Method and system for constructing multi-dimensional VOC detection dataset, and computer program product

Abstract

This application relates to a method for constructing a multi-dimensional VOC detection dataset. The method includes: merging VOC detection data obtained by one semiconductor gas sensor among a plurality of semiconductor gas sensors into VOC detection data of a dimension assigned to the semiconductor gas sensor, to construct a multi-dimensional VOC detection dataset (S1). This application further relates to a system for constructing a multi-dimensional VOC detection dataset and a computer program product. According to this application, VOC detection data obtained by a same semiconductor gas sensor is merged into one-dimensional VOC detection data. Therefore, a multi-dimensional VOC detection dataset is constructed, thereby improving richness of information included in the VOC detection dataset, laying a foundation for training of a deep learning model for executing different identification tasks and identification of a VOC component, and effectively improving an identification capability and prediction accuracy of the deep learning model about a VOC gas component.

Description

[0001] METHOD AND SYSTEM FOR CONSTRUCTING MULTI¬

[0002] DIMENSIONAL VOC DETECTION DATASET, AND COMPUTER PROGRAM PRODUCT

[0003] TECHNICAL FIELD

[0004] This application relates to the field of VOC identification technologies, and in particular, to a method for constructing a multi-dimensional VOC (volatile organic compound) detection dataset, a system for constructing a multi-dimensional VOC detection dataset, and a computer program product, to at least assist in implementing steps of the method according to this application.

[0005] BACKGROUND

[0006] In a household appliance (such as a refrigerator, a laundry machine, or a dish-washing machine), a VOC gas in an object placing space is usually detected by using a VOC gas sensor made of a metal oxide. Time sequence response sample data of the VOC gas sensor for VOC gases of different types and different concentrations at each temperature may be obtained by applying a periodically changing heating temperature to the gas sensor, and the obtained time sequence response sample data is analyzed by a deep learning model, so that the type and concentration of the VOC gas may be identified. However, because the obtained time sequence response sample data is one-dimensional data, the deep learning model can extract less effective information from the one-dimensional time sequence response sample data, and prediction precision is low. This greatly limits application of a VOC gas sensor to, for example, a complex scenario of a household appliance.

[0007] Therefore, there is a need for improving a current manner of constructing a VOC detection dataset.

[0008] SUMMARY

[0009] An objective of this application is to provide a method for constructing a multidimensional VOC (volatile organic compound) detection dataset, a system for constructing a multi-dimensional VOC detection dataset, and a computer program product, to resolve problems in the existing technology. Based on a core idea of this application:

[0010] According to a first aspect of this application, a method for constructing a multidimensional VOC detection dataset is provided. The method includes:

[0011] - step SI: merging VOC detection data obtained by one semiconductor gas sensor among a plurality of semiconductor gas sensors into VOC detection data of a dimension assigned to the semiconductor gas sensor, to construct a multi-dimensional VOC detection dataset.

[0012] Based on a core idea of this application, VOC detection data obtained by a same semiconductor gas sensor is merged into one-dimensional VOC detection data. Therefore, a multi-dimensional VOC detection dataset is constructed, thereby improving richness of information included in the VOC detection data set, laying a foundation for training of a deep learning model for executing different identification tasks and identification of a VOC component, and effectively improving an identification capability and prediction accuracy of the deep learning model about a VOC gas component.

[0013] According to an embodiment of this application, step SI may include:

[0014] - step SI 1: performing cyclic temperature modulation in a preset temperature range on the plurality of semiconductor gas sensors, and obtaining VOC detection data of each semiconductor gas sensor by sampling, for example, using a sliding sampling window technique, in a cyclic temperature modulation period; and

[0015] - step S13: merging VOC detection data obtained by one semiconductor gas sensor in each cyclic temperature modulation period into VOC detection data of a dimension assigned to the semiconductor gas sensor, to construct a multi-dimensional VOC detection dataset.

[0016] Different types of VOC gas detection data may be obtained by heating each semiconductor gas sensor and maintaining the temperature in different temperature ranges. In addition, by using the sliding sampling window technique, manpower and time costs can be significantly reduced, interference of a random error and a human factor on sample data can be effectively reduced, and distribution of obtained VOC detection data samples is balanced.

