Method, device and equipment for determining glycerol distribution of heated non-combustible cigarette and medium

Abstract

The invention discloses a glycerin distribution determination method, device and equipment for a heat-not-burn cigarette and a medium. The method comprises the following steps: acquiring a basic cutting segment set corresponding to a target heating non-combustion cigarette; determining target near-infrared hyperspectral data corresponding to target segmented cigarettes in the basic segmentation set based on a preset near-infrared hyperspectral imaging technology, and performing region segmentation on the target near-infrared hyperspectral data based on a preset threshold segmentation method to determine a corresponding region of interest and an average spectrum corresponding to the region of interest; and performing regression analysis on the average spectrum based on a target regression model set to obtain a prediction result corresponding to each target regression sub-model in the target regression model set, and determining a glycerin content distribution result corresponding to the target heating non-combustion cigarette based on the prediction result corresponding to each target regression sub-model. According to the technical scheme, the glycerol distribution of the cigarette core section in the heated non-combustible cigarette can be rapidly detected, and the detection efficiency of the glycerol distribution is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of cigarette production, and particularly to a method, device, equipment and medium for determining the glycerol distribution of heat-not-burn cigarettes. Background Art

[0002] A heat-not-burn cigarette is a tobacco product that uses a special heat source to only heat and not burn tobacco materials. Glycerol, also known as glycerin, is an important auxiliary material for preparing the tobacco core section in heat-not-burn cigarettes, and is an important humectant for improving the processing strength of raw materials and a smoke-promoting agent for promoting the smoke release of cigarette sticks in the heat-not-burn state. In the technical field of cigarette production, quickly and accurately detecting the glycerol distribution in the tobacco core section of heat-not-burn cigarettes is of great significance for the research and development and quality inspection of heat-not-burn cigarettes.

[0003] In the prior art, the detection of the glycerol distribution in the tobacco core section of heat-not-burn cigarettes mainly follows the chemical detection methods in tobacco and tobacco products, such as gas chromatography, liquid chromatography, mass spectrometry and corresponding combined methods. However, using chemical detection methods to detect the glycerol distribution in the tobacco core section of heat-not-burn cigarettes requires a large amount of time and labor costs. Moreover, due to the cumbersome pretreatment process of its technology and the limitation of the detection limit, it is difficult to obtain the two-dimensional glycerol content distribution detection of the tobacco core section. Therefore, how to quickly detect the glycerol distribution in the tobacco core section of heat-not-burn cigarettes and improve the detection efficiency of glycerol distribution is an urgent problem to be solved at present. Summary of the Invention

[0004] The present invention provides a method, device, equipment and medium for determining the glycerol distribution of heat-not-burn cigarettes, which can solve the problem of low detection efficiency of the glycerol distribution of heat-not-burn cigarettes.

[0005] According to one aspect of the present invention, there is provided a method for determining the glycerol distribution of heat-not-burn cigarettes, including:

[0006] Obtaining a set of basic cut segments corresponding to a target heat-not-burn cigarette; wherein, each target segment cigarette is included in the set of basic cut segments;

[0007] Based on a preset near-infrared hyperspectral imaging technology, determining target near-infrared hyperspectral data corresponding to the target segment cigarette, and based on a preset threshold segmentation method, performing region segmentation on the target near-infrared hyperspectral data to determine an interested region corresponding to the target segment cigarette and an average spectrum corresponding to the interested region;

[0008] Performing regression analysis on the average spectrum based on the target regression model set to obtain the prediction results corresponding to each target regression sub-model in the target regression model set, and determining the glycerol content distribution result corresponding to the target heat-not-burn cigarette based on the prediction results corresponding to each target regression sub-model.

[0009] According to another aspect of the present invention, there is provided a device for determining the glycerol distribution of a heat-not-burn cigarette, comprising:

[0010] A data acquisition module for acquiring a set of basic cut segments corresponding to a target heat-not-burn cigarette; wherein, each target segment cigarette is included in the set of basic cut segments;

[0011] A data preprocessing module for determining the target near-infrared hyperspectral data corresponding to the target segment cigarette based on a preset near-infrared hyperspectral imaging technique, and performing region segmentation on the target near-infrared hyperspectral data based on a preset threshold segmentation method to determine the region of interest corresponding to the target segment cigarette and the average spectrum corresponding to the region of interest;

[0012] A result generation module for performing regression analysis on the average spectrum based on the target regression model set to obtain the prediction results corresponding to each target regression sub-model in the target regression model set, and determining the glycerol content distribution result corresponding to the target heat-not-burn cigarette based on the prediction results corresponding to each target regression sub-model.

[0013] According to another aspect of the present invention, there is provided an electronic device, the electronic device comprising:

[0014] At least one processor; and

[0015] A memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program executable by the at least one processor, and when the computer program is executed by the at least one processor, the at least one processor is enabled to execute the method for determining the glycerol distribution of a heat-not-burn cigarette according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement the method for determining the glycerol distribution of a heat-not-burn cigarette according to any embodiment of the present invention when executed.

[0018] According to another aspect of the present invention, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the method for determining the glycerol distribution of a heat-not-burn cigarette according to any embodiment of the present invention.

[0019] In the technical solution of the embodiment of the present invention, the target near-infrared hyperspectral data corresponding to the target segmented cigarette in the basic cutting segmentation set corresponding to the target heated non-combustible cigarette is determined by preset near-infrared hyperspectral imaging technology, and the target near-infrared hyperspectral data is regionally segmented based on a preset threshold segmentation method to determine the region of interest corresponding to the target segmented cigarette and the average spectrum corresponding to the region of interest. Finally, regression analysis is performed on the average spectrum based on the target regression model set to obtain the prediction results corresponding to each target regression sub-model in the target regression model set, and the glycerol content distribution result corresponding to the target heated non-combustible cigarette is determined based on the prediction results corresponding to each target regression sub-model. Since the near-infrared hyperspectral imaging technology and the regression model are used to detect the glycerol distribution of the heated non-combustible cigarette, the problem of low detection efficiency of the glycerol distribution of the heated non-combustible cigarette is solved, and the rapid detection of the glycerol distribution in the tobacco core section of the heated non-combustible cigarette can be realized, improving the detection efficiency of the glycerol distribution.

[0020] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. Description of the Drawings

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts.

