions, and the computer instructions are used to make a computer execute the gas identification method suitable for a home environment according to the first aspect or any one of the corresponding embodiments thereof. BRIEF DESCRIPTION OF DRAWINGS

[0035] In order to more clearly illustrate the specific embodiments of the present application or the technical solutions in the prior art, the drawings needed in the specific embodiments or the prior art description will be briefly introduced as follows. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0036] Figure 1 is a flowchart of a gas identification method suitable for a home environment according to an embodiment of the present application;

[0037] Figure 2is a flowchart of another gas identification method suitable for a home environment according to an embodiment of the present application;

[0038] Figure 3 is a flowchart of yet another gas identification method suitable for a home environment according to an embodiment of the present application;

[0039] Figure 4 is a schematic diagram of a measurement linear space according to an embodiment of the present application;

[0040] Figure 5 is a schematic diagram of a Gaussian transform kernel space according to an embodiment of the present application;

[0041] Figure 6 is a flowchart of still another gas identification method suitable for a home environment according to an embodiment of the present application;

[0042] Figure 7 is a flowchart of a kernel-based LDA algorithm according to an embodiment of the present application;

[0043] Figure 8 is a structural block diagram of a gas identification device suitable for a home environment according to an embodiment of the present application;

[0044] Figure 9 is a hardware structure schematic diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0045] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0046] The electronic nose is introduced into the field of home health services to solve the problem of olfactory quantification, wherein the common gas sources in the room environment are shown in Table 1 as follows:

[0047] Table 1:

[0048]

[0049] The electronic nose can solve the problem of olfactory quantification, but there are also some problems.

[0050] First, the introduction of the electronic nose into the field of home health services results in few supporting facilities, high production and research and development costs.

[0051] Secondly, there is also a certain degree of ethics and regulatory difficulties: on the one hand, body odor and other indicators belong to personal privacy with a lot of information; on the other hand, if the high-end perfume, red wine and other product indicators will appear some subversion. Therefore, in the stage of unclear supervision, excessive investment in research and development actually exist certain risk.

[0052] At present, the successful commercial application of the related market is formaldehyde removal service, due to the time-limited equipment price of the measurement time, which is the main reason why the electronic nose cannot be widely used in the field of home health services.

[0053] Therefore, to solve the above technical problems, the embodiment of the present application provides a gas identification method suitable for a home environment.

[0054] According to the embodiment of the present application, a gas identification method suitable for a home environment is provided, and it should be noted that the steps shown in the flowchart of the drawing can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from here.

[0055] In the present embodiment, a gas identification method suitable for a home environment is provided, which can be used in the mobile terminal described above, such as mobile phone, tablet computer, etc. Figure 1 The flowchart of a gas identification method suitable for a home environment according to the embodiment of the present application is shown in FIG. Figure 1 As shown in the figure, the flow includes the following steps:

[0056] Step S101, acquiring the real-time measurement value of the smell collected by the multi-factor gas sensitive sensor, and constructing the real-time measurement value curve based on the real-time measurement value of the smell.

[0057] Specifically, the main interference in the home environment can be evaluated by the multi-factor weighted gas sensitive material product; for example, the related meteorological PM2.5 sensor (a sensor for monitoring the dust concentration in the surrounding air, i.e. the size of PM2.5 value) generally adopts oscillating balance method or weighing method, which has high measurement accuracy and high cost, but in order to reduce the cost, the household PM2.5 sensor adopts light scattering method, and the relationship between light scattering and particle concentration is easily disturbed by temperature and other factors, so the accuracy is not as good as the oscillating balance method; therefore, 10 light scattering PM2.5 sensors and 1 temperature and humidity sensor constitute a multi-factor gas sensitive sensor, and the cost of 10 light scattering PM2.5 sensors and 1 temperature and humidity sensor is much lower than that of 30 balance method sensors, which greatly improves the accuracy of gas identification in the home environment while reducing the cost.

[0058] Step S102, legitimacy verification is performed on the real-time measurement value curve, and a virtual measurement value sequence is generated based on the legitimacy verification result.