[0017] According to another embodiment of this application, step SI may further include:

[0018] - step SI 2: based on a temperature feature of each semiconductor gas sensor, respectively labeling VOC detection data obtained by a corresponding semiconductor gas sensor in each cyclic temperature modulation period with a label for indicating a VOC component, where the VOC component particularly includes a type and / or concentration of a VOC gas; and

[0019] - step SI 4: assigning a label to VOC detection data of a corresponding dimension based on a labeled label.

[0020] The labeled label may lay a foundation of training the deep learning model using the VOC detection data.

[0021] According to another embodiment of this application, step SI may further include:

[0022] - step S 15 : normalizing VOC detection data of one dimension based on a maximum VOC detection data value and a minimum VOC detection data value in the VOC detection data of the corresponding dimension.

[0023] In this manner, all elements of VOC detection data of each dimension are normalized into a value range of 0 to 1, thereby improving processing efficiency of the VOC detection data of each dimension. According to another embodiment of this application, step SI may further include:

[0024] - step SI 6: performing feature importance analysis on VOC detection data of each dimension, and merging the VOC detection data of each dimension based on an analysis result of the feature importance, to reduce a dimension of the VOC detection dataset.

[0025] Optionally, based on the analysis result of the feature importance, a weight factor of VOC detection data assigned to a dimension with low feature importance may be assigned to the VOC detection data of the dimension with low feature importance, and a product of the VOC detection data of the dimension with low feature importance and the weight factor assigned to the dimension is merged into VOC detection data of a dimension with high feature importance, thereby reducing the dimensions of the VOC detection data, and effectively improving the efficiency of processing the VOC detection data by the deep learning model.

[0026] Optionally, in particular, a weight factor of VOC detection data of a dimension with feature importance lower than a preset threshold may be set to zero. Therefore, VOC detection data of an inaccurate dimension is deleted as a whole, to eliminate possible negative impacts on a detection result, thereby further improving processing efficiency and prediction accuracy of the deep learning model.

[0027] According to another embodiment of this application, the plurality of semiconductor gas sensors are made of same or different semiconductor materials, and the semiconductor gas sensors made of different semiconductor materials have different temperature features, so that different semiconductor gas sensors respectively present different sensitivity to different types of VOC gases in different temperature ranges.

[0028] According to another embodiment of this application, the method may further include: - step S2: training, based at least on the multi-dimensional VOC detection dataset, a deep learning model for identifying the VOC component.

[0029] According to another embodiment of this application, the method may further include:

[0030] - step S3: determining, based at least on the multi-dimensional VOC detection dataset, a detected VOC component by the deep learning model for identifying the VOC component, where the VOC component particularly includes a type and / or the concentration of the VOC, and the like.

[0031] Compared with the existing technology of identifying a VOC gas component based on one-dimensional VOC detection data, identification of a VOC gas component by a deep learning model based on a multi-dimensional VOC detection dataset greatly improves accuracy.

[0032] According to a second aspect of this application, a system for constructing a multidimensional VOC detection dataset is provided. The system is configured to perform the method according to this application. The system may include the following components:

[0033] - a plurality of semiconductor gas sensors, configured to respectively obtain VOC detection data;

[0034] - a data construction module, configured to merge VOC detection data obtained by one semiconductor gas sensor among the plurality of semiconductor gas sensors into VOC detection data of a dimension assigned to the semiconductor gas sensor, to construct a multidimensional VOC detection dataset.

[0035] According to another embodiment of this application, the system may further include a deep learning model. A detected VOC component is identified by the deep learning model based at least on the multi-dimensional VOC detection dataset, where the VOC component particularly includes a type and / or concentration of the VOC, and the like.

[0036] According to another embodiment of this application, the system may further include a data labeling module, configured to respectively label, based on a temperature feature of each semiconductor gas sensor, VOC detection data obtained by a corresponding semiconductor gas sensor with a label for indicating a VOC component, and assign a label to VOC detection data of a corresponding dimension based on a labeled label, where the VOC component particularly includes a type and / or concentration of the VOC. The labeled label may lay a foundation of training the deep learning model using the VOC detection data.