[0022] Figure 1 is a flowchart of a method for determining the glycerol distribution of a heated non-combustible cigarette according to Embodiment 1 of the present invention;

[0023] Figure 2 is a flowchart of a method for determining the glycerol distribution of a heated non-combustible cigarette according to Embodiment 2 of the present invention;

[0024] Figure 3 is a schematic structural diagram of a device for determining the glycerol distribution of a heated non-combustible cigarette according to Embodiment 3 of the present invention;

[0025] Figure 4 is a schematic structural diagram of an electronic device for implementing the method for determining the glycerol distribution of a heated non-combustible cigarette according to the embodiment of the present invention. Detailed Embodiments

[0026] To enable those skilled in the art to better understand the solution of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0027] It should be noted that the terms "target", "history", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances, so that the embodiments of the present invention described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0028] Embodiment 1

[0029] Figure 1 FIG. is a flowchart of a method for determining the glycerol distribution of a heat-not-burn cigarette provided in Embodiment 1 of the present invention. This embodiment is applicable to the situation of detecting the glycerol distribution of a heat-not-burn cigarette. This method can be executed by a device for determining the glycerol distribution of a heat-not-burn cigarette. The device for determining the glycerol distribution of a heat-not-burn cigarette can be implemented in the form of hardware and / or software, and the device for determining the glycerol distribution of a heat-not-burn cigarette can be configured in an electronic device. As Figure 1 shown, the method includes:

[0030] S110. Obtain a basic cutting segment set corresponding to the target heat-not-burn cigarette; wherein, each target segment cigarette is included in the basic cutting segment set.

[0031] Among them, the target heat-not-burn cigarette can refer to the heat-not-burn cigarette selected for glycerol distribution detection. Exemplarily, the target heat-not-burn cigarette can be any heat-not-burn cigarette in the production batch that currently needs to be detected for glycerol distribution. The segment cigarette can refer to the cut segment corresponding to the heat-not-burn cigarette. The target segment cigarette can refer to the segment cigarette corresponding to the target heat-not-burn cigarette. The cutting segment set can refer to the set composed of each segment cigarette corresponding to the same heat-not-burn cigarette. Usually, one heat-not-burn cigarette corresponds to one cutting segment set. The basic cutting segment set can refer to the cutting segment set corresponding to the target heat-not-burn cigarette.

[0032] S120. Determine the target near-infrared hyperspectral data corresponding to the target segmented cigarette using a preset near-infrared hyperspectral imaging technique, and perform regional segmentation on the target near-infrared hyperspectral data using a preset threshold segmentation method to determine the region of interest corresponding to the target segmented cigarette and the average spectrum corresponding to the region of interest.

[0033] Among them, the near-infrared hyperspectral imaging technique can refer to an advanced detection method that combines spectral analysis and imaging. Through the near-infrared hyperspectral imaging technique, a sample can be cut into tiny pieces, the spectral information of each tiny piece can be scanned using an infrared spectrometer, and these spectral information can be matched one by one with the three-dimensional coordinates of each tiny piece, and finally a spectral image of the sample in three-dimensional space can be obtained. The preset near-infrared hyperspectral imaging technique can refer to a pre-selected near-infrared hyperspectral imaging technique. Exemplarily, the preset near-infrared hyperspectral imaging technique can be a compressive sensing hyperspectral imaging method or a deep learning fusion method. The near-infrared hyperspectral data can refer to the spectral image collected using the near-infrared hyperspectral imaging technique. The target near-infrared hyperspectral data can refer to the near-infrared hyperspectral data obtained after collecting the target segmented cigarette using the preset near-infrared hyperspectral imaging technique.

[0034] Among them, the preset threshold segmentation method can refer to a method preset for limiting the regional segmentation process. Exemplarily, the preset threshold segmentation method can be an automatic threshold segmentation (Otsu) method for grayscale images. The region of interest can refer to the key information in the near-infrared hyperspectral data for centralized processing or analysis. Exemplarily, the preset threshold segmentation method can be used to calculate the threshold for the near-infrared hyperspectral data, and the calculated threshold result can be used to determine the region of interest. The average spectrum can refer to the average value of each near-infrared hyperspectral data in the region of interest.

[0035] S130. Perform regression analysis on the average spectrum based on the target regression model set to obtain the prediction results corresponding to each target regression sub-model in the target regression model set, and determine the glycerol content distribution result corresponding to the target heat-not-burn cigarette based on the prediction results corresponding to each target regression sub-model.

[0036] Among them, the regression sub-model can refer to a model used to analyze the relationship between variables and predict continuous results. The regression model set can refer to a set composed of multiple regression sub-models. Generally, the prediction functions corresponding to each regression sub-model in the same regression model set are the same.

[0037] Among them, the target regression sub-model can refer to a regression sub-model used to analyze the relationship between glycerol content and hyperspectral data and predict the glycerol content. The glycerol distribution of the heat-not-burn cigarette can be detected through the target regression sub-model. Exemplarily, the target regression sub-model can be a Self-organizing feature Map (SOM) neural network model, a Radical Basis Function (RBF) neural network model, a Back-Propagation (BP) network model, a Simple Recurrent Neural Network (Elman) model, etc. The target regression model set can refer to a set composed of each target regression sub-model with the same prediction function.

[0038] Among them, the prediction result can refer to the predicted value of the glycerol content output by the target regression sub-model. Usually, one target regression sub-model corresponds to one prediction result. Each prediction result contains the longitudinal glycerol content representing the glycerol content distribution in the longitudinal direction of the tobacco rod segment and the axial glycerol content representing the glycerol content distribution in the axial direction of the tobacco rod segment corresponding to the same segmented cigarette rod. The glycerol content distribution result can refer to the glycerol content distribution of the target heat-not-burn cigarette. Exemplarily, the glycerol content distribution result can include the glycerol content distribution of all segmented cigarette rods in the target heat-not-burn cigarette.

[0039] The technical solution of the embodiment of the present invention determines the target near-infrared hyperspectral data corresponding to the target segmented cigarette rod in the basic cutting segmented set corresponding to the target heat-not-burn cigarette through the preset near-infrared hyperspectral imaging technology, and performs regional segmentation on the target near-infrared hyperspectral data based on the preset threshold segmentation method to determine the region of interest corresponding to the target segmented cigarette rod and the average spectrum corresponding to the region of interest. Finally, regression analysis is performed on the average spectrum based on the target regression model set to obtain the prediction results corresponding to each target regression sub-model in the target regression model set, and the glycerol content distribution result corresponding to the target heat-not-burn cigarette is determined based on the prediction results corresponding to each target regression sub-model. Since the near-infrared hyperspectral imaging technology and the regression model are used to detect the glycerol distribution of the heat-not-burn cigarette, the problem of low detection efficiency of the glycerol distribution of the heat-not-burn cigarette is solved, and the rapid detection of the glycerol distribution in the tobacco rod segment of the heat-not-burn cigarette can be realized, improving the detection efficiency of the glycerol distribution.