[0059] Specifically, due to the interference of electrical appliances, the real-time measurement value of the odor deviates, and therefore, legitimacy verification needs to be performed on the real-time measurement value curve, and data filtering is further performed, and obviously unreasonable data is directly discarded. For example, the real-time measurement value of the light scattering PM2.5 sensor deviates due to the fluctuation of the wind blowing gas flow rate, and therefore, legitimacy verification needs to be performed on the real-time measurement value curve, and the periodic and continuous three-second or five-second fluctuation in the real-time measurement value curve is further removed.

[0060] Step S103, a kernel function is configured for the virtual measurement value sequence, and a kernel space distribution is generated.

[0061] Specifically, through experiments, the X-axis dispersion corresponding to the Gaussian kernel function is obviously the largest, and therefore, the kernel function adopts the Gaussian kernel function.

[0062] Step S104, based on the kernel space distribution, a kernel linear discriminant analysis (LDA) is used to generate a home environment gas recognition result.

[0063] The home environment gas recognition method provided in this embodiment uses a low-cost sensor and improves the recognition degree of the electronic nose on common gases in the bedroom. The effectiveness of the real-time measurement value is ensured by performing legitimacy verification on the real-time measurement value curve. Based on the kernel space distribution, a kernel linear discriminant analysis is used to generate a home environment gas recognition result, which greatly reduces the calculation amount of the odor recognition in the home environment and improves the accuracy of the gas recognition in the home environment.

[0064] In this embodiment, a home environment gas recognition method is provided, which can be used in the mobile terminal such as a mobile phone, a tablet computer and the like. Figure 2 A flowchart of a home environment gas recognition method according to an embodiment of the present application is shown in FIG. 1, which includes the following steps: Figure 2

[0065] Step S201, odor real-time measurement values collected by a multi-factor gas sensitive sensor are acquired, and a real-time measurement value curve is constructed based on the odor real-time measurement values. For details, refer to step S101 in the embodiment shown in FIG. 1, which will not be repeated here. Figure 1

[0066] Step S202, legitimacy verification is performed on the real-time measurement value curve, and a virtual measurement value sequence is generated based on the legitimacy verification result.

[0067] Specifically, the step S202 includes:​​

[0068] Step S2021, the real-time measurement value curve is verified for legitimacy, and when the legitimacy verification result is that there is an illegal measurement value, the real-time measurement value curve is processed for weighted dimensionality increase to generate an extended value curve.

[0069] Specifically, a better pattern matching experience is provided by classification of the calibration data, and the serial number corresponding to the multi-factor gas sensitive sensor of the electronic nose can be weighted according to the data type, that is, calibration grouping; for example, the electronic nose reports 2-way data sequences, that is, a D1 formaldehyde data sequence and a D2 carbon dioxide data sequence, and after processing the difference between D1 and D2, an extended value curve D3 is added, D3=D1+0.1*D2.

[0070] Further, when the legitimacy verification result is that the real-time measurement value has legitimacy, the real-time measurement value curve is cleaned to generate a virtual quantity measurement value sequence.

[0071] Step S2022, the extended value curve is cleaned to generate a virtual quantity measurement value sequence.

[0072] Step S203, the virtual quantity measurement value sequence is configured with a kernel function to generate a kernel space distribution. For details, please refer to Figure 1 Step S103 of the embodiment shown in

[0073] Step S204, based on the kernel space distribution, a kernel linear discriminant analysis method is used to generate a home environment gas identification result. For details, please refer to Figure 1 Step S104 of the embodiment shown in

[0074] The home environment gas identification method provided in this embodiment uses the serial number in the sensor array of the electronic nose, which can be weighted according to the data type, that is, calibration grouping, and further provides a better pattern matching experience by classification of the calibration data, greatly reducing the calculation amount of odor identification in the home environment and improving the accuracy of gas identification in the home environment.

[0075] In this embodiment, a home environment gas identification method is provided, which can be used in the mobile terminal such as a mobile phone, a tablet computer, etc. Figure 3 is a flowchart of a home environment gas identification method according to an embodiment of the present application, as shown in Figure 3 The flowchart includes the following steps:

[0076] Step S301, acquire the odor real-time measurement value collected by the multi-factor gas sensitive sensor, and construct a real-time measurement value curve based on the odor real-time measurement value. For details, please refer to Figure 2 Step S201 of the embodiment shown in

[0077] Step S302: Perform a validity check on the real-time measurement curve, and generate a virtual quantity measurement value sequence based on the validity check result. For details, please refer to [link to relevant documentation]. Figure 2 Step S202 of the illustrated embodiment will not be described again here.