[0037] According to another embodiment of this application, the system may further include a model training module, configured to train, based at least on the multi-dimensional VOC detection dataset, the deep learning model for identifying the VOC component.

[0038] According to a third aspect of this application, a computer program product, for example, a computer-readable program carrier, is provided, including computer program instructions. When the computer program instructions are executed by a processor, the steps of the method according to this application are at least assisted in being implemented.

[0039] BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The following describes this application in more detail with reference to the accompanying drawings, to better understand the principles, features, and advantages of this application. The accompanying drawings include:

[0041] FIG. 1 shows a block diagram of a method for constructing a multi-dimensional VOC detection dataset according to an exemplary embodiment of this application;

[0042] FIG. 2 shows a block diagram of a method for constructing a multi-dimensional VOC detection dataset according to another exemplary embodiment of this application;

[0043] FIG. 3 shows a block diagram of a method for constructing a multi-dimensional VOC detection dataset according to another exemplary embodiment of this application;

[0044] FIG. 4 shows a block diagram of a method for constructing a multi-dimensional VOC detection dataset according to another exemplary embodiment of this application;

[0045] FIG. 5 shows a block diagram of a method for constructing a multi-dimensional VOC detection dataset according to another exemplary embodiment of this application;

[0046] FIG. 6 shows a block diagram of a method for constructing a multi-dimensional VOC detection dataset according to another exemplary embodiment of this application;

[0047] FIG. 7 shows a block diagram of a method for constructing a multi-dimensional VOC detection dataset according to another exemplary embodiment of this application;

[0048] FIG. 8 shows a block diagram of a system for constructing a multi-dimensional VOC detection dataset according to an exemplary embodiment of this application; and

[0049] FIG. 9 shows a block diagram of a system for constructing a multi-dimensional VOC detection dataset according to another exemplary embodiment of this application.

[0050] DETAILED DESCRIPTION

[0051] To make technical problems to be resolved, technical solutions, and beneficial technical effects of this application clearer and more comprehensible, this application is further described in detail below with reference to the accompanying drawings and a plurality of exemplary embodiments. It should be understood that specific embodiments described herein are merely used for explaining this application but are not used for limiting the protection scope of this application.

[0052] FIG. 1 shows a working flowchart of a method for constructing a multi-dimensional VOC detection dataset according to an exemplary embodiment of this application. The following exemplary embodiments describe the method according to this application in more detail.

[0053] The method may include step SI. In step SI, VOC detection data obtained by one semiconductor gas sensor among a plurality of semiconductor gas sensors is merged into VOC detection data of a dimension assigned to the semiconductor gas sensor, to construct a multidimensional VOC detection dataset.

[0054] A plurality of semiconductor gas sensors are usually disposed in a household appliance (such as a refrigerator, a laundry machine, and a dish-washing machine), and are configured to respectively obtain VOC detection data. The plurality of semiconductor gas sensors may be made of same semiconductor materials. For example, the semiconductor gas sensors are zinc oxide gas sensors having excellent gas-sensitive performance and wide applicability. Because temperature features of the zinc gas sensors indicate that the zinc gas sensors present different sensitivity to different types of VOC gases in different temperature ranges, corresponding VOC gas detection data may be obtained by heating each zinc gas sensor and maintaining the temperature in different temperature ranges.

[0055] Optionally, the plurality of semiconductor gas sensors may alternatively be made of different semiconductor materials, and the semiconductor gas sensors made of different semiconductor materials have different temperature features. To be specific, different semiconductor gas sensors respectively present different sensitivity to different types of gases in different temperature ranges. For example, semiconductor gas sensors made of Co-doped SnO2 nano-sensitive materials present high sensitivity to formaldehyde and acetone in a preset temperature range.

[0056] A system 1 for constructing a multi-dimensional VOC detection dataset shown in FIG. 8 and FIG. 9 includes, for example, a first semiconductor gas sensor 111 , a second semiconductor gas sensor 112, a third semiconductor gas sensor 113, and a fourth semiconductor gas sensor 114. The semiconductor gas sensors may respectively present different sensitivity to different types of gases in different temperature ranges. In the existing technology, data output by a semiconductor gas sensor is one-dimensional VOC detection data. The following describes a process of constructing a multi-dimensional VOC detection dataset in detail with reference to working flowcharts of a method for constructing a multi-dimensional VOC detection dataset according to another exemplary embodiment of this application shown in FIG. 2 to FIG. 5.