[0040] Embodiment 2

[0041] Figure 2The flowchart of a method for determining the glycerol distribution of a heat-not-burn cigarette provided in the second embodiment of the present invention. This embodiment is refined based on the above embodiment. Specifically, in this embodiment, the operation of determining the target near-infrared hyperspectral data corresponding to the target segmented cigarette based on the preset near-infrared hyperspectral imaging technology is refined, and specifically may include: imaging and collecting the target segmented cigarette based on the preset near-infrared hyperspectral imaging technology to obtain the basic near-infrared hyperspectral data corresponding to the target segmented cigarette; performing black-and-white correction on the basic near-infrared hyperspectral data based on the preset correction technology to obtain the corrected near-infrared hyperspectral data corresponding to the target segmented cigarette; performing noise reduction processing on the corrected near-infrared hyperspectral data based on the preset noise reduction method to obtain the target near-infrared hyperspectral data corresponding to the target segmented cigarette. As Figure 2 shown, the method includes:

[0042] S210. Obtain the total length of the cigarette of the target heat-not-burn cigarette.

[0043] Among them, the total length of the cigarette may refer to the actual length of the cigarette of the target heat-not-burn cigarette. Exemplarily, the total length of the cigarette may be the length between the head end of the filter rod section and the tail end of the tobacco section in the target heat-not-burn cigarette. Generally, the total length of the cigarette of the target heat-not-burn cigarette can be determined by using image acquisition technology, or can be determined by using physical measurement methods. The embodiments of the present invention do not make specific limitations on this.

[0044] S220. Perform cutting processing on the target heat-not-burn cigarette based on the preset segmentation interval and the total length of the cigarette to obtain a basic cutting segment set corresponding to the target heat-not-burn cigarette; wherein, each target segmented cigarette is included in the basic cutting segment set.

[0045] Among them, the preset segmentation interval may refer to a preset value used to evaluate the segmentation length. Exemplarily, the preset segmentation interval may be a fixed separation length, such as 5 cm. It may also be an average segmentation length, such as one-fifth of the total length of the cigarette. The cutting processing may refer to the operation of cutting the heat-not-burn cigarette by using cutting technology. Exemplarily, the cutting technology may include physical means such as mechanical cutting, ultra-short pulse laser cutting or laser ablation.

[0046] Specifically, after determining the target heat-not-burn cigarette that needs to be detected for glycerol distribution, first, obtain the total length of the cigarette of the target heat-not-burn cigarette. Then, perform cutting processing on the total length of the cigarette of the target heat-not-burn cigarette according to the preset segmentation interval to obtain each target segmented cigarette corresponding to the target heat-not-burn cigarette, and arrange the target segmented cigarettes corresponding to the same target heat-not-burn cigarette in the cutting order to form a basic cutting segment set. Thus, it can provide an effective basis for subsequent operations.

[0047] S230. Image acquisition is performed on the target segmented cigarette using a preset near-infrared hyperspectral imaging technique to obtain the basic near-infrared hyperspectral data corresponding to the target segmented cigarette.

[0048] Among them, the basic near-infrared hyperspectral data can refer to the near-infrared hyperspectral data obtained by directly imaging and collecting the target segmented cigarette using a preset near-infrared hyperspectral imaging technique. Usually, the basic near-infrared hyperspectral data can be the near-infrared hyperspectral data that has not been processed.

[0049] S240. Black-and-white correction is performed on the basic near-infrared hyperspectral data based on a preset correction technique to obtain the corrected near-infrared hyperspectral data corresponding to the target segmented cigarette.

[0050] Among them, the preset correction technique can refer to a method preset for data correction of near-infrared hyperspectral data. Exemplarily, the preset correction technique can be a black-and-white board correction method. Specifically, the black-and-white board correction method can be represented by the formula: O can represent the basic near-infrared hyperspectral data, B can represent the all-black calibration image obtained by scanning the blackboard built into the instrument, and W can represent the all-white calibration image obtained by scanning the standard white correction board with a reflectivity of 99% built into the instrument. The corrected near-infrared hyperspectral data can refer to the near-infrared hyperspectral data obtained by performing black-and-white correction on the basic near-infrared hyperspectral data using a preset correction technique.

[0051] S250. Noise reduction processing is performed on the corrected near-infrared hyperspectral data based on a preset noise reduction method to obtain the target near-infrared hyperspectral data corresponding to the target segmented cigarette.

[0052] Among them, the preset noise reduction method can refer to a method preset for noise reduction processing of near-infrared hyperspectral data. Exemplarily, the preset noise reduction method can be methods such as minimum noise fraction or wavelet transform.

[0053] Specifically, after obtaining the basic cutting segment set corresponding to the target heated tobacco product, the preset near-infrared hyperspectral imaging technique can be used to perform imaging acquisition on each target segmented cigarette in the basic cutting segment set to obtain the basic near-infrared hyperspectral data corresponding to the target segmented cigarette. Furthermore, the preset correction technique is used to perform black-and-white correction on the basic near-infrared hyperspectral data to obtain the corrected near-infrared hyperspectral data corresponding to each target segmented cigarette. Finally, the preset noise reduction method is used to perform noise reduction processing on each corrected near-infrared hyperspectral data respectively. Thus, the target near-infrared hyperspectral data corresponding to each target segmented cigarette can be obtained, providing an effective basis for subsequent glycerol content detection.

[0054] S260: Determine the characteristic band corresponding to the target segmented cigarette based on the cigarette type corresponding to the target segmented cigarette.

[0055] Among them, the cigarette type may refer to the type of tobacco formula corresponding to the segmented cigarette. Usually, different tobacco formulas correspond to different cigarette types. The cigarette types corresponding to the segmented cigarettes in the same heat-not-burn cigarette are consistent. The characteristic band may refer to the band with the highest degree of information. Usually, different cigarette types correspond to different characteristic bands, and the characteristic band corresponding to the cigarette type can be determined according to the production standard.

[0056] S270, determining a basic single-band image corresponding to the target near-infrared hyperspectral data based on the characteristic band, and binarizing the basic single-band image to obtain a target single-band image corresponding to the target near-infrared hyperspectral data.

[0057] Among them, the basic single-band image may refer to the hyperspectral data corresponding to the characteristic band in the target near-infrared hyperspectral data. Binarization processing may refer to the technology of simplifying the hyperspectral data to 0 and 255 using an adaptive threshold. Specifically, by setting a dynamic threshold, elements above the value are set to 255, and elements below or equal to the value are set to 0. In this way, the entire image can present an obvious black and white effect. The target single-band image may refer to a single-band image obtained by binarizing the basic single-band image.