[0078] Step S303: Configure the kernel function for the virtual quantity measurement value sequence to generate the kernel space distribution.

[0079] Specifically, step S303 includes:

[0080] Step S3031: Perform a Laplace transform on the virtual quantity measurement value sequence to generate a linear space of measurement values.

[0081] Specifically, such as Figure 4 As shown, the linear space of the measured values ​​represents the temporal change of gas from when it is detected by the sensor until it dissipates. This linear measurement can be represented as x1, x2, ... x N .

[0082] Step S3032: The linear space of the measured values ​​is mapped to the Gaussian transform kernel space using the Gaussian kernel function to generate the kernel space distribution.

[0083] Specifically, by performing a Gaussian transform on the linear space of measured values ​​using a Gaussian kernel function, the distribution of the Gaussian transform kernel space can be obtained, such as... Figure 5 As shown, the expression is as follows:

[0084]

[0085] Where β represents the parameter, and x and y represent the data in the linear space of the measured values.

[0086] Step S304: Based on the spatial distribution of the kernel, generate the gas identification results of the home environment using the kernel linear discriminant analysis method.

[0087] Specifically, step S304 includes:

[0088] Step S3041: Nonlinear features of the nuclear spatial distribution are extracted using nuclear linear discriminant analysis to generate gas features.

[0089] Specifically, a nonlinear transformation is used to map the data in the input kernel space distribution to a high-dimensional feature space. The data points after the nonlinear transformation are φ(x1), φ(x2), ..., φ(x... N ); Calculate the kernel matrix K = [K(i,j)] of the training sample set based on the determined kernel function and optimized kernel function parameters, where,

[0090]

[0091] Furthermore, maximizing the Fisher criterion function is transformed into solving the problem of generalized eigenvalues. The eigenvalues ​​are obtained. And solve for the eigenvector z r =[α1,α2,…α N ] T , where λ r Represents a constant.

[0092] Furthermore, the eigenvalues ​​are sorted in descending order; the φ(x) values ​​in the training samples are then... i The projection onto the k-th eigenvector is used as the nonlinear feature y of the sample. r :

[0093]

[0094] Furthermore, the kernel matrix K' between the test sample and the training set samples is calculated, and then the test sample is projected onto the feature vector to obtain the gas features.

[0095] Step S3042: Input the gas features into the classifier to determine the gas category and generate the gas identification result for the home environment.

[0096] Specifically, the similarity between gas features and training gas samples is calculated by a classifier to determine the training gas sample that is most similar to the gas features. Then, the category corresponding to the training gas sample is taken as the category corresponding to the gas features to obtain the gas category of the home environment.

[0097] By constructing an upgraded kernel function suitable for gas recognition patterns in modern bedroom environments, a kernel-based LDA pattern matching method was used in a home environment.

[0098] This embodiment provides a gas identification method suitable for home environments. By utilizing kernel linear discriminant analysis, the nonlinear characteristics of different types of gases can be better characterized, improving the signal differences of samples after nonlinear mapping in the high-dimensional feature space, thereby enhancing the accuracy of gas identification in home environments.

[0099] This embodiment provides a gas identification method suitable for home environments, which can be used in the aforementioned mobile terminals, such as mobile phones and tablets. Figure 6 This is a flowchart of a gas identification method suitable for home environments according to an embodiment of the present invention, such as... Figure 6 As shown, the process includes the following steps:

[0100] Step S601: Obtain real-time odor measurement values ​​from the multi-factor gas sensor, and construct a real-time measurement curve based on these values. For details, please refer to [link to relevant documentation]. Figure 5Step S301 of the illustrated embodiment, which will not be repeated here.

[0101] Step S602, legitimacy verification is performed on the real-time measurement value curve, and a virtual measurement value sequence is generated based on the legitimacy verification result. For details, please refer to Figure 5 Step S302 of the illustrated embodiment, which will not be repeated here.