[0057] As shown in FIG. 2, step SI may include step Si l and step S13. In step Si l, cyclic temperature modulation in a preset temperature range is performed on the plurality of semiconductor gas sensors, and VOC detection data of each semiconductor gas sensor is obtained by sampling, for example, using a sliding sampling window technique, in a cyclic temperature modulation period. A current having a modulated waveform, for example, a rectangular wave having a modulation period Tt, a maximum current value Im in, 3. 1T13X11T1L11T1 current value Imax, and a duty ratio D, may be applied to a semiconductor gas sensor in a cyclic temperature modulation period of, for example, 100°C to 120°C, to increase a temperature of the semiconductor gas sensor and maintain the temperature in a first preset temperature range. The semiconductor gas sensor is, for example, highly sensitive to a first VOC gas in the first preset temperature range, thereby obtaining a VOC time sequence response of the first VOC gas, sampling the VOC time sequence response at a fixed sampling frequency to obtain VOC time sequence response data on the first VOC gas. Next, the temperature of the semiconductor gas sensor is further increased by applying a current having a modulated waveform and is maintained in a second preset temperature range, thereby obtaining VOC time sequence response data on a second VOC gas. The rest can be deduced by analogy until the temperature of the semiconductor gas sensor traverses the entire cyclic temperature modulation period from 100°C to 120°C. Then, a next cyclic temperature modulation period is repeatedly performed after the temperature of the semiconductor gas sensor is reduced to 100°C.

[0058] Herein, each semiconductor gas sensor may be heated, and the temperature may be maintained in different preset temperature ranges, so as to obtain VOC time sequence response data of VOC gases of as many types as possible. The plurality of semiconductor gas sensors therein may alternatively be heated, and the temperatures are maintained in a same preset temperature range. In addition, VOC time sequence response data of some types of VOC gases is repeatedly detected, to check credibility of VOC gases related to the functionality and / or safety of a household appliance, such as VOC gases generated due to food burning, VOC gases generated due to leakage of a ventilation system, and VOC gases generated due to mildew in a laundry machine or a dish-washing machine.

[0059] For example, a sliding sampling window may be disposed on a time axis of the VOC time sequence response data. A sampling window width Tcis equal to an integer (m) multiple of a modulation period Tt of the applied waveform, and a sliding step length is one sampling data point. The sampling window slides in a direction of a time axis from a first sampling data point of the VOC time sequence response data. Each time the sampling window slides for one step length, all sampling data in the sampling window is captured as one group of VOC time sequence response sample data, so that a plurality of groups of VOC time sequence response sample data can be obtained for each type of VOC gas, and VOC detection data of each semiconductor gas sensor is obtained by continuous resampling of the VOC time sequence response data point by point, thereby significantly reducing manpower and time costs, and effectively reducing interference of a random error and a human factor to the sample data. In addition, distribution of obtained VOC detection data samples is balanced.

[0060] In step SI 3, VOC detection data obtained by one semiconductor gas sensor in each cyclic temperature modulation period is merged into VOC detection data of a dimension assigned to the semiconductor gas sensor, to construct a multi-dimensional VOC detection dataset. In the meaning of this application, the term "merging" may be understood as: constructing one row of data elements using VOC detection data obtained by one semiconductor gas sensor in a cyclic temperature modulation period, and processing the VOC detection data of the semiconductor gas sensor one by one in the cyclic temperature modulation periods in this manner, to construct corresponding rows of data elements, where quantities of VOC detection data obtained in each cyclic temperature modulation period are equal, to be specific, quantities of data elements in each row are equal. Therefore, a matrix in which a quantity of rows is equal to a quantity of cyclic temperature modulation periods may be constructed by using these rows of data elements. The matrix is VOC detection data assigned to one dimension of the semiconductor gas sensor. Herein, data processing, including label assignment, normalization, feature importance analysis, and / or weight factor assignment, may be uniformly performed on VOC detection data of a same dimension. VOC detection data of a corresponding dimension is constructed in this manner for each semiconductor gas sensor, thereby obtaining a multidimensional VOC detection dataset. For example, VOC detection data of a first dimension is made of VOC detection data obtained by the first semiconductor gas sensor 111 in a plurality of cyclic temperature modulation periods, VOC detection data of a second dimension is made of VOC detection data obtained by the second semiconductor gas sensor 112 in a plurality of cyclic temperature modulation periods, VOC detection data of a third dimension is made of VOC detection data obtained by the third semiconductor gas sensor 113 in a plurality of cyclic temperature modulation periods, VOC detection data of a fourth dimension is made of VOC detection data obtained by the fourth semiconductor gas sensor 114 in a plurality of cyclic temperature modulation periods, and so on. In view of the fact that quantities of cyclic temperature modulation periods in which each semiconductor gas sensor performs VOC gas detection are equal, VOC detection data volumes of each dimension are also equal.