[0058] S280, performing regional segmentation on the target single-band image based on a preset threshold segmentation method to obtain a region of interest corresponding to the target segmented cigarette.

[0059] S290, performing block processing on the near-infrared hyperspectral data within the region of interest based on a preset superpixel segmentation method to obtain a block result, and determining an average spectrum corresponding to the region of interest based on the block result.

[0060] The preset superpixel segmentation method may refer to a preset algorithm for subdividing a digital image into a plurality of image sub-regions. Exemplarily, the preset superpixel segmentation method may be a simple linear iterative clustering (SLIC) algorithm, or a fast watershed superpixel segmentation algorithm, etc. The block result may refer to an image sub-region obtained by block-processing the near-infrared hyperspectral data in the region of interest using the preset superpixel segmentation method.

[0061] Specifically, after obtaining the target near-infrared hyperspectral data corresponding to the target segmented cigarette, the characteristic wavelength band corresponding to the target segmented cigarette can be determined based on the cigarette type of the target segmented cigarette, and the basic single-wavelength image corresponding to the characteristic wavelength band can be extracted from the target near-infrared hyperspectral data. Furthermore, the basic single-wavelength image is binarized to obtain the target single-wavelength image corresponding to the target near-infrared hyperspectral data. Further, the target single-wavelength image is segmented by using a preset threshold segmentation method to determine the region of interest that meets the preset threshold segmentation method, and the hyperspectral data within this region is extracted. Finally, the near-infrared hyperspectral data within the region of interest is segmented into blocks by using a preset superpixel segmentation method, and the hyperspectral data of each block is calculated by averaging. Thus, the average spectrum corresponding to the region of interest is obtained, providing an effective basis for subsequent model prediction.

[0062] S2100. Perform regression analysis on the average spectrum based on the target regression model set to obtain the prediction results corresponding to each target regression sub-model in the target regression model set.

[0063] In an alternative embodiment, before performing regression analysis on the average spectrum based on the target regression model set to obtain the prediction results corresponding to each target regression sub-model in the target regression model set, it further includes:

[0064] Step a1. Obtain the historical heated tobacco product set corresponding to the target heated tobacco product and the historical cutting segment set corresponding to each historical heated tobacco product in the historical heated tobacco product set; wherein, the historical heated tobacco product set includes each historical heated tobacco product, and the historical cutting segment set includes each historical segmented cigarette corresponding to the same historical heated tobacco product.

[0065] Among them, the historical heated tobacco product can refer to the heated tobacco product produced by the production system during the historical time period. Exemplarily, the historical heated tobacco product can be the heated tobacco product produced by the same production equipment as the target heated tobacco product during the historical time period, or the heated tobacco product produced by a production equipment different from the target heated tobacco product during the historical time period. The historical heated tobacco product set can refer to the set composed of multiple historical heated tobacco products within a preset time period. Exemplarily, the historical heated tobacco product set can be 10 heated tobacco products produced in the previous week. The historical segmented cigarette can refer to the segmented cigarette corresponding to the historical heated tobacco product. The historical cutting segment set can refer to the cutting segment set corresponding to the historical heated tobacco product.

[0066] Step a2. Collect the glycerol content of each historical segmented cigarette in the historical cutting segment set based on a preset chemical detection method to obtain the glycerol content corresponding to each historical segmented cigarette.

[0067] Among them, the preset chemical detection method may refer to a chemical detection method for glycerol content set in advance. Exemplarily, the preset chemical detection method may be gas chromatography, liquid chromatography, mass spectrometry, and corresponding combined methods. The glycerol content may refer to the glycerol value obtained by using a chemical detection method.

[0068] Step a3: Determine the historical near-infrared hyperspectral data corresponding to each historical segmented cigarette in the historical cutting segmented set based on the preset near-infrared hyperspectral imaging technology, and perform regional segmentation on the historical near-infrared hyperspectral data based on the preset threshold segmentation method to determine the region of interest corresponding to the historical segmented cigarette and the average spectrum corresponding to the region of interest.

[0069] Among them, the historical near-infrared hyperspectral data may refer to the near-infrared hyperspectral data obtained by collecting historical segmented cigarettes using the preset near-infrared hyperspectral imaging technology.

[0070] Step a4: Combine and process the glycerol content and the average spectrum corresponding to the same historical segmented cigarette in the historical cutting segmented set to generate the basic glycerol content distribution corresponding to the historical heat-not-burn cigarette, and summarize and process the basic glycerol content distributions corresponding to each historical heat-not-burn cigarette in the historical heat-not-burn cigarette set to generate a basic data set.

[0071] Among them, the basic glycerol content distribution may refer to the content distribution situation corresponding to the historical segmented cigarette. The basic data set may refer to the data set obtained by summarizing and processing the basic glycerol content distributions corresponding to each historical heat-not-burn cigarette in the historical heat-not-burn cigarette set.

[0072] Step a5: Divide and process the basic data set based on the preset data division strategy to obtain a training set and a validation set, perform model training on the basic regression model set based on the training set and the preset model parameters to obtain a set of candidate regression models, and perform model validation on the set of candidate regression models based on the validation set to obtain a trained set of target regression models.

[0073] Among them, the preset data division strategy may refer to a method preset for limiting the data set division process. Exemplarily, the preset data division strategy may be that the training set and the validation set are divided in a ratio of 8:2, or the training set and the validation set are divided in a ratio of 7:3. The training set may refer to the data set used for training the model. The validation set may refer to the data set used for adjusting the model parameters and preventing overfitting.

[0074] Among them, the preset model parameters can refer to the pre-set model parameters. Exemplarily, the preset model parameters can include the number of iterations, population size, crossover probability, mutation probability, etc. The basic regression model set can refer to a set of regression models that have not been trained. The candidate regression model set can refer to a set of regression models after preliminary training.

[0075] Specifically, before predicting the glycerol content, the historical heated tobacco product set corresponding to the target heated tobacco product and the historical cut segment set corresponding to each historical heated tobacco product in the historical heated tobacco product set can be obtained first. Furthermore, based on the preset chemical detection method, the glycerol content of each historical segmented cigarette in the historical cut segment set is collected to obtain the glycerol content corresponding to each historical segmented cigarette, and based on the preset near-infrared hyperspectral imaging technology, the historical near-infrared hyperspectral data corresponding to each historical segmented cigarette in the historical cut segment set is determined. Based on the preset threshold segmentation method, the historical near-infrared hyperspectral data is segmented to determine the region of interest corresponding to the historical segmented cigarette and the average spectrum corresponding to the region of interest. Further, the glycerol content and the average spectrum corresponding to the same historical segmented cigarette in the historical cut segment set are combined and processed to generate the basic glycerol content distribution corresponding to the historical heated tobacco product. The basic glycerol content distributions corresponding to each historical heated tobacco product in the historical heated tobacco product set are summarized and processed to generate a basic data set, and the basic data set is divided and processed based on the preset data division strategy to obtain a training set and a validation set. Finally, based on the training set and the preset model parameters, the basic regression model set is trained. By selecting the characteristic wavelengths and optimizing the model parameters, such as the characteristic bands, characteristic band coefficients, and biases, the redundancy of the model is reduced and the efficiency of the model is improved, so as to obtain a candidate regression model set including the trained characteristic bands, characteristic band coefficients, and biases, and the candidate regression model set is verified based on the validation set to obtain the trained target regression model set.