[0102] Step S603, a kernel function is configured for the virtual measurement value sequence, and a kernel space distribution is generated. For details, please refer to Figure 5 Step S303 of the illustrated embodiment, which will not be repeated here.

[0103] Step S604, based on the kernel space distribution, a home environment gas identification result is generated by using kernel linear discriminant analysis method. For details, please refer to Figure 5 Step S304 of the illustrated embodiment, which will not be repeated here.

[0104] Step S605, a report quality score is given to the home environment gas identification result, a home environment gas quality is generated, and the current home environment is adjusted based on the home environment gas quality.

[0105] Specifically, the above step S605 includes:

[0106] Step S6051, when the home environment gas quality is unqualified, the home environment gas quality is sent to the user end, so that the user analyzes the breath state report, and adjusts the current home environment based on the analysis result.

[0107] Specifically, as Figure 7 indicated, when the home environment gas quality is unqualified, manual analysis and global optimization are performed by the user, a cleaning strategy with greater separation degree is used to clean the extension value curve, and the kernel function is reconfigured for the virtual measurement value sequence.

[0108] Step S6052, or, when the home environment gas quality is qualified, a breath state report is generated and stored.

[0109] For example, when applied to a dormitory environment, the breath state report is submitted to a sleep aid platform.

[0110] In this embodiment, a gas identification device suitable for a home environment is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments, and has been described above. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware, or a combination of software and hardware is also possible and contemplated.

[0111] The embodiment provides a gas identification device suitable for a home environment, as shown in the accompanying drawings, comprising: Figure 8

[0112] The acquisition module 801 is configured to acquire a smell real-time measurement value collected by a multi-factor gas sensitive sensor, and construct a real-time measurement value curve based on the smell real-time measurement value.

[0113] The legality verification module 802 is configured to perform legality verification on the real-time measurement value curve, and generate a virtual measurement value sequence based on a legality verification result.

[0114] The configuration module 803 is configured to configure a kernel function on the virtual measurement value sequence, and generate a kernel space distribution.

[0115] The generation module 804 is configured to generate a home environment gas identification result based on the kernel space distribution and by using a kernel linear discriminant analysis method.

[0116] In some optional embodiments, the legality verification module 802 comprises:

[0117] The verification unit is configured to perform legality verification on the real-time measurement value curve, and when the legality verification result is that there is an illegitimate measurement value, perform weighted dimension increasing processing on the real-time measurement value curve, and generate an extended value curve.

[0118] The first cleaning unit is configured to clean the extended value curve, and generate the virtual measurement value sequence.

[0119] In some optional embodiments, the legality verification module 802 further comprises:

[0120] The second cleaning unit is configured to, when the legality verification result is that the real-time measurement value is legitimate, clean the real-time measurement value curve, and generate the virtual measurement value sequence.

[0121] In some optional embodiments, the configuration module 803 comprises:

[0122] The transformation unit is configured to perform Laplace transformation on the virtual measurement value sequence, and generate a measurement value linear space.

[0123] The mapping unit is configured to map the measurement value linear space to a Gaussian transformation kernel space by using a Gaussian kernel function, and generate the kernel space distribution.

[0124] In some optional embodiments, the generation module 804 comprises:

[0125] The extraction unit is configured to perform non-linear feature extraction on the kernel space distribution by using the kernel linear discriminant analysis method, and generate a gas feature.

[0126] ​A determination unit is configured to input the gas feature into a classifier, determine the gas category, and generate a home environment gas identification result.

[0127] In some optional embodiments, the method further comprises:

[0128] A scoring module is configured to score the home environment gas identification result, generate a home environment gas quality, and adjust the current home environment based on the home environment gas quality.

[0129] In some optional embodiments, the scoring module comprises:

[0130] An analysis unit is configured to, when the home environment gas quality is unqualified, send the home environment gas quality to a user terminal, so that the user analyzes the breath status report, and adjusts the current home environment based on the analysis result.

[0131] A storage unit is configured to, when the home environment gas quality is qualified, generate a breath status report, and store the breath status report.