[0061] In view of the fact that VOC detection data is required to have a label when a deep learning model 15 is trained using the VOC detection data, the following describes a VOC detection data labeling process in detail with reference to a working flowchart of a method for constructing a multi-dimensional VOC detection dataset according to another exemplary embodiment of this application shown in FIG. 3.

[0062] As shown in FIG. 3, step SI may further include steps S12 and SI 4. In step SI 2, based on a temperature feature of each semiconductor gas sensor, VOC detection data obtained by a corresponding semiconductor gas sensor in each cyclic temperature modulation period is respectively labeled with a label for indicating a VOC component, where the VOC component particularly includes a type and / or concentration of a VOC gas, and the like. In an exemplary test scenario in which there are h types and k concentrations of VOC gases, VOC detection data obtained by a corresponding semiconductor gas sensor may be respectively labeled with h*k labels on the type and concentration of the VOC gas, so that the VOC detection data presents a significant sample difference.

[0063] In a process of merging VOC detection data of different dimensions, a label may be assigned to VOC detection data of a corresponding dimension based on a labeled label in step S14, so that VOC detection data of each dimension obtained by merging has a corresponding label.

[0064] To improve processing efficiency of VOC detection data of each dimension, FIG. 4 shows a working flowchart of a method for constructing a multi-dimensional VOC detection dataset according to another exemplary embodiment of this application. Step SI may further include step S 15. In step S 15, V OC detection data of one dimension is normalized based on a maximum VOC detection data value and a minimum VOC detection data value in the VOC detection data of the corresponding dimension, so that all elements of the VOC detection data of each dimension are normalized into a value range of 0 to 1.

[0065] In the presence of a larger number of semiconductor gas sensors in the system 1, there are also many dimensions of obtained VOC detection data. VOC detection data of excessive dimensions may affect processing efficiency of the deep learning model 15, and VOC detection data of dimensions obtained by the semiconductor gas sensors with low detection precision may affect prediction accuracy of the deep learning model 15. Therefore, there is a requirement of reducing the dimensions of the VOC detection data in some application scenarios. A process of reducing a dimension of VOC detection data is described in detail below with reference to a working flowchart of a method for constructing a multi-dimensional VOC detection dataset according to another exemplary embodiment of this application shown in FIG. 5.

[0066] As shown in FIG. 5, step SI may further include step SI 6. In step SI 6, feature importance analysis is performed on VOC detection data of each dimension, and the VOC detection data of each dimension is merged based on an analysis result of the feature importance, to reduce a dimension of the VOC detection dataset. Herein, feature importance analysis may be performed on the VOC detection data, for example, in terms of a type, a concentration, and detection precision of a VOC gas. VOC detection data with more types of VOC gas (particularly, including a VOC gas of a type related to the functionality and / or safety of a household appliance), a higher concentration, and / or a higher detection precision has high feature importance, while VOC detection data with fewer types of VOC gas, a lower concentration, and / or a lower detection precision has low feature importance. Based on the analysis result of the feature importance, a weight factor of VOC detection data assigned to a dimension with low feature importance is assigned to the VOC detection data of the dimension with low feature importance, and a product of the VOC detection data of the dimension with low feature importance and the weight factor assigned to the dimension is merged into VOC detection data of a dimension with high feature importance.