[0076] It should be noted that in the embodiments of the present invention, the training process of the target regression model set can be completed before predicting the glycerol content, and the embodiments of the present invention do not specifically limit this.

[0077] S2110. Process the prediction results corresponding to the respective target regression sub-models by taking the mean to obtain the longitudinal glycerol content and the axial glycerol content corresponding to the target segmented cigarette.

[0078] Among them, the mean processing may refer to the operation of calculating the mean of the prediction results corresponding to each target regression sub-model in the same set of target regression models. The longitudinal glycerol content may refer to the result obtained by performing mean processing on the longitudinal glycerol contents corresponding to each target regression sub-model in the same set of target regression models. The axial glycerol content may refer to the result obtained by performing mean processing on the axial glycerol contents corresponding to each target regression sub-model in the same set of target regression models.

[0079] S2120. Perform interpolation processing on the longitudinal glycerol content and the axial glycerol content based on a preset interpolation method to obtain a three-dimensional glycerol content distribution model corresponding to the target segmented cigarette.

[0080] Among them, the preset interpolation method may refer to a method that is preset to construct a continuous function through known discrete point data to predict the spatial distribution of an unknown region. Exemplarily, the preset interpolation method may be a linear interpolation method, a polynomial interpolation method, a Lagrange interpolation method, etc. The three-dimensional glycerol content distribution model may refer to the three-dimensional spatial distribution result of the glycerol content corresponding to the target segmented cigarette.

[0081] S2130. Based on the cigarette order of each target segmented cigarette in the target heat-not-burn cigarette, summarize and process the three-dimensional glycerol content distribution models corresponding to each target segmented cigarette to obtain a glycerol content distribution result corresponding to the target heat-not-burn cigarette.

[0082] Among them, the cigarette order may refer to the arrangement order of each target segmented cigarette in the same target heat-not-burn cigarette. Exemplarily, the cigarette order may be the segmentation order of each target segmented cigarette in the target heat-not-burn cigarette.

[0083] Specifically, after obtaining the prediction results corresponding to each target regression sub-model in the set of target regression models, the prediction results of each target regression sub-model corresponding to the same target segmented cigarette may be subjected to mean processing to obtain the longitudinal glycerol content and the axial glycerol content corresponding to the target segmented cigarette. Furthermore, the longitudinal glycerol content and the axial glycerol content are subjected to interpolation processing using a preset interpolation method to obtain a three-dimensional glycerol content distribution model corresponding to the target segmented cigarette. Finally, according to the cigarette order of each target segmented cigarette in the target heat-not-burn cigarette, the three-dimensional glycerol content distribution models corresponding to each target segmented cigarette are summarized and processed. Thus, a glycerol content distribution result corresponding to the target heat-not-burn cigarette is obtained.

[0084] S2140. Determine a set of glycerol content distribution results corresponding to the target production batch based on the target production batch corresponding to the target heat-not-burn cigarette; wherein, the set of glycerol content distribution results includes a preset number of glycerol content distribution results.

[0085] Among them, the production batch may refer to the serial number of heat-not-burn cigarettes produced within a certain period. Usually, within a certain period, each heat-not-burn cigarette produced at one time and completely identical in terms of quality, structure, and manufacturing method corresponds to the same production batch. The target production batch may refer to the production batch corresponding to the target heat-not-burn cigarette.

[0086] Among them, the preset quantity may refer to a numerically value preset for evaluating the quantity of the glycerol content distribution result. Exemplarily, the preset quantity may be 20 or 10. The set of glycerol content distribution results may refer to a set integrating the preset quantity of glycerol content distribution results.

[0087] S2150. Perform data analysis on the set of glycerol content distribution results based on a preset data evaluation criterion to obtain a production analysis result corresponding to the target production batch.

[0088] Among them, the preset data evaluation criterion may refer to a criterion preset for performing data analysis on the set of glycerol content distribution results. Exemplarily, the preset data evaluation criterion may be that the glycerol content distribution exceeds a set content threshold. The production analysis result may refer to an analysis result obtained by performing data analysis on the set of glycerol content distribution results. Exemplarily, the production analysis result may be that the set of glycerol content distribution results meets the preset data evaluation criterion, or the set of glycerol content distribution results does not meet the preset data evaluation criterion. The production situation of the target production batch can be determined through the production analysis result, providing an effective indication for subsequent production work.

[0089] The technical solution of the embodiment of the present invention performs cutting processing on the target heat-not-burn cigarette through a preset segmentation interval and the total length of the cigarette stick of the target heat-not-burn cigarette to obtain a basic cutting segmentation set corresponding to the target heat-not-burn cigarette; wherein, each target segmented cigarette stick is included in the basic cutting segmentation set. Furthermore, based on the preset near-infrared hyperspectral imaging technology, imaging acquisition is performed on the target segmented cigarette stick to obtain basic near-infrared hyperspectral data corresponding to the target segmented cigarette stick. Based on the preset calibration technology, black-and-white calibration is performed on the basic near-infrared hyperspectral data to obtain calibrated near-infrared hyperspectral data corresponding to the target segmented cigarette stick, and based on the preset noise reduction method, noise reduction processing is performed on the calibrated near-infrared hyperspectral data to obtain target near-infrared hyperspectral data corresponding to the target segmented cigarette stick. Further, based on the cigarette stick type corresponding to the target segmented cigarette stick, the characteristic wavelength band corresponding to the target segmented cigarette stick is determined. Based on the characteristic wavelength band, the basic single-wavelength image corresponding to the target near-infrared hyperspectral data is determined. The basic single-wavelength image is binary-processed to obtain the target single-wavelength image corresponding to the target near-infrared hyperspectral data. Based on the preset threshold segmentation method, region segmentation is performed on the target single-wavelength image as the region of interest corresponding to the target segmented cigarette stick, and based on the preset superpixel segmentation method, the near-infrared hyperspectral data in the region of interest is block-processed to obtain a block result. Based on the block result, the average spectrum corresponding to the region of interest is determined. Further, regression analysis is performed on the average spectrum based on the target regression model set to obtain the prediction results corresponding to each target regression sub-model in the target regression model set. The prediction results corresponding to each target regression sub-model are mean-processed to obtain the longitudinal glycerol content and the axial glycerol content corresponding to the target segmented cigarette stick. Based on the preset interpolation method, interpolation processing is performed on the longitudinal glycerol content and the axial glycerol content to obtain a three-dimensional distribution model of the glycerol content corresponding to the target segmented cigarette stick, and based on the cigarette stick sorting of each target segmented cigarette stick in the target heat-not-burn cigarette, the three-dimensional distribution models of the glycerol content corresponding to each target segmented cigarette stick are aggregated to obtain the glycerol content distribution result corresponding to the target heat-not-burn cigarette. Finally, based on the target production batch corresponding to the target heat-not-burn cigarette, a set of glycerol content distribution results corresponding to the target production batch is determined, and data analysis is performed on the set of glycerol content distribution results based on the preset data evaluation criteria to obtain the production analysis result corresponding to the target production batch. Since the near-infrared hyperspectral imaging technology and the regression model are used for detecting the glycerol distribution of the heat-not-burn cigarette, the problem of low detection efficiency of the glycerol distribution of the heat-not-burn cigarette is solved, and rapid detection of the glycerol distribution in the tobacco core section of the heat-not-burn cigarette can be realized, improving the detection efficiency of the glycerol distribution.