[0132] Further function descriptions of the above-mentioned modules and units are the same as those of the corresponding embodiments, and will not be repeated here.

[0133] The gas identification device suitable for the home environment in the embodiment is presented in the form of a functional unit. The unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and a memory executing one or more software or fixed programs, and / or other devices that can provide the above-mentioned functions.

[0134] The embodiment of the present application also provides a computer device having the above-mentioned Figure 8 gas identification device suitable for the home environment.

[0135] Please refer to Figure 9 , Figure 9 is a structural schematic diagram of a computer device provided by an optional embodiment of the present application, as shown in Figure 9As shown, the computer device includes one or more processors 10, memory 20, and interfaces 30 for external devices such as a keyboard and a mouse and a disk drive. One or more of the interfaces 30 enable a user to interact with the computer device. In some embodiments, the interface 30 also includes an input device, such as a microphone, or output device, such as a speaker. Figure 9 The processor 10 is used in the description as an example.

[0136] The processor 10 can be a central processing unit, a network processor, or a combination thereof. The processor 10 can further include a hardware chip. The hardware chip can be an application specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device can be a complex programmable logic device, a field programmable logic device, a general array logic, or any combination thereof.

[0137] The memory 20 stores instructions that can be executed by the at least one processor 10 to cause the at least one processor 10 to perform the methods described in the above embodiments.

[0138] The memory 20 can include a program storage area and a data storage area. The program storage area can store an operating system, application programs, and the like for use by the at least one processor 10. The data storage area can store data created by the computer device, as well as data received by the computer device. The memory 20 can include a cache memory (not shown) for the at least one processor 10, as well as a RAM and a ROM. The memory 20 can also include a non-volatile memory, such as a magnetic disk or an optical disk, for example. The memory 20 can include a combination of cache memory, a RAM, a ROM, and the non-volatile memory. In some embodiments, the memory 20 can include a remote-proximate memory, which can be connected to the computer device through a network. Examples of the network include, but are not limited to, the Internet, an intranet, an extranet, a local area network, a wide area network, a metropolitan area network, a personal area network, a campus area network, a space area network, a terrestrial network, a wireless network, a global network such as the Internet, a private network such as an enterprise intranet, a local network such as a LAN, a cellular network, a satellite network, a home network, a personal area network, and the like, or a combination thereof.

[0139] The memory 20 can include a volatile memory, such as a RAM, for example. The memory 20 can also include a non-volatile memory, such as a flash memory, a hard disk, or a solid-state drive, for example. The memory 20 can also include a combination of the above-mentioned types of memories.

[0140] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 can be connected through a bus or other means, Figure 9 The bus connection is taken as an example.

[0141] The input device 30 can receive inputted digital or character information, and generate key signal input related to user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a trackpad, a touchpad, a pointing stick, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 can include a display device, an auxiliary lighting device (e.g., an LED), a tactile feedback device (e.g., a vibration motor), etc. The display device includes but is not limited to a liquid crystal display, a light-emitting diode, a display, and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0142] The embodiments of the present application also provide a computer readable storage medium, and the method according to the embodiments of the present application can be implemented in hardware, firmware, or recorded in a storage medium, or stored in a remote storage medium or a non-transitory machine readable storage medium and downloaded from a network and stored in a local storage medium, so that the method described herein can be processed by such software on a storage medium using a general purpose computer, a special purpose processor, or programmable or special purpose hardware. The storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk or a solid state disk, etc. Further, the storage medium can also include a combination of the above-mentioned types of memories. It can be understood that the computer, the processor, the microprocessor controller or the programmable hardware includes a storage component that can store or receive software or computer code, when the software or computer code is accessed and executed by the computer, the processor or the hardware, the method shown in the above embodiments is implemented.

[0143] Although the embodiments of the present application are described in conjunction with the accompanying drawings, various modifications and changes can be made by those skilled in the art without departing from the spirit and scope of the present application, and such modifications and changes fall within the scope defined by the appended claims.