[0067] For example, the label of the VOC detection data of the fourth dimension has fewer types of VOC gas, a lower concentration, or a lower detection precision, and the VOC detection data of the fourth dimension may be merged into the VOC detection data of another dimension, thereby reducing the dimensions of the VOC detection data. In particular, when it is identified, according to the VOC detection data of the fourth dimension, that the VOC detection data of the fourth semiconductor gas sensor 114 obviously deviates from a normal detection concentration range, it may be determined that the feature importance of the VOC detection data of the fourth dimension is less than a preset threshold, and a weight factor of VOC detection data of a dimension with feature importance lower than a preset threshold is set to zero. Therefore, VOC detection data of an inaccurate dimension is deleted as a whole, to eliminate possible negative impacts on a detection result, thereby improving processing efficiency and prediction accuracy of the deep learning model 15.

[0068] FIG. 6 shows a block diagram of a method for constructing a multi-dimensional VOC detection dataset according to another exemplary embodiment of this application. Only differences from the embodiment shown in FIG. 1 are described below. For brevity, same steps are not described again.

[0069] As shown in FIG. 6, the method may further include step S2. In step S2, a deep learning model 15 for identifying the VOC component is trained based at least on the multi-dimensional VOC detection dataset. Because VOC detection data of each dimension has a label on a type and / or concentration of a VOC gas, the deep learning model 15 may obtain a capability of identifying the type and / or concentration of the VOC gas in a learning process of the multidimensional VOC detection dataset. The deep learning model 15 includes, for example, a convolutional neural network, a multilayer self-encoding neural network, and / or a deep belief network.

[0070] In view of abundant information included in the multi-dimensional VOC detection data, a plurality of deep learning sub-models may be disposed to participate in the learning process of the multi-dimensional VOC detection dataset, to improve the identification capability and prediction accuracy of the deep learning model, where the deep learning sub-models are respectively configured to execute different identification tasks. For example, in an application scenario of a refrigerator, because different types of foods emit different types and different concentrations of VOC as freshness changes, a deep learning sub-model may be provided for each type of food, for example, a first deep learning sub-model for identifying freshness of a strawberry, a second deep learning sub-model for identifying freshness of a litchi, and a third deep learning sub-model for identifying freshness of a waxberry. For another example, in an application scenario of a laundry machine or a dish-washing machine, a fourth deep learning sub-model for identifying a type and / or concentration of mildew may be provided.

[0071] FIG. 7 shows a block diagram of a method for constructing a multi-dimensional VOC detection dataset according to another exemplary embodiment of this application. Only differences from the embodiment shown in FIG. 6 are described below. For brevity, same steps are not described again.

[0072] As shown in FIG. 7, the method may further include step S3. In step S3, a detected VOC component is determined by the deep learning model 15 for identifying the VOC component based at least on the multi-dimensional VOC detection dataset, where the VOC component particularly includes a type and / or the concentration of the VOC. For example, in an application scenario of a refrigerator, a type and concentration of a VOC gas may be identified by the trained first, second, or third deep learning sub-model based on the multi-dimensional VOC detection dataset, and freshness of a strawberry, a litchi, or a waxberry may be respectively evaluated based on the identified type and concentration of the VOC. For example, in an application scenario of a laundry machine or a dish-washing machine, a type and concentration of a VOC may be identified by the trained fourth deep learning sub-model based on the multidimensional VOC detection dataset, and a type and / or concentration of mildew may be evaluated based on the identified type and concentration of the VOC.

[0073] It should be noted that a current deep learning model cannot accurately identify a type and concentration of a VOC gas based on one-dimensional VOC detection data. According to test data, average accuracy of evaluating, based on one-dimensional VOC detection data, freshness of various types of foods by a deep learning sub-model trained based on the one-dimensional VOC detection data is only 26%. For example, accuracy of evaluating freshness of a strawberry is 63%, accuracy of evaluating freshness of a litchi is 46%, and accuracy of evaluating freshness of a litchi is 42%. According to the trained deep learning sub-model of this application, average accuracy of evaluating freshness of various types of foods based on a multi-dimensional VOC detection dataset is 85%. For example, accuracy of evaluating freshness of a strawberry is 86%, accuracy of evaluating freshness of a litchi is 85%, accuracy of evaluating freshness of a litchi is 75%, and so on.