[0090] Embodiment III

[0091] Figure 3 It is a schematic structural diagram of a device for determining the glycerol distribution of a heat-not-burn cigarette provided by Embodiment III of the present invention. As Figure 3As shown, the device includes: a data acquisition module 310, a data preprocessing module 320, and a result generation module 330;

[0092] Among them, the data acquisition module 310 is used to acquire a basic cutting segment set corresponding to a target heat-not-burn cigarette; wherein, each target segment cigarette is included in the basic cutting segment set;

[0093] The data preprocessing module 320 is used to determine target near-infrared hyperspectral data corresponding to the target segment cigarette based on a preset near-infrared hyperspectral imaging technology, and perform region segmentation on the target near-infrared hyperspectral data based on a preset threshold segmentation method to determine an interested region corresponding to the target segment cigarette and an average spectrum corresponding to the interested region;

[0094] The result generation module 330 is used to perform regression analysis on the average spectrum based on a target regression model set to obtain prediction results corresponding to each target regression sub-model in the target regression model set, and determine a glycerol content distribution result corresponding to the target heat-not-burn cigarette based on the prediction results corresponding to each target regression sub-model.

[0095] The technical solution of the embodiment of the present invention determines target near-infrared hyperspectral data corresponding to a target segment cigarette in a basic cutting segment set corresponding to a target heat-not-burn cigarette through a preset near-infrared hyperspectral imaging technology, and performs region segmentation on the target near-infrared hyperspectral data based on a preset threshold segmentation method to determine an interested region corresponding to the target segment cigarette and an average spectrum corresponding to the interested region. Finally, regression analysis is performed on the average spectrum based on a target regression model set to obtain prediction results corresponding to each target regression sub-model in the target regression model set, and a glycerol content distribution result corresponding to the target heat-not-burn cigarette is determined based on the prediction results corresponding to each target regression sub-model. Since near-infrared hyperspectral imaging technology and regression models are used for detecting the glycerol distribution of heat-not-burn cigarettes, the problem of low detection efficiency of the glycerol distribution of heat-not-burn cigarettes is solved, and rapid detection of the glycerol distribution in the tobacco core segment of heat-not-burn cigarettes can be achieved, improving the detection efficiency of the glycerol distribution.

[0096] Optionally, the data acquisition module 310 may specifically be used for:

[0097] Acquire the total length of the cigarette of the target heat-not-burn cigarette;

[0098] Perform cutting processing on the target heat-not-burn cigarette based on a preset segmentation interval and the total length of the cigarette to obtain a basic cutting segment set corresponding to the target heat-not-burn cigarette.

[0099] Optionally, the data preprocessing module 320 may specifically be used for:

[0100] Image acquisition is performed on the target segmented cigarette using a preset near-infrared hyperspectral imaging technique to obtain the basic near-infrared hyperspectral data corresponding to the target segmented cigarette;

[0101] Based on a preset calibration technique, black-and-white calibration is performed on the basic near-infrared hyperspectral data to obtain the calibrated near-infrared hyperspectral data corresponding to the target segmented cigarette;

[0102] Based on a preset noise reduction method, noise reduction processing is performed on the calibrated near-infrared hyperspectral data to obtain the target near-infrared hyperspectral data corresponding to the target segmented cigarette.

[0103] Optionally, the data preprocessing module 320 can specifically be used for:

[0104] Determine the characteristic wavelength band corresponding to the target segmented cigarette based on the cigarette type corresponding to the target segmented cigarette;

[0105] Based on the characteristic wavelength band, determine the basic single-wavelength image corresponding to the target near-infrared hyperspectral data, and perform binary processing on the basic single-wavelength image to obtain the target single-wavelength image corresponding to the target near-infrared hyperspectral data;

[0106] Perform region segmentation on the target single-wavelength image based on a preset threshold segmentation method as the region of interest corresponding to the target segmented cigarette;

[0107] Perform block processing on the near-infrared hyperspectral data within the region of interest based on a preset superpixel segmentation method to obtain a block result, and determine the average spectrum corresponding to the region of interest based on the block result.

[0108] Optionally, the glycerol distribution determination device for a heat-not-burn cigarette may further include: a model training module, configured to obtain a set of historical heat-not-burn cigarettes corresponding to a target heat-not-burn cigarette and a set of historical cut segments corresponding to each historical heat-not-burn cigarette in the set of historical heat-not-burn cigarettes before performing regression analysis on the average spectrum based on the target regression model set to obtain prediction results corresponding to each target regression sub-model in the target regression model set; wherein, the set of historical heat-not-burn cigarettes includes each historical heat-not-burn cigarette, and the set of historical cut segments includes each historical segmented cigarette corresponding to the same historical heat-not-burn cigarette; collecting the glycerol content of each historical segmented cigarette in the set of historical cut segments based on a preset chemical detection method to obtain the glycerol content corresponding to each historical segmented cigarette; determining the historical near-infrared hyperspectral data corresponding to each historical segmented cigarette in the set of historical cut segments based on a preset near-infrared hyperspectral imaging technique, and performing region segmentation on the historical near-infrared hyperspectral data based on a preset threshold segmentation method to determine the region of interest corresponding to the historical segmented cigarette and the average spectrum corresponding to the region of interest; combining and processing the glycerol content and the average spectrum corresponding to the same historical segmented cigarette in the set of historical cut segments to generate a basic glycerol content distribution corresponding to the historical heat-not-burn cigarette, summarizing and processing the basic glycerol content distributions corresponding to each historical heat-not-burn cigarette in the set of historical heat-not-burn cigarettes to generate a basic data set; dividing and processing the basic data set based on a preset data division strategy to obtain a training set and a validation set, training a basic regression model set based on the training set and preset model parameters to obtain a set of candidate regression models, and validating the set of candidate regression models based on the validation set to obtain a trained target regression model set.