Claims

1. A gas identification method suitable for home environments, characterized in that, The method includes: Obtain real-time odor measurement values ​​collected by a multi-factor gas sensor, and construct a real-time measurement value curve based on the real-time odor measurement values; The real-time measurement curve is validated for legality, and a sequence of virtual quantity measurement values ​​is generated based on the validation results. Configure a kernel function on the virtual quantity measurement value sequence to generate a kernel space distribution; Based on the aforementioned nuclear spatial distribution, the nuclear linear discriminant analysis method is used to generate gas identification results for the home environment. The real-time measurement curve is validated for legality, and a sequence of virtual quantity measurement values ​​is generated based on the validation results, including: The real-time measurement curve is validated for legality. If the validation result indicates the presence of invalid measurement values, the real-time measurement curve is weighted and upgraded to generate an extended value curve. The extended value curve is cleaned to generate the virtual quantity measurement value sequence; The method further includes: performing a validity check on the real-time measurement curve, generating a virtual quantity measurement value sequence based on the validity check result, and also including: When the validity verification result indicates that the real-time measurement value is valid, the real-time measurement value curve is cleaned to generate the virtual quantity measurement value sequence. Configure a kernel function on the virtual quantity measurement value sequence to generate a kernel space distribution, including: Perform a Laplace transform on the virtual quantity measurement value sequence to generate a linear space of measurement values; The linear space of the measured values ​​is mapped to the Gaussian transform kernel space using a Gaussian kernel function to generate the kernel space distribution. Based on the aforementioned nuclear spatial distribution, the residential environment gas identification results are generated using kernel linear discriminant analysis, including: The nuclear linear discriminant analysis method is used to extract nonlinear features from the nuclear spatial distribution to generate gas features; The gas features are input into a classifier to determine the gas category and generate the gas identification result for the home environment.

2. The method according to claim 1, characterized in that, Also includes: The home environment gas identification results are scored for report quality, home environment gas quality is generated, and the current home environment is adjusted based on the home environment gas quality.

3. The method according to claim 2, characterized in that, The report quality score is calculated based on the identified home environment gas quality, generating a home environment gas quality report. The current home environment is then adjusted based on this gas quality report, including: When the gas quality of the home environment is unqualified, the gas quality of the home environment will be sent to the user terminal so that the user can analyze the gas status report and adjust the current home environment based on the analysis results. Alternatively, when the gas quality in the home environment is within acceptable limits, an air quality report is generated and stored.

4. A gas identification device suitable for home environments, characterized in that, The device includes: The acquisition module is used to acquire real-time odor measurement values ​​collected by the multi-factor gas sensor and construct a real-time measurement value curve based on the real-time odor measurement values; The legality verification module is used to verify the legality of the real-time measurement curve and generate a virtual quantity measurement value sequence based on the legality verification result; The configuration module is used to configure kernel functions for the virtual quantity measurement value sequence and generate a kernel space distribution; The generation module is used to generate home environment gas identification results based on the said kernel spatial distribution using kernel linear discriminant analysis. The validity verification module includes: The verification unit is used to verify the validity of the real-time measurement curve. When the validity verification result is that there is an invalid measurement value, the real-time measurement curve is weighted and upgraded to generate an extended value curve. The first cleaning unit is used to clean the extended value curve and generate a sequence of virtual quantity measurement values; The validity verification module also includes: The second cleaning unit is used to clean the real-time measurement curve and generate a virtual quantity measurement value sequence when the legality verification result shows that the real-time measurement value is legal. The configuration module includes: The transformation unit is used to perform a Laplace transform on the sequence of virtual quantity measurement values ​​to generate a linear space of measurement values. The mapping unit is used to map the linear space of measured values ​​to the Gaussian transform kernel space using the Gaussian kernel function, thereby generating the kernel space distribution. The generation module includes: The extraction unit is used to extract nonlinear features from the spatial distribution of the nucleus using nuclear linear discriminant analysis to generate gas features. The determination unit is used to input gas features into the classifier, determine the gas category, and generate gas identification results for the home environment.

5. A computer device, characterized in that, include: A memory and a processor are communicatively connected, the memory storing computer instructions, and the processor executing the computer instructions to perform the gas identification method for a home environment as described in any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a computer to perform the gas identification method for a home environment as described in any one of claims 1 to 3.

Images