[0074] According to this embodiment of this application, by constructing a multi-dimensional VOC detection dataset, richness of information included in the VOC detection dataset can be improved, to lay a foundation for training of a deep learning model for executing different identification tasks and identification of a VOC component, thereby effectively improving the identification capability and prediction accuracy of the deep learning model for a VOC gas component.

[0075] In addition, it should be noted that sequence numbers of steps described herein do not necessarily represent an order, but are merely reference numerals. The order may be changed according to specific situations, provided that the technical objectives of this application can be achieved.

[0076] FIG. 8 shows a block diagram of a system 1 for constructing a multi-dimensional VOC detection dataset according to an exemplary embodiment of this application.

[0077] As shown in FIG. 8, the system 1 may include the following components:

[0078] - a plurality of semiconductor gas sensors, configured to respectively obtain VOC detection data, and including, for example, a first semiconductor gas sensor 111, a second semiconductor gas sensor 112, a third semiconductor gas sensor 113, and / or a fourth semiconductor gas sensor 114;

[0079] - a data construction module 12, configured to merge VOC detection data obtained by one semiconductor gas sensor among the plurality of semiconductor gas sensors into VOC detection data of a dimension assigned to the semiconductor gas sensor, to construct a multidimensional VOC detection dataset.

[0080] Optionally, the system 1 may further include a deep learning model 15. A detected VOC component is identified by the deep learning model 15 based at least on the multi-dimensional VOC detection dataset, where the VOC component particularly includes a type and / or concentration of the VOC.

[0081] FIG. 9 shows a block diagram of a system 1 for constructing a multi-dimensional VOC detection dataset according to another exemplary embodiment of this application. In this embodiment, a training process of the deep learning model 15 is performed. Only differences from the embodiment shown in FIG. 8 are described below.

[0082] As shown in FIG. 9, the system 1 may further include a data labeling module 13, configured to respectively label, based on a temperature feature of each semiconductor gas sensor, VOC detection data obtained by a corresponding semiconductor gas sensor with a label for indicating a VOC component, and assign a label to VOC detection data of a corresponding dimension based on a labeled label, where the VOC component particularly includes a type and / or concentration of the VOC, and the like.

[0083] Optionally, the system 1 may further include a model training module 14, configured to train, based at least on the multi-dimensional VOC detection dataset, the deep learning model 15 for identifying the VOC component. A detected VOC component may be identified by the trained deep learning model 15 based at least on the multi-dimensional VOC detection dataset.

[0084] It will be appreciated that the expressions "first", "second", "third", and the like are merely used for descriptive purposes, and should not be understood as indicating or implying relative importance, nor as implicitly specifying the quantity of indicated technical features.

[0085] Although specific embodiments have been described above, these embodiments are not intended to limit the scope of this application, even when only a single embodiment is described with respect to specific features. Feature examples provided in the disclosure of this application are intended to be exemplary rather than limiting, unless indicated differently. In a specific implementation, a plurality of features may be combined with each other according to actual requirements and in a technically feasible case. Various replacements, changes, and alterations may further be conceived without departing from the spirit and scope of this application.

Claims

1. CLAIMSWhat is claimed is:

1. A method for constructing a multi-dimensional VOC detection dataset, the method comprising: step SI : merging VOC detection data obtained by one semiconductor gas sensor (111, 112, 113, 114) among a plurality of semiconductor gas sensors (111, 112, 113, 114) into VOC detection data of a dimension assigned to the semiconductor gas sensor (111, 112, 113, 114), to construct a multi-dimensional VOC detection dataset.

2. The method according to claim 1, wherein step SI comprises: step SI 1 : performing cyclic temperature modulation in a preset temperature range on the plurality of semiconductor gas sensors (111, 112, 113, 114), and obtaining VOC detection data of each semiconductor gas sensor (111, 112, 113, 114) by sampling, for example, using a sliding sampling window technique, in a cyclic temperature modulation period; and step SI 3: merging VOC detection data obtained by one semiconductor gas sensor (111, 112, 113, 114) in each cyclic temperature modulation period into VOC detection data of a dimension assigned to the semiconductor gas sensor (111, 112, 113, 114), to construct a multidimensional VOC detection dataset.