[0109] Optionally, the result generation module 330 may specifically be configured to:

[0110] Perform mean processing on the prediction results corresponding to each target regression sub-model to obtain the longitudinal glycerol content and the axial glycerol content corresponding to the target segmented cigarette;

[0111] Perform interpolation processing on the longitudinal glycerol content and the axial glycerol content based on a preset interpolation method to obtain a three-dimensional glycerol content distribution model corresponding to the target segmented cigarette;

[0112] Based on the cigarette order of each target segmented cigarette in the target heat-not-burn cigarette, summarize and process the three-dimensional glycerol content distribution models corresponding to each target segmented cigarette to obtain the glycerol content distribution result corresponding to the target heat-not-burn cigarette.

[0113] Optionally, the glycerol distribution determination device for a heat-not-burn cigarette may further include: a post-processing module, configured to, after determining the glycerol content distribution result corresponding to the target heat-not-burn cigarette based on the prediction results corresponding to the respective target regression sub-models, determine a set of glycerol content distribution results corresponding to the target production batch based on the target production batch corresponding to the target heat-not-burn cigarette; wherein the set of glycerol content distribution results includes a preset number of glycerol content distribution results; perform data analysis on the set of glycerol content distribution results based on a preset data evaluation criterion to obtain a production analysis result corresponding to the target production batch.

[0114] The glycerol distribution determination device for a heat-not-burn cigarette provided by an embodiment of the present invention can execute the glycerol distribution determination method for a heat-not-burn cigarette provided by any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the method.

[0115] Embodiment 4

[0116] Figure 4 FIG. shows a schematic structural diagram of an electronic device 410 that can be used to implement an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, a personal digital processor, a cellular phone, a smart phone, a wearable device (such as a helmet, glasses, a watch, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0117] As Figure 4 shown, the electronic device 410 includes at least one processor 420, and a memory communicatively connected to at least one processor 420, such as a read-only memory (ROM) 430, a random access memory (RAM) 440, etc., wherein the memory stores a computer program executable by at least one processor, and the processor 420 can execute various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 430 or the computer program loaded from the storage unit 490 into the random access memory (RAM) 440. In the RAM 440, various programs and data required for the operation of the electronic device 410 can also be stored. The processor 420, the ROM 430, and the RAM 440 are connected to each other through a bus 450. The input / output (I / O) interface 460 is also connected to the bus 450.

[0118] Multiple components in the electronic device 410 are connected to the I / O interface 460, including: an input unit 470, such as a keyboard, a mouse, etc.; an output unit 480, such as various types of displays, speakers, etc.; a storage unit 490, such as a disk, an optical disc, etc.; and a communication unit 4100, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 4100 allows the electronic device 410 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0119] The processor 420 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 420 include but are not limited to a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 420 executes the various methods and processes described above, such as the method for determining the glycerol distribution of a heated non-combustible cigarette.

[0120] The method includes:

[0121] Obtaining a set of basic cut segments corresponding to a target heated non-combustible cigarette; wherein, each target segmented cigarette is included in the set of basic cut segments;

[0122] Determining target near-infrared hyperspectral data corresponding to the target segmented cigarette based on a preset near-infrared hyperspectral imaging technology, and performing region segmentation on the target near-infrared hyperspectral data based on a preset threshold segmentation method to determine an interested region corresponding to the target segmented cigarette and an average spectrum corresponding to the interested region;

[0123] Performing regression analysis on the average spectrum based on a set of target regression models to obtain prediction results corresponding to each target regression sub-model in the set of target regression models, and determining a glycerol content distribution result corresponding to the target heated non-combustible cigarette based on the prediction results corresponding to each target regression sub-model.

[0124] In some embodiments, the method for determining the glycerol distribution of a heat-not-burn cigarette can be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 490. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 410 via the ROM 430 and / or the communication unit 4100. When the computer program is loaded into the RAM 440 and executed by the processor 420, one or more steps of the method for determining the glycerol distribution of the heat-not-burn cigarette described above can be performed. Alternatively, in other embodiments, the processor 420 can be configured to perform the method for determining the glycerol distribution of the heat-not-burn cigarette by any other suitable means (e.g., by means of firmware).

[0125] The various embodiments of the systems and techniques described above in this document can be implemented in digital electronic circuitry, integrated circuit systems, field-programmable gate arrays (FPGA), application-specific integrated circuits (ASIC), application-specific standard products (ASSP), systems-on-a-chip (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a dedicated or general-purpose programmable processor that receives data and instructions from a storage system, at least one input device, and at least one output device, and transmits the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0126] The computer programs for implementing the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to the processor of a general-purpose computer, a dedicated computer, or other programmable data processing device, such that when the computer programs are executed by the processor, the functions / operations specified in the flowchart and / or block diagram are implemented. The computer programs can be executed entirely on the machine, partially on the machine, as a stand-alone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0127] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0128] To provide for interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can also be used to provide for interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0129] The systems and techniques described herein can be implemented in a computing system that includes backend components (such as, for example, a data server), or a computing system that includes middleware components (such as, for example, an application server), or a computing system that includes frontend components (such as, for example, a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (such as, for example, a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0130] A computing system may include a client and a server. The client and the server are generally far from each other and usually interact via a communication network. The relationship between the client and the server is created by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, and solves the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0131] An embodiment of the present application also discloses a computer program product, which includes a computer program that, when executed by a processor, implements the method for determining the glycerol distribution of a heat-not-burn cigarette provided in any embodiment of the present application. This program product and the method for determining the glycerol distribution of a heat-not-burn cigarette disclosed in each embodiment of the present application belong to the same inventive concept, and thus will not be elaborated herein.

[0132] It should be understood that various forms of the processes shown above can be used, steps can be reordered, added, or deleted. For example, the steps recited in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is made herein.