3. The method according to claim 2, wherein step SI further comprises: step S12: based on a temperature feature of each semiconductor gas sensor (111, 112, 113, 114), respectively labeling VOC detection data obtained by a corresponding semiconductor gas sensor (111, 112, 113, 114) in each cyclic temperature modulation period with a label for indicating a VOC component, wherein the VOC component particularly comprises a type and / or concentration of a VOC gas; and step SI 4: assigning a label to VOC detection data of a corresponding dimension based on a labeled label.

4. The method according to any one of claims 1 to 3, wherein step SI further comprises: step S15: normalizing VOC detection data of one dimension based on a maximum VOC detection data value and a minimum VOC detection data value in the VOC detection data of the corresponding dimension.

5. The method according to any one of claims 1 to 3, wherein step SI further comprises: step SI 6: performing feature importance analysis on VOC detection data of eachdimension, and merging the VOC detection data of each dimension based on an analysis result of the feature importance, to reduce a dimension of the VOC detection dataset.

6. The method according to claim 5, wherein based on the analysis result of the feature importance, a weight factor of VOC detection data assigned to a dimension with low feature importance is assigned to the VOC detection data of the dimension with low feature importance, and a product of the VOC detection data of the dimension with low feature importance and the weight factor assigned to the dimension is merged into VOC detection data of a dimension with high feature importance, in particular, a weight factor of VOC detection data of a dimension with feature importance lower than a preset threshold being set to zero.

7. The method according to any one of claims 1 to 3, wherein the plurality of semiconductor gas sensors (111, 112, 113, 114) are made of same or different semiconductor materials, and the semiconductor gas sensors (111, 112, 113, 114) made of different semiconductor materials have different temperature features.

8. The method according to claim 3, wherein the method further comprises: step S2: training, based at least on the multi-dimensional VOC detection dataset, a deep learning model (15) for identifying the VOC component.

9. The method according to claim 1, 2 or 8, wherein the method further comprises: step S3: determining, based at least on the multi-dimensional VOC detection dataset, a detected VOC component by the deep learning model (15) for identifying the VOC component, wherein the VOC component particularly comprises a type and / or the concentration of the VOC.

10. A system (1) for constructing a multi-dimensional VOC detection dataset, wherein the system (1) is configured to perform the method according to any one of claims 1 to 9, and the system (1) comprises the following components: a plurality of semiconductor gas sensors (111, 112, 113, 114), configured to respectively obtain VOC detection data; a data construction module (12), configured to merge VOC detection data obtained by one semiconductor gas sensor (111, 112, 113, 114) among the plurality of semiconductor gas sensors (111, 112, 113, 114) into VOC detection data of a dimension assigned to the semiconductor gas sensor (111, 112, 113, 114), to construct a multi-dimensional VOC detection dataset.

11. The system (1) according to claim 10, wherein the system (1) further comprises a datalabeling module (13), configured to respectively label, based on a temperature feature of each semiconductor gas sensor (111, 112, 113, 114), VOC detection data obtained by a corresponding semiconductor gas sensor (111, 112, 113, 114) with a label for indicating a VOC component, and assign a label to VOC detection data of a corresponding dimension based on alabeled label, wherein the VOC component particularly comprises atype and / or concentration of the VOC.

12. The system (1) according to claim 10 or 11, wherein the system (1) further comprises a deep learning model (15), and a detected VOC component is identified by the deep learning model (15) based at least on the multi-dimensional VOC detection dataset, wherein the VOC component particularly comprises atype and / or concentration of the VOC.

13. The system (1) according to claim 12, wherein the system (1) further comprises a model training module (14), configured to train, based at least on the multi-dimensional VOC detection dataset, the deep learning model (15) for identifying the VOC component.

14. A computer program product, for example, a computer-readable program carrier, comprising or storing computer program instructions, wherein when the computer program instructions are executed by a processor, the steps of the method according to any one of claims 1 to 9 are at least assisted in being implemented.

Images