[0133] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for determining glycerin distribution of a heat-not-burn cigarette, characterized in that: include: Obtaining a basic cutting segment set corresponding to a target heat-not-burn cigarette; wherein the basic cutting segment set includes each target segmented cigarette; Determine the target near-infrared hyperspectral data corresponding to the target segmented cigarette based on a preset near-infrared hyperspectral imaging technology, and perform regional segmentation on the target near-infrared hyperspectral data based on a preset threshold segmentation method to determine the region of interest corresponding to the target segmented cigarette and the average spectrum corresponding to the region of interest; The average spectrum is subjected to regression analysis based on the target regression model set to obtain prediction results corresponding to each target regression sub-model in the target regression model set, and the glycerin content distribution result corresponding to the target heat-not-burn cigarette is determined based on the prediction results corresponding to each target regression sub-model.

2. The method according to claim 1, characterized in that The step of obtaining a basic cutting segment set corresponding to the target heat-not-burn cigarette includes: Obtaining the total length of a target heat-not-burn cigarette; The target heat-not-burn cigarette is cut based on a preset segmentation interval and the total length of the cigarette to obtain a basic cutting segment set corresponding to the target heat-not-burn cigarette.

3. The method according to claim 1, characterized in that The method of determining the target near-infrared hyperspectral data corresponding to the target segmented cigarette based on the preset near-infrared hyperspectral imaging technology includes: Based on the preset near-infrared hyperspectral imaging technology, the target segmented cigarette is imaged and collected to obtain basic near-infrared hyperspectral data corresponding to the target segmented cigarette; Performing black-white correction on the basic near-infrared hyperspectral data based on a preset correction technology to obtain corrected near-infrared hyperspectral data corresponding to the target segmented cigarette; The corrected near-infrared hyperspectral data is subjected to denoising based on a preset denoising method to obtain target near-infrared hyperspectral data corresponding to the target segmented cigarette.

4. The method according to claim 1, characterized in that The method of performing regional segmentation on the target near-infrared hyperspectral data based on a preset threshold segmentation method, and determining the region of interest corresponding to the target segmented cigarette and the average spectrum corresponding to the region of interest, includes: Determine the characteristic band corresponding to the target segmented cigarette based on the cigarette type corresponding to the target segmented cigarette; Determine a basic single-band image corresponding to the target near-infrared hyperspectral data based on the characteristic band, and binarize the basic single-band image to obtain a target single-band image corresponding to the target near-infrared hyperspectral data; Performing regional segmentation on the target single-band image based on a preset threshold segmentation method as a region of interest corresponding to the target segmented cigarette; The near-infrared hyperspectral data in the region of interest is segmented into blocks based on a preset superpixel segmentation method to obtain a segmentation result, and an average spectrum corresponding to the region of interest is determined based on the segmentation result.

5. The method according to claim 1, characterized in that Before performing regression analysis on the average spectrum based on the target regression model set to obtain prediction results corresponding to each target regression sub-model in the target regression model set, the method further includes: Obtain a historical heat-not-burn cigarette set corresponding to a target heat-not-burn cigarette and a historical cut segment set corresponding to each historical heat-not-burn cigarette in the historical heat-not-burn cigarette set; wherein the historical heat-not-burn cigarette set includes each historical heat-not-burn cigarette, and the historical cut segment set includes each historical segment cigarette corresponding to the same historical heat-not-burn cigarette; Based on a preset chemical detection method, the glycerin content of each historical segment cigarette in the historical cutting segment set is collected to obtain the glycerin content corresponding to each historical segment cigarette; Determine the historical near-infrared hyperspectral data corresponding to each historical segmented cigarette in the historical cut segmentation set based on a preset near-infrared hyperspectral imaging technology, and perform regional segmentation on the historical near-infrared hyperspectral data based on a preset threshold segmentation method to determine the region of interest corresponding to the historical segmented cigarette and the average spectrum corresponding to the region of interest; Combine and process the glycerin content and average spectrum corresponding to the same historical segment cigarette in the historical cut segment set to generate the basic glycerin content distribution corresponding to the historical heat-not-burn cigarettes, and summarize and process the basic glycerin content distribution corresponding to each historical heat-not-burn cigarette in the historical heat-not-burn cigarette set to generate a basic data set; The basic data set is divided and processed based on a preset data partitioning strategy to obtain a training set and a validation set, model training is performed on a basic regression model set based on the training set and preset model parameters to obtain a candidate regression model set, and model validation is performed on the candidate regression model set based on the validation set to obtain a trained target regression model set.

6. The method according to claim 1, characterized in that The step of determining the glycerin content distribution result corresponding to the target heat-not-burn cigarette based on the prediction results corresponding to each target regression sub-model includes: Mean processing is performed on the prediction results corresponding to each target regression sub-model to obtain the longitudinal glycerin content and the axial glycerin content corresponding to the target segmented cigarette; Based on a preset interpolation method, the longitudinal glycerin content and the axial glycerin content are interpolated to obtain a three-dimensional distribution model of glycerin content corresponding to the target segmented cigarette; Based on the cigarette ranking of each target segment cigarette in the target heat-not-burn cigarette, the three-dimensional distribution model of glycerin content corresponding to each target segment cigarette is summarized and processed to obtain the glycerin content distribution result corresponding to the target heat-not-burn cigarette.

7. The method according to claim 1, characterized in that After determining the glycerin content distribution result corresponding to the target heat-not-burn cigarette based on the prediction results corresponding to each target regression sub-model, the method further includes: Based on the target production batch corresponding to the target heat-not-burn cigarette, determine a glycerin content distribution result set corresponding to the target production batch; wherein the glycerin content distribution result set includes a preset number of glycerin content distribution results; The glycerol content distribution result set is subjected to data analysis based on a preset data evaluation standard to obtain a production analysis result corresponding to the target production batch.

8. A device for determining glycerin distribution of heat-not-burn cigarettes, characterized in that: include: A data acquisition module, used to acquire a basic cut segment set corresponding to a target heat-not-burn cigarette; wherein the basic cut segment set includes each target segment cigarette; A data preprocessing module, used to determine the target near-infrared hyperspectral data corresponding to the target segmented cigarette based on a preset near-infrared hyperspectral imaging technology, and to perform regional segmentation on the target near-infrared hyperspectral data based on a preset threshold segmentation method, to determine the region of interest corresponding to the target segmented cigarette and the average spectrum corresponding to the region of interest; The result generation module is used to perform regression analysis on the average spectrum based on the target regression model set to obtain the prediction results corresponding to each target regression sub-model in the target regression model set, and determine the glycerin content distribution result corresponding to the target heat-not-burn cigarette based on the prediction results corresponding to each target regression sub-model.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the method for determining the glycerin distribution of the heat-not-burn cigarette according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for determining the glycerin distribution of a heat-not-burn cigarette according to any one of claims 1 to 7 when executed.

